Token | a |
Token ID | 257 |
Feature activation | +2.02e-02 |
Pos logit contributions | |
utonium | +0.070 |
puter | +0.065 |
APH | +0.058 |
awei | +0.057 |
izoph | +0.056 |
Neg logit contributions | |
xual | -0.064 |
blank | -0.064 |
relativity | -0.063 |
Ples | -0.062 |
manship | -0.062 |
Token | political |
Token ID | 1964 |
Feature activation | +3.67e-02 |
Pos logit contributions | |
utonium | +0.062 |
puter | +0.058 |
APH | +0.052 |
awei | +0.051 |
ritten | +0.050 |
Neg logit contributions | |
xual | -0.050 |
blank | -0.049 |
relativity | -0.049 |
manship | -0.048 |
Ples | -0.048 |
Token | � |
Token ID | 564 |
Feature activation | +6.69e-02 |
Pos logit contributions | |
utonium | +0.119 |
puter | +0.112 |
APH | +0.101 |
awei | +0.100 |
ritten | +0.099 |
Neg logit contributions | |
xual | -0.085 |
blank | -0.083 |
relativity | -0.082 |
Ples | -0.080 |
manship | -0.080 |
Token | � |
Token ID | 246 |
Feature activation | +6.76e-03 |
Pos logit contributions | |
utonium | +0.168 |
puter | +0.156 |
awei | +0.133 |
APH | +0.133 |
ritten | +0.130 |
Neg logit contributions | |
xual | -0.205 |
relativity | -0.203 |
blank | -0.201 |
Ples | -0.199 |
manship | -0.198 |
Token | dial |
Token ID | 38969 |
Feature activation | -6.00e-02 |
Pos logit contributions | |
utonium | +0.021 |
puter | +0.020 |
APH | +0.018 |
awei | +0.017 |
ritten | +0.017 |
Neg logit contributions | |
relativity | -0.017 |
xual | -0.017 |
Ples | -0.016 |
blank | -0.016 |
Lovecraft | -0.016 |
Token | ogue |
Token ID | 5119 |
Feature activation | +5.45e-01 |
Pos logit contributions | |
xual | +0.209 |
relativity | +0.208 |
blank | +0.206 |
Ples | +0.204 |
manship | +0.203 |
Neg logit contributions | |
utonium | -0.126 |
puter | -0.116 |
awei | -0.095 |
APH | -0.095 |
ordable | -0.092 |
Token | � |
Token ID | 447 |
Feature activation | +3.10e-02 |
Pos logit contributions | |
utonium | +1.659 |
puter | +1.579 |
APH | +1.405 |
awei | +1.370 |
ordable | +1.356 |
Neg logit contributions | |
xual | -1.325 |
blank | -1.316 |
relativity | -1.311 |
Ples | -1.277 |
Lovecraft | -1.260 |
Token | � |
Token ID | 247 |
Feature activation | +3.16e-02 |
Pos logit contributions | |
utonium | +0.073 |
puter | +0.066 |
awei | +0.056 |
APH | +0.056 |
ritten | +0.055 |
Neg logit contributions | |
xual | -0.100 |
relativity | -0.100 |
blank | -0.099 |
Ples | -0.098 |
manship | -0.097 |
Token | . |
Token ID | 13 |
Feature activation | +2.08e-02 |
Pos logit contributions | |
utonium | +0.098 |
puter | +0.093 |
APH | +0.083 |
awei | +0.082 |
ritten | +0.081 |
Neg logit contributions | |
xual | -0.077 |
relativity | -0.076 |
blank | -0.075 |
Ples | -0.073 |
manship | -0.073 |
Token |
|
Token ID | 198 |
Feature activation | +2.31e-02 |
Pos logit contributions | |
utonium | +0.066 |
puter | +0.061 |
APH | +0.056 |
awei | +0.054 |
izoph | +0.053 |
Neg logit contributions | |
xual | -0.050 |
relativity | -0.049 |
blank | -0.049 |
manship | -0.047 |
Ples | -0.046 |
Token |
|
Token ID | 198 |
Feature activation | +2.62e-02 |
Pos logit contributions | |
utonium | +0.078 |
puter | +0.074 |
awei | +0.066 |
APH | +0.066 |
izoph | +0.065 |
Neg logit contributions | |
xual | -0.051 |
blank | -0.050 |
relativity | -0.050 |
manship | -0.049 |
Ples | -0.049 |
Token | . |
Token ID | 13 |
Feature activation | +4.15e-02 |
Pos logit contributions | |
utonium | +0.089 |
puter | +0.084 |
awei | +0.075 |
APH | +0.075 |
izoph | +0.073 |
Neg logit contributions | |
xual | -0.065 |
relativity | -0.064 |
blank | -0.064 |
manship | -0.062 |
Ples | -0.062 |
Token | There |
Token ID | 1318 |
Feature activation | -3.66e-02 |
Pos logit contributions | |
utonium | +0.134 |
puter | +0.126 |
APH | +0.114 |
awei | +0.112 |
izoph | +0.110 |
Neg logit contributions | |
xual | -0.098 |
relativity | -0.096 |
blank | -0.095 |
manship | -0.092 |
Ples | -0.091 |
Token | is |
Token ID | 318 |
Feature activation | +2.02e-02 |
Pos logit contributions | |
xual | +0.086 |
relativity | +0.085 |
blank | +0.084 |
Ples | +0.082 |
manship | +0.081 |
Neg logit contributions | |
utonium | -0.118 |
puter | -0.110 |
awei | -0.099 |
APH | -0.098 |
ritten | -0.097 |
Token | undeniable |
Token ID | 36332 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
utonium | +0.057 |
puter | +0.053 |
APH | +0.046 |
awei | +0.046 |
ritten | +0.046 |
Neg logit contributions | |
xual | -0.055 |
blank | -0.055 |
relativity | -0.054 |
Ples | -0.054 |
manship | -0.053 |
Token | arist |
Token ID | 28631 |
Feature activation | +4.35e-02 |
Pos logit contributions | |
utonium | +0.323 |
puter | +0.302 |
APH | +0.273 |
awei | +0.272 |
ritten | +0.270 |
Neg logit contributions | |
xual | -0.240 |
blank | -0.237 |
relativity | -0.231 |
Ples | -0.228 |
manship | -0.226 |
Token | ocratic |
Token ID | 15405 |
Feature activation | +5.26e-01 |
Pos logit contributions | |
utonium | +0.120 |
puter | +0.110 |
APH | +0.096 |
awei | +0.096 |
ritten | +0.095 |
Neg logit contributions | |
xual | -0.123 |
relativity | -0.122 |
blank | -0.121 |
Ples | -0.119 |
manship | -0.118 |
Token | leaning |
Token ID | 21804 |
Feature activation | +7.64e-02 |
Pos logit contributions | |
utonium | +1.671 |
puter | +1.562 |
APH | +1.422 |
awei | +1.417 |
ritten | +1.392 |
Neg logit contributions | |
xual | -1.232 |
blank | -1.212 |
Ples | -1.173 |
relativity | -1.168 |
manship | -1.136 |
Token | in |
Token ID | 287 |
Feature activation | -3.90e-02 |
Pos logit contributions | |
utonium | +0.233 |
puter | +0.219 |
APH | +0.195 |
awei | +0.195 |
ritten | +0.191 |
Neg logit contributions | |
xual | -0.190 |
blank | -0.188 |
relativity | -0.187 |
Ples | -0.182 |
manship | -0.178 |
Token | Nietzsche |
Token ID | 40258 |
Feature activation | +8.05e-03 |
Pos logit contributions | |
xual | +0.089 |
blank | +0.087 |
relativity | +0.086 |
manship | +0.084 |
Ples | +0.083 |
Neg logit contributions | |
utonium | -0.128 |
puter | -0.121 |
APH | -0.109 |
awei | -0.108 |
ritten | -0.106 |
Token | � |
Token ID | 447 |
Feature activation | -1.30e-03 |
Pos logit contributions | |
utonium | +0.030 |
puter | +0.028 |
APH | +0.026 |
awei | +0.025 |
ritten | +0.025 |
Neg logit contributions | |
xual | -0.015 |
relativity | -0.015 |
blank | -0.015 |
Ples | -0.014 |
manship | -0.014 |
Token | � |
Token ID | 247 |
Feature activation | +1.56e-02 |
Pos logit contributions | |
xual | +0.005 |
relativity | +0.005 |
blank | +0.005 |
manship | +0.005 |
Ples | +0.005 |
Neg logit contributions | |
utonium | -0.002 |
puter | -0.002 |
awei | -0.002 |
APH | -0.002 |
izoph | -0.002 |
Token | hell |
Token ID | 5968 |
Feature activation | +3.14e-02 |
Pos logit contributions | |
utonium | +0.047 |
puter | +0.044 |
awei | +0.039 |
APH | +0.039 |
ritten | +0.039 |
Neg logit contributions | |
xual | -0.033 |
relativity | -0.032 |
blank | -0.032 |
manship | -0.031 |
Ples | -0.031 |
Token | he |
Token ID | 339 |
Feature activation | +2.44e-02 |
Pos logit contributions | |
utonium | +0.096 |
puter | +0.090 |
awei | +0.080 |
APH | +0.079 |
ordable | +0.078 |
Neg logit contributions | |
xual | -0.079 |
relativity | -0.077 |
blank | -0.077 |
Ples | -0.075 |
manship | -0.075 |
Token | would |
Token ID | 561 |
Feature activation | +1.97e-02 |
Pos logit contributions | |
utonium | +0.079 |
puter | +0.074 |
awei | +0.066 |
APH | +0.066 |
ritten | +0.065 |
Neg logit contributions | |
xual | -0.057 |
relativity | -0.056 |
blank | -0.056 |
Ples | -0.054 |
manship | -0.054 |
Token | ever |
Token ID | 1683 |
Feature activation | -6.39e-02 |
Pos logit contributions | |
utonium | +0.061 |
puter | +0.058 |
awei | +0.051 |
APH | +0.051 |
ritten | +0.050 |
Neg logit contributions | |
xual | -0.048 |
relativity | -0.048 |
blank | -0.047 |
Ples | -0.046 |
manship | -0.046 |
Token | paraph |
Token ID | 38624 |
Feature activation | -2.10e-02 |
Pos logit contributions | |
xual | +0.156 |
relativity | +0.154 |
blank | +0.152 |
Ples | +0.149 |
manship | +0.149 |
Neg logit contributions | |
utonium | -0.200 |
puter | -0.189 |
awei | -0.167 |
APH | -0.166 |
ritten | -0.164 |
Token | rase |
Token ID | 22789 |
Feature activation | +4.83e-01 |
Pos logit contributions | |
xual | +0.079 |
relativity | +0.078 |
blank | +0.078 |
manship | +0.077 |
Ples | +0.077 |
Neg logit contributions | |
utonium | -0.039 |
puter | -0.034 |
awei | -0.028 |
APH | -0.027 |
izoph | -0.026 |
Token | that |
Token ID | 326 |
Feature activation | +1.49e-02 |
Pos logit contributions | |
utonium | +1.390 |
puter | +1.310 |
APH | +1.148 |
awei | +1.145 |
ritten | +1.140 |
Neg logit contributions | |
xual | -1.267 |
blank | -1.214 |
relativity | -1.208 |
Ples | -1.198 |
manship | -1.192 |
Token | back |
Token ID | 736 |
Feature activation | +1.66e-02 |
Pos logit contributions | |
utonium | +0.048 |
puter | +0.046 |
APH | +0.041 |
awei | +0.041 |
izoph | +0.040 |
Neg logit contributions | |
xual | -0.034 |
relativity | -0.033 |
blank | -0.033 |
manship | -0.033 |
Ples | -0.032 |
Token | to |
Token ID | 284 |
Feature activation | -4.91e-02 |
Pos logit contributions | |
utonium | +0.049 |
puter | +0.046 |
APH | +0.041 |
awei | +0.040 |
ritten | +0.040 |
Neg logit contributions | |
xual | -0.044 |
relativity | -0.043 |
blank | -0.042 |
Ples | -0.041 |
manship | -0.041 |
Token | ownership |
Token ID | 9238 |
Feature activation | -1.02e-02 |
Pos logit contributions | |
xual | +0.127 |
relativity | +0.124 |
blank | +0.123 |
manship | +0.121 |
Ples | +0.120 |
Neg logit contributions | |
utonium | -0.147 |
puter | -0.138 |
awei | -0.122 |
APH | -0.121 |
ritten | -0.119 |
Token | ," |
Token ID | 553 |
Feature activation | -4.87e-02 |
Pos logit contributions | |
xual | +0.024 |
relativity | +0.023 |
blank | +0.023 |
Ples | +0.023 |
manship | +0.023 |
Neg logit contributions | |
utonium | -0.033 |
puter | -0.031 |
APH | -0.027 |
awei | -0.027 |
ritten | -0.027 |
Token | going |
Token ID | 1016 |
Feature activation | -3.87e-02 |
Pos logit contributions | |
utonium | +0.153 |
puter | +0.144 |
awei | +0.127 |
APH | +0.127 |
ordable | +0.124 |
Neg logit contributions | |
xual | -0.117 |
relativity | -0.114 |
blank | -0.113 |
manship | -0.110 |
Ples | -0.110 |
Token | to |
Token ID | 284 |
Feature activation | -1.41e-03 |
Pos logit contributions | |
xual | +0.096 |
relativity | +0.095 |
blank | +0.094 |
manship | +0.093 |
Ples | +0.091 |
Neg logit contributions | |
utonium | -0.120 |
puter | -0.113 |
APH | -0.100 |
awei | -0.100 |
ritten | -0.098 |
Token | have |
Token ID | 423 |
Feature activation | -6.12e-03 |
Pos logit contributions | |
xual | +0.004 |
relativity | +0.003 |
blank | +0.003 |
manship | +0.003 |
Ples | +0.003 |
Neg logit contributions | |
utonium | -0.004 |
puter | -0.004 |
APH | -0.004 |
awei | -0.004 |
ritten | -0.004 |
Token | to |
Token ID | 284 |
Feature activation | +1.63e-02 |
Pos logit contributions | |
xual | +0.016 |
relativity | +0.015 |
blank | +0.015 |
manship | +0.015 |
Ples | +0.015 |
Neg logit contributions | |
utonium | -0.018 |
puter | -0.017 |
APH | -0.015 |
awei | -0.015 |
ordable | -0.015 |
Token | paraph |
Token ID | 38624 |
Feature activation | -2.52e-02 |
Pos logit contributions | |
utonium | +0.050 |
puter | +0.047 |
awei | +0.042 |
APH | +0.042 |
izoph | +0.041 |
Neg logit contributions | |
xual | -0.040 |
relativity | -0.040 |
blank | -0.039 |
manship | -0.038 |
Ples | -0.038 |
Token | rase |
Token ID | 22789 |
Feature activation | +4.75e-01 |
Pos logit contributions | |
xual | +0.094 |
relativity | +0.093 |
blank | +0.093 |
manship | +0.092 |
Ples | +0.091 |
Neg logit contributions | |
utonium | -0.046 |
puter | -0.042 |
awei | -0.033 |
APH | -0.033 |
izoph | -0.032 |
Token | here |
Token ID | 994 |
Feature activation | +1.53e-03 |
Pos logit contributions | |
utonium | +1.400 |
puter | +1.305 |
APH | +1.168 |
awei | +1.151 |
ritten | +1.142 |
Neg logit contributions | |
xual | -1.224 |
relativity | -1.176 |
blank | -1.175 |
manship | -1.151 |
Ples | -1.142 |
Token | — |
Token ID | 851 |
Feature activation | +4.64e-03 |
Pos logit contributions | |
utonium | +0.005 |
puter | +0.005 |
APH | +0.004 |
awei | +0.004 |
ritten | +0.004 |
Neg logit contributions | |
xual | -0.004 |
relativity | -0.003 |
blank | -0.003 |
Ples | -0.003 |
manship | -0.003 |
Token | that |
Token ID | 326 |
Feature activation | -3.74e-03 |
Pos logit contributions | |
utonium | +0.014 |
puter | +0.013 |
APH | +0.011 |
awei | +0.011 |
ordable | +0.011 |
Neg logit contributions | |
xual | -0.012 |
relativity | -0.012 |
blank | -0.012 |
manship | -0.012 |
Ples | -0.012 |
Token | the |
Token ID | 262 |
Feature activation | +3.60e-02 |
Pos logit contributions | |
xual | +0.010 |
blank | +0.010 |
relativity | +0.010 |
manship | +0.009 |
Ples | +0.009 |
Neg logit contributions | |
utonium | -0.011 |
puter | -0.010 |
APH | -0.009 |
awei | -0.009 |
izoph | -0.009 |
Token | reason |
Token ID | 1738 |
Feature activation | -6.89e-02 |
Pos logit contributions | |
utonium | +0.111 |
puter | +0.103 |
APH | +0.092 |
awei | +0.091 |
izoph | +0.090 |
Neg logit contributions | |
xual | -0.091 |
relativity | -0.088 |
blank | -0.088 |
manship | -0.087 |
Ples | -0.085 |
Token | � |
Token ID | 247 |
Feature activation | -2.42e-02 |
Pos logit contributions | |
xual | +0.079 |
relativity | +0.079 |
blank | +0.078 |
manship | +0.077 |
Ples | +0.077 |
Neg logit contributions | |
utonium | -0.045 |
puter | -0.041 |
awei | -0.034 |
APH | -0.034 |
izoph | -0.032 |
Token | t |
Token ID | 83 |
Feature activation | -3.94e-02 |
Pos logit contributions | |
relativity | +0.051 |
xual | +0.051 |
blank | +0.050 |
manship | +0.049 |
Ples | +0.049 |
Neg logit contributions | |
utonium | -0.083 |
puter | -0.078 |
APH | -0.070 |
awei | -0.070 |
ordable | -0.070 |
Token | capture |
Token ID | 8006 |
Feature activation | -4.29e-02 |
Pos logit contributions | |
xual | +0.096 |
blank | +0.093 |
relativity | +0.093 |
Ples | +0.091 |
manship | +0.091 |
Neg logit contributions | |
utonium | -0.123 |
puter | -0.115 |
APH | -0.103 |
awei | -0.103 |
ordable | -0.101 |
Token | how |
Token ID | 703 |
Feature activation | +4.85e-02 |
Pos logit contributions | |
xual | +0.112 |
relativity | +0.110 |
blank | +0.109 |
manship | +0.107 |
Ples | +0.107 |
Neg logit contributions | |
utonium | -0.127 |
puter | -0.119 |
APH | -0.106 |
awei | -0.105 |
ordable | -0.103 |
Token | hor |
Token ID | 3076 |
Feature activation | -4.56e-02 |
Pos logit contributions | |
utonium | +0.148 |
puter | +0.138 |
APH | +0.123 |
awei | +0.123 |
izoph | +0.120 |
Neg logit contributions | |
xual | -0.123 |
relativity | -0.120 |
blank | -0.120 |
manship | -0.117 |
Ples | -0.117 |
Token | rid |
Token ID | 6058 |
Feature activation | +4.54e-01 |
Pos logit contributions | |
xual | +0.151 |
relativity | +0.150 |
blank | +0.147 |
manship | +0.146 |
Ples | +0.145 |
Neg logit contributions | |
utonium | -0.104 |
puter | -0.095 |
APH | -0.081 |
awei | -0.081 |
izoph | -0.079 |
Token | the |
Token ID | 262 |
Feature activation | -4.19e-03 |
Pos logit contributions | |
utonium | +1.304 |
puter | +1.211 |
APH | +1.078 |
awei | +1.059 |
ordable | +1.050 |
Neg logit contributions | |
xual | -1.224 |
relativity | -1.187 |
blank | -1.184 |
manship | -1.152 |
Ples | -1.152 |
Token | patient |
Token ID | 5827 |
Feature activation | +4.80e-02 |
Pos logit contributions | |
xual | +0.011 |
relativity | +0.010 |
blank | +0.010 |
manship | +0.010 |
Ples | +0.010 |
Neg logit contributions | |
utonium | -0.013 |
puter | -0.012 |
APH | -0.011 |
awei | -0.011 |
izoph | -0.011 |
Token | � |
Token ID | 447 |
Feature activation | +6.44e-04 |
Pos logit contributions | |
utonium | +0.159 |
puter | +0.150 |
APH | +0.135 |
awei | +0.134 |
ritten | +0.132 |
Neg logit contributions | |
xual | -0.109 |
relativity | -0.107 |
blank | -0.106 |
manship | -0.103 |
Ples | -0.102 |
Token | � |
Token ID | 247 |
Feature activation | -3.92e-03 |
Pos logit contributions | |
utonium | +0.001 |
puter | +0.001 |
awei | +0.001 |
APH | +0.001 |
izoph | +0.001 |
Neg logit contributions | |
xual | -0.003 |
relativity | -0.003 |
blank | -0.002 |
manship | -0.002 |
Ples | -0.002 |
Token | s |
Token ID | 82 |
Feature activation | +6.08e-03 |
Pos logit contributions | |
xual | +0.007 |
relativity | +0.007 |
blank | +0.007 |
manship | +0.006 |
Ples | +0.006 |
Neg logit contributions | |
utonium | -0.015 |
puter | -0.014 |
awei | -0.013 |
APH | -0.013 |
ritten | -0.013 |
Token | Acceler |
Token ID | 29805 |
Feature activation | -3.86e-02 |
Pos logit contributions | |
xual | +0.095 |
blank | +0.093 |
relativity | +0.092 |
Ples | +0.089 |
manship | +0.088 |
Neg logit contributions | |
utonium | -0.119 |
puter | -0.111 |
APH | -0.100 |
awei | -0.099 |
ritten | -0.097 |
Token | ator |
Token ID | 1352 |
Feature activation | -3.68e-03 |
Pos logit contributions | |
xual | +0.100 |
relativity | +0.098 |
blank | +0.096 |
Ples | +0.094 |
manship | +0.094 |
Neg logit contributions | |
utonium | -0.118 |
puter | -0.110 |
APH | -0.098 |
awei | -0.097 |
ritten | -0.095 |
Token | Mass |
Token ID | 5674 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
xual | +0.009 |
relativity | +0.009 |
blank | +0.009 |
manship | +0.009 |
Ples | +0.009 |
Neg logit contributions | |
utonium | -0.011 |
puter | -0.011 |
APH | -0.009 |
awei | -0.009 |
ritten | -0.009 |
Token | Spect |
Token ID | 13058 |
Feature activation | +9.74e-02 |
Pos logit contributions | |
xual | +0.339 |
blank | +0.327 |
relativity | +0.325 |
manship | +0.318 |
Ples | +0.314 |
Neg logit contributions | |
utonium | -0.388 |
puter | -0.365 |
APH | -0.322 |
awei | -0.319 |
ritten | -0.311 |
Token | rom |
Token ID | 398 |
Feature activation | -5.64e-02 |
Pos logit contributions | |
utonium | +0.209 |
puter | +0.189 |
APH | +0.160 |
awei | +0.159 |
ordable | +0.155 |
Neg logit contributions | |
xual | -0.338 |
relativity | -0.333 |
blank | -0.330 |
manship | -0.323 |
Ples | -0.321 |
Token | etry |
Token ID | 11973 |
Feature activation | +4.47e-01 |
Pos logit contributions | |
xual | +0.133 |
relativity | +0.131 |
blank | +0.129 |
manship | +0.127 |
Ples | +0.126 |
Neg logit contributions | |
utonium | -0.183 |
puter | -0.172 |
APH | -0.154 |
awei | -0.154 |
ordable | -0.152 |
Token | ( |
Token ID | 357 |
Feature activation | -1.57e-02 |
Pos logit contributions | |
utonium | +1.395 |
puter | +1.302 |
APH | +1.172 |
awei | +1.157 |
ordable | +1.129 |
Neg logit contributions | |
xual | -1.103 |
blank | -1.063 |
relativity | -1.039 |
manship | -1.023 |
Lovecraft | -1.013 |
Token | AMS |
Token ID | 40834 |
Feature activation | -1.30e-02 |
Pos logit contributions | |
xual | +0.045 |
relativity | +0.044 |
blank | +0.044 |
Ples | +0.043 |
manship | +0.043 |
Neg logit contributions | |
utonium | -0.043 |
puter | -0.039 |
APH | -0.035 |
awei | -0.034 |
ordable | -0.033 |
Token | ) |
Token ID | 8 |
Feature activation | +1.83e-02 |
Pos logit contributions | |
xual | +0.028 |
blank | +0.027 |
relativity | +0.027 |
Ples | +0.026 |
manship | +0.026 |
Neg logit contributions | |
utonium | -0.045 |
puter | -0.043 |
APH | -0.039 |
awei | -0.039 |
ordable | -0.038 |
Token | tests |
Token ID | 5254 |
Feature activation | -1.10e-02 |
Pos logit contributions | |
utonium | +0.056 |
puter | +0.052 |
APH | +0.046 |
awei | +0.046 |
ordable | +0.045 |
Neg logit contributions | |
xual | -0.046 |
blank | -0.045 |
relativity | -0.045 |
manship | -0.044 |
Ples | -0.044 |
Token | of |
Token ID | 286 |
Feature activation | -1.22e-02 |
Pos logit contributions | |
xual | +0.027 |
blank | +0.027 |
relativity | +0.027 |
Ples | +0.026 |
Lovecraft | +0.026 |
Neg logit contributions | |
utonium | -0.034 |
puter | -0.032 |
awei | -0.029 |
APH | -0.029 |
ordable | -0.028 |
Token | service |
Token ID | 2139 |
Feature activation | -3.26e-02 |
Pos logit contributions | |
utonium | +0.137 |
puter | +0.128 |
awei | +0.113 |
APH | +0.113 |
izoph | +0.110 |
Neg logit contributions | |
xual | -0.125 |
relativity | -0.123 |
blank | -0.123 |
manship | -0.120 |
Ples | -0.119 |
Token | from |
Token ID | 422 |
Feature activation | +5.11e-02 |
Pos logit contributions | |
xual | +0.080 |
relativity | +0.079 |
blank | +0.078 |
manship | +0.076 |
Ples | +0.076 |
Neg logit contributions | |
utonium | -0.102 |
puter | -0.096 |
awei | -0.085 |
APH | -0.085 |
ordable | -0.083 |
Token | 2017 |
Token ID | 2177 |
Feature activation | -6.93e-02 |
Pos logit contributions | |
utonium | +0.152 |
puter | +0.142 |
awei | +0.125 |
APH | +0.125 |
izoph | +0.122 |
Neg logit contributions | |
xual | -0.134 |
relativity | -0.131 |
blank | -0.131 |
manship | -0.128 |
Ples | -0.127 |
Token | . |
Token ID | 13 |
Feature activation | +1.26e-02 |
Pos logit contributions | |
xual | +0.165 |
relativity | +0.162 |
blank | +0.160 |
manship | +0.156 |
Ples | +0.155 |
Neg logit contributions | |
utonium | -0.223 |
puter | -0.209 |
APH | -0.187 |
awei | -0.187 |
ordable | -0.183 |
Token | Nom |
Token ID | 21198 |
Feature activation | -8.80e-02 |
Pos logit contributions | |
utonium | +0.040 |
puter | +0.037 |
APH | +0.033 |
awei | +0.033 |
ordable | +0.032 |
Neg logit contributions | |
xual | -0.031 |
relativity | -0.030 |
blank | -0.030 |
manship | -0.029 |
Lovecraft | -0.028 |
Token | inal |
Token ID | 1292 |
Feature activation | +4.42e-01 |
Pos logit contributions | |
xual | +0.240 |
relativity | +0.234 |
blank | +0.232 |
manship | +0.228 |
Ples | +0.226 |
Neg logit contributions | |
utonium | -0.256 |
puter | -0.240 |
awei | -0.209 |
APH | -0.208 |
ordable | -0.205 |
Token | service |
Token ID | 2139 |
Feature activation | -3.88e-02 |
Pos logit contributions | |
utonium | +1.309 |
puter | +1.214 |
awei | +1.066 |
APH | +1.063 |
ordable | +1.048 |
Neg logit contributions | |
xual | -1.189 |
blank | -1.145 |
relativity | -1.131 |
manship | -1.115 |
Lovecraft | -1.092 |
Token | life |
Token ID | 1204 |
Feature activation | -4.93e-03 |
Pos logit contributions | |
xual | +0.094 |
blank | +0.091 |
relativity | +0.090 |
manship | +0.087 |
Ples | +0.087 |
Neg logit contributions | |
utonium | -0.125 |
puter | -0.117 |
APH | -0.104 |
awei | -0.104 |
ordable | -0.102 |
Token | is |
Token ID | 318 |
Feature activation | +1.17e-02 |
Pos logit contributions | |
xual | +0.011 |
blank | +0.010 |
relativity | +0.010 |
manship | +0.010 |
Ples | +0.010 |
Neg logit contributions | |
utonium | -0.017 |
puter | -0.016 |
awei | -0.014 |
APH | -0.014 |
ordable | -0.014 |
Token | 25 |
Token ID | 1679 |
Feature activation | -3.82e-02 |
Pos logit contributions | |
utonium | +0.030 |
puter | +0.028 |
awei | +0.024 |
APH | +0.024 |
izoph | +0.023 |
Neg logit contributions | |
xual | -0.035 |
relativity | -0.035 |
blank | -0.035 |
manship | -0.034 |
Ples | -0.034 |
Token | years |
Token ID | 812 |
Feature activation | +5.81e-02 |
Pos logit contributions | |
xual | +0.117 |
relativity | +0.115 |
blank | +0.115 |
manship | +0.112 |
Ples | +0.112 |
Neg logit contributions | |
utonium | -0.096 |
puter | -0.089 |
awei | -0.076 |
APH | -0.076 |
ordable | -0.074 |
Token | Soul |
Token ID | 8653 |
Feature activation | -3.65e-03 |
Pos logit contributions | |
utonium | +0.069 |
puter | +0.065 |
APH | +0.057 |
awei | +0.057 |
izoph | +0.057 |
Neg logit contributions | |
xual | -0.061 |
relativity | -0.060 |
blank | -0.059 |
manship | -0.058 |
Ples | -0.057 |
Token | ful |
Token ID | 913 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
xual | +0.009 |
relativity | +0.009 |
blank | +0.009 |
manship | +0.009 |
Ples | +0.009 |
Neg logit contributions | |
utonium | -0.011 |
puter | -0.011 |
APH | -0.009 |
awei | -0.009 |
izoph | -0.009 |
Token | , |
Token ID | 11 |
Feature activation | +1.00e-02 |
Pos logit contributions | |
xual | +0.226 |
relativity | +0.224 |
blank | +0.222 |
Ples | +0.216 |
manship | +0.215 |
Neg logit contributions | |
utonium | -0.335 |
puter | -0.318 |
APH | -0.283 |
awei | -0.281 |
izoph | -0.279 |
Token | Trans |
Token ID | 3602 |
Feature activation | +2.32e-02 |
Pos logit contributions | |
utonium | +0.030 |
puter | +0.028 |
APH | +0.025 |
awei | +0.025 |
izoph | +0.025 |
Neg logit contributions | |
xual | -0.026 |
relativity | -0.025 |
blank | -0.025 |
manship | -0.024 |
Ples | -0.024 |
Token | cend |
Token ID | 15695 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
utonium | +0.069 |
puter | +0.066 |
awei | +0.056 |
izoph | +0.056 |
APH | +0.056 |
Neg logit contributions | |
relativity | -0.061 |
xual | -0.060 |
blank | -0.059 |
Ples | -0.059 |
manship | -0.058 |
Token | ental |
Token ID | 2470 |
Feature activation | +4.27e-01 |
Pos logit contributions | |
relativity | +0.471 |
xual | +0.470 |
blank | +0.462 |
manship | +0.457 |
Ples | +0.457 |
Neg logit contributions | |
utonium | -0.284 |
puter | -0.256 |
awei | -0.213 |
APH | -0.211 |
ritten | -0.207 |
Token | , |
Token ID | 11 |
Feature activation | +6.64e-03 |
Pos logit contributions | |
utonium | +1.359 |
puter | +1.293 |
APH | +1.148 |
izoph | +1.134 |
awei | +1.128 |
Neg logit contributions | |
xual | -0.991 |
relativity | -0.975 |
blank | -0.973 |
manship | -0.945 |
Ples | -0.943 |
Token | Kn |
Token ID | 6102 |
Feature activation | +3.46e-02 |
Pos logit contributions | |
utonium | +0.020 |
puter | +0.019 |
APH | +0.017 |
awei | +0.016 |
izoph | +0.016 |
Neg logit contributions | |
xual | -0.017 |
relativity | -0.017 |
blank | -0.017 |
manship | -0.016 |
Ples | -0.016 |
Token | ows |
Token ID | 1666 |
Feature activation | -5.37e-02 |
Pos logit contributions | |
utonium | +0.096 |
puter | +0.088 |
awei | +0.076 |
APH | +0.075 |
ritten | +0.075 |
Neg logit contributions | |
xual | -0.100 |
relativity | -0.100 |
blank | -0.098 |
manship | -0.096 |
Ples | -0.096 |
Token | value |
Token ID | 1988 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
xual | +0.133 |
relativity | +0.130 |
blank | +0.129 |
Ples | +0.126 |
manship | +0.123 |
Neg logit contributions | |
utonium | -0.168 |
puter | -0.157 |
awei | -0.139 |
APH | -0.138 |
ordable | -0.136 |
Token | of |
Token ID | 286 |
Feature activation | +1.32e-02 |
Pos logit contributions | |
utonium | +0.327 |
puter | +0.308 |
awei | +0.275 |
APH | +0.275 |
ordable | +0.268 |
Neg logit contributions | |
xual | -0.247 |
blank | -0.241 |
relativity | -0.240 |
Ples | -0.238 |
manship | -0.233 |
Token | salt |
Token ID | 8268 |
Feature activation | -8.13e-02 |
Pos logit contributions | |
xual | +0.104 |
relativity | +0.102 |
blank | +0.101 |
manship | +0.100 |
Ples | +0.099 |
Neg logit contributions | |
utonium | -0.111 |
puter | -0.105 |
awei | -0.091 |
APH | -0.091 |
izoph | -0.089 |
Token | trucks |
Token ID | 13960 |
Feature activation | +5.81e-02 |
Pos logit contributions | |
xual | +0.202 |
relativity | +0.197 |
blank | +0.193 |
manship | +0.193 |
Lovecraft | +0.188 |
Neg logit contributions | |
utonium | -0.253 |
puter | -0.242 |
APH | -0.212 |
awei | -0.210 |
ordable | -0.207 |
Token | because |
Token ID | 780 |
Feature activation | -9.91e-03 |
Pos logit contributions | |
utonium | +0.191 |
puter | +0.180 |
awei | +0.161 |
APH | +0.161 |
ordable | +0.158 |
Neg logit contributions | |
xual | -0.133 |
relativity | -0.130 |
blank | -0.129 |
manship | -0.125 |
Ples | -0.125 |
Token | the |
Token ID | 262 |
Feature activation | -7.92e-03 |
Pos logit contributions | |
xual | +0.025 |
relativity | +0.024 |
blank | +0.024 |
manship | +0.023 |
Ples | +0.023 |
Neg logit contributions | |
utonium | -0.031 |
puter | -0.029 |
awei | -0.026 |
APH | -0.026 |
izoph | -0.025 |
Token | grid |
Token ID | 10706 |
Feature activation | -4.93e-02 |
Pos logit contributions | |
xual | +0.022 |
relativity | +0.021 |
blank | +0.021 |
manship | +0.020 |
Ples | +0.020 |
Neg logit contributions | |
utonium | -0.023 |
puter | -0.021 |
awei | -0.019 |
APH | -0.019 |
izoph | -0.018 |
Token | lock |
Token ID | 5354 |
Feature activation | +4.21e-01 |
Pos logit contributions | |
xual | +0.144 |
relativity | +0.141 |
blank | +0.140 |
Ples | +0.137 |
manship | +0.136 |
Neg logit contributions | |
utonium | -0.133 |
puter | -0.125 |
awei | -0.107 |
APH | -0.107 |
ritten | -0.104 |
Token | was |
Token ID | 373 |
Feature activation | +5.85e-03 |
Pos logit contributions | |
utonium | +1.304 |
puter | +1.239 |
APH | +1.092 |
awei | +1.087 |
ordable | +1.066 |
Neg logit contributions | |
xual | -1.032 |
relativity | -1.005 |
blank | -0.999 |
Ples | -0.969 |
manship | -0.965 |
Token | too |
Token ID | 1165 |
Feature activation | -5.83e-02 |
Pos logit contributions | |
utonium | +0.018 |
puter | +0.017 |
APH | +0.015 |
awei | +0.015 |
izoph | +0.014 |
Neg logit contributions | |
xual | -0.015 |
relativity | -0.015 |
blank | -0.015 |
manship | -0.014 |
Ples | -0.014 |
Token | thick |
Token ID | 6546 |
Feature activation | +2.47e-02 |
Pos logit contributions | |
xual | +0.145 |
relativity | +0.141 |
blank | +0.140 |
manship | +0.138 |
Ples | +0.137 |
Neg logit contributions | |
utonium | -0.181 |
puter | -0.171 |
awei | -0.152 |
APH | -0.151 |
ordable | -0.148 |
Token | to |
Token ID | 284 |
Feature activation | -2.67e-02 |
Pos logit contributions | |
utonium | +0.079 |
puter | +0.074 |
APH | +0.066 |
awei | +0.066 |
ordable | +0.065 |
Neg logit contributions | |
xual | -0.059 |
relativity | -0.058 |
blank | -0.057 |
Ples | -0.056 |
manship | -0.055 |
Token | navigate |
Token ID | 16500 |
Feature activation | +3.47e-02 |
Pos logit contributions | |
xual | +0.065 |
relativity | +0.064 |
blank | +0.063 |
manship | +0.062 |
Ples | +0.061 |
Neg logit contributions | |
utonium | -0.084 |
puter | -0.079 |
APH | -0.070 |
awei | -0.070 |
izoph | -0.069 |
Token | ple |
Token ID | 1154 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
xual | +0.141 |
relativity | +0.140 |
blank | +0.138 |
manship | +0.136 |
Ples | +0.136 |
Neg logit contributions | |
utonium | -0.107 |
puter | -0.098 |
APH | -0.084 |
awei | -0.084 |
ritten | -0.081 |
Token | tes |
Token ID | 4879 |
Feature activation | +4.98e-02 |
Pos logit contributions | |
utonium | +0.370 |
puter | +0.348 |
ordable | +0.310 |
APH | +0.309 |
awei | +0.308 |
Neg logit contributions | |
relativity | -0.251 |
xual | -0.250 |
blank | -0.246 |
manship | -0.239 |
Ples | -0.234 |
Token | glucose |
Token ID | 15701 |
Feature activation | -4.07e-02 |
Pos logit contributions | |
utonium | +0.140 |
puter | +0.131 |
APH | +0.114 |
awei | +0.114 |
ritten | +0.112 |
Neg logit contributions | |
xual | -0.138 |
relativity | -0.136 |
blank | -0.135 |
manship | -0.133 |
Ples | -0.131 |
Token | and |
Token ID | 290 |
Feature activation | -1.52e-02 |
Pos logit contributions | |
xual | +0.100 |
relativity | +0.099 |
blank | +0.098 |
manship | +0.096 |
Ples | +0.096 |
Neg logit contributions | |
utonium | -0.127 |
puter | -0.119 |
APH | -0.106 |
awei | -0.105 |
ordable | -0.103 |
Token | glyc |
Token ID | 40232 |
Feature activation | +7.52e-04 |
Pos logit contributions | |
xual | +0.039 |
blank | +0.038 |
relativity | +0.038 |
manship | +0.037 |
Ples | +0.037 |
Neg logit contributions | |
utonium | -0.046 |
puter | -0.043 |
awei | -0.038 |
APH | -0.038 |
izoph | -0.037 |
Token | ogen |
Token ID | 6644 |
Feature activation | +4.08e-01 |
Pos logit contributions | |
utonium | +0.002 |
puter | +0.002 |
awei | +0.001 |
APH | +0.001 |
ritten | +0.001 |
Neg logit contributions | |
xual | -0.002 |
relativity | -0.002 |
blank | -0.002 |
manship | -0.002 |
Ples | -0.002 |
Token | rapidly |
Token ID | 8902 |
Feature activation | +3.67e-02 |
Pos logit contributions | |
utonium | +1.270 |
puter | +1.196 |
APH | +1.061 |
awei | +1.045 |
ordable | +1.027 |
Neg logit contributions | |
xual | -0.995 |
relativity | -0.974 |
blank | -0.964 |
Ples | -0.951 |
manship | -0.944 |
Token | , |
Token ID | 11 |
Feature activation | -1.49e-02 |
Pos logit contributions | |
utonium | +0.116 |
puter | +0.108 |
APH | +0.097 |
awei | +0.096 |
ordable | +0.094 |
Neg logit contributions | |
xual | -0.088 |
relativity | -0.087 |
blank | -0.086 |
manship | -0.084 |
Ples | -0.084 |
Token | forcing |
Token ID | 10833 |
Feature activation | +1.52e-02 |
Pos logit contributions | |
xual | +0.038 |
relativity | +0.037 |
blank | +0.037 |
manship | +0.036 |
Ples | +0.036 |
Neg logit contributions | |
utonium | -0.046 |
puter | -0.043 |
APH | -0.038 |
awei | -0.038 |
ordable | -0.037 |
Token | the |
Token ID | 262 |
Feature activation | -1.58e-03 |
Pos logit contributions | |
utonium | +0.043 |
puter | +0.040 |
awei | +0.035 |
APH | +0.035 |
izoph | +0.035 |
Neg logit contributions | |
xual | -0.042 |
relativity | -0.041 |
blank | -0.041 |
manship | -0.040 |
Ples | -0.040 |
Token | body |
Token ID | 1767 |
Feature activation | -1.05e-02 |
Pos logit contributions | |
xual | +0.005 |
blank | +0.004 |
relativity | +0.004 |
manship | +0.004 |
Ples | +0.004 |
Neg logit contributions | |
utonium | -0.004 |
puter | -0.004 |
APH | -0.003 |
awei | -0.003 |
izoph | -0.003 |
Token | to |
Token ID | 284 |
Feature activation | +5.29e-02 |
Pos logit contributions | |
xual | +0.157 |
relativity | +0.155 |
blank | +0.154 |
Ples | +0.150 |
manship | +0.149 |
Neg logit contributions | |
utonium | -0.198 |
puter | -0.186 |
APH | -0.165 |
awei | -0.164 |
ordable | -0.161 |
Token | use |
Token ID | 779 |
Feature activation | +2.14e-03 |
Pos logit contributions | |
utonium | +0.164 |
puter | +0.154 |
APH | +0.137 |
awei | +0.137 |
izoph | +0.134 |
Neg logit contributions | |
xual | -0.131 |
relativity | -0.129 |
blank | -0.128 |
Ples | -0.125 |
manship | -0.125 |
Token | cannabis |
Token ID | 9499 |
Feature activation | +2.83e-02 |
Pos logit contributions | |
utonium | +0.006 |
puter | +0.006 |
APH | +0.005 |
awei | +0.005 |
izoph | +0.005 |
Neg logit contributions | |
xual | -0.006 |
relativity | -0.006 |
blank | -0.006 |
Ples | -0.006 |
manship | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | -6.12e-03 |
Pos logit contributions | |
utonium | +0.092 |
puter | +0.087 |
APH | +0.078 |
awei | +0.077 |
ordable | +0.076 |
Neg logit contributions | |
xual | -0.066 |
relativity | -0.065 |
blank | -0.065 |
Ples | -0.063 |
manship | -0.063 |
Token | Ed |
Token ID | 1717 |
Feature activation | +6.45e-03 |
Pos logit contributions | |
xual | +0.015 |
relativity | +0.015 |
blank | +0.015 |
manship | +0.014 |
Ples | +0.014 |
Neg logit contributions | |
utonium | -0.019 |
puter | -0.018 |
APH | -0.016 |
awei | -0.016 |
ordable | -0.016 |
Token | ibles |
Token ID | 18764 |
Feature activation | +4.05e-01 |
Pos logit contributions | |
utonium | +0.018 |
puter | +0.017 |
APH | +0.015 |
awei | +0.015 |
ordable | +0.014 |
Neg logit contributions | |
xual | -0.018 |
relativity | -0.018 |
blank | -0.018 |
manship | -0.017 |
Ples | -0.017 |
Token | , |
Token ID | 11 |
Feature activation | -9.34e-04 |
Pos logit contributions | |
utonium | +1.288 |
puter | +1.213 |
APH | +1.083 |
awei | +1.068 |
ordable | +1.060 |
Neg logit contributions | |
xual | -0.961 |
relativity | -0.945 |
blank | -0.941 |
Ples | -0.919 |
manship | -0.908 |
Token | vapor |
Token ID | 20199 |
Feature activation | -9.75e-03 |
Pos logit contributions | |
xual | +0.002 |
relativity | +0.002 |
blank | +0.002 |
manship | +0.002 |
Ples | +0.002 |
Neg logit contributions | |
utonium | -0.003 |
puter | -0.003 |
APH | -0.002 |
awei | -0.002 |
izoph | -0.002 |
Token | izers |
Token ID | 11341 |
Feature activation | +6.27e-02 |
Pos logit contributions | |
xual | +0.033 |
relativity | +0.033 |
blank | +0.032 |
manship | +0.032 |
Ples | +0.032 |
Neg logit contributions | |
utonium | -0.021 |
puter | -0.020 |
APH | -0.016 |
awei | -0.016 |
izoph | -0.016 |
Token | … |
Token ID | 1399 |
Feature activation | -7.75e-02 |
Pos logit contributions | |
utonium | +0.208 |
puter | +0.196 |
APH | +0.175 |
awei | +0.174 |
ordable | +0.171 |
Neg logit contributions | |
xual | -0.142 |
relativity | -0.140 |
blank | -0.139 |
Ples | -0.135 |
manship | -0.134 |
Token |
|
Token ID | 198 |
Feature activation | -4.52e-03 |
Pos logit contributions | |
xual | +0.189 |
relativity | +0.187 |
blank | +0.183 |
Ples | +0.180 |
manship | +0.179 |
Neg logit contributions | |
utonium | -0.244 |
puter | -0.229 |
APH | -0.204 |
awei | -0.203 |
ordable | -0.199 |
Token | live |
Token ID | 2107 |
Feature activation | +4.44e-02 |
Pos logit contributions | |
utonium | +0.008 |
puter | +0.008 |
awei | +0.007 |
APH | +0.007 |
ordable | +0.007 |
Neg logit contributions | |
xual | -0.007 |
relativity | -0.007 |
blank | -0.007 |
Ples | -0.007 |
manship | -0.007 |
Token | far |
Token ID | 1290 |
Feature activation | +3.92e-02 |
Pos logit contributions | |
utonium | +0.132 |
puter | +0.123 |
awei | +0.109 |
APH | +0.109 |
ordable | +0.107 |
Neg logit contributions | |
xual | -0.118 |
blank | -0.113 |
relativity | -0.113 |
Ples | -0.111 |
manship | -0.110 |
Token | away |
Token ID | 1497 |
Feature activation | -4.81e-02 |
Pos logit contributions | |
utonium | +0.148 |
puter | +0.141 |
awei | +0.128 |
APH | +0.128 |
ritten | +0.125 |
Neg logit contributions | |
xual | -0.072 |
relativity | -0.068 |
blank | -0.067 |
manship | -0.066 |
Ples | -0.065 |
Token | . |
Token ID | 13 |
Feature activation | +4.24e-02 |
Pos logit contributions | |
xual | +0.119 |
relativity | +0.116 |
blank | +0.115 |
manship | +0.113 |
Ples | +0.112 |
Neg logit contributions | |
utonium | -0.150 |
puter | -0.141 |
awei | -0.125 |
APH | -0.125 |
ordable | -0.122 |
Token | Gam |
Token ID | 14014 |
Feature activation | +2.04e-03 |
Pos logit contributions | |
utonium | +0.134 |
puter | +0.126 |
APH | +0.112 |
awei | +0.112 |
ordable | +0.109 |
Neg logit contributions | |
xual | -0.103 |
relativity | -0.101 |
blank | -0.100 |
manship | -0.097 |
Ples | -0.096 |
Token | ers |
Token ID | 364 |
Feature activation | +3.98e-01 |
Pos logit contributions | |
utonium | +0.008 |
puter | +0.008 |
awei | +0.007 |
APH | +0.007 |
ritten | +0.007 |
Neg logit contributions | |
xual | -0.003 |
relativity | -0.003 |
blank | -0.003 |
Ples | -0.003 |
Lovecraft | -0.003 |
Token | from |
Token ID | 422 |
Feature activation | +2.52e-02 |
Pos logit contributions | |
utonium | +1.445 |
puter | +1.374 |
APH | +1.237 |
awei | +1.234 |
ritten | +1.219 |
Neg logit contributions | |
xual | -0.777 |
relativity | -0.755 |
blank | -0.747 |
Ples | -0.727 |
manship | -0.713 |
Token | all |
Token ID | 477 |
Feature activation | +7.01e-03 |
Pos logit contributions | |
utonium | +0.076 |
puter | +0.071 |
awei | +0.063 |
APH | +0.063 |
ordable | +0.062 |
Neg logit contributions | |
xual | -0.065 |
relativity | -0.063 |
blank | -0.063 |
manship | -0.061 |
Ples | -0.061 |
Token | over |
Token ID | 625 |
Feature activation | -1.55e-03 |
Pos logit contributions | |
utonium | +0.021 |
puter | +0.020 |
awei | +0.018 |
APH | +0.018 |
ordable | +0.017 |
Neg logit contributions | |
xual | -0.018 |
blank | -0.018 |
relativity | -0.017 |
manship | -0.017 |
Ples | -0.017 |
Token | the |
Token ID | 262 |
Feature activation | +5.38e-02 |
Pos logit contributions | |
xual | +0.004 |
blank | +0.004 |
relativity | +0.004 |
manship | +0.004 |
Ples | +0.004 |
Neg logit contributions | |
utonium | -0.004 |
puter | -0.004 |
awei | -0.004 |
APH | -0.004 |
ordable | -0.003 |
Token | country |
Token ID | 1499 |
Feature activation | +3.36e-02 |
Pos logit contributions | |
utonium | +0.178 |
puter | +0.169 |
awei | +0.151 |
APH | +0.150 |
ordable | +0.147 |
Neg logit contributions | |
xual | -0.122 |
relativity | -0.118 |
blank | -0.118 |
manship | -0.117 |
Ples | -0.115 |
Token | that |
Token ID | 326 |
Feature activation | +3.02e-02 |
Pos logit contributions | |
utonium | +0.077 |
puter | +0.072 |
awei | +0.064 |
APH | +0.064 |
ritten | +0.062 |
Neg logit contributions | |
xual | -0.070 |
relativity | -0.069 |
blank | -0.068 |
manship | -0.066 |
Ples | -0.066 |
Token | holds |
Token ID | 6622 |
Feature activation | +3.16e-02 |
Pos logit contributions | |
utonium | +0.099 |
puter | +0.093 |
awei | +0.083 |
APH | +0.083 |
ordable | +0.081 |
Neg logit contributions | |
xual | -0.071 |
relativity | -0.068 |
blank | -0.068 |
manship | -0.066 |
Ples | -0.066 |
Token | a |
Token ID | 257 |
Feature activation | +1.99e-02 |
Pos logit contributions | |
utonium | +0.088 |
puter | +0.082 |
awei | +0.072 |
APH | +0.072 |
ordable | +0.071 |
Neg logit contributions | |
xual | -0.089 |
relativity | -0.086 |
blank | -0.086 |
manship | -0.084 |
Ples | -0.084 |
Token | " |
Token ID | 366 |
Feature activation | +2.96e-02 |
Pos logit contributions | |
utonium | +0.058 |
puter | +0.054 |
awei | +0.048 |
APH | +0.048 |
ritten | +0.047 |
Neg logit contributions | |
xual | -0.053 |
relativity | -0.052 |
blank | -0.052 |
manship | -0.051 |
Ples | -0.050 |
Token | nom |
Token ID | 26601 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
utonium | +0.091 |
puter | +0.086 |
awei | +0.076 |
APH | +0.076 |
ordable | +0.074 |
Neg logit contributions | |
xual | -0.075 |
relativity | -0.074 |
blank | -0.071 |
Ples | -0.071 |
manship | -0.071 |
Token | inal |
Token ID | 1292 |
Feature activation | +3.94e-01 |
Pos logit contributions | |
xual | +0.431 |
relativity | +0.426 |
blank | +0.423 |
manship | +0.417 |
Ples | +0.416 |
Neg logit contributions | |
utonium | -0.256 |
puter | -0.232 |
awei | -0.192 |
APH | -0.191 |
ordable | -0.184 |
Token | interest |
Token ID | 1393 |
Feature activation | -4.34e-02 |
Pos logit contributions | |
utonium | +1.169 |
puter | +1.091 |
awei | +0.964 |
APH | +0.962 |
ordable | +0.950 |
Neg logit contributions | |
xual | -1.044 |
relativity | -0.999 |
blank | -0.998 |
manship | -0.978 |
Ples | -0.971 |
Token | " |
Token ID | 1 |
Feature activation | -1.92e-02 |
Pos logit contributions | |
xual | +0.101 |
relativity | +0.098 |
blank | +0.096 |
Ples | +0.094 |
manship | +0.094 |
Neg logit contributions | |
utonium | -0.143 |
puter | -0.135 |
APH | -0.120 |
awei | -0.120 |
ordable | -0.118 |
Token | in |
Token ID | 287 |
Feature activation | -4.64e-02 |
Pos logit contributions | |
xual | +0.049 |
relativity | +0.049 |
blank | +0.048 |
manship | +0.047 |
Ples | +0.047 |
Neg logit contributions | |
utonium | -0.058 |
puter | -0.054 |
awei | -0.048 |
APH | -0.048 |
ordable | -0.047 |
Token | White |
Token ID | 2635 |
Feature activation | +4.47e-02 |
Pos logit contributions | |
xual | +0.127 |
relativity | +0.124 |
blank | +0.123 |
manship | +0.121 |
Ples | +0.120 |
Neg logit contributions | |
utonium | -0.133 |
puter | -0.124 |
APH | -0.109 |
awei | -0.109 |
ordable | -0.106 |
Token | Marsh |
Token ID | 9786 |
Feature activation | +6.24e-02 |
Pos logit contributions | |
utonium | +0.145 |
puter | +0.135 |
awei | +0.121 |
APH | +0.119 |
ritten | +0.119 |
Neg logit contributions | |
xual | -0.107 |
relativity | -0.104 |
blank | -0.101 |
Ples | -0.099 |
manship | -0.098 |
Token | while |
Token ID | 981 |
Feature activation | -1.31e-02 |
Pos logit contributions | |
utonium | +0.051 |
puter | +0.048 |
awei | +0.042 |
APH | +0.042 |
izoph | +0.041 |
Neg logit contributions | |
xual | -0.040 |
relativity | -0.039 |
blank | -0.039 |
manship | -0.038 |
Ples | -0.037 |
Token | everyone |
Token ID | 2506 |
Feature activation | +1.07e-02 |
Pos logit contributions | |
xual | +0.035 |
relativity | +0.034 |
blank | +0.034 |
manship | +0.033 |
Ples | +0.033 |
Neg logit contributions | |
utonium | -0.038 |
puter | -0.036 |
APH | -0.032 |
awei | -0.032 |
ordable | -0.031 |
Token | was |
Token ID | 373 |
Feature activation | -1.87e-02 |
Pos logit contributions | |
utonium | +0.036 |
puter | +0.034 |
awei | +0.030 |
APH | +0.030 |
ordable | +0.029 |
Neg logit contributions | |
xual | -0.024 |
relativity | -0.023 |
blank | -0.023 |
manship | -0.023 |
Ples | -0.023 |
Token | in |
Token ID | 287 |
Feature activation | -4.74e-03 |
Pos logit contributions | |
xual | +0.047 |
relativity | +0.046 |
blank | +0.046 |
manship | +0.045 |
Ples | +0.045 |
Neg logit contributions | |
utonium | -0.058 |
puter | -0.054 |
awei | -0.048 |
APH | -0.048 |
ritten | -0.047 |
Token | grid |
Token ID | 10706 |
Feature activation | -5.64e-02 |
Pos logit contributions | |
xual | +0.012 |
relativity | +0.012 |
blank | +0.012 |
manship | +0.012 |
Ples | +0.011 |
Neg logit contributions | |
utonium | -0.014 |
puter | -0.013 |
APH | -0.012 |
awei | -0.012 |
ordable | -0.012 |
Token | lock |
Token ID | 5354 |
Feature activation | +3.91e-01 |
Pos logit contributions | |
xual | +0.166 |
relativity | +0.163 |
blank | +0.162 |
manship | +0.159 |
Ples | +0.159 |
Neg logit contributions | |
utonium | -0.150 |
puter | -0.139 |
APH | -0.121 |
awei | -0.120 |
izoph | -0.117 |
Token | , |
Token ID | 11 |
Feature activation | -8.46e-03 |
Pos logit contributions | |
utonium | +1.249 |
puter | +1.188 |
APH | +1.052 |
awei | +1.041 |
ordable | +1.029 |
Neg logit contributions | |
xual | -0.918 |
relativity | -0.899 |
blank | -0.887 |
Ples | -0.867 |
manship | -0.859 |
Token | they |
Token ID | 484 |
Feature activation | -2.70e-03 |
Pos logit contributions | |
xual | +0.022 |
relativity | +0.022 |
blank | +0.022 |
manship | +0.021 |
Ples | +0.021 |
Neg logit contributions | |
utonium | -0.025 |
puter | -0.024 |
APH | -0.021 |
awei | -0.021 |
ordable | -0.020 |
Token | couldn |
Token ID | 3521 |
Feature activation | -2.78e-02 |
Pos logit contributions | |
xual | +0.007 |
relativity | +0.007 |
blank | +0.006 |
manship | +0.006 |
Ples | +0.006 |
Neg logit contributions | |
utonium | -0.008 |
puter | -0.008 |
APH | -0.007 |
awei | -0.007 |
ritten | -0.007 |
Token | � |
Token ID | 447 |
Feature activation | -5.37e-03 |
Pos logit contributions | |
xual | +0.061 |
relativity | +0.060 |
blank | +0.060 |
manship | +0.059 |
Ples | +0.058 |
Neg logit contributions | |
utonium | -0.094 |
puter | -0.089 |
awei | -0.080 |
APH | -0.079 |
izoph | -0.078 |
Token | � |
Token ID | 247 |
Feature activation | -5.94e-03 |
Pos logit contributions | |
xual | +0.020 |
relativity | +0.020 |
blank | +0.020 |
manship | +0.019 |
Ples | +0.019 |
Neg logit contributions | |
utonium | -0.010 |
puter | -0.009 |
awei | -0.007 |
APH | -0.007 |
izoph | -0.007 |
Token | the |
Token ID | 262 |
Feature activation | +9.30e-02 |
Pos logit contributions | |
utonium | +0.108 |
puter | +0.100 |
APH | +0.089 |
awei | +0.089 |
izoph | +0.087 |
Neg logit contributions | |
xual | -0.094 |
relativity | -0.093 |
blank | -0.093 |
manship | -0.091 |
Ples | -0.089 |
Token | til |
Token ID | 21502 |
Feature activation | -7.40e-02 |
Pos logit contributions | |
utonium | +0.280 |
puter | +0.263 |
awei | +0.234 |
APH | +0.233 |
izoph | +0.231 |
Neg logit contributions | |
xual | -0.236 |
blank | -0.232 |
relativity | -0.232 |
manship | -0.226 |
Ples | -0.223 |
Token | ap |
Token ID | 499 |
Feature activation | +4.51e-02 |
Pos logit contributions | |
xual | +0.249 |
relativity | +0.248 |
blank | +0.242 |
Ples | +0.241 |
manship | +0.240 |
Neg logit contributions | |
utonium | -0.167 |
puter | -0.151 |
APH | -0.129 |
awei | -0.127 |
izoph | -0.125 |
Token | ia |
Token ID | 544 |
Feature activation | +5.49e-02 |
Pos logit contributions | |
utonium | +0.138 |
puter | +0.129 |
APH | +0.115 |
izoph | +0.114 |
awei | +0.114 |
Neg logit contributions | |
xual | -0.114 |
relativity | -0.113 |
blank | -0.111 |
Ples | -0.109 |
manship | -0.108 |
Token | fil |
Token ID | 1226 |
Feature activation | +6.54e-02 |
Pos logit contributions | |
utonium | +0.168 |
puter | +0.157 |
APH | +0.141 |
awei | +0.139 |
ritten | +0.137 |
Neg logit contributions | |
xual | -0.137 |
relativity | -0.135 |
blank | -0.135 |
Ples | -0.129 |
manship | -0.129 |
Token | lets |
Token ID | 5289 |
Feature activation | +3.89e-01 |
Pos logit contributions | |
utonium | +0.196 |
puter | +0.183 |
APH | +0.160 |
ritten | +0.159 |
ordable | +0.159 |
Neg logit contributions | |
xual | -0.171 |
relativity | -0.170 |
blank | -0.165 |
manship | -0.164 |
Lovecraft | -0.162 |
Token | are |
Token ID | 389 |
Feature activation | +4.86e-02 |
Pos logit contributions | |
utonium | +1.142 |
puter | +1.059 |
APH | +0.941 |
awei | +0.932 |
ritten | +0.924 |
Neg logit contributions | |
xual | -1.025 |
relativity | -1.003 |
blank | -0.997 |
Ples | -0.970 |
manship | -0.963 |
Token | the |
Token ID | 262 |
Feature activation | +4.46e-02 |
Pos logit contributions | |
utonium | +0.152 |
puter | +0.142 |
awei | +0.127 |
APH | +0.127 |
ritten | +0.125 |
Neg logit contributions | |
xual | -0.119 |
relativity | -0.117 |
blank | -0.114 |
manship | -0.113 |
Ples | -0.111 |
Token | same |
Token ID | 976 |
Feature activation | -4.21e-02 |
Pos logit contributions | |
utonium | +0.152 |
puter | +0.143 |
awei | +0.130 |
APH | +0.129 |
izoph | +0.127 |
Neg logit contributions | |
xual | -0.096 |
relativity | -0.095 |
blank | -0.093 |
manship | -0.092 |
Ples | -0.090 |
Token | exact |
Token ID | 2748 |
Feature activation | -2.86e-02 |
Pos logit contributions | |
xual | +0.104 |
relativity | +0.104 |
blank | +0.102 |
manship | +0.100 |
Ples | +0.099 |
Neg logit contributions | |
utonium | -0.129 |
puter | -0.121 |
APH | -0.108 |
awei | -0.108 |
izoph | -0.107 |
Token | size |
Token ID | 2546 |
Feature activation | +6.28e-02 |
Pos logit contributions | |
xual | +0.071 |
relativity | +0.070 |
blank | +0.069 |
manship | +0.068 |
Ples | +0.067 |
Neg logit contributions | |
utonium | -0.088 |
puter | -0.083 |
awei | -0.074 |
APH | -0.074 |
izoph | -0.073 |
Token | � |
Token ID | 251 |
Feature activation | -1.53e-02 |
Pos logit contributions | |
xual | +0.114 |
relativity | +0.113 |
blank | +0.112 |
Ples | +0.110 |
manship | +0.110 |
Neg logit contributions | |
utonium | -0.093 |
puter | -0.086 |
awei | -0.074 |
APH | -0.074 |
ordable | -0.071 |
Token | � |
Token ID | 564 |
Feature activation | -4.63e-02 |
Pos logit contributions | |
xual | +0.040 |
relativity | +0.039 |
blank | +0.038 |
manship | +0.038 |
Ples | +0.038 |
Neg logit contributions | |
utonium | -0.046 |
puter | -0.043 |
APH | -0.039 |
awei | -0.038 |
ordable | -0.038 |
Token | � |
Token ID | 250 |
Feature activation | -4.31e-02 |
Pos logit contributions | |
xual | +0.148 |
relativity | +0.146 |
blank | +0.145 |
manship | +0.143 |
Ples | +0.143 |
Neg logit contributions | |
utonium | -0.111 |
puter | -0.102 |
awei | -0.087 |
APH | -0.087 |
izoph | -0.084 |
Token | rac |
Token ID | 11510 |
Feature activation | +5.63e-02 |
Pos logit contributions | |
xual | +0.115 |
relativity | +0.113 |
blank | +0.111 |
manship | +0.110 |
Ples | +0.109 |
Neg logit contributions | |
utonium | -0.126 |
puter | -0.118 |
APH | -0.105 |
awei | -0.104 |
ordable | -0.102 |
Token | etr |
Token ID | 21879 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
utonium | +0.206 |
puter | +0.195 |
APH | +0.176 |
awei | +0.176 |
ordable | +0.173 |
Neg logit contributions | |
xual | -0.111 |
relativity | -0.109 |
blank | -0.107 |
manship | -0.104 |
Ples | -0.104 |
Token | ack |
Token ID | 441 |
Feature activation | +3.87e-01 |
Pos logit contributions | |
utonium | +0.249 |
puter | +0.222 |
awei | +0.184 |
APH | +0.184 |
izoph | +0.176 |
Neg logit contributions | |
xual | -0.441 |
relativity | -0.435 |
blank | -0.429 |
manship | -0.425 |
Ples | -0.425 |
Token | � |
Token ID | 447 |
Feature activation | -2.45e-02 |
Pos logit contributions | |
utonium | +1.207 |
puter | +1.146 |
APH | +1.014 |
awei | +1.014 |
ordable | +0.994 |
Neg logit contributions | |
xual | -0.955 |
relativity | -0.929 |
blank | -0.918 |
manship | -0.898 |
Ples | -0.896 |
Token | � |
Token ID | 251 |
Feature activation | -1.19e-02 |
Pos logit contributions | |
xual | +0.084 |
relativity | +0.084 |
blank | +0.083 |
Ples | +0.082 |
manship | +0.082 |
Neg logit contributions | |
utonium | -0.053 |
puter | -0.048 |
awei | -0.040 |
APH | -0.040 |
izoph | -0.038 |
Token | bass |
Token ID | 12702 |
Feature activation | -6.12e-02 |
Pos logit contributions | |
xual | +0.029 |
relativity | +0.029 |
blank | +0.028 |
Ples | +0.028 |
manship | +0.028 |
Neg logit contributions | |
utonium | -0.037 |
puter | -0.035 |
APH | -0.031 |
awei | -0.031 |
ordable | -0.030 |
Token | driver |
Token ID | 4639 |
Feature activation | -2.43e-02 |
Pos logit contributions | |
xual | +0.145 |
relativity | +0.140 |
blank | +0.138 |
manship | +0.136 |
Ples | +0.136 |
Neg logit contributions | |
utonium | -0.198 |
puter | -0.190 |
APH | -0.168 |
awei | -0.166 |
ordable | -0.164 |
Token | , |
Token ID | 11 |
Feature activation | -4.72e-03 |
Pos logit contributions | |
xual | +0.057 |
relativity | +0.056 |
blank | +0.055 |
manship | +0.054 |
Ples | +0.054 |
Neg logit contributions | |
utonium | -0.079 |
puter | -0.075 |
APH | -0.067 |
awei | -0.067 |
ordable | -0.065 |
Token | : |
Token ID | 25 |
Feature activation | -3.90e-02 |
Pos logit contributions | |
xual | +0.094 |
relativity | +0.093 |
blank | +0.091 |
Ples | +0.089 |
manship | +0.088 |
Neg logit contributions | |
utonium | -0.137 |
puter | -0.130 |
APH | -0.117 |
awei | -0.116 |
ritten | -0.116 |
Token | 14 |
Token ID | 1415 |
Feature activation | -2.13e-02 |
Pos logit contributions | |
xual | +0.096 |
relativity | +0.094 |
blank | +0.093 |
manship | +0.091 |
Ples | +0.091 |
Neg logit contributions | |
utonium | -0.122 |
puter | -0.115 |
awei | -0.102 |
APH | -0.102 |
ritten | -0.100 |
Token | games |
Token ID | 1830 |
Feature activation | -9.66e-04 |
Pos logit contributions | |
xual | +0.054 |
relativity | +0.053 |
blank | +0.052 |
manship | +0.051 |
Ples | +0.051 |
Neg logit contributions | |
utonium | -0.065 |
puter | -0.061 |
APH | -0.054 |
awei | -0.054 |
ritten | -0.053 |
Token | over |
Token ID | 625 |
Feature activation | -2.23e-02 |
Pos logit contributions | |
xual | +0.002 |
relativity | +0.002 |
blank | +0.002 |
Ples | +0.002 |
manship | +0.002 |
Neg logit contributions | |
utonium | -0.003 |
puter | -0.003 |
awei | -0.003 |
APH | -0.003 |
ordable | -0.003 |
Token | Gam |
Token ID | 14014 |
Feature activation | -2.14e-02 |
Pos logit contributions | |
xual | +0.058 |
relativity | +0.056 |
blank | +0.056 |
manship | +0.055 |
Ples | +0.054 |
Neg logit contributions | |
utonium | -0.067 |
puter | -0.063 |
awei | -0.056 |
APH | -0.055 |
izoph | -0.054 |
Token | ers |
Token ID | 364 |
Feature activation | +3.85e-01 |
Pos logit contributions | |
xual | +0.055 |
relativity | +0.054 |
blank | +0.053 |
Ples | +0.052 |
manship | +0.052 |
Neg logit contributions | |
utonium | -0.065 |
puter | -0.061 |
awei | -0.054 |
APH | -0.054 |
izoph | -0.053 |
Token | 2 |
Token ID | 17 |
Feature activation | -1.39e-02 |
Pos logit contributions | |
utonium | +1.190 |
puter | +1.114 |
APH | +1.001 |
awei | +0.990 |
izoph | +0.984 |
Neg logit contributions | |
xual | -0.955 |
relativity | -0.932 |
blank | -0.907 |
Ples | -0.904 |
manship | -0.897 |
Token | and |
Token ID | 290 |
Feature activation | -3.35e-02 |
Pos logit contributions | |
xual | +0.033 |
relativity | +0.033 |
blank | +0.032 |
manship | +0.032 |
Ples | +0.031 |
Neg logit contributions | |
utonium | -0.044 |
puter | -0.042 |
awei | -0.037 |
APH | -0.037 |
izoph | -0.036 |
Token | Titan |
Token ID | 11977 |
Feature activation | +5.69e-03 |
Pos logit contributions | |
xual | +0.085 |
relativity | +0.083 |
blank | +0.083 |
manship | +0.081 |
Ples | +0.080 |
Neg logit contributions | |
utonium | -0.103 |
puter | -0.096 |
awei | -0.085 |
APH | -0.085 |
izoph | -0.084 |
Token | , |
Token ID | 11 |
Feature activation | -4.85e-04 |
Pos logit contributions | |
utonium | +0.018 |
puter | +0.017 |
awei | +0.016 |
APH | +0.015 |
izoph | +0.015 |
Neg logit contributions | |
xual | -0.013 |
relativity | -0.013 |
blank | -0.013 |
manship | -0.013 |
Ples | -0.013 |
Token | adding |
Token ID | 4375 |
Feature activation | +1.67e-02 |
Pos logit contributions | |
xual | +0.001 |
relativity | +0.001 |
blank | +0.001 |
manship | +0.001 |
Ples | +0.001 |
Neg logit contributions | |
utonium | -0.002 |
puter | -0.001 |
awei | -0.001 |
APH | -0.001 |
ordable | -0.001 |
Token | terms |
Token ID | 2846 |
Feature activation | -2.35e-02 |
Pos logit contributions | |
xual | +0.092 |
blank | +0.089 |
relativity | +0.089 |
manship | +0.087 |
Ples | +0.086 |
Neg logit contributions | |
utonium | -0.108 |
puter | -0.101 |
APH | -0.090 |
awei | -0.089 |
ritten | -0.088 |
Token | ; |
Token ID | 26 |
Feature activation | +1.16e-03 |
Pos logit contributions | |
xual | +0.053 |
relativity | +0.052 |
blank | +0.052 |
Ples | +0.051 |
manship | +0.050 |
Neg logit contributions | |
utonium | -0.078 |
puter | -0.073 |
APH | -0.066 |
awei | -0.065 |
ritten | -0.064 |
Token | for |
Token ID | 329 |
Feature activation | +8.25e-03 |
Pos logit contributions | |
utonium | +0.004 |
puter | +0.003 |
APH | +0.003 |
awei | +0.003 |
ritten | +0.003 |
Neg logit contributions | |
xual | -0.003 |
blank | -0.003 |
relativity | -0.003 |
manship | -0.003 |
Ples | -0.003 |
Token | James |
Token ID | 3700 |
Feature activation | +4.25e-02 |
Pos logit contributions | |
utonium | +0.027 |
puter | +0.025 |
APH | +0.022 |
awei | +0.022 |
ritten | +0.022 |
Neg logit contributions | |
xual | -0.019 |
blank | -0.019 |
relativity | -0.019 |
manship | -0.018 |
Ples | -0.018 |
Token | Fraz |
Token ID | 36914 |
Feature activation | +5.98e-02 |
Pos logit contributions | |
utonium | +0.140 |
puter | +0.131 |
APH | +0.118 |
awei | +0.117 |
ritten | +0.115 |
Neg logit contributions | |
xual | -0.098 |
relativity | -0.096 |
blank | -0.095 |
manship | -0.092 |
Ples | -0.091 |
Token | er |
Token ID | 263 |
Feature activation | +3.84e-01 |
Pos logit contributions | |
utonium | +0.289 |
puter | +0.277 |
awei | +0.258 |
APH | +0.257 |
izoph | +0.254 |
Neg logit contributions | |
xual | -0.046 |
relativity | -0.043 |
blank | -0.042 |
manship | -0.039 |
Ples | -0.038 |
Token | , |
Token ID | 11 |
Feature activation | +9.76e-03 |
Pos logit contributions | |
utonium | +1.343 |
puter | +1.263 |
APH | +1.146 |
awei | +1.141 |
izoph | +1.124 |
Neg logit contributions | |
xual | -0.798 |
blank | -0.765 |
relativity | -0.749 |
manship | -0.743 |
Ples | -0.738 |
Token | all |
Token ID | 477 |
Feature activation | +1.14e-02 |
Pos logit contributions | |
utonium | +0.033 |
puter | +0.031 |
APH | +0.028 |
awei | +0.028 |
izoph | +0.027 |
Neg logit contributions | |
xual | -0.022 |
blank | -0.021 |
relativity | -0.021 |
manship | -0.021 |
Ples | -0.020 |
Token | of |
Token ID | 286 |
Feature activation | +3.13e-02 |
Pos logit contributions | |
utonium | +0.041 |
puter | +0.039 |
APH | +0.035 |
awei | +0.035 |
izoph | +0.035 |
Neg logit contributions | |
xual | -0.023 |
blank | -0.022 |
relativity | -0.021 |
manship | -0.021 |
Ples | -0.021 |
Token | myth |
Token ID | 7918 |
Feature activation | +8.32e-02 |
Pos logit contributions | |
utonium | +0.099 |
puter | +0.092 |
APH | +0.083 |
awei | +0.082 |
izoph | +0.081 |
Neg logit contributions | |
xual | -0.076 |
blank | -0.074 |
relativity | -0.073 |
manship | -0.072 |
Ples | -0.071 |
Token | � |
Token ID | 447 |
Feature activation | +2.17e-02 |
Pos logit contributions | |
utonium | +0.270 |
puter | +0.253 |
APH | +0.227 |
awei | +0.224 |
ritten | +0.221 |
Neg logit contributions | |
xual | -0.196 |
blank | -0.191 |
relativity | -0.190 |
Ples | -0.186 |
manship | -0.185 |
Token | traditionally |
Token ID | 16083 |
Feature activation | +1.45e-02 |
Pos logit contributions | |
utonium | +0.095 |
puter | +0.089 |
APH | +0.080 |
awei | +0.079 |
ritten | +0.077 |
Neg logit contributions | |
xual | -0.081 |
blank | -0.079 |
relativity | -0.079 |
Ples | -0.077 |
manship | -0.077 |
Token | the |
Token ID | 262 |
Feature activation | -9.72e-03 |
Pos logit contributions | |
utonium | +0.041 |
puter | +0.038 |
APH | +0.034 |
awei | +0.034 |
ritten | +0.033 |
Neg logit contributions | |
xual | -0.040 |
blank | -0.039 |
relativity | -0.038 |
Ples | -0.038 |
manship | -0.038 |
Token | realm |
Token ID | 13360 |
Feature activation | -9.38e-02 |
Pos logit contributions | |
xual | +0.021 |
blank | +0.020 |
relativity | +0.020 |
manship | +0.020 |
Ples | +0.019 |
Neg logit contributions | |
utonium | -0.034 |
puter | -0.032 |
APH | -0.029 |
awei | -0.029 |
ritten | -0.028 |
Token | of |
Token ID | 286 |
Feature activation | +3.26e-02 |
Pos logit contributions | |
xual | +0.185 |
relativity | +0.180 |
blank | +0.179 |
Ples | +0.174 |
manship | +0.173 |
Neg logit contributions | |
utonium | -0.339 |
puter | -0.321 |
APH | -0.291 |
awei | -0.289 |
ritten | -0.285 |
Token | metaph |
Token ID | 13738 |
Feature activation | +6.16e-02 |
Pos logit contributions | |
utonium | +0.101 |
puter | +0.095 |
APH | +0.085 |
awei | +0.084 |
ritten | +0.083 |
Neg logit contributions | |
xual | -0.080 |
blank | -0.079 |
relativity | -0.078 |
Ples | -0.077 |
manship | -0.077 |
Token | ysics |
Token ID | 23154 |
Feature activation | +3.80e-01 |
Pos logit contributions | |
utonium | +0.189 |
puter | +0.176 |
APH | +0.157 |
awei | +0.156 |
ordable | +0.154 |
Neg logit contributions | |
xual | -0.156 |
relativity | -0.154 |
blank | -0.152 |
Ples | -0.149 |
manship | -0.149 |
Token | or |
Token ID | 393 |
Feature activation | -1.35e-02 |
Pos logit contributions | |
utonium | +1.208 |
puter | +1.144 |
APH | +1.033 |
awei | +1.010 |
ritten | +0.998 |
Neg logit contributions | |
xual | -0.897 |
blank | -0.868 |
relativity | -0.863 |
Ples | -0.848 |
manship | -0.836 |
Token | the |
Token ID | 262 |
Feature activation | +3.65e-03 |
Pos logit contributions | |
xual | +0.032 |
blank | +0.031 |
relativity | +0.030 |
Ples | +0.030 |
manship | +0.030 |
Neg logit contributions | |
utonium | -0.043 |
puter | -0.041 |
APH | -0.037 |
awei | -0.036 |
izoph | -0.036 |
Token | transcend |
Token ID | 26231 |
Feature activation | -3.21e-02 |
Pos logit contributions | |
utonium | +0.013 |
puter | +0.013 |
APH | +0.012 |
awei | +0.012 |
izoph | +0.011 |
Neg logit contributions | |
xual | -0.007 |
blank | -0.007 |
relativity | -0.007 |
manship | -0.007 |
Ples | -0.006 |
Token | ent |
Token ID | 298 |
Feature activation | +4.04e-02 |
Pos logit contributions | |
xual | +0.108 |
relativity | +0.106 |
blank | +0.106 |
Ples | +0.104 |
manship | +0.104 |
Neg logit contributions | |
utonium | -0.072 |
puter | -0.066 |
APH | -0.055 |
awei | -0.055 |
ritten | -0.054 |
Token | , |
Token ID | 11 |
Feature activation | +9.99e-03 |
Pos logit contributions | |
utonium | +0.142 |
puter | +0.136 |
APH | +0.123 |
awei | +0.122 |
ritten | +0.120 |
Neg logit contributions | |
xual | -0.082 |
blank | -0.080 |
relativity | -0.078 |
manship | -0.077 |
Ples | -0.077 |
Token | urga |
Token ID | 45098 |
Feature activation | +3.34e-02 |
Pos logit contributions | |
utonium | +0.051 |
puter | +0.047 |
awei | +0.043 |
APH | +0.043 |
izoph | +0.042 |
Neg logit contributions | |
xual | -0.041 |
relativity | -0.041 |
manship | -0.040 |
blank | -0.039 |
Ples | -0.039 |
Token | on |
Token ID | 261 |
Feature activation | +2.23e-01 |
Pos logit contributions | |
utonium | +0.101 |
puter | +0.095 |
awei | +0.084 |
APH | +0.083 |
ritten | +0.083 |
Neg logit contributions | |
xual | -0.087 |
relativity | -0.084 |
blank | -0.082 |
Lovecraft | -0.079 |
Ples | -0.079 |
Token | , |
Token ID | 11 |
Feature activation | +8.08e-02 |
Pos logit contributions | |
utonium | +0.706 |
puter | +0.668 |
awei | +0.599 |
APH | +0.596 |
izoph | +0.583 |
Neg logit contributions | |
xual | -0.540 |
relativity | -0.517 |
blank | -0.514 |
manship | -0.501 |
Ples | -0.497 |
Token | Far |
Token ID | 6755 |
Feature activation | -6.68e-02 |
Pos logit contributions | |
utonium | +0.249 |
puter | +0.234 |
awei | +0.209 |
APH | +0.208 |
ordable | +0.204 |
Neg logit contributions | |
xual | -0.203 |
relativity | -0.197 |
blank | -0.196 |
manship | -0.191 |
Ples | -0.187 |
Token | id |
Token ID | 312 |
Feature activation | -6.14e-02 |
Pos logit contributions | |
xual | +0.160 |
relativity | +0.157 |
blank | +0.153 |
manship | +0.151 |
Ples | +0.151 |
Neg logit contributions | |
utonium | -0.216 |
puter | -0.203 |
awei | -0.181 |
APH | -0.180 |
izoph | -0.177 |
Token | abad |
Token ID | 17325 |
Feature activation | +3.80e-01 |
Pos logit contributions | |
xual | +0.194 |
relativity | +0.192 |
blank | +0.187 |
Ples | +0.186 |
manship | +0.185 |
Neg logit contributions | |
utonium | -0.150 |
puter | -0.139 |
awei | -0.119 |
APH | -0.117 |
ordable | -0.114 |
Token | and |
Token ID | 290 |
Feature activation | -2.26e-03 |
Pos logit contributions | |
utonium | +1.195 |
puter | +1.129 |
awei | +1.009 |
APH | +1.006 |
ritten | +0.981 |
Neg logit contributions | |
xual | -0.923 |
relativity | -0.887 |
blank | -0.879 |
manship | -0.857 |
Ples | -0.856 |
Token | other |
Token ID | 584 |
Feature activation | +9.12e-03 |
Pos logit contributions | |
xual | +0.006 |
relativity | +0.006 |
blank | +0.006 |
manship | +0.005 |
Ples | +0.005 |
Neg logit contributions | |
utonium | -0.007 |
puter | -0.007 |
awei | -0.006 |
APH | -0.006 |
ordable | -0.006 |
Token | districts |
Token ID | 12815 |
Feature activation | +8.48e-02 |
Pos logit contributions | |
utonium | +0.028 |
puter | +0.026 |
awei | +0.023 |
APH | +0.023 |
ordable | +0.023 |
Neg logit contributions | |
xual | -0.023 |
blank | -0.023 |
relativity | -0.023 |
manship | -0.022 |
Ples | -0.022 |
Token | of |
Token ID | 286 |
Feature activation | -5.30e-02 |
Pos logit contributions | |
utonium | +0.272 |
puter | +0.255 |
APH | +0.230 |
awei | +0.229 |
ordable | +0.225 |
Neg logit contributions | |
xual | -0.202 |
relativity | -0.196 |
blank | -0.193 |
Ples | -0.187 |
manship | -0.186 |
Token | H |
Token ID | 367 |
Feature activation | +6.21e-03 |
Pos logit contributions | |
xual | +0.147 |
relativity | +0.143 |
blank | +0.143 |
manship | +0.140 |
Ples | +0.139 |
Neg logit contributions | |
utonium | -0.149 |
puter | -0.139 |
APH | -0.122 |
awei | -0.122 |
ritten | -0.119 |
Token | linked |
Token ID | 6692 |
Feature activation | -1.65e-02 |
Pos logit contributions | |
xual | +0.028 |
blank | +0.027 |
relativity | +0.027 |
Ples | +0.026 |
manship | +0.026 |
Neg logit contributions | |
utonium | -0.024 |
puter | -0.022 |
APH | -0.019 |
awei | -0.019 |
ritten | -0.019 |
Token | to |
Token ID | 284 |
Feature activation | -1.12e-02 |
Pos logit contributions | |
xual | +0.041 |
relativity | +0.041 |
blank | +0.040 |
manship | +0.039 |
Ples | +0.039 |
Neg logit contributions | |
utonium | -0.051 |
puter | -0.048 |
APH | -0.043 |
awei | -0.043 |
ritten | -0.042 |
Token | Obama |
Token ID | 2486 |
Feature activation | -6.83e-02 |
Pos logit contributions | |
xual | +0.029 |
relativity | +0.029 |
blank | +0.029 |
manship | +0.028 |
Ples | +0.028 |
Neg logit contributions | |
utonium | -0.033 |
puter | -0.031 |
awei | -0.028 |
APH | -0.028 |
ritten | -0.027 |
Token | 's |
Token ID | 338 |
Feature activation | -3.20e-02 |
Pos logit contributions | |
xual | +0.136 |
relativity | +0.133 |
blank | +0.131 |
Ples | +0.128 |
manship | +0.126 |
Neg logit contributions | |
utonium | -0.246 |
puter | -0.234 |
awei | -0.211 |
APH | -0.211 |
ritten | -0.207 |
Token | chair |
Token ID | 5118 |
Feature activation | -4.37e-02 |
Pos logit contributions | |
xual | +0.085 |
relativity | +0.082 |
blank | +0.082 |
Ples | +0.080 |
manship | +0.080 |
Neg logit contributions | |
utonium | -0.095 |
puter | -0.088 |
awei | -0.078 |
APH | -0.078 |
ordable | -0.076 |
Token | manship |
Token ID | 25428 |
Feature activation | -5.37e-01 |
Pos logit contributions | |
xual | +0.017 |
relativity | +0.014 |
blank | +0.012 |
Ples | +0.011 |
Lovecraft | +0.009 |
Neg logit contributions | |
utonium | -0.228 |
puter | -0.220 |
awei | -0.206 |
APH | -0.205 |
ordable | -0.203 |
Token | of |
Token ID | 286 |
Feature activation | +1.42e-03 |
Pos logit contributions | |
xual | +1.129 |
relativity | +1.107 |
blank | +1.095 |
Ples | +1.062 |
manship | +1.048 |
Neg logit contributions | |
utonium | -1.874 |
puter | -1.769 |
awei | -1.601 |
APH | -1.596 |
ritten | -1.561 |
Token | the |
Token ID | 262 |
Feature activation | -9.62e-04 |
Pos logit contributions | |
utonium | +0.004 |
puter | +0.004 |
awei | +0.003 |
APH | +0.003 |
ritten | +0.003 |
Neg logit contributions | |
xual | -0.004 |
relativity | -0.004 |
blank | -0.004 |
Ples | -0.004 |
manship | -0.004 |
Token | Chicago |
Token ID | 4842 |
Feature activation | -4.19e-02 |
Pos logit contributions | |
xual | +0.002 |
relativity | +0.002 |
blank | +0.002 |
manship | +0.002 |
Ples | +0.002 |
Neg logit contributions | |
utonium | -0.003 |
puter | -0.003 |
awei | -0.003 |
APH | -0.003 |
ritten | -0.002 |
Token | Ann |
Token ID | 5506 |
Feature activation | -3.77e-02 |
Pos logit contributions | |
xual | +0.094 |
blank | +0.090 |
relativity | +0.090 |
manship | +0.087 |
Ples | +0.087 |
Neg logit contributions | |
utonium | -0.141 |
puter | -0.132 |
APH | -0.120 |
awei | -0.120 |
ritten | -0.117 |
Token | enberg |
Token ID | 23140 |
Feature activation | +6.71e-03 |
Pos logit contributions | |
xual | +0.077 |
relativity | +0.073 |
blank | +0.072 |
Ples | +0.070 |
manship | +0.070 |
Neg logit contributions | |
utonium | -0.137 |
puter | -0.130 |
APH | -0.116 |
awei | -0.116 |
ordable | -0.115 |
Token | Gay |
Token ID | 16013 |
Feature activation | +4.06e-02 |
Pos logit contributions | |
utonium | +0.032 |
puter | +0.030 |
awei | +0.026 |
APH | +0.026 |
ritten | +0.026 |
Neg logit contributions | |
xual | -0.024 |
relativity | -0.024 |
blank | -0.023 |
manship | -0.023 |
Ples | -0.023 |
Token | Away |
Token ID | 21986 |
Feature activation | -8.07e-02 |
Pos logit contributions | |
utonium | +0.126 |
puter | +0.118 |
APH | +0.104 |
awei | +0.104 |
ritten | +0.103 |
Neg logit contributions | |
xual | -0.100 |
relativity | -0.099 |
blank | -0.098 |
manship | -0.096 |
Ples | -0.095 |
Token | � |
Token ID | 447 |
Feature activation | +3.67e-02 |
Pos logit contributions | |
xual | +0.193 |
relativity | +0.191 |
blank | +0.188 |
Ples | +0.183 |
manship | +0.183 |
Neg logit contributions | |
utonium | -0.256 |
puter | -0.241 |
APH | -0.215 |
awei | -0.215 |
ritten | -0.211 |
Token | � |
Token ID | 247 |
Feature activation | +8.63e-04 |
Pos logit contributions | |
utonium | +0.072 |
puter | +0.063 |
awei | +0.052 |
APH | +0.052 |
ritten | +0.050 |
Neg logit contributions | |
xual | -0.133 |
relativity | -0.133 |
blank | -0.132 |
Ples | -0.130 |
manship | -0.129 |
Token | ser |
Token ID | 1055 |
Feature activation | -2.77e-02 |
Pos logit contributions | |
utonium | +0.003 |
puter | +0.003 |
APH | +0.002 |
awei | +0.002 |
ritten | +0.002 |
Neg logit contributions | |
xual | -0.002 |
relativity | -0.002 |
blank | -0.002 |
Ples | -0.002 |
manship | -0.002 |
Token | mons |
Token ID | 11567 |
Feature activation | -5.16e-01 |
Pos logit contributions | |
xual | +0.045 |
relativity | +0.044 |
blank | +0.042 |
Ples | +0.041 |
manship | +0.041 |
Neg logit contributions | |
utonium | -0.111 |
puter | -0.105 |
APH | -0.097 |
awei | -0.097 |
ritten | -0.095 |
Token | , |
Token ID | 11 |
Feature activation | -3.82e-02 |
Pos logit contributions | |
xual | +1.172 |
relativity | +1.153 |
blank | +1.144 |
Ples | +1.113 |
manship | +1.110 |
Neg logit contributions | |
utonium | -1.713 |
puter | -1.612 |
APH | -1.444 |
awei | -1.442 |
izoph | -1.414 |
Token | the |
Token ID | 262 |
Feature activation | -7.92e-03 |
Pos logit contributions | |
xual | +0.094 |
relativity | +0.093 |
blank | +0.092 |
manship | +0.090 |
Ples | +0.090 |
Neg logit contributions | |
utonium | -0.119 |
puter | -0.111 |
APH | -0.099 |
awei | -0.099 |
ritten | -0.097 |
Token | man |
Token ID | 582 |
Feature activation | +2.07e-02 |
Pos logit contributions | |
xual | +0.022 |
relativity | +0.021 |
blank | +0.021 |
manship | +0.021 |
Ples | +0.021 |
Neg logit contributions | |
utonium | -0.023 |
puter | -0.021 |
awei | -0.018 |
APH | -0.018 |
izoph | -0.018 |
Token | who |
Token ID | 508 |
Feature activation | +1.70e-03 |
Pos logit contributions | |
utonium | +0.062 |
puter | +0.058 |
awei | +0.051 |
APH | +0.051 |
ritten | +0.050 |
Neg logit contributions | |
xual | -0.054 |
relativity | -0.053 |
blank | -0.052 |
Ples | -0.051 |
manship | -0.051 |
Token | once |
Token ID | 1752 |
Feature activation | +1.30e-02 |
Pos logit contributions | |
utonium | +0.005 |
puter | +0.005 |
APH | +0.004 |
awei | +0.004 |
ordable | +0.004 |
Neg logit contributions | |
xual | -0.004 |
relativity | -0.004 |
blank | -0.004 |
Ples | -0.004 |
manship | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | +2.64e-02 |
Pos logit contributions | |
utonium | +0.103 |
puter | +0.096 |
awei | +0.085 |
APH | +0.084 |
ordable | +0.082 |
Neg logit contributions | |
xual | -0.102 |
relativity | -0.101 |
blank | -0.100 |
manship | -0.098 |
Ples | -0.098 |
Token | Department |
Token ID | 2732 |
Feature activation | +4.74e-02 |
Pos logit contributions | |
utonium | +0.080 |
puter | +0.075 |
awei | +0.067 |
APH | +0.067 |
ordable | +0.065 |
Neg logit contributions | |
xual | -0.067 |
relativity | -0.066 |
blank | -0.065 |
manship | -0.064 |
Ples | -0.064 |
Token | of |
Token ID | 286 |
Feature activation | +2.25e-02 |
Pos logit contributions | |
utonium | +0.171 |
puter | +0.162 |
APH | +0.146 |
awei | +0.146 |
ordable | +0.143 |
Neg logit contributions | |
xual | -0.093 |
relativity | -0.092 |
blank | -0.091 |
Ples | -0.087 |
manship | -0.087 |
Token | Education |
Token ID | 7868 |
Feature activation | -1.67e-02 |
Pos logit contributions | |
utonium | +0.060 |
puter | +0.056 |
APH | +0.048 |
awei | +0.048 |
ordable | +0.048 |
Neg logit contributions | |
xual | -0.066 |
relativity | -0.064 |
blank | -0.064 |
Ples | -0.063 |
manship | -0.062 |
Token | recons |
Token ID | 23898 |
Feature activation | -3.27e-02 |
Pos logit contributions | |
xual | +0.037 |
blank | +0.036 |
relativity | +0.036 |
Ples | +0.034 |
Lovecraft | +0.034 |
Neg logit contributions | |
utonium | -0.056 |
puter | -0.053 |
awei | -0.047 |
APH | -0.047 |
ordable | -0.046 |
Token | iders |
Token ID | 4157 |
Feature activation | -5.08e-01 |
Pos logit contributions | |
xual | +0.073 |
relativity | +0.072 |
blank | +0.071 |
Ples | +0.069 |
manship | +0.068 |
Neg logit contributions | |
utonium | -0.110 |
puter | -0.103 |
awei | -0.093 |
APH | -0.092 |
ordable | -0.091 |
Token | the |
Token ID | 262 |
Feature activation | +3.21e-02 |
Pos logit contributions | |
xual | +1.290 |
relativity | +1.259 |
blank | +1.257 |
manship | +1.227 |
Ples | +1.227 |
Neg logit contributions | |
utonium | -1.546 |
puter | -1.447 |
APH | -1.286 |
awei | -1.284 |
ordable | -1.256 |
Token | guidance |
Token ID | 11154 |
Feature activation | +1.33e-02 |
Pos logit contributions | |
utonium | +0.101 |
puter | +0.095 |
awei | +0.084 |
APH | +0.084 |
izoph | +0.083 |
Neg logit contributions | |
xual | -0.078 |
relativity | -0.076 |
blank | -0.076 |
manship | -0.074 |
Ples | -0.074 |
Token | provided |
Token ID | 2810 |
Feature activation | +2.84e-02 |
Pos logit contributions | |
utonium | +0.043 |
puter | +0.040 |
awei | +0.036 |
APH | +0.036 |
ritten | +0.035 |
Neg logit contributions | |
xual | -0.031 |
relativity | -0.031 |
blank | -0.030 |
Ples | -0.030 |
manship | -0.030 |
Token | to |
Token ID | 284 |
Feature activation | +2.71e-02 |
Pos logit contributions | |
utonium | +0.087 |
puter | +0.081 |
awei | +0.072 |
APH | +0.072 |
ordable | +0.071 |
Neg logit contributions | |
xual | -0.071 |
relativity | -0.070 |
blank | -0.070 |
Ples | -0.068 |
manship | -0.068 |
Token | schools |
Token ID | 4266 |
Feature activation | +4.48e-02 |
Pos logit contributions | |
utonium | +0.079 |
puter | +0.073 |
awei | +0.065 |
APH | +0.065 |
izoph | +0.063 |
Neg logit contributions | |
xual | -0.072 |
relativity | -0.071 |
blank | -0.071 |
manship | -0.069 |
Ples | -0.069 |
Token | in |
Token ID | 287 |
Feature activation | -5.75e-02 |
Pos logit contributions | |
utonium | +0.145 |
puter | +0.136 |
awei | +0.122 |
APH | +0.122 |
ordable | +0.120 |
Neg logit contributions | |
xual | -0.111 |
relativity | -0.108 |
blank | -0.106 |
Ples | -0.104 |
manship | -0.103 |
Token | the |
Token ID | 262 |
Feature activation | -8.59e-02 |
Pos logit contributions | |
xual | +0.153 |
relativity | +0.148 |
blank | +0.147 |
manship | +0.145 |
Ples | +0.143 |
Neg logit contributions | |
utonium | -0.169 |
puter | -0.157 |
APH | -0.139 |
awei | -0.139 |
ordable | -0.137 |
Token | agreement |
Token ID | 4381 |
Feature activation | -6.10e-03 |
Pos logit contributions | |
xual | +0.216 |
relativity | +0.209 |
blank | +0.208 |
manship | +0.204 |
Ples | +0.202 |
Neg logit contributions | |
utonium | -0.266 |
puter | -0.248 |
awei | -0.221 |
APH | -0.220 |
ordable | -0.217 |
Token | . |
Token ID | 13 |
Feature activation | -6.08e-02 |
Pos logit contributions | |
xual | +0.014 |
relativity | +0.014 |
blank | +0.014 |
Ples | +0.014 |
manship | +0.013 |
Neg logit contributions | |
utonium | -0.020 |
puter | -0.019 |
awei | -0.017 |
APH | -0.017 |
ritten | -0.016 |
Token | Analy |
Token ID | 16213 |
Feature activation | -9.04e-02 |
Pos logit contributions | |
xual | +0.151 |
relativity | +0.147 |
blank | +0.143 |
manship | +0.139 |
Ples | +0.137 |
Neg logit contributions | |
utonium | -0.191 |
puter | -0.179 |
APH | -0.161 |
awei | -0.159 |
ordable | -0.156 |
Token | sts |
Token ID | 6448 |
Feature activation | -4.69e-01 |
Pos logit contributions | |
xual | +0.189 |
relativity | +0.187 |
blank | +0.185 |
Ples | +0.179 |
manship | +0.179 |
Neg logit contributions | |
utonium | -0.318 |
puter | -0.298 |
awei | -0.269 |
APH | -0.269 |
ritten | -0.265 |
Token | that |
Token ID | 326 |
Feature activation | -4.17e-02 |
Pos logit contributions | |
xual | +1.237 |
relativity | +1.221 |
blank | +1.210 |
manship | +1.185 |
Ples | +1.181 |
Neg logit contributions | |
utonium | -1.387 |
puter | -1.295 |
awei | -1.143 |
APH | -1.140 |
izoph | -1.115 |
Token | have |
Token ID | 423 |
Feature activation | -3.62e-02 |
Pos logit contributions | |
xual | +0.110 |
relativity | +0.108 |
blank | +0.107 |
manship | +0.105 |
Ples | +0.105 |
Neg logit contributions | |
utonium | -0.123 |
puter | -0.115 |
awei | -0.102 |
APH | -0.102 |
izoph | -0.099 |
Token | followed |
Token ID | 3940 |
Feature activation | +1.52e-02 |
Pos logit contributions | |
xual | +0.101 |
relativity | +0.099 |
blank | +0.099 |
manship | +0.096 |
Ples | +0.096 |
Neg logit contributions | |
utonium | -0.102 |
puter | -0.095 |
awei | -0.083 |
APH | -0.083 |
ritten | -0.081 |
Token | the |
Token ID | 262 |
Feature activation | -4.52e-02 |
Pos logit contributions | |
utonium | +0.044 |
puter | +0.041 |
APH | +0.036 |
awei | +0.036 |
ordable | +0.035 |
Neg logit contributions | |
xual | -0.041 |
blank | -0.040 |
relativity | -0.040 |
Ples | -0.039 |
manship | -0.039 |
Token | process |
Token ID | 1429 |
Feature activation | -9.76e-02 |
Pos logit contributions | |
xual | +0.111 |
relativity | +0.107 |
blank | +0.107 |
manship | +0.104 |
Ples | +0.104 |
Neg logit contributions | |
utonium | -0.143 |
puter | -0.133 |
awei | -0.119 |
APH | -0.119 |
ordable | -0.117 |
Token | u |
Token ID | 84 |
Feature activation | -5.21e-02 |
Pos logit contributions | |
utonium | +0.165 |
puter | +0.156 |
awei | +0.141 |
APH | +0.141 |
izoph | +0.139 |
Neg logit contributions | |
xual | -0.092 |
relativity | -0.090 |
blank | -0.090 |
manship | -0.087 |
Ples | -0.086 |
Token | will |
Token ID | 481 |
Feature activation | -3.27e-02 |
Pos logit contributions | |
xual | +0.113 |
relativity | +0.109 |
blank | +0.108 |
Ples | +0.105 |
manship | +0.104 |
Neg logit contributions | |
utonium | -0.179 |
puter | -0.168 |
APH | -0.152 |
awei | -0.152 |
ordable | -0.148 |
Token | lose |
Token ID | 4425 |
Feature activation | -1.09e-02 |
Pos logit contributions | |
xual | +0.080 |
relativity | +0.078 |
blank | +0.078 |
manship | +0.076 |
Ples | +0.075 |
Neg logit contributions | |
utonium | -0.102 |
puter | -0.096 |
APH | -0.085 |
awei | -0.085 |
ritten | -0.083 |
Token | her |
Token ID | 607 |
Feature activation | -3.32e-03 |
Pos logit contributions | |
xual | +0.028 |
relativity | +0.028 |
blank | +0.027 |
manship | +0.027 |
Ples | +0.027 |
Neg logit contributions | |
utonium | -0.033 |
puter | -0.031 |
awei | -0.027 |
APH | -0.027 |
ordable | -0.027 |
Token | chair |
Token ID | 5118 |
Feature activation | -1.47e-02 |
Pos logit contributions | |
xual | +0.008 |
relativity | +0.008 |
blank | +0.008 |
Ples | +0.008 |
manship | +0.008 |
Neg logit contributions | |
utonium | -0.010 |
puter | -0.010 |
awei | -0.009 |
APH | -0.008 |
ordable | -0.008 |
Token | manship |
Token ID | 25428 |
Feature activation | -4.59e-01 |
Pos logit contributions | |
xual | +0.012 |
relativity | +0.011 |
blank | +0.010 |
Ples | +0.009 |
Lovecraft | +0.009 |
Neg logit contributions | |
utonium | -0.071 |
puter | -0.068 |
APH | -0.063 |
awei | -0.063 |
ordable | -0.063 |
Token | . |
Token ID | 13 |
Feature activation | -8.28e-02 |
Pos logit contributions | |
xual | +1.031 |
relativity | +1.013 |
blank | +1.001 |
Ples | +0.974 |
manship | +0.970 |
Neg logit contributions | |
utonium | -1.537 |
puter | -1.448 |
awei | -1.299 |
APH | -1.297 |
ordable | -1.271 |
Token | Throughout |
Token ID | 24581 |
Feature activation | -4.31e-02 |
Pos logit contributions | |
xual | +0.204 |
relativity | +0.199 |
blank | +0.196 |
manship | +0.190 |
Ples | +0.187 |
Neg logit contributions | |
utonium | -0.260 |
puter | -0.244 |
APH | -0.220 |
awei | -0.216 |
ordable | -0.213 |
Token | the |
Token ID | 262 |
Feature activation | -3.44e-02 |
Pos logit contributions | |
xual | +0.115 |
blank | +0.112 |
relativity | +0.112 |
manship | +0.108 |
Ples | +0.107 |
Neg logit contributions | |
utonium | -0.126 |
puter | -0.118 |
APH | -0.105 |
awei | -0.103 |
ordable | -0.103 |
Token | campaign |
Token ID | 1923 |
Feature activation | -2.27e-03 |
Pos logit contributions | |
xual | +0.086 |
relativity | +0.084 |
blank | +0.083 |
manship | +0.081 |
Ples | +0.081 |
Neg logit contributions | |
utonium | -0.106 |
puter | -0.099 |
APH | -0.088 |
awei | -0.088 |
ordable | -0.087 |
Token | , |
Token ID | 11 |
Feature activation | -1.73e-02 |
Pos logit contributions | |
xual | +0.005 |
relativity | +0.005 |
blank | +0.005 |
manship | +0.005 |
Ples | +0.005 |
Neg logit contributions | |
utonium | -0.007 |
puter | -0.007 |
APH | -0.006 |
awei | -0.006 |
ritten | -0.006 |
Token | Balk |
Token ID | 29643 |
Feature activation | -5.62e-02 |
Pos logit contributions | |
utonium | +0.021 |
puter | +0.020 |
APH | +0.017 |
awei | +0.017 |
ordable | +0.017 |
Neg logit contributions | |
xual | -0.017 |
relativity | -0.016 |
blank | -0.016 |
manship | -0.016 |
Ples | -0.016 |
Token | an |
Token ID | 272 |
Feature activation | +8.30e-02 |
Pos logit contributions | |
xual | +0.154 |
relativity | +0.152 |
blank | +0.150 |
manship | +0.148 |
Lovecraft | +0.146 |
Neg logit contributions | |
utonium | -0.162 |
puter | -0.150 |
awei | -0.132 |
APH | -0.131 |
ordable | -0.130 |
Token | countries |
Token ID | 2678 |
Feature activation | +4.52e-02 |
Pos logit contributions | |
utonium | +0.246 |
puter | +0.229 |
awei | +0.202 |
APH | +0.201 |
ordable | +0.198 |
Neg logit contributions | |
xual | -0.220 |
relativity | -0.214 |
blank | -0.214 |
manship | -0.208 |
Ples | -0.207 |
Token | . |
Token ID | 13 |
Feature activation | -4.33e-02 |
Pos logit contributions | |
utonium | +0.142 |
puter | +0.133 |
awei | +0.119 |
APH | +0.118 |
ordable | +0.116 |
Neg logit contributions | |
xual | -0.111 |
relativity | -0.108 |
blank | -0.107 |
manship | -0.104 |
Ples | -0.103 |
Token | Analy |
Token ID | 16213 |
Feature activation | -4.97e-02 |
Pos logit contributions | |
xual | +0.107 |
relativity | +0.105 |
blank | +0.104 |
manship | +0.101 |
Lovecraft | +0.099 |
Neg logit contributions | |
utonium | -0.136 |
puter | -0.127 |
APH | -0.114 |
awei | -0.113 |
ordable | -0.110 |
Token | sts |
Token ID | 6448 |
Feature activation | -4.46e-01 |
Pos logit contributions | |
xual | +0.104 |
relativity | +0.104 |
blank | +0.102 |
Ples | +0.099 |
manship | +0.098 |
Neg logit contributions | |
utonium | -0.174 |
puter | -0.163 |
awei | -0.147 |
APH | -0.147 |
ritten | -0.145 |
Token | say |
Token ID | 910 |
Feature activation | +1.53e-02 |
Pos logit contributions | |
xual | +1.172 |
relativity | +1.155 |
blank | +1.146 |
manship | +1.121 |
Ples | +1.118 |
Neg logit contributions | |
utonium | -1.324 |
puter | -1.237 |
awei | -1.092 |
APH | -1.090 |
izoph | -1.065 |
Token | supplies |
Token ID | 9416 |
Feature activation | +6.74e-02 |
Pos logit contributions | |
utonium | +0.046 |
puter | +0.043 |
awei | +0.038 |
APH | +0.037 |
ordable | +0.037 |
Neg logit contributions | |
xual | -0.040 |
blank | -0.039 |
relativity | -0.039 |
manship | -0.038 |
Lovecraft | -0.037 |
Token | could |
Token ID | 714 |
Feature activation | +6.69e-03 |
Pos logit contributions | |
utonium | +0.210 |
puter | +0.196 |
APH | +0.174 |
awei | +0.173 |
ordable | +0.170 |
Neg logit contributions | |
xual | -0.168 |
blank | -0.163 |
relativity | -0.163 |
Ples | -0.158 |
Lovecraft | -0.156 |
Token | in |
Token ID | 287 |
Feature activation | +1.61e-03 |
Pos logit contributions | |
utonium | +0.020 |
puter | +0.019 |
APH | +0.017 |
awei | +0.016 |
ordable | +0.016 |
Neg logit contributions | |
xual | -0.017 |
relativity | -0.017 |
blank | -0.017 |
manship | -0.016 |
Ples | -0.016 |
Token | theory |
Token ID | 4583 |
Feature activation | -4.78e-03 |
Pos logit contributions | |
utonium | +0.005 |
puter | +0.005 |
APH | +0.004 |
awei | +0.004 |
ritten | +0.004 |
Neg logit contributions | |
xual | -0.004 |
blank | -0.004 |
relativity | -0.004 |
manship | -0.004 |
Ples | -0.004 |
Token | group |
Token ID | 1448 |
Feature activation | +2.10e-03 |
Pos logit contributions | |
xual | +0.208 |
relativity | +0.205 |
blank | +0.203 |
manship | +0.198 |
Ples | +0.197 |
Neg logit contributions | |
utonium | -0.247 |
puter | -0.231 |
awei | -0.206 |
APH | -0.204 |
ritten | -0.200 |
Token | . |
Token ID | 13 |
Feature activation | -2.57e-03 |
Pos logit contributions | |
utonium | +0.007 |
puter | +0.006 |
awei | +0.005 |
APH | +0.005 |
ritten | +0.005 |
Neg logit contributions | |
xual | -0.005 |
relativity | -0.005 |
blank | -0.005 |
manship | -0.005 |
Ples | -0.005 |
Token |
|
Token ID | 198 |
Feature activation | -9.73e-03 |
Pos logit contributions | |
xual | +0.006 |
relativity | +0.006 |
blank | +0.006 |
manship | +0.006 |
Ples | +0.006 |
Neg logit contributions | |
utonium | -0.008 |
puter | -0.007 |
APH | -0.007 |
awei | -0.007 |
ritten | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | +1.78e-03 |
Pos logit contributions | |
xual | +0.021 |
relativity | +0.021 |
blank | +0.021 |
manship | +0.021 |
Ples | +0.020 |
Neg logit contributions | |
utonium | -0.033 |
puter | -0.031 |
awei | -0.028 |
APH | -0.028 |
izoph | -0.027 |
Token | Analy |
Token ID | 37702 |
Feature activation | -3.68e-02 |
Pos logit contributions | |
utonium | +0.005 |
puter | +0.005 |
APH | +0.005 |
awei | +0.004 |
ritten | +0.004 |
Neg logit contributions | |
xual | -0.005 |
relativity | -0.005 |
Ples | -0.004 |
blank | -0.004 |
manship | -0.004 |
Token | sts |
Token ID | 6448 |
Feature activation | -4.40e-01 |
Pos logit contributions | |
xual | +0.077 |
relativity | +0.076 |
blank | +0.075 |
Ples | +0.073 |
manship | +0.073 |
Neg logit contributions | |
utonium | -0.130 |
puter | -0.122 |
APH | -0.109 |
awei | -0.109 |
ritten | -0.108 |
Token | said |
Token ID | 531 |
Feature activation | -1.41e-02 |
Pos logit contributions | |
xual | +1.155 |
relativity | +1.137 |
blank | +1.129 |
manship | +1.103 |
Ples | +1.102 |
Neg logit contributions | |
utonium | -1.306 |
puter | -1.219 |
awei | -1.077 |
APH | -1.076 |
ritten | -1.050 |
Token | the |
Token ID | 262 |
Feature activation | -4.26e-03 |
Pos logit contributions | |
xual | +0.038 |
blank | +0.037 |
relativity | +0.037 |
manship | +0.036 |
Ples | +0.036 |
Neg logit contributions | |
utonium | -0.041 |
puter | -0.038 |
awei | -0.034 |
APH | -0.034 |
ordable | -0.033 |
Token | rupture |
Token ID | 46836 |
Feature activation | +1.20e-02 |
Pos logit contributions | |
xual | +0.011 |
relativity | +0.011 |
blank | +0.011 |
manship | +0.010 |
Ples | +0.010 |
Neg logit contributions | |
utonium | -0.013 |
puter | -0.012 |
awei | -0.011 |
APH | -0.011 |
izoph | -0.010 |
Token | was |
Token ID | 373 |
Feature activation | +5.24e-03 |
Pos logit contributions | |
utonium | +0.039 |
puter | +0.036 |
awei | +0.032 |
APH | +0.032 |
ordable | +0.032 |
Neg logit contributions | |
xual | -0.029 |
relativity | -0.028 |
blank | -0.028 |
Ples | -0.027 |
Lovecraft | -0.027 |
Token | due |
Token ID | 2233 |
Feature activation | +2.08e-02 |
Pos logit contributions | |
utonium | +0.015 |
puter | +0.014 |
awei | +0.012 |
APH | +0.012 |
ritten | +0.012 |
Neg logit contributions | |
xual | -0.014 |
blank | -0.014 |
relativity | -0.014 |
Ples | -0.014 |
manship | -0.013 |
Token | counterparts |
Token ID | 16054 |
Feature activation | +3.79e-02 |
Pos logit contributions | |
xual | +0.042 |
relativity | +0.041 |
blank | +0.041 |
manship | +0.040 |
Ples | +0.040 |
Neg logit contributions | |
utonium | -0.048 |
puter | -0.045 |
awei | -0.040 |
APH | -0.040 |
ritten | -0.039 |
Token | . |
Token ID | 13 |
Feature activation | +1.95e-02 |
Pos logit contributions | |
utonium | +0.122 |
puter | +0.115 |
awei | +0.103 |
APH | +0.103 |
ordable | +0.100 |
Neg logit contributions | |
xual | -0.090 |
relativity | -0.088 |
blank | -0.087 |
Ples | -0.084 |
manship | -0.084 |
Token |
|
Token ID | 198 |
Feature activation | +2.57e-02 |
Pos logit contributions | |
utonium | +0.061 |
puter | +0.057 |
APH | +0.051 |
awei | +0.051 |
ritten | +0.049 |
Neg logit contributions | |
xual | -0.049 |
relativity | -0.047 |
blank | -0.046 |
manship | -0.046 |
Ples | -0.045 |
Token |
|
Token ID | 198 |
Feature activation | +3.90e-02 |
Pos logit contributions | |
utonium | +0.087 |
puter | +0.082 |
awei | +0.074 |
APH | +0.073 |
izoph | +0.073 |
Neg logit contributions | |
xual | -0.056 |
blank | -0.056 |
relativity | -0.056 |
manship | -0.054 |
Ples | -0.054 |
Token | Analy |
Token ID | 37702 |
Feature activation | -1.86e-02 |
Pos logit contributions | |
utonium | +0.121 |
puter | +0.114 |
APH | +0.104 |
awei | +0.101 |
ritten | +0.100 |
Neg logit contributions | |
xual | -0.098 |
relativity | -0.096 |
blank | -0.092 |
manship | -0.091 |
Ples | -0.091 |
Token | sts |
Token ID | 6448 |
Feature activation | -4.30e-01 |
Pos logit contributions | |
xual | +0.039 |
relativity | +0.038 |
blank | +0.038 |
Ples | +0.037 |
manship | +0.037 |
Neg logit contributions | |
utonium | -0.066 |
puter | -0.062 |
APH | -0.056 |
awei | -0.056 |
ritten | -0.055 |
Token | say |
Token ID | 910 |
Feature activation | +2.85e-02 |
Pos logit contributions | |
xual | +1.070 |
relativity | +1.053 |
blank | +1.044 |
manship | +1.020 |
Ples | +1.017 |
Neg logit contributions | |
utonium | -1.337 |
puter | -1.253 |
awei | -1.113 |
APH | -1.112 |
izoph | -1.087 |
Token | that |
Token ID | 326 |
Feature activation | +3.99e-03 |
Pos logit contributions | |
utonium | +0.083 |
puter | +0.078 |
awei | +0.069 |
APH | +0.069 |
ritten | +0.067 |
Neg logit contributions | |
xual | -0.076 |
relativity | -0.073 |
blank | -0.073 |
manship | -0.071 |
Ples | -0.071 |
Token | the |
Token ID | 262 |
Feature activation | +2.45e-02 |
Pos logit contributions | |
utonium | +0.012 |
puter | +0.012 |
APH | +0.010 |
awei | +0.010 |
izoph | +0.010 |
Neg logit contributions | |
xual | -0.010 |
relativity | -0.010 |
blank | -0.010 |
manship | -0.009 |
Ples | -0.009 |
Token | Kremlin |
Token ID | 19077 |
Feature activation | -1.96e-02 |
Pos logit contributions | |
utonium | +0.076 |
puter | +0.071 |
APH | +0.063 |
awei | +0.063 |
ritten | +0.062 |
Neg logit contributions | |
xual | -0.061 |
relativity | -0.059 |
blank | -0.059 |
manship | -0.058 |
Ples | -0.057 |
Token | � |
Token ID | 447 |
Feature activation | +2.46e-02 |
Pos logit contributions | |
xual | +0.043 |
relativity | +0.042 |
blank | +0.042 |
manship | +0.041 |
Ples | +0.041 |
Neg logit contributions | |
utonium | -0.066 |
puter | -0.063 |
APH | -0.056 |
awei | -0.056 |
ritten | -0.055 |
Token | as |
Token ID | 355 |
Feature activation | -6.67e-03 |
Pos logit contributions | |
xual | +0.052 |
relativity | +0.051 |
blank | +0.050 |
Ples | +0.049 |
manship | +0.049 |
Neg logit contributions | |
utonium | -0.062 |
puter | -0.057 |
APH | -0.051 |
awei | -0.051 |
ritten | -0.050 |
Token | � |
Token ID | 564 |
Feature activation | +1.57e-02 |
Pos logit contributions | |
xual | +0.017 |
relativity | +0.017 |
blank | +0.017 |
manship | +0.016 |
Ples | +0.016 |
Neg logit contributions | |
utonium | -0.020 |
puter | -0.019 |
APH | -0.017 |
awei | -0.017 |
izoph | -0.016 |
Token | � |
Token ID | 250 |
Feature activation | -1.34e-02 |
Pos logit contributions | |
utonium | +0.034 |
puter | +0.031 |
awei | +0.025 |
APH | +0.025 |
ritten | +0.024 |
Neg logit contributions | |
xual | -0.054 |
relativity | -0.054 |
blank | -0.053 |
manship | -0.053 |
Ples | -0.053 |
Token | He |
Token ID | 1544 |
Feature activation | -1.59e-02 |
Pos logit contributions | |
xual | +0.031 |
relativity | +0.031 |
blank | +0.030 |
Ples | +0.030 |
manship | +0.030 |
Neg logit contributions | |
utonium | -0.044 |
puter | -0.041 |
APH | -0.037 |
awei | -0.037 |
ritten | -0.036 |
Token | sed |
Token ID | 10081 |
Feature activation | +1.50e-02 |
Pos logit contributions | |
xual | +0.035 |
relativity | +0.035 |
blank | +0.034 |
Ples | +0.034 |
manship | +0.034 |
Neg logit contributions | |
utonium | -0.053 |
puter | -0.050 |
awei | -0.045 |
APH | -0.045 |
ritten | -0.044 |
Token | uced |
Token ID | 19513 |
Feature activation | -4.06e-01 |
Pos logit contributions | |
utonium | +0.044 |
puter | +0.042 |
awei | +0.037 |
APH | +0.036 |
ritten | +0.036 |
Neg logit contributions | |
xual | -0.039 |
relativity | -0.039 |
blank | -0.039 |
manship | -0.038 |
Ples | -0.038 |
Token | her |
Token ID | 607 |
Feature activation | +4.52e-02 |
Pos logit contributions | |
xual | +1.023 |
relativity | +1.008 |
blank | +1.000 |
manship | +0.975 |
Ples | +0.968 |
Neg logit contributions | |
utonium | -1.248 |
puter | -1.170 |
awei | -1.038 |
APH | -1.037 |
izoph | -1.012 |
Token | through |
Token ID | 832 |
Feature activation | +1.24e-02 |
Pos logit contributions | |
utonium | +0.140 |
puter | +0.132 |
APH | +0.117 |
awei | +0.116 |
ritten | +0.114 |
Neg logit contributions | |
xual | -0.112 |
relativity | -0.110 |
blank | -0.108 |
Ples | -0.106 |
manship | -0.106 |
Token | abduction |
Token ID | 39630 |
Feature activation | -4.39e-02 |
Pos logit contributions | |
utonium | +0.038 |
puter | +0.036 |
APH | +0.032 |
awei | +0.032 |
izoph | +0.031 |
Neg logit contributions | |
xual | -0.030 |
relativity | -0.030 |
blank | -0.030 |
manship | -0.029 |
Ples | -0.029 |
Token | . |
Token ID | 13 |
Feature activation | +1.47e-03 |
Pos logit contributions | |
xual | +0.101 |
relativity | +0.100 |
blank | +0.099 |
Ples | +0.096 |
manship | +0.096 |
Neg logit contributions | |
utonium | -0.142 |
puter | -0.134 |
APH | -0.121 |
awei | -0.120 |
ritten | -0.117 |
Token | � |
Token ID | 447 |
Feature activation | +9.67e-03 |
Pos logit contributions | |
utonium | +0.004 |
puter | +0.004 |
APH | +0.004 |
awei | +0.004 |
ritten | +0.004 |
Neg logit contributions | |
xual | -0.004 |
relativity | -0.004 |
blank | -0.004 |
manship | -0.004 |
Ples | -0.004 |
Token | and |
Token ID | 290 |
Feature activation | +1.64e-03 |
Pos logit contributions | |
utonium | +0.061 |
puter | +0.057 |
APH | +0.051 |
awei | +0.050 |
ritten | +0.049 |
Neg logit contributions | |
xual | -0.049 |
blank | -0.048 |
relativity | -0.047 |
Ples | -0.046 |
Lovecraft | -0.045 |
Token | his |
Token ID | 465 |
Feature activation | -6.05e-02 |
Pos logit contributions | |
utonium | +0.005 |
puter | +0.005 |
awei | +0.004 |
APH | +0.004 |
ritten | +0.004 |
Neg logit contributions | |
xual | -0.004 |
blank | -0.004 |
relativity | -0.004 |
Ples | -0.004 |
manship | -0.004 |
Token | genius |
Token ID | 15632 |
Feature activation | +3.10e-02 |
Pos logit contributions | |
xual | +0.148 |
blank | +0.144 |
relativity | +0.142 |
Ples | +0.140 |
manship | +0.139 |
Neg logit contributions | |
utonium | -0.190 |
puter | -0.179 |
awei | -0.159 |
APH | -0.158 |
ritten | -0.156 |
Token | for |
Token ID | 329 |
Feature activation | -3.28e-02 |
Pos logit contributions | |
utonium | +0.105 |
puter | +0.100 |
awei | +0.089 |
APH | +0.089 |
ritten | +0.087 |
Neg logit contributions | |
xual | -0.068 |
blank | -0.066 |
relativity | -0.065 |
Ples | -0.064 |
Lovecraft | -0.063 |
Token | sales |
Token ID | 4200 |
Feature activation | -8.47e-02 |
Pos logit contributions | |
xual | +0.087 |
blank | +0.085 |
relativity | +0.084 |
manship | +0.083 |
Ples | +0.083 |
Neg logit contributions | |
utonium | -0.096 |
puter | -0.090 |
awei | -0.080 |
APH | -0.079 |
ordable | -0.077 |
Token | manship |
Token ID | 25428 |
Feature activation | -4.04e-01 |
Pos logit contributions | |
xual | +0.197 |
blank | +0.192 |
relativity | +0.192 |
Ples | +0.187 |
Lovecraft | +0.184 |
Neg logit contributions | |
utonium | -0.273 |
puter | -0.259 |
awei | -0.233 |
APH | -0.232 |
ordable | -0.225 |
Token | to |
Token ID | 284 |
Feature activation | -2.70e-02 |
Pos logit contributions | |
xual | +0.929 |
relativity | +0.912 |
blank | +0.906 |
Ples | +0.881 |
manship | +0.878 |
Neg logit contributions | |
utonium | -1.326 |
puter | -1.248 |
awei | -1.119 |
APH | -1.117 |
ritten | -1.090 |
Token | convince |
Token ID | 11508 |
Feature activation | -3.14e-02 |
Pos logit contributions | |
xual | +0.066 |
relativity | +0.065 |
blank | +0.065 |
manship | +0.063 |
Ples | +0.063 |
Neg logit contributions | |
utonium | -0.084 |
puter | -0.079 |
awei | -0.070 |
APH | -0.070 |
ordable | -0.069 |
Token | NASA |
Token ID | 8884 |
Feature activation | +2.55e-02 |
Pos logit contributions | |
xual | +0.087 |
relativity | +0.085 |
blank | +0.085 |
manship | +0.083 |
Ples | +0.082 |
Neg logit contributions | |
utonium | -0.088 |
puter | -0.083 |
awei | -0.072 |
APH | -0.072 |
ordable | -0.070 |
Token | to |
Token ID | 284 |
Feature activation | -4.18e-03 |
Pos logit contributions | |
utonium | +0.077 |
puter | +0.073 |
awei | +0.064 |
APH | +0.064 |
ordable | +0.063 |
Neg logit contributions | |
xual | -0.065 |
relativity | -0.063 |
blank | -0.063 |
Ples | -0.062 |
manship | -0.061 |
Token | marry |
Token ID | 12479 |
Feature activation | -2.07e-02 |
Pos logit contributions | |
xual | +0.011 |
relativity | +0.011 |
blank | +0.011 |
manship | +0.010 |
Ples | +0.010 |
Neg logit contributions | |
utonium | -0.012 |
puter | -0.012 |
awei | -0.010 |
APH | -0.010 |
ordable | -0.010 |
Token | the |
Token ID | 262 |
Feature activation | -2.16e-02 |
Pos logit contributions | |
xual | +0.091 |
blank | +0.089 |
relativity | +0.089 |
manship | +0.086 |
Ples | +0.086 |
Neg logit contributions | |
utonium | -0.108 |
puter | -0.102 |
awei | -0.091 |
APH | -0.090 |
ordable | -0.089 |
Token | allegations |
Token ID | 7636 |
Feature activation | +1.83e-02 |
Pos logit contributions | |
xual | +0.050 |
blank | +0.049 |
relativity | +0.049 |
manship | +0.048 |
Ples | +0.048 |
Neg logit contributions | |
utonium | -0.070 |
puter | -0.066 |
awei | -0.059 |
APH | -0.059 |
izoph | -0.058 |
Token | . |
Token ID | 13 |
Feature activation | +2.91e-02 |
Pos logit contributions | |
utonium | +0.059 |
puter | +0.056 |
awei | +0.050 |
APH | +0.050 |
ordable | +0.049 |
Neg logit contributions | |
xual | -0.043 |
relativity | -0.042 |
blank | -0.042 |
Ples | -0.040 |
manship | -0.040 |
Token |
|
Token ID | 198 |
Feature activation | +2.00e-02 |
Pos logit contributions | |
utonium | +0.091 |
puter | +0.085 |
APH | +0.076 |
awei | +0.075 |
ordable | +0.074 |
Neg logit contributions | |
xual | -0.072 |
relativity | -0.071 |
blank | -0.070 |
manship | -0.068 |
Ples | -0.068 |
Token |
|
Token ID | 198 |
Feature activation | +1.19e-02 |
Pos logit contributions | |
utonium | +0.068 |
puter | +0.064 |
awei | +0.058 |
APH | +0.057 |
izoph | +0.057 |
Neg logit contributions | |
xual | -0.044 |
blank | -0.044 |
relativity | -0.044 |
manship | -0.042 |
Ples | -0.042 |
Token | Mc |
Token ID | 9742 |
Feature activation | -3.95e-01 |
Pos logit contributions | |
utonium | +0.036 |
puter | +0.034 |
APH | +0.031 |
awei | +0.030 |
ritten | +0.030 |
Neg logit contributions | |
xual | -0.031 |
relativity | -0.030 |
Ples | -0.029 |
blank | -0.029 |
Lovecraft | -0.028 |
Token | Donald |
Token ID | 7371 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
blank | +1.028 |
xual | +1.027 |
relativity | +1.017 |
manship | +0.993 |
Ples | +0.988 |
Neg logit contributions | |
utonium | -1.170 |
puter | -1.081 |
awei | -0.958 |
APH | -0.953 |
izoph | -0.936 |
Token | 's |
Token ID | 338 |
Feature activation | -6.82e-03 |
Pos logit contributions | |
utonium | +0.370 |
puter | +0.352 |
awei | +0.320 |
APH | +0.317 |
ritten | +0.315 |
Neg logit contributions | |
xual | -0.193 |
relativity | -0.186 |
blank | -0.184 |
manship | -0.181 |
Ples | -0.179 |
Token | did |
Token ID | 750 |
Feature activation | -2.17e-02 |
Pos logit contributions | |
xual | +0.018 |
blank | +0.017 |
relativity | +0.017 |
Ples | +0.017 |
manship | +0.017 |
Neg logit contributions | |
utonium | -0.020 |
puter | -0.019 |
awei | -0.017 |
APH | -0.017 |
ordable | -0.016 |
Token | not |
Token ID | 407 |
Feature activation | -4.22e-02 |
Pos logit contributions | |
xual | +0.067 |
blank | +0.066 |
relativity | +0.066 |
manship | +0.065 |
Ples | +0.065 |
Neg logit contributions | |
utonium | -0.054 |
puter | -0.050 |
APH | -0.043 |
awei | -0.042 |
ordable | -0.042 |
Token | comment |
Token ID | 2912 |
Feature activation | -5.98e-03 |
Pos logit contributions | |
xual | +0.119 |
relativity | +0.116 |
blank | +0.116 |
manship | +0.114 |
Ples | +0.114 |
Neg logit contributions | |
utonium | -0.115 |
puter | -0.108 |
awei | -0.094 |
APH | -0.093 |
ordable | -0.092 |
Token | Restaurant |
Token ID | 26078 |
Feature activation | +2.67e-03 |
Pos logit contributions | |
xual | +0.120 |
relativity | +0.119 |
blank | +0.117 |
manship | +0.115 |
Ples | +0.113 |
Neg logit contributions | |
utonium | -0.144 |
puter | -0.135 |
APH | -0.120 |
awei | -0.120 |
izoph | -0.117 |
Token | manager |
Token ID | 4706 |
Feature activation | -6.24e-02 |
Pos logit contributions | |
utonium | +0.008 |
puter | +0.008 |
awei | +0.007 |
APH | +0.007 |
ritten | +0.007 |
Neg logit contributions | |
blank | -0.006 |
xual | -0.006 |
relativity | -0.006 |
manship | -0.006 |
Ples | -0.006 |
Token | � |
Token ID | 564 |
Feature activation | -1.35e-02 |
Pos logit contributions | |
xual | +0.143 |
blank | +0.140 |
relativity | +0.140 |
manship | +0.136 |
Ples | +0.136 |
Neg logit contributions | |
utonium | -0.203 |
puter | -0.191 |
awei | -0.172 |
APH | -0.170 |
ritten | -0.168 |
Token | � |
Token ID | 246 |
Feature activation | -8.58e-02 |
Pos logit contributions | |
xual | +0.043 |
relativity | +0.042 |
blank | +0.042 |
manship | +0.041 |
Ples | +0.041 |
Neg logit contributions | |
utonium | -0.033 |
puter | -0.030 |
awei | -0.026 |
APH | -0.026 |
ritten | -0.025 |
Token | apolog |
Token ID | 46407 |
Feature activation | -6.80e-02 |
Pos logit contributions | |
relativity | +0.197 |
xual | +0.197 |
blank | +0.189 |
Ples | +0.189 |
manship | +0.186 |
Neg logit contributions | |
utonium | -0.281 |
puter | -0.266 |
awei | -0.238 |
APH | -0.237 |
ordable | -0.233 |
Token | ises |
Token ID | 2696 |
Feature activation | -3.89e-01 |
Pos logit contributions | |
xual | +0.159 |
relativity | +0.158 |
blank | +0.158 |
manship | +0.154 |
Ples | +0.154 |
Neg logit contributions | |
utonium | -0.219 |
puter | -0.205 |
awei | -0.183 |
APH | -0.182 |
ordable | -0.180 |
Token | � |
Token ID | 447 |
Feature activation | -1.94e-02 |
Pos logit contributions | |
xual | +0.929 |
relativity | +0.922 |
blank | +0.921 |
manship | +0.895 |
Ples | +0.894 |
Neg logit contributions | |
utonium | -1.226 |
puter | -1.154 |
awei | -1.029 |
APH | -1.028 |
ordable | -1.007 |
Token | � |
Token ID | 247 |
Feature activation | -4.09e-02 |
Pos logit contributions | |
xual | +0.071 |
relativity | +0.071 |
blank | +0.070 |
Ples | +0.069 |
manship | +0.069 |
Neg logit contributions | |
utonium | -0.037 |
puter | -0.033 |
awei | -0.027 |
APH | -0.027 |
ritten | -0.026 |
Token | to |
Token ID | 284 |
Feature activation | -7.16e-03 |
Pos logit contributions | |
relativity | +0.097 |
xual | +0.097 |
blank | +0.096 |
Ples | +0.094 |
manship | +0.094 |
Neg logit contributions | |
utonium | -0.128 |
puter | -0.121 |
awei | -0.108 |
APH | -0.107 |
ordable | -0.106 |
Token | homophobic |
Token ID | 36034 |
Feature activation | -6.91e-04 |
Pos logit contributions | |
xual | +0.018 |
relativity | +0.018 |
blank | +0.018 |
manship | +0.018 |
Ples | +0.018 |
Neg logit contributions | |
utonium | -0.021 |
puter | -0.020 |
APH | -0.018 |
awei | -0.018 |
ordable | -0.017 |
Token | customers |
Token ID | 4297 |
Feature activation | +1.92e-02 |
Pos logit contributions | |
xual | +0.002 |
relativity | +0.002 |
blank | +0.002 |
manship | +0.002 |
Ples | +0.002 |
Neg logit contributions | |
utonium | -0.002 |
puter | -0.002 |
awei | -0.002 |
APH | -0.002 |
ritten | -0.002 |
Token | Post |
Token ID | 2947 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
utonium | +0.232 |
puter | +0.217 |
awei | +0.191 |
APH | +0.190 |
ordable | +0.187 |
Neg logit contributions | |
xual | -0.207 |
relativity | -0.204 |
blank | -0.201 |
manship | -0.197 |
Ples | -0.197 |
Token | reading |
Token ID | 3555 |
Feature activation | -8.39e-02 |
Pos logit contributions | |
xual | +0.257 |
relativity | +0.255 |
blank | +0.250 |
Ples | +0.244 |
manship | +0.242 |
Neg logit contributions | |
utonium | -0.385 |
puter | -0.365 |
APH | -0.326 |
awei | -0.325 |
ritten | -0.322 |
Token | " |
Token ID | 366 |
Feature activation | -4.42e-02 |
Pos logit contributions | |
xual | +0.220 |
relativity | +0.215 |
blank | +0.214 |
Ples | +0.208 |
manship | +0.206 |
Neg logit contributions | |
utonium | -0.250 |
puter | -0.234 |
APH | -0.206 |
awei | -0.205 |
izoph | -0.203 |
Token | ISIS |
Token ID | 29322 |
Feature activation | -5.41e-02 |
Pos logit contributions | |
xual | +0.114 |
relativity | +0.113 |
blank | +0.109 |
manship | +0.108 |
Ples | +0.108 |
Neg logit contributions | |
utonium | -0.133 |
puter | -0.125 |
APH | -0.112 |
awei | -0.110 |
ordable | -0.108 |
Token | Ur |
Token ID | 8799 |
Feature activation | +1.13e-02 |
Pos logit contributions | |
xual | +0.131 |
relativity | +0.129 |
blank | +0.128 |
manship | +0.124 |
Ples | +0.123 |
Neg logit contributions | |
utonium | -0.170 |
puter | -0.160 |
APH | -0.144 |
awei | -0.142 |
izoph | -0.140 |
Token | ges |
Token ID | 3212 |
Feature activation | -3.83e-01 |
Pos logit contributions | |
utonium | +0.028 |
puter | +0.026 |
awei | +0.022 |
APH | +0.022 |
izoph | +0.022 |
Neg logit contributions | |
xual | -0.035 |
relativity | -0.035 |
blank | -0.034 |
Lovecraft | -0.034 |
manship | -0.034 |
Token | Jihad |
Token ID | 35243 |
Feature activation | +1.20e-02 |
Pos logit contributions | |
xual | +0.976 |
relativity | +0.964 |
blank | +0.952 |
manship | +0.929 |
Ples | +0.925 |
Neg logit contributions | |
utonium | -1.165 |
puter | -1.091 |
awei | -0.965 |
APH | -0.962 |
ordable | -0.943 |
Token | ists |
Token ID | 1023 |
Feature activation | +4.58e-02 |
Pos logit contributions | |
utonium | +0.040 |
puter | +0.038 |
APH | +0.034 |
awei | +0.034 |
ordable | +0.033 |
Neg logit contributions | |
xual | -0.027 |
relativity | -0.027 |
blank | -0.026 |
manship | -0.026 |
Ples | -0.025 |
Token | To |
Token ID | 1675 |
Feature activation | -1.95e-02 |
Pos logit contributions | |
utonium | +0.140 |
puter | +0.132 |
APH | +0.116 |
awei | +0.116 |
ordable | +0.114 |
Neg logit contributions | |
xual | -0.116 |
relativity | -0.114 |
blank | -0.112 |
manship | -0.109 |
Ples | -0.109 |
Token | Attack |
Token ID | 8307 |
Feature activation | -4.87e-02 |
Pos logit contributions | |
xual | +0.048 |
relativity | +0.047 |
blank | +0.046 |
manship | +0.045 |
Ples | +0.044 |
Neg logit contributions | |
utonium | -0.061 |
puter | -0.058 |
APH | -0.051 |
awei | -0.051 |
izoph | -0.050 |
Token | Canadians |
Token ID | 14008 |
Feature activation | -1.93e-02 |
Pos logit contributions | |
xual | +0.124 |
relativity | +0.123 |
blank | +0.120 |
manship | +0.117 |
Ples | +0.115 |
Neg logit contributions | |
utonium | -0.148 |
puter | -0.139 |
awei | -0.122 |
APH | -0.122 |
ordable | -0.121 |
Token | (* |
Token ID | 20789 |
Feature activation | -2.68e-02 |
Pos logit contributions | |
xual | +0.043 |
relativity | +0.042 |
blank | +0.041 |
manship | +0.041 |
Ples | +0.040 |
Neg logit contributions | |
utonium | -0.053 |
puter | -0.050 |
APH | -0.044 |
awei | -0.044 |
ritten | -0.043 |
Token | mark |
Token ID | 1317 |
Feature activation | -2.10e-02 |
Pos logit contributions | |
xual | +0.067 |
relativity | +0.066 |
blank | +0.065 |
Ples | +0.064 |
manship | +0.064 |
Neg logit contributions | |
utonium | -0.082 |
puter | -0.078 |
APH | -0.068 |
awei | -0.068 |
ritten | -0.067 |
Token | locations |
Token ID | 7064 |
Feature activation | +1.10e-02 |
Pos logit contributions | |
xual | +0.055 |
relativity | +0.054 |
blank | +0.053 |
Ples | +0.052 |
manship | +0.052 |
Neg logit contributions | |
utonium | -0.062 |
puter | -0.059 |
APH | -0.051 |
awei | -0.051 |
ritten | -0.050 |
Token | as |
Token ID | 355 |
Feature activation | -1.42e-02 |
Pos logit contributions | |
utonium | +0.034 |
puter | +0.032 |
APH | +0.028 |
awei | +0.028 |
ritten | +0.028 |
Neg logit contributions | |
xual | -0.028 |
relativity | -0.027 |
blank | -0.027 |
Ples | -0.026 |
manship | -0.026 |
Token | Sear |
Token ID | 42016 |
Feature activation | -7.55e-02 |
Pos logit contributions | |
xual | +0.038 |
relativity | +0.037 |
blank | +0.037 |
manship | +0.036 |
Ples | +0.036 |
Neg logit contributions | |
utonium | -0.042 |
puter | -0.039 |
awei | -0.034 |
APH | -0.034 |
ritten | -0.034 |
Token | ched |
Token ID | 1740 |
Feature activation | -3.83e-01 |
Pos logit contributions | |
xual | +0.226 |
relativity | +0.223 |
blank | +0.220 |
manship | +0.217 |
Ples | +0.214 |
Neg logit contributions | |
utonium | -0.198 |
puter | -0.183 |
APH | -0.160 |
awei | -0.158 |
ordable | -0.155 |
Token | *) |
Token ID | 31936 |
Feature activation | +1.84e-01 |
Pos logit contributions | |
xual | +0.900 |
relativity | +0.885 |
blank | +0.876 |
manship | +0.857 |
Ples | +0.853 |
Neg logit contributions | |
utonium | -1.240 |
puter | -1.166 |
awei | -1.041 |
APH | -1.040 |
izoph | -1.018 |
Token | Table |
Token ID | 8655 |
Feature activation | +1.41e-02 |
Pos logit contributions | |
utonium | +0.613 |
puter | +0.579 |
awei | +0.520 |
APH | +0.517 |
izoph | +0.508 |
Neg logit contributions | |
xual | -0.414 |
relativity | -0.404 |
blank | -0.399 |
manship | -0.392 |
Ples | -0.391 |
Token | [ |
Token ID | 58 |
Feature activation | +3.53e-02 |
Pos logit contributions | |
utonium | +0.043 |
puter | +0.040 |
APH | +0.036 |
awei | +0.036 |
ritten | +0.035 |
Neg logit contributions | |
xual | -0.036 |
relativity | -0.036 |
blank | -0.035 |
Ples | -0.034 |
manship | -0.034 |
Token | index |
Token ID | 6376 |
Feature activation | -3.75e-02 |
Pos logit contributions | |
utonium | +0.105 |
puter | +0.098 |
APH | +0.087 |
awei | +0.086 |
ritten | +0.084 |
Neg logit contributions | |
xual | -0.093 |
relativity | -0.091 |
blank | -0.089 |
Ples | -0.088 |
manship | -0.088 |
Token | State |
Token ID | 9012 |
Feature activation | +1.19e-02 |
Pos logit contributions | |
xual | +0.091 |
relativity | +0.090 |
blank | +0.087 |
manship | +0.086 |
Ples | +0.086 |
Neg logit contributions | |
utonium | -0.118 |
puter | -0.111 |
APH | -0.100 |
awei | -0.099 |
ritten | -0.097 |
Token | but |
Token ID | 475 |
Feature activation | -2.07e-02 |
Pos logit contributions | |
xual | +0.074 |
blank | +0.072 |
relativity | +0.072 |
manship | +0.071 |
Ples | +0.070 |
Neg logit contributions | |
utonium | -0.109 |
puter | -0.103 |
awei | -0.092 |
APH | -0.092 |
ritten | -0.090 |
Token | the |
Token ID | 262 |
Feature activation | -2.31e-03 |
Pos logit contributions | |
xual | +0.053 |
blank | +0.052 |
relativity | +0.052 |
manship | +0.051 |
Ples | +0.050 |
Neg logit contributions | |
utonium | -0.062 |
puter | -0.058 |
awei | -0.052 |
APH | -0.052 |
ritten | -0.050 |
Token | AI |
Token ID | 9552 |
Feature activation | -2.71e-02 |
Pos logit contributions | |
xual | +0.006 |
blank | +0.005 |
relativity | +0.005 |
manship | +0.005 |
Ples | +0.005 |
Neg logit contributions | |
utonium | -0.007 |
puter | -0.007 |
APH | -0.006 |
awei | -0.006 |
izoph | -0.006 |
Token | January |
Token ID | 3269 |
Feature activation | -3.98e-02 |
Pos logit contributions | |
xual | +0.060 |
blank | +0.059 |
relativity | +0.059 |
Ples | +0.058 |
manship | +0.057 |
Neg logit contributions | |
utonium | -0.090 |
puter | -0.085 |
APH | -0.077 |
awei | -0.076 |
ritten | -0.075 |
Token | analy |
Token ID | 4284 |
Feature activation | -4.53e-02 |
Pos logit contributions | |
xual | +0.089 |
relativity | +0.088 |
blank | +0.086 |
manship | +0.084 |
Ples | +0.084 |
Neg logit contributions | |
utonium | -0.132 |
puter | -0.125 |
APH | -0.111 |
awei | -0.111 |
ritten | -0.109 |
Token | zes |
Token ID | 12271 |
Feature activation | -3.81e-01 |
Pos logit contributions | |
relativity | +0.116 |
xual | +0.116 |
blank | +0.115 |
manship | +0.112 |
Ples | +0.111 |
Neg logit contributions | |
utonium | -0.136 |
puter | -0.126 |
APH | -0.111 |
awei | -0.111 |
ritten | -0.109 |
Token | your |
Token ID | 534 |
Feature activation | -6.60e-02 |
Pos logit contributions | |
xual | +0.968 |
relativity | +0.947 |
blank | +0.945 |
Ples | +0.920 |
manship | +0.920 |
Neg logit contributions | |
utonium | -1.159 |
puter | -1.087 |
awei | -0.966 |
APH | -0.965 |
ritten | -0.943 |
Token | actions |
Token ID | 4028 |
Feature activation | +5.33e-02 |
Pos logit contributions | |
xual | +0.176 |
relativity | +0.172 |
blank | +0.172 |
Ples | +0.167 |
manship | +0.167 |
Neg logit contributions | |
utonium | -0.193 |
puter | -0.181 |
awei | -0.159 |
APH | -0.159 |
izoph | -0.155 |
Token | at |
Token ID | 379 |
Feature activation | -3.51e-03 |
Pos logit contributions | |
utonium | +0.169 |
puter | +0.159 |
APH | +0.142 |
awei | +0.141 |
ritten | +0.138 |
Neg logit contributions | |
xual | -0.128 |
relativity | -0.126 |
blank | -0.125 |
Ples | -0.122 |
manship | -0.121 |
Token | length |
Token ID | 4129 |
Feature activation | +9.52e-02 |
Pos logit contributions | |
xual | +0.009 |
blank | +0.009 |
relativity | +0.009 |
manship | +0.009 |
Ples | +0.009 |
Neg logit contributions | |
utonium | -0.010 |
puter | -0.010 |
APH | -0.009 |
awei | -0.008 |
ritten | -0.008 |
Token | , |
Token ID | 11 |
Feature activation | -2.21e-02 |
Pos logit contributions | |
utonium | +0.306 |
puter | +0.288 |
APH | +0.258 |
awei | +0.257 |
ritten | +0.251 |
Neg logit contributions | |
xual | -0.223 |
relativity | -0.218 |
blank | -0.217 |
Ples | -0.212 |
manship | -0.211 |
Token | F |
Token ID | 376 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
xual | +0.017 |
relativity | +0.017 |
blank | +0.017 |
manship | +0.017 |
Ples | +0.017 |
Neg logit contributions | |
utonium | -0.018 |
puter | -0.017 |
APH | -0.015 |
awei | -0.015 |
izoph | -0.014 |
Token | ED |
Token ID | 1961 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
utonium | +0.198 |
puter | +0.174 |
APH | +0.145 |
awei | +0.138 |
ritten | +0.136 |
Neg logit contributions | |
xual | -0.408 |
relativity | -0.402 |
blank | -0.398 |
Ples | -0.397 |
manship | -0.397 |
Token | state |
Token ID | 1181 |
Feature activation | -4.95e-02 |
Pos logit contributions | |
xual | +0.324 |
relativity | +0.316 |
blank | +0.312 |
manship | +0.306 |
Ples | +0.306 |
Neg logit contributions | |
utonium | -0.467 |
puter | -0.440 |
APH | -0.399 |
awei | -0.389 |
ritten | -0.387 |
Token | ) |
Token ID | 8 |
Feature activation | -1.23e-02 |
Pos logit contributions | |
xual | +0.106 |
relativity | +0.103 |
blank | +0.102 |
Ples | +0.100 |
manship | +0.099 |
Neg logit contributions | |
utonium | -0.171 |
puter | -0.162 |
APH | -0.145 |
awei | -0.144 |
ritten | -0.142 |
Token | accompl |
Token ID | 6424 |
Feature activation | -5.72e-02 |
Pos logit contributions | |
xual | +0.027 |
relativity | +0.026 |
blank | +0.026 |
manship | +0.025 |
Ples | +0.025 |
Neg logit contributions | |
utonium | -0.042 |
puter | -0.039 |
awei | -0.036 |
APH | -0.035 |
ordable | -0.035 |
Token | ishes |
Token ID | 5614 |
Feature activation | -3.76e-01 |
Pos logit contributions | |
xual | +0.161 |
relativity | +0.160 |
blank | +0.158 |
manship | +0.156 |
Ples | +0.155 |
Neg logit contributions | |
utonium | -0.159 |
puter | -0.146 |
awei | -0.129 |
APH | -0.128 |
ordable | -0.126 |
Token | all |
Token ID | 477 |
Feature activation | +3.90e-03 |
Pos logit contributions | |
xual | +0.967 |
relativity | +0.952 |
blank | +0.945 |
manship | +0.925 |
Ples | +0.922 |
Neg logit contributions | |
utonium | -1.134 |
puter | -1.059 |
awei | -0.939 |
APH | -0.936 |
izoph | -0.916 |
Token | of |
Token ID | 286 |
Feature activation | +5.60e-02 |
Pos logit contributions | |
utonium | +0.013 |
puter | +0.012 |
APH | +0.011 |
awei | +0.011 |
izoph | +0.011 |
Neg logit contributions | |
xual | -0.009 |
blank | -0.009 |
relativity | -0.009 |
manship | -0.008 |
Ples | -0.008 |
Token | these |
Token ID | 777 |
Feature activation | +5.09e-02 |
Pos logit contributions | |
utonium | +0.158 |
puter | +0.146 |
APH | +0.129 |
awei | +0.128 |
izoph | +0.125 |
Neg logit contributions | |
xual | -0.156 |
relativity | -0.152 |
blank | -0.152 |
Ples | -0.149 |
manship | -0.149 |
Token | , |
Token ID | 11 |
Feature activation | +7.34e-03 |
Pos logit contributions | |
utonium | +0.165 |
puter | +0.155 |
awei | +0.139 |
APH | +0.139 |
izoph | +0.136 |
Neg logit contributions | |
xual | -0.120 |
relativity | -0.117 |
blank | -0.116 |
manship | -0.114 |
Ples | -0.113 |
Token | very |
Token ID | 845 |
Feature activation | +4.05e-03 |
Pos logit contributions | |
utonium | +0.023 |
puter | +0.022 |
APH | +0.019 |
awei | +0.019 |
ordable | +0.019 |
Neg logit contributions | |
xual | -0.018 |
relativity | -0.017 |
blank | -0.017 |
manship | -0.017 |
Ples | -0.017 |
Token | of |
Token ID | 286 |
Feature activation | -3.81e-02 |
Pos logit contributions | |
xual | +0.092 |
relativity | +0.091 |
blank | +0.090 |
manship | +0.087 |
Ples | +0.087 |
Neg logit contributions | |
utonium | -0.180 |
puter | -0.170 |
awei | -0.154 |
APH | -0.154 |
ordable | -0.151 |
Token | the |
Token ID | 262 |
Feature activation | -4.57e-02 |
Pos logit contributions | |
xual | +0.109 |
relativity | +0.108 |
blank | +0.107 |
manship | +0.105 |
Ples | +0.104 |
Neg logit contributions | |
utonium | -0.103 |
puter | -0.096 |
awei | -0.084 |
APH | -0.084 |
ordable | -0.081 |
Token | company |
Token ID | 1664 |
Feature activation | +4.03e-03 |
Pos logit contributions | |
xual | +0.126 |
relativity | +0.124 |
blank | +0.124 |
manship | +0.121 |
Ples | +0.120 |
Neg logit contributions | |
utonium | -0.129 |
puter | -0.121 |
awei | -0.106 |
APH | -0.105 |
ordable | -0.102 |
Token | 's |
Token ID | 338 |
Feature activation | -1.70e-02 |
Pos logit contributions | |
utonium | +0.015 |
puter | +0.014 |
awei | +0.013 |
APH | +0.013 |
ordable | +0.013 |
Neg logit contributions | |
xual | -0.008 |
relativity | -0.007 |
blank | -0.007 |
Ples | -0.007 |
manship | -0.007 |
Token | enroll |
Token ID | 14627 |
Feature activation | +1.27e-02 |
Pos logit contributions | |
xual | +0.052 |
relativity | +0.052 |
blank | +0.052 |
manship | +0.050 |
Ples | +0.050 |
Neg logit contributions | |
utonium | -0.042 |
puter | -0.039 |
awei | -0.034 |
APH | -0.033 |
ordable | -0.033 |
Token | ments |
Token ID | 902 |
Feature activation | -3.75e-01 |
Pos logit contributions | |
utonium | +0.041 |
puter | +0.039 |
awei | +0.035 |
APH | +0.034 |
ordable | +0.034 |
Neg logit contributions | |
xual | -0.030 |
relativity | -0.030 |
blank | -0.029 |
Ples | -0.028 |
manship | -0.028 |
Token | allegedly |
Token ID | 7910 |
Feature activation | +2.56e-03 |
Pos logit contributions | |
xual | +0.975 |
relativity | +0.963 |
blank | +0.954 |
Ples | +0.931 |
manship | +0.931 |
Neg logit contributions | |
utonium | -1.121 |
puter | -1.047 |
awei | -0.926 |
APH | -0.922 |
ordable | -0.902 |
Token | involved |
Token ID | 2950 |
Feature activation | -8.45e-02 |
Pos logit contributions | |
utonium | +0.008 |
puter | +0.007 |
awei | +0.006 |
APH | +0.006 |
ordable | +0.006 |
Neg logit contributions | |
xual | -0.007 |
relativity | -0.006 |
blank | -0.006 |
Ples | -0.006 |
manship | -0.006 |
Token | overriding |
Token ID | 44987 |
Feature activation | -5.64e-02 |
Pos logit contributions | |
xual | +0.233 |
relativity | +0.229 |
blank | +0.227 |
manship | +0.223 |
Ples | +0.221 |
Neg logit contributions | |
utonium | -0.240 |
puter | -0.224 |
awei | -0.197 |
APH | -0.196 |
ordable | -0.191 |
Token | a |
Token ID | 257 |
Feature activation | -1.52e-02 |
Pos logit contributions | |
xual | +0.154 |
relativity | +0.150 |
blank | +0.149 |
manship | +0.146 |
Lovecraft | +0.145 |
Neg logit contributions | |
utonium | -0.160 |
puter | -0.150 |
awei | -0.133 |
APH | -0.131 |
ordable | -0.130 |
Token | system |
Token ID | 1080 |
Feature activation | +3.91e-02 |
Pos logit contributions | |
xual | +0.041 |
relativity | +0.040 |
blank | +0.040 |
manship | +0.039 |
Ples | +0.039 |
Neg logit contributions | |
utonium | -0.044 |
puter | -0.041 |
awei | -0.036 |
APH | -0.036 |
ritten | -0.035 |
Token | will |
Token ID | 481 |
Feature activation | -1.91e-02 |
Pos logit contributions | |
xual | +0.086 |
relativity | +0.085 |
blank | +0.084 |
Ples | +0.082 |
manship | +0.082 |
Neg logit contributions | |
utonium | -0.124 |
puter | -0.116 |
awei | -0.103 |
APH | -0.103 |
ordable | -0.101 |
Token | receive |
Token ID | 3328 |
Feature activation | -3.22e-02 |
Pos logit contributions | |
xual | +0.047 |
relativity | +0.046 |
blank | +0.045 |
manship | +0.044 |
Ples | +0.044 |
Neg logit contributions | |
utonium | -0.060 |
puter | -0.056 |
awei | -0.050 |
APH | -0.050 |
ritten | -0.049 |
Token | the |
Token ID | 262 |
Feature activation | -2.43e-02 |
Pos logit contributions | |
xual | +0.090 |
relativity | +0.088 |
blank | +0.088 |
manship | +0.086 |
Ples | +0.086 |
Neg logit contributions | |
utonium | -0.090 |
puter | -0.084 |
awei | -0.074 |
APH | -0.073 |
ordable | -0.072 |
Token | income |
Token ID | 3739 |
Feature activation | +6.09e-03 |
Pos logit contributions | |
xual | +0.061 |
relativity | +0.060 |
blank | +0.059 |
manship | +0.059 |
Ples | +0.058 |
Neg logit contributions | |
utonium | -0.074 |
puter | -0.070 |
awei | -0.062 |
APH | -0.061 |
ordable | -0.061 |
Token | uncond |
Token ID | 31776 |
Feature activation | -3.06e-02 |
Pos logit contributions | |
utonium | +0.019 |
puter | +0.018 |
awei | +0.016 |
APH | +0.016 |
ordable | +0.015 |
Neg logit contributions | |
xual | -0.015 |
relativity | -0.015 |
blank | -0.015 |
manship | -0.014 |
Ples | -0.014 |
Token | itionally |
Token ID | 8736 |
Feature activation | -3.65e-01 |
Pos logit contributions | |
xual | +0.084 |
relativity | +0.083 |
blank | +0.083 |
manship | +0.081 |
Ples | +0.081 |
Neg logit contributions | |
utonium | -0.087 |
puter | -0.081 |
awei | -0.071 |
APH | -0.071 |
izoph | -0.069 |
Token | while |
Token ID | 981 |
Feature activation | -1.04e-02 |
Pos logit contributions | |
xual | +0.825 |
relativity | +0.810 |
blank | +0.803 |
Ples | +0.783 |
manship | +0.782 |
Neg logit contributions | |
utonium | -1.217 |
puter | -1.143 |
awei | -1.025 |
APH | -1.025 |
ordable | -1.005 |
Token | others |
Token ID | 1854 |
Feature activation | +4.84e-02 |
Pos logit contributions | |
xual | +0.027 |
relativity | +0.027 |
blank | +0.027 |
manship | +0.026 |
Ples | +0.026 |
Neg logit contributions | |
utonium | -0.031 |
puter | -0.029 |
awei | -0.025 |
APH | -0.025 |
ordable | -0.025 |
Token | will |
Token ID | 481 |
Feature activation | -1.94e-02 |
Pos logit contributions | |
utonium | +0.160 |
puter | +0.150 |
APH | +0.134 |
awei | +0.134 |
ordable | +0.132 |
Neg logit contributions | |
xual | -0.111 |
relativity | -0.108 |
blank | -0.108 |
Ples | -0.105 |
manship | -0.104 |
Token | have |
Token ID | 423 |
Feature activation | -5.44e-02 |
Pos logit contributions | |
xual | +0.048 |
relativity | +0.047 |
blank | +0.047 |
manship | +0.046 |
Ples | +0.046 |
Neg logit contributions | |
utonium | -0.061 |
puter | -0.057 |
APH | -0.050 |
awei | -0.050 |
ritten | -0.050 |
Token | conditions |
Token ID | 3403 |
Feature activation | -1.09e-02 |
Pos logit contributions | |
xual | +0.139 |
relativity | +0.136 |
blank | +0.135 |
Ples | +0.132 |
manship | +0.132 |
Neg logit contributions | |
utonium | -0.166 |
puter | -0.155 |
awei | -0.138 |
APH | -0.137 |
ordable | -0.135 |
Token |
|
Token ID | 198 |
Feature activation | +7.58e-03 |
Pos logit contributions | |
xual | +0.008 |
blank | +0.008 |
relativity | +0.008 |
manship | +0.007 |
Ples | +0.007 |
Neg logit contributions | |
utonium | -0.012 |
puter | -0.011 |
awei | -0.010 |
APH | -0.010 |
izoph | -0.010 |
Token | No |
Token ID | 2949 |
Feature activation | -4.02e-03 |
Pos logit contributions | |
utonium | +0.023 |
puter | +0.022 |
APH | +0.020 |
awei | +0.019 |
ritten | +0.019 |
Neg logit contributions | |
xual | -0.019 |
relativity | -0.019 |
Ples | -0.018 |
manship | -0.018 |
blank | -0.018 |
Token | major |
Token ID | 1688 |
Feature activation | -3.33e-02 |
Pos logit contributions | |
xual | +0.010 |
relativity | +0.010 |
blank | +0.010 |
manship | +0.010 |
Ples | +0.010 |
Neg logit contributions | |
utonium | -0.012 |
puter | -0.012 |
APH | -0.010 |
awei | -0.010 |
ordable | -0.010 |
Token | out |
Token ID | 503 |
Feature activation | -1.19e-02 |
Pos logit contributions | |
xual | +0.085 |
relativity | +0.083 |
blank | +0.082 |
Ples | +0.081 |
manship | +0.080 |
Neg logit contributions | |
utonium | -0.101 |
puter | -0.094 |
awei | -0.084 |
APH | -0.084 |
ordable | -0.082 |
Token | bur |
Token ID | 6236 |
Feature activation | +1.61e-02 |
Pos logit contributions | |
relativity | +0.027 |
xual | +0.027 |
Lovecraft | +0.026 |
blank | +0.026 |
Ples | +0.026 |
Neg logit contributions | |
utonium | -0.039 |
puter | -0.037 |
APH | -0.033 |
awei | -0.033 |
ordable | -0.033 |
Token | sts |
Token ID | 6448 |
Feature activation | -3.63e-01 |
Pos logit contributions | |
utonium | +0.057 |
puter | +0.054 |
awei | +0.049 |
APH | +0.049 |
ritten | +0.048 |
Neg logit contributions | |
xual | -0.033 |
relativity | -0.032 |
blank | -0.032 |
manship | -0.031 |
Ples | -0.031 |
Token | marked |
Token ID | 7498 |
Feature activation | +6.10e-02 |
Pos logit contributions | |
xual | +0.926 |
relativity | +0.916 |
blank | +0.900 |
Ples | +0.881 |
manship | +0.872 |
Neg logit contributions | |
utonium | -1.103 |
puter | -1.031 |
awei | -0.915 |
APH | -0.912 |
ordable | -0.896 |
Token | the |
Token ID | 262 |
Feature activation | +7.41e-02 |
Pos logit contributions | |
utonium | +0.176 |
puter | +0.165 |
APH | +0.147 |
awei | +0.145 |
ritten | +0.142 |
Neg logit contributions | |
xual | -0.162 |
relativity | -0.161 |
blank | -0.158 |
manship | -0.155 |
Ples | -0.154 |
Token | SB |
Token ID | 18056 |
Feature activation | -5.18e-02 |
Pos logit contributions | |
utonium | +0.222 |
puter | +0.206 |
APH | +0.184 |
awei | +0.183 |
ritten | +0.179 |
Neg logit contributions | |
xual | -0.193 |
relativity | -0.189 |
blank | -0.187 |
manship | -0.183 |
Ples | -0.182 |
Token | 6 |
Token ID | 21 |
Feature activation | -1.98e-02 |
Pos logit contributions | |
xual | +0.150 |
relativity | +0.148 |
blank | +0.145 |
Ples | +0.144 |
manship | +0.143 |
Neg logit contributions | |
utonium | -0.140 |
puter | -0.128 |
APH | -0.114 |
awei | -0.112 |
ordable | -0.110 |
Token | hearing |
Token ID | 4854 |
Feature activation | +1.24e-02 |
Pos logit contributions | |
xual | +0.048 |
relativity | +0.048 |
blank | +0.047 |
manship | +0.047 |
Ples | +0.046 |
Neg logit contributions | |
utonium | -0.061 |
puter | -0.057 |
APH | -0.051 |
awei | -0.051 |
ritten | -0.050 |
Token | h |
Token ID | 289 |
Feature activation | -5.27e-03 |
Pos logit contributions | |
xual | +0.073 |
relativity | +0.072 |
blank | +0.071 |
manship | +0.070 |
Ples | +0.069 |
Neg logit contributions | |
utonium | -0.089 |
puter | -0.084 |
awei | -0.074 |
APH | -0.074 |
ritten | -0.072 |
Token | iked |
Token ID | 17951 |
Feature activation | -1.00e-03 |
Pos logit contributions | |
xual | +0.013 |
relativity | +0.012 |
blank | +0.012 |
manship | +0.012 |
Ples | +0.012 |
Neg logit contributions | |
utonium | -0.017 |
puter | -0.016 |
awei | -0.014 |
APH | -0.014 |
ritten | -0.014 |
Token | in |
Token ID | 287 |
Feature activation | +1.20e-02 |
Pos logit contributions | |
xual | +0.003 |
relativity | +0.003 |
blank | +0.003 |
manship | +0.003 |
Ples | +0.002 |
Neg logit contributions | |
utonium | -0.003 |
puter | -0.003 |
APH | -0.002 |
awei | -0.002 |
ordable | -0.002 |
Token | rain |
Token ID | 6290 |
Feature activation | -5.41e-03 |
Pos logit contributions | |
utonium | +0.035 |
puter | +0.033 |
APH | +0.029 |
awei | +0.029 |
ordable | +0.028 |
Neg logit contributions | |
xual | -0.032 |
relativity | -0.031 |
blank | -0.031 |
manship | -0.030 |
Ples | -0.030 |
Token | fore |
Token ID | 754 |
Feature activation | +1.55e-02 |
Pos logit contributions | |
xual | +0.013 |
relativity | +0.013 |
blank | +0.012 |
manship | +0.012 |
Ples | +0.012 |
Neg logit contributions | |
utonium | -0.017 |
puter | -0.016 |
APH | -0.014 |
awei | -0.014 |
izoph | -0.014 |
Token | sts |
Token ID | 6448 |
Feature activation | -3.62e-01 |
Pos logit contributions | |
utonium | +0.055 |
puter | +0.052 |
APH | +0.047 |
awei | +0.047 |
ritten | +0.046 |
Neg logit contributions | |
xual | -0.032 |
relativity | -0.031 |
blank | -0.030 |
Ples | -0.030 |
manship | -0.030 |
Token | , |
Token ID | 11 |
Feature activation | +5.58e-03 |
Pos logit contributions | |
xual | +0.852 |
relativity | +0.840 |
blank | +0.830 |
manship | +0.810 |
Ples | +0.808 |
Neg logit contributions | |
utonium | -1.173 |
puter | -1.102 |
APH | -0.985 |
awei | -0.985 |
izoph | -0.963 |
Token | in |
Token ID | 287 |
Feature activation | +2.72e-02 |
Pos logit contributions | |
utonium | +0.017 |
puter | +0.016 |
APH | +0.015 |
awei | +0.014 |
ordable | +0.014 |
Neg logit contributions | |
xual | -0.014 |
relativity | -0.014 |
blank | -0.013 |
manship | -0.013 |
Ples | -0.013 |
Token | deserts |
Token ID | 45288 |
Feature activation | -9.14e-02 |
Pos logit contributions | |
utonium | +0.083 |
puter | +0.078 |
APH | +0.069 |
awei | +0.069 |
ordable | +0.068 |
Neg logit contributions | |
xual | -0.068 |
relativity | -0.067 |
blank | -0.066 |
manship | -0.065 |
Ples | -0.064 |
Token | , |
Token ID | 11 |
Feature activation | -1.55e-02 |
Pos logit contributions | |
xual | +0.211 |
relativity | +0.207 |
blank | +0.203 |
manship | +0.199 |
Ples | +0.198 |
Neg logit contributions | |
utonium | -0.297 |
puter | -0.281 |
APH | -0.253 |
awei | -0.251 |
izoph | -0.247 |
Token | and |
Token ID | 290 |
Feature activation | -2.11e-02 |
Pos logit contributions | |
xual | +0.039 |
relativity | +0.039 |
blank | +0.038 |
manship | +0.038 |
Ples | +0.037 |
Neg logit contributions | |
utonium | -0.047 |
puter | -0.044 |
APH | -0.040 |
awei | -0.040 |
ordable | -0.039 |
Token | ple |
Token ID | 1154 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
xual | +0.141 |
relativity | +0.140 |
blank | +0.138 |
manship | +0.136 |
Ples | +0.136 |
Neg logit contributions | |
utonium | -0.107 |
puter | -0.098 |
APH | -0.084 |
awei | -0.084 |
ritten | -0.081 |
Token | tes |
Token ID | 4879 |
Feature activation | +4.98e-02 |
Pos logit contributions | |
utonium | +0.370 |
puter | +0.348 |
ordable | +0.310 |
APH | +0.309 |
awei | +0.308 |
Neg logit contributions | |
relativity | -0.251 |
xual | -0.250 |
blank | -0.246 |
manship | -0.239 |
Ples | -0.234 |
Token | glucose |
Token ID | 15701 |
Feature activation | -4.07e-02 |
Pos logit contributions | |
utonium | +0.140 |
puter | +0.131 |
APH | +0.114 |
awei | +0.114 |
ritten | +0.112 |
Neg logit contributions | |
xual | -0.138 |
relativity | -0.136 |
blank | -0.135 |
manship | -0.133 |
Ples | -0.131 |
Token | and |
Token ID | 290 |
Feature activation | -1.52e-02 |
Pos logit contributions | |
xual | +0.100 |
relativity | +0.099 |
blank | +0.098 |
manship | +0.096 |
Ples | +0.096 |
Neg logit contributions | |
utonium | -0.127 |
puter | -0.119 |
APH | -0.106 |
awei | -0.105 |
ordable | -0.103 |
Token | glyc |
Token ID | 40232 |
Feature activation | +7.52e-04 |
Pos logit contributions | |
xual | +0.039 |
blank | +0.038 |
relativity | +0.038 |
manship | +0.037 |
Ples | +0.037 |
Neg logit contributions | |
utonium | -0.046 |
puter | -0.043 |
awei | -0.038 |
APH | -0.038 |
izoph | -0.037 |
Token | ogen |
Token ID | 6644 |
Feature activation | +4.08e-01 |
Pos logit contributions | |
utonium | +0.002 |
puter | +0.002 |
awei | +0.001 |
APH | +0.001 |
ritten | +0.001 |
Neg logit contributions | |
xual | -0.002 |
relativity | -0.002 |
blank | -0.002 |
manship | -0.002 |
Ples | -0.002 |
Token | rapidly |
Token ID | 8902 |
Feature activation | +3.67e-02 |
Pos logit contributions | |
utonium | +1.270 |
puter | +1.196 |
APH | +1.061 |
awei | +1.045 |
ordable | +1.027 |
Neg logit contributions | |
xual | -0.995 |
relativity | -0.974 |
blank | -0.964 |
Ples | -0.951 |
manship | -0.944 |
Token | , |
Token ID | 11 |
Feature activation | -1.49e-02 |
Pos logit contributions | |
utonium | +0.116 |
puter | +0.108 |
APH | +0.097 |
awei | +0.096 |
ordable | +0.094 |
Neg logit contributions | |
xual | -0.088 |
relativity | -0.087 |
blank | -0.086 |
manship | -0.084 |
Ples | -0.084 |
Token | forcing |
Token ID | 10833 |
Feature activation | +1.52e-02 |
Pos logit contributions | |
xual | +0.038 |
relativity | +0.037 |
blank | +0.037 |
manship | +0.036 |
Ples | +0.036 |
Neg logit contributions | |
utonium | -0.046 |
puter | -0.043 |
APH | -0.038 |
awei | -0.038 |
ordable | -0.037 |
Token | the |
Token ID | 262 |
Feature activation | -1.58e-03 |
Pos logit contributions | |
utonium | +0.043 |
puter | +0.040 |
awei | +0.035 |
APH | +0.035 |
izoph | +0.035 |
Neg logit contributions | |
xual | -0.042 |
relativity | -0.041 |
blank | -0.041 |
manship | -0.040 |
Ples | -0.040 |
Token | body |
Token ID | 1767 |
Feature activation | -1.05e-02 |
Pos logit contributions | |
xual | +0.005 |
blank | +0.004 |
relativity | +0.004 |
manship | +0.004 |
Ples | +0.004 |
Neg logit contributions | |
utonium | -0.004 |
puter | -0.004 |
APH | -0.003 |
awei | -0.003 |
izoph | -0.003 |
Token | receiver |
Token ID | 9733 |
Feature activation | -4.64e-02 |
Pos logit contributions | |
xual | +0.299 |
relativity | +0.290 |
blank | +0.287 |
Ples | +0.287 |
manship | +0.286 |
Neg logit contributions | |
utonium | -0.321 |
puter | -0.303 |
APH | -0.269 |
awei | -0.265 |
ordable | -0.259 |
Token | with |
Token ID | 351 |
Feature activation | -3.71e-03 |
Pos logit contributions | |
xual | +0.112 |
relativity | +0.109 |
blank | +0.108 |
Ples | +0.106 |
manship | +0.105 |
Neg logit contributions | |
utonium | -0.148 |
puter | -0.140 |
awei | -0.124 |
APH | -0.124 |
ritten | -0.121 |
Token | an |
Token ID | 281 |
Feature activation | -3.94e-03 |
Pos logit contributions | |
xual | +0.010 |
blank | +0.010 |
relativity | +0.010 |
manship | +0.010 |
Ples | +0.010 |
Neg logit contributions | |
utonium | -0.010 |
puter | -0.010 |
awei | -0.009 |
APH | -0.009 |
ritten | -0.008 |
Token | internal |
Token ID | 5387 |
Feature activation | -6.88e-02 |
Pos logit contributions | |
xual | +0.011 |
relativity | +0.010 |
blank | +0.010 |
manship | +0.010 |
Ples | +0.010 |
Neg logit contributions | |
utonium | -0.011 |
puter | -0.011 |
awei | -0.010 |
APH | -0.010 |
ordable | -0.009 |
Token | fer |
Token ID | 11354 |
Feature activation | -2.15e-03 |
Pos logit contributions | |
xual | +0.170 |
relativity | +0.163 |
blank | +0.162 |
manship | +0.160 |
Ples | +0.158 |
Neg logit contributions | |
utonium | -0.217 |
puter | -0.205 |
awei | -0.182 |
APH | -0.181 |
ritten | -0.177 |
Token | rite |
Token ID | 6525 |
Feature activation | +3.26e-01 |
Pos logit contributions | |
xual | +0.009 |
relativity | +0.009 |
blank | +0.009 |
manship | +0.009 |
Ples | +0.009 |
Neg logit contributions | |
utonium | -0.003 |
puter | -0.003 |
awei | -0.002 |
APH | -0.002 |
izoph | -0.002 |
Token | rod |
Token ID | 15299 |
Feature activation | +6.22e-02 |
Pos logit contributions | |
utonium | +1.060 |
puter | +0.999 |
APH | +0.891 |
awei | +0.887 |
ritten | +0.869 |
Neg logit contributions | |
xual | -0.774 |
relativity | -0.745 |
blank | -0.728 |
manship | -0.727 |
Ples | -0.721 |
Token | antenna |
Token ID | 20509 |
Feature activation | -3.99e-02 |
Pos logit contributions | |
utonium | +0.197 |
puter | +0.187 |
awei | +0.165 |
APH | +0.165 |
ritten | +0.161 |
Neg logit contributions | |
xual | -0.151 |
relativity | -0.147 |
blank | -0.146 |
Ples | -0.142 |
manship | -0.142 |
Token | and |
Token ID | 290 |
Feature activation | +7.14e-03 |
Pos logit contributions | |
xual | +0.096 |
relativity | +0.094 |
blank | +0.093 |
manship | +0.091 |
Ples | +0.091 |
Neg logit contributions | |
utonium | -0.127 |
puter | -0.120 |
awei | -0.106 |
APH | -0.106 |
ordable | -0.104 |
Token | start |
Token ID | 923 |
Feature activation | -3.04e-02 |
Pos logit contributions | |
utonium | +0.022 |
puter | +0.020 |
APH | +0.018 |
awei | +0.018 |
ritten | +0.018 |
Neg logit contributions | |
xual | -0.018 |
blank | -0.018 |
relativity | -0.018 |
manship | -0.017 |
Ples | -0.017 |
Token | moving |
Token ID | 3867 |
Feature activation | +6.94e-02 |
Pos logit contributions | |
xual | +0.079 |
relativity | +0.078 |
blank | +0.077 |
Ples | +0.075 |
manship | +0.075 |
Neg logit contributions | |
utonium | -0.091 |
puter | -0.086 |
awei | -0.075 |
APH | -0.075 |
izoph | -0.073 |
Token | summer |
Token ID | 3931 |
Feature activation | +3.41e-02 |
Pos logit contributions | |
utonium | +0.176 |
puter | +0.165 |
APH | +0.147 |
awei | +0.147 |
ritten | +0.145 |
Neg logit contributions | |
xual | -0.135 |
blank | -0.131 |
relativity | -0.131 |
manship | -0.128 |
Ples | -0.127 |
Token | � |
Token ID | 447 |
Feature activation | +4.15e-02 |
Pos logit contributions | |
utonium | +0.112 |
puter | +0.106 |
APH | +0.095 |
awei | +0.095 |
ritten | +0.093 |
Neg logit contributions | |
xual | -0.077 |
relativity | -0.076 |
blank | -0.075 |
Ples | -0.073 |
manship | -0.073 |
Token | � |
Token ID | 247 |
Feature activation | +8.26e-03 |
Pos logit contributions | |
utonium | +0.079 |
puter | +0.070 |
awei | +0.058 |
APH | +0.057 |
izoph | +0.055 |
Neg logit contributions | |
xual | -0.153 |
relativity | -0.151 |
blank | -0.151 |
Ples | -0.149 |
manship | -0.148 |
Token | s |
Token ID | 82 |
Feature activation | -7.27e-03 |
Pos logit contributions | |
utonium | +0.027 |
puter | +0.025 |
APH | +0.023 |
awei | +0.023 |
ritten | +0.022 |
Neg logit contributions | |
xual | -0.019 |
relativity | -0.019 |
blank | -0.018 |
Ples | -0.018 |
manship | -0.018 |
Token | euph |
Token ID | 40381 |
Feature activation | +3.77e-02 |
Pos logit contributions | |
xual | +0.019 |
relativity | +0.018 |
blank | +0.018 |
manship | +0.018 |
Ples | +0.018 |
Neg logit contributions | |
utonium | -0.022 |
puter | -0.020 |
APH | -0.018 |
awei | -0.018 |
ritten | -0.018 |
Token | oria |
Token ID | 7661 |
Feature activation | +3.08e-01 |
Pos logit contributions | |
utonium | +0.103 |
puter | +0.096 |
APH | +0.083 |
awei | +0.083 |
ritten | +0.081 |
Neg logit contributions | |
xual | -0.108 |
relativity | -0.107 |
blank | -0.106 |
manship | -0.104 |
Ples | -0.103 |
Token | has |
Token ID | 468 |
Feature activation | +2.54e-02 |
Pos logit contributions | |
utonium | +1.007 |
puter | +0.950 |
awei | +0.854 |
APH | +0.853 |
ritten | +0.834 |
Neg logit contributions | |
xual | -0.699 |
blank | -0.688 |
relativity | -0.680 |
Ples | -0.662 |
manship | -0.654 |
Token | vanished |
Token ID | 23717 |
Feature activation | +2.28e-02 |
Pos logit contributions | |
utonium | +0.076 |
puter | +0.071 |
awei | +0.063 |
APH | +0.063 |
ritten | +0.062 |
Neg logit contributions | |
xual | -0.066 |
relativity | -0.064 |
blank | -0.064 |
manship | -0.062 |
Ples | -0.062 |
Token | . |
Token ID | 13 |
Feature activation | +8.90e-03 |
Pos logit contributions | |
utonium | +0.074 |
puter | +0.070 |
awei | +0.062 |
APH | +0.062 |
ritten | +0.061 |
Neg logit contributions | |
xual | -0.053 |
relativity | -0.052 |
blank | -0.052 |
manship | -0.050 |
Ples | -0.050 |
Token | So |
Token ID | 1406 |
Feature activation | +2.54e-02 |
Pos logit contributions | |
utonium | +0.028 |
puter | +0.026 |
APH | +0.023 |
awei | +0.023 |
izoph | +0.023 |
Neg logit contributions | |
xual | -0.022 |
relativity | -0.022 |
blank | -0.021 |
manship | -0.021 |
Ples | -0.020 |
Token | far |
Token ID | 1290 |
Feature activation | +4.88e-02 |
Pos logit contributions | |
utonium | +0.080 |
puter | +0.075 |
APH | +0.067 |
awei | +0.066 |
izoph | +0.065 |
Neg logit contributions | |
xual | -0.062 |
relativity | -0.060 |
blank | -0.060 |
Ples | -0.059 |
manship | -0.059 |
Token | � |
Token ID | 564 |
Feature activation | +4.20e-02 |
Pos logit contributions | |
utonium | +0.185 |
puter | +0.173 |
APH | +0.155 |
awei | +0.154 |
ritten | +0.150 |
Neg logit contributions | |
xual | -0.147 |
relativity | -0.143 |
blank | -0.141 |
manship | -0.138 |
Ples | -0.136 |
Token | � |
Token ID | 250 |
Feature activation | +1.30e-02 |
Pos logit contributions | |
utonium | +0.113 |
puter | +0.105 |
awei | +0.091 |
APH | +0.091 |
izoph | +0.089 |
Neg logit contributions | |
xual | -0.121 |
relativity | -0.120 |
blank | -0.119 |
Ples | -0.117 |
manship | -0.116 |
Token | The |
Token ID | 464 |
Feature activation | -1.49e-02 |
Pos logit contributions | |
utonium | +0.039 |
puter | +0.037 |
APH | +0.033 |
awei | +0.033 |
ritten | +0.032 |
Neg logit contributions | |
xual | -0.034 |
relativity | -0.033 |
blank | -0.032 |
manship | -0.031 |
Ples | -0.031 |
Token | one |
Token ID | 530 |
Feature activation | +2.29e-03 |
Pos logit contributions | |
xual | +0.038 |
relativity | +0.037 |
blank | +0.037 |
manship | +0.036 |
Ples | +0.035 |
Neg logit contributions | |
utonium | -0.046 |
puter | -0.043 |
awei | -0.038 |
APH | -0.038 |
ritten | -0.037 |
Token | kilomet |
Token ID | 11866 |
Feature activation | +7.28e-02 |
Pos logit contributions | |
utonium | +0.008 |
puter | +0.007 |
awei | +0.007 |
APH | +0.007 |
ritten | +0.007 |
Neg logit contributions | |
xual | -0.005 |
relativity | -0.005 |
blank | -0.005 |
Ples | -0.005 |
manship | -0.005 |
Token | re |
Token ID | 260 |
Feature activation | +2.79e-01 |
Pos logit contributions | |
utonium | +0.243 |
puter | +0.230 |
APH | +0.209 |
awei | +0.205 |
ritten | +0.202 |
Neg logit contributions | |
xual | -0.161 |
relativity | -0.161 |
blank | -0.156 |
manship | -0.155 |
Ples | -0.153 |
Token | to |
Token ID | 284 |
Feature activation | +3.02e-02 |
Pos logit contributions | |
utonium | +0.853 |
puter | +0.807 |
awei | +0.715 |
APH | +0.713 |
ritten | +0.702 |
Neg logit contributions | |
xual | -0.703 |
relativity | -0.677 |
blank | -0.674 |
manship | -0.658 |
Ples | -0.657 |
Token | go |
Token ID | 467 |
Feature activation | +2.80e-02 |
Pos logit contributions | |
utonium | +0.090 |
puter | +0.085 |
awei | +0.074 |
APH | +0.074 |
ritten | +0.073 |
Neg logit contributions | |
xual | -0.079 |
relativity | -0.077 |
blank | -0.076 |
manship | -0.075 |
Ples | -0.074 |
Token | mark |
Token ID | 1317 |
Feature activation | +4.52e-02 |
Pos logit contributions | |
utonium | +0.089 |
puter | +0.083 |
awei | +0.074 |
APH | +0.074 |
ritten | +0.073 |
Neg logit contributions | |
xual | -0.068 |
relativity | -0.066 |
blank | -0.066 |
manship | -0.064 |
Ples | -0.064 |
Token | was |
Token ID | 373 |
Feature activation | +8.56e-03 |
Pos logit contributions | |
utonium | +0.141 |
puter | +0.134 |
awei | +0.118 |
APH | +0.118 |
ritten | +0.116 |
Neg logit contributions | |
xual | -0.110 |
relativity | -0.108 |
blank | -0.107 |
Ples | -0.104 |
Lovecraft | -0.103 |
Token | the |
Token ID | 262 |
Feature activation | +3.61e-02 |
Pos logit contributions | |
utonium | +0.025 |
puter | +0.024 |
APH | +0.021 |
awei | +0.021 |
ritten | +0.021 |
Neg logit contributions | |
xual | -0.022 |
relativity | -0.022 |
blank | -0.022 |
manship | -0.021 |
Ples | -0.021 |
Token | in |
Token ID | 287 |
Feature activation | +1.78e-02 |
Pos logit contributions | |
utonium | +0.045 |
puter | +0.043 |
awei | +0.038 |
APH | +0.038 |
izoph | +0.037 |
Neg logit contributions | |
xual | -0.035 |
relativity | -0.035 |
blank | -0.035 |
manship | -0.034 |
Ples | -0.034 |
Token | court |
Token ID | 2184 |
Feature activation | -2.59e-02 |
Pos logit contributions | |
utonium | +0.044 |
puter | +0.041 |
awei | +0.035 |
APH | +0.035 |
ordable | +0.034 |
Neg logit contributions | |
xual | -0.055 |
relativity | -0.054 |
blank | -0.054 |
manship | -0.053 |
Ples | -0.052 |
Token | on |
Token ID | 319 |
Feature activation | -2.34e-02 |
Pos logit contributions | |
xual | +0.064 |
relativity | +0.063 |
blank | +0.062 |
manship | +0.061 |
Ples | +0.060 |
Neg logit contributions | |
utonium | -0.081 |
puter | -0.076 |
awei | -0.068 |
APH | -0.068 |
izoph | -0.066 |
Token | the |
Token ID | 262 |
Feature activation | +9.88e-03 |
Pos logit contributions | |
xual | +0.056 |
relativity | +0.055 |
blank | +0.054 |
manship | +0.053 |
Ples | +0.053 |
Neg logit contributions | |
utonium | -0.075 |
puter | -0.070 |
awei | -0.063 |
APH | -0.063 |
ritten | -0.061 |
Token | inter |
Token ID | 987 |
Feature activation | +5.20e-02 |
Pos logit contributions | |
utonium | +0.030 |
puter | +0.028 |
awei | +0.025 |
APH | +0.025 |
izoph | +0.024 |
Neg logit contributions | |
xual | -0.025 |
relativity | -0.025 |
blank | -0.025 |
manship | -0.024 |
Ples | -0.024 |
Token | lock |
Token ID | 5354 |
Feature activation | +2.75e-01 |
Pos logit contributions | |
utonium | +0.139 |
puter | +0.130 |
awei | +0.113 |
APH | +0.112 |
ritten | +0.110 |
Neg logit contributions | |
xual | -0.151 |
relativity | -0.149 |
blank | -0.147 |
Ples | -0.145 |
manship | -0.145 |
Token | violation |
Token ID | 8747 |
Feature activation | -1.68e-02 |
Pos logit contributions | |
utonium | +0.884 |
puter | +0.843 |
awei | +0.752 |
APH | +0.743 |
ritten | +0.733 |
Neg logit contributions | |
xual | -0.648 |
relativity | -0.626 |
blank | -0.624 |
Ples | -0.606 |
manship | -0.600 |
Token | on |
Token ID | 319 |
Feature activation | -4.70e-03 |
Pos logit contributions | |
xual | +0.037 |
relativity | +0.036 |
blank | +0.036 |
Ples | +0.035 |
manship | +0.034 |
Neg logit contributions | |
utonium | -0.057 |
puter | -0.054 |
APH | -0.048 |
awei | -0.048 |
ritten | -0.047 |
Token | May |
Token ID | 1737 |
Feature activation | +4.78e-03 |
Pos logit contributions | |
xual | +0.011 |
relativity | +0.011 |
blank | +0.011 |
manship | +0.011 |
Ples | +0.011 |
Neg logit contributions | |
utonium | -0.015 |
puter | -0.014 |
awei | -0.013 |
APH | -0.013 |
ritten | -0.012 |
Token | 26 |
Token ID | 2608 |
Feature activation | -3.70e-02 |
Pos logit contributions | |
utonium | +0.010 |
puter | +0.009 |
awei | +0.008 |
APH | +0.008 |
izoph | +0.008 |
Neg logit contributions | |
xual | -0.016 |
relativity | -0.016 |
blank | -0.016 |
manship | -0.016 |
Ples | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | -7.82e-03 |
Pos logit contributions | |
xual | +0.097 |
relativity | +0.095 |
blank | +0.094 |
Ples | +0.092 |
manship | +0.092 |
Neg logit contributions | |
utonium | -0.110 |
puter | -0.103 |
APH | -0.091 |
awei | -0.090 |
ritten | -0.089 |
Token | , |
Token ID | 11 |
Feature activation | -2.69e-02 |
Pos logit contributions | |
xual | +0.002 |
relativity | +0.002 |
blank | +0.002 |
Ples | +0.002 |
manship | +0.002 |
Neg logit contributions | |
utonium | -0.002 |
puter | -0.002 |
awei | -0.002 |
APH | -0.002 |
ordable | -0.002 |
Token | something |
Token ID | 1223 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
xual | +0.076 |
relativity | +0.075 |
blank | +0.074 |
manship | +0.073 |
Ples | +0.072 |
Neg logit contributions | |
utonium | -0.074 |
puter | -0.068 |
awei | -0.060 |
APH | -0.060 |
ordable | -0.058 |
Token | Ro |
Token ID | 5564 |
Feature activation | +6.18e-02 |
Pos logit contributions | |
xual | +0.357 |
blank | +0.344 |
relativity | +0.343 |
Ples | +0.334 |
manship | +0.333 |
Neg logit contributions | |
utonium | -0.413 |
puter | -0.388 |
awei | -0.341 |
APH | -0.339 |
ordable | -0.337 |
Token | eth |
Token ID | 2788 |
Feature activation | -5.26e-02 |
Pos logit contributions | |
utonium | +0.250 |
puter | +0.239 |
awei | +0.219 |
APH | +0.217 |
izoph | +0.215 |
Neg logit contributions | |
xual | -0.094 |
relativity | -0.093 |
blank | -0.092 |
Ples | -0.088 |
manship | -0.087 |
Token | lis |
Token ID | 27999 |
Feature activation | -3.30e-03 |
Pos logit contributions | |
xual | +0.069 |
relativity | +0.068 |
blank | +0.067 |
manship | +0.064 |
Ples | +0.064 |
Neg logit contributions | |
utonium | -0.224 |
puter | -0.214 |
APH | -0.198 |
awei | -0.197 |
izoph | -0.195 |
Token | berger |
Token ID | 21041 |
Feature activation | +7.98e-02 |
Pos logit contributions | |
xual | +0.008 |
blank | +0.008 |
relativity | +0.008 |
manship | +0.008 |
Ples | +0.008 |
Neg logit contributions | |
utonium | -0.010 |
puter | -0.009 |
awei | -0.008 |
APH | -0.008 |
izoph | -0.008 |
Token | definitely |
Token ID | 4753 |
Feature activation | -4.28e-02 |
Pos logit contributions | |
utonium | +0.270 |
puter | +0.252 |
awei | +0.227 |
APH | +0.226 |
ritten | +0.223 |
Neg logit contributions | |
xual | -0.176 |
relativity | -0.170 |
blank | -0.170 |
Ples | -0.165 |
manship | -0.163 |
Token | has |
Token ID | 468 |
Feature activation | -6.10e-03 |
Pos logit contributions | |
xual | +0.091 |
blank | +0.088 |
relativity | +0.088 |
Ples | +0.086 |
manship | +0.084 |
Neg logit contributions | |
utonium | -0.148 |
puter | -0.139 |
awei | -0.125 |
APH | -0.125 |
ordable | -0.123 |
Token | at |
Token ID | 379 |
Feature activation | -9.79e-03 |
Pos logit contributions | |
xual | +0.016 |
blank | +0.016 |
relativity | +0.015 |
Ples | +0.015 |
manship | +0.015 |
Neg logit contributions | |
utonium | -0.018 |
puter | -0.017 |
awei | -0.015 |
APH | -0.015 |
ordable | -0.015 |
Token | his |
Token ID | 465 |
Feature activation | +1.10e-02 |
Pos logit contributions | |
xual | +0.026 |
relativity | +0.025 |
blank | +0.025 |
manship | +0.025 |
Ples | +0.025 |
Neg logit contributions | |
utonium | -0.029 |
puter | -0.027 |
APH | -0.024 |
awei | -0.024 |
ordable | -0.023 |
Token | disposal |
Token ID | 18264 |
Feature activation | +4.17e-02 |
Pos logit contributions | |
utonium | +0.027 |
puter | +0.026 |
awei | +0.022 |
APH | +0.022 |
ordable | +0.021 |
Neg logit contributions | |
xual | -0.034 |
relativity | -0.034 |
blank | -0.033 |
manship | -0.033 |
Ples | -0.033 |
Token | is |
Token ID | 318 |
Feature activation | +1.58e-02 |
Pos logit contributions | |
xual | +0.225 |
relativity | +0.218 |
blank | +0.217 |
Ples | +0.213 |
Lovecraft | +0.207 |
Neg logit contributions | |
utonium | -0.306 |
puter | -0.289 |
awei | -0.257 |
APH | -0.257 |
ritten | -0.252 |
Token | wrong |
Token ID | 2642 |
Feature activation | +4.71e-02 |
Pos logit contributions | |
utonium | +0.045 |
puter | +0.042 |
awei | +0.037 |
APH | +0.037 |
ritten | +0.036 |
Neg logit contributions | |
xual | -0.044 |
relativity | -0.042 |
blank | -0.042 |
Ples | -0.041 |
manship | -0.041 |
Token | , |
Token ID | 11 |
Feature activation | -1.38e-02 |
Pos logit contributions | |
utonium | +0.150 |
puter | +0.141 |
APH | +0.127 |
awei | +0.126 |
ritten | +0.124 |
Neg logit contributions | |
xual | -0.113 |
relativity | -0.109 |
blank | -0.109 |
Ples | -0.107 |
manship | -0.106 |
Token | and |
Token ID | 290 |
Feature activation | -4.02e-02 |
Pos logit contributions | |
xual | +0.035 |
relativity | +0.034 |
blank | +0.034 |
manship | +0.034 |
Ples | +0.034 |
Neg logit contributions | |
utonium | -0.042 |
puter | -0.039 |
APH | -0.035 |
awei | -0.035 |
ritten | -0.034 |
Token | they |
Token ID | 484 |
Feature activation | -4.16e-02 |
Pos logit contributions | |
xual | +0.103 |
blank | +0.100 |
relativity | +0.099 |
Ples | +0.098 |
manship | +0.097 |
Neg logit contributions | |
utonium | -0.122 |
puter | -0.114 |
APH | -0.101 |
awei | -0.101 |
ritten | -0.098 |
Token | lack |
Token ID | 3092 |
Feature activation | +3.33e-02 |
Pos logit contributions | |
xual | +0.104 |
relativity | +0.100 |
blank | +0.099 |
Ples | +0.099 |
manship | +0.097 |
Neg logit contributions | |
utonium | -0.129 |
puter | -0.121 |
APH | -0.108 |
awei | -0.107 |
ritten | -0.106 |
Token | the |
Token ID | 262 |
Feature activation | -8.04e-02 |
Pos logit contributions | |
utonium | +0.098 |
puter | +0.091 |
APH | +0.081 |
awei | +0.080 |
ritten | +0.079 |
Neg logit contributions | |
xual | -0.088 |
blank | -0.086 |
relativity | -0.086 |
Ples | -0.084 |
manship | -0.084 |
Token | lead |
Token ID | 1085 |
Feature activation | -3.37e-02 |
Pos logit contributions | |
xual | +0.201 |
blank | +0.196 |
relativity | +0.196 |
manship | +0.191 |
Ples | +0.191 |
Neg logit contributions | |
utonium | -0.248 |
puter | -0.232 |
awei | -0.207 |
APH | -0.206 |
izoph | -0.202 |
Token | - |
Token ID | 12 |
Feature activation | +5.76e-02 |
Pos logit contributions | |
xual | +0.078 |
relativity | +0.077 |
blank | +0.075 |
Ples | +0.075 |
manship | +0.073 |
Neg logit contributions | |
utonium | -0.110 |
puter | -0.103 |
APH | -0.093 |
awei | -0.092 |
ritten | -0.091 |
Token | in |
Token ID | 259 |
Feature activation | +3.61e-02 |
Pos logit contributions | |
utonium | +0.187 |
puter | +0.177 |
awei | +0.157 |
APH | +0.157 |
ritten | +0.156 |
Neg logit contributions | |
xual | -0.135 |
relativity | -0.133 |
Ples | -0.129 |
blank | -0.128 |
Lovecraft | -0.127 |
Token | character |
Token ID | 2095 |
Feature activation | +7.27e-02 |
Pos logit contributions | |
utonium | +0.115 |
puter | +0.107 |
awei | +0.096 |
APH | +0.096 |
ritten | +0.094 |
Neg logit contributions | |
xual | -0.087 |
relativity | -0.085 |
blank | -0.084 |
Ples | -0.082 |
manship | -0.081 |
Token | Virginia |
Token ID | 6025 |
Feature activation | +4.87e-02 |
Pos logit contributions | |
xual | +0.034 |
relativity | +0.033 |
blank | +0.033 |
manship | +0.032 |
Ples | +0.031 |
Neg logit contributions | |
utonium | -0.046 |
puter | -0.043 |
APH | -0.039 |
awei | -0.039 |
ordable | -0.038 |
Token | undergrad |
Token ID | 43485 |
Feature activation | +1.97e-02 |
Pos logit contributions | |
utonium | +0.138 |
puter | +0.129 |
APH | +0.112 |
awei | +0.112 |
ritten | +0.109 |
Neg logit contributions | |
xual | -0.135 |
blank | -0.132 |
relativity | -0.130 |
Ples | -0.129 |
manship | -0.129 |
Token | who |
Token ID | 508 |
Feature activation | -4.85e-03 |
Pos logit contributions | |
utonium | +0.064 |
puter | +0.061 |
awei | +0.054 |
APH | +0.054 |
ritten | +0.053 |
Neg logit contributions | |
xual | -0.046 |
relativity | -0.045 |
blank | -0.045 |
Ples | -0.044 |
manship | -0.044 |
Token | served |
Token ID | 4983 |
Feature activation | -5.43e-02 |
Pos logit contributions | |
xual | +0.013 |
blank | +0.012 |
relativity | +0.012 |
manship | +0.012 |
Ples | +0.012 |
Neg logit contributions | |
utonium | -0.015 |
puter | -0.014 |
awei | -0.012 |
APH | -0.012 |
ritten | -0.012 |
Token | 18 |
Token ID | 1248 |
Feature activation | +2.87e-02 |
Pos logit contributions | |
xual | +0.151 |
blank | +0.148 |
relativity | +0.147 |
manship | +0.144 |
Ples | +0.143 |
Neg logit contributions | |
utonium | -0.153 |
puter | -0.142 |
awei | -0.125 |
APH | -0.124 |
ordable | -0.121 |
Token | months |
Token ID | 1933 |
Feature activation | +6.50e-02 |
Pos logit contributions | |
utonium | +0.073 |
puter | +0.066 |
APH | +0.058 |
awei | +0.057 |
ritten | +0.056 |
Neg logit contributions | |
xual | -0.088 |
relativity | -0.086 |
blank | -0.085 |
Ples | -0.084 |
manship | -0.084 |
Token | behind |
Token ID | 2157 |
Feature activation | -4.14e-02 |
Pos logit contributions | |
utonium | +0.200 |
puter | +0.186 |
APH | +0.166 |
awei | +0.165 |
ritten | +0.162 |
Neg logit contributions | |
xual | -0.165 |
relativity | -0.159 |
blank | -0.158 |
Ples | -0.155 |
manship | -0.154 |
Token | bars |
Token ID | 9210 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
xual | +0.104 |
relativity | +0.097 |
blank | +0.097 |
manship | +0.095 |
Ples | +0.094 |
Neg logit contributions | |
utonium | -0.131 |
puter | -0.123 |
ritten | -0.108 |
awei | -0.108 |
APH | -0.108 |
Token | in |
Token ID | 287 |
Feature activation | +3.71e-02 |
Pos logit contributions | |
utonium | +0.481 |
puter | +0.450 |
APH | +0.399 |
awei | +0.399 |
ritten | +0.393 |
Neg logit contributions | |
xual | -0.368 |
relativity | -0.357 |
blank | -0.356 |
Ples | -0.348 |
Lovecraft | -0.343 |
Token | the |
Token ID | 262 |
Feature activation | +2.68e-02 |
Pos logit contributions | |
utonium | +0.110 |
puter | +0.102 |
APH | +0.089 |
awei | +0.089 |
ritten | +0.088 |
Neg logit contributions | |
xual | -0.099 |
blank | -0.094 |
relativity | -0.094 |
manship | -0.093 |
Ples | -0.091 |
Token | her |
Token ID | 607 |
Feature activation | +7.71e-02 |
Pos logit contributions | |
utonium | +0.085 |
puter | +0.078 |
awei | +0.069 |
APH | +0.069 |
ritten | +0.069 |
Neg logit contributions | |
xual | -0.067 |
blank | -0.064 |
relativity | -0.063 |
manship | -0.063 |
Ples | -0.061 |
Token | but |
Token ID | 475 |
Feature activation | -1.85e-02 |
Pos logit contributions | |
xual | +0.222 |
relativity | +0.215 |
blank | +0.212 |
manship | +0.208 |
Ples | +0.207 |
Neg logit contributions | |
utonium | -0.305 |
puter | -0.289 |
awei | -0.257 |
APH | -0.256 |
ritten | -0.251 |
Token | would |
Token ID | 561 |
Feature activation | -9.01e-03 |
Pos logit contributions | |
xual | +0.046 |
relativity | +0.045 |
blank | +0.045 |
manship | +0.044 |
Ples | +0.044 |
Neg logit contributions | |
utonium | -0.057 |
puter | -0.054 |
awei | -0.048 |
APH | -0.048 |
ordable | -0.047 |
Token | keep |
Token ID | 1394 |
Feature activation | -2.01e-02 |
Pos logit contributions | |
xual | +0.023 |
relativity | +0.023 |
blank | +0.022 |
manship | +0.022 |
Ples | +0.022 |
Neg logit contributions | |
utonium | -0.027 |
puter | -0.026 |
APH | -0.023 |
awei | -0.023 |
ritten | -0.022 |
Token | riding |
Token ID | 10311 |
Feature activation | -3.17e-03 |
Pos logit contributions | |
xual | +0.054 |
blank | +0.052 |
relativity | +0.052 |
manship | +0.051 |
Ples | +0.051 |
Neg logit contributions | |
utonium | -0.058 |
puter | -0.054 |
awei | -0.048 |
APH | -0.048 |
ritten | -0.047 |
Token | aggressively |
Token ID | 19855 |
Feature activation | +5.26e-02 |
Pos logit contributions | |
xual | +0.008 |
relativity | +0.007 |
blank | +0.007 |
Ples | +0.007 |
manship | +0.007 |
Neg logit contributions | |
utonium | -0.010 |
puter | -0.009 |
APH | -0.008 |
awei | -0.008 |
ritten | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | +1.33e-02 |
Pos logit contributions | |
utonium | +0.168 |
puter | +0.158 |
APH | +0.141 |
awei | +0.140 |
ordable | +0.137 |
Neg logit contributions | |
xual | -0.126 |
relativity | -0.123 |
blank | -0.121 |
Ples | -0.119 |
manship | -0.118 |
Token | � |
Token ID | 564 |
Feature activation | +3.39e-02 |
Pos logit contributions | |
utonium | +0.040 |
puter | +0.037 |
APH | +0.033 |
awei | +0.033 |
ritten | +0.032 |
Neg logit contributions | |
xual | -0.035 |
relativity | -0.034 |
blank | -0.034 |
manship | -0.033 |
Ples | -0.032 |
Token | � |
Token ID | 250 |
Feature activation | +3.67e-04 |
Pos logit contributions | |
utonium | +0.093 |
puter | +0.086 |
awei | +0.075 |
APH | +0.074 |
izoph | +0.073 |
Neg logit contributions | |
xual | -0.096 |
relativity | -0.096 |
blank | -0.095 |
Ples | -0.093 |
manship | -0.093 |
Token | The |
Token ID | 464 |
Feature activation | -2.46e-02 |
Pos logit contributions | |
utonium | +0.001 |
puter | +0.001 |
APH | +0.001 |
awei | +0.001 |
ritten | +0.001 |
Neg logit contributions | |
xual | -0.001 |
relativity | -0.001 |
blank | -0.001 |
manship | -0.001 |
Ples | -0.001 |
Token | legs |
Token ID | 7405 |
Feature activation | -2.29e-02 |
Pos logit contributions | |
xual | +0.061 |
blank | +0.059 |
relativity | +0.059 |
manship | +0.058 |
Ples | +0.057 |
Neg logit contributions | |
utonium | -0.077 |
puter | -0.072 |
awei | -0.064 |
APH | -0.064 |
ritten | -0.063 |
Token | are |
Token ID | 389 |
Feature activation | -4.44e-03 |
Pos logit contributions | |
xual | +0.058 |
relativity | +0.056 |
blank | +0.056 |
Ples | +0.054 |
Lovecraft | +0.053 |
Neg logit contributions | |
utonium | -0.071 |
puter | -0.067 |
APH | -0.059 |
awei | -0.059 |
ritten | -0.058 |
Token | were |
Token ID | 547 |
Feature activation | -7.04e-03 |
Pos logit contributions | |
utonium | +0.051 |
puter | +0.048 |
APH | +0.042 |
awei | +0.042 |
ritten | +0.041 |
Neg logit contributions | |
xual | -0.045 |
relativity | -0.044 |
blank | -0.044 |
Ples | -0.043 |
manship | -0.043 |
Token | left |
Token ID | 1364 |
Feature activation | -1.97e-02 |
Pos logit contributions | |
xual | +0.019 |
relativity | +0.018 |
blank | +0.018 |
manship | +0.018 |
Ples | +0.018 |
Neg logit contributions | |
utonium | -0.021 |
puter | -0.019 |
awei | -0.017 |
APH | -0.017 |
ritten | -0.017 |
Token | struggling |
Token ID | 9648 |
Feature activation | -5.03e-03 |
Pos logit contributions | |
xual | +0.050 |
relativity | +0.049 |
blank | +0.048 |
Ples | +0.047 |
manship | +0.047 |
Neg logit contributions | |
utonium | -0.061 |
puter | -0.057 |
awei | -0.050 |
APH | -0.050 |
ordable | -0.049 |
Token | to |
Token ID | 284 |
Feature activation | +8.06e-03 |
Pos logit contributions | |
xual | +0.013 |
relativity | +0.012 |
blank | +0.012 |
Ples | +0.012 |
manship | +0.012 |
Neg logit contributions | |
utonium | -0.016 |
puter | -0.015 |
APH | -0.013 |
awei | -0.013 |
ordable | -0.013 |
Token | f |
Token ID | 277 |
Feature activation | +4.64e-03 |
Pos logit contributions | |
utonium | +0.026 |
puter | +0.024 |
awei | +0.022 |
APH | +0.022 |
izoph | +0.021 |
Neg logit contributions | |
xual | -0.019 |
relativity | -0.019 |
blank | -0.019 |
manship | -0.018 |
Ples | -0.018 |
Token | athom |
Token ID | 32910 |
Feature activation | +5.23e-02 |
Pos logit contributions | |
utonium | +0.008 |
puter | +0.007 |
awei | +0.005 |
APH | +0.005 |
izoph | +0.005 |
Neg logit contributions | |
xual | -0.018 |
relativity | -0.018 |
blank | -0.018 |
manship | -0.018 |
Ples | -0.018 |
Token | the |
Token ID | 262 |
Feature activation | +2.27e-02 |
Pos logit contributions | |
utonium | +0.167 |
puter | +0.158 |
APH | +0.141 |
awei | +0.140 |
izoph | +0.138 |
Neg logit contributions | |
xual | -0.124 |
relativity | -0.121 |
blank | -0.120 |
manship | -0.117 |
Ples | -0.116 |
Token | origin |
Token ID | 8159 |
Feature activation | -3.32e-02 |
Pos logit contributions | |
utonium | +0.070 |
puter | +0.066 |
APH | +0.058 |
awei | +0.058 |
izoph | +0.057 |
Neg logit contributions | |
xual | -0.057 |
relativity | -0.056 |
blank | -0.056 |
manship | -0.055 |
Ples | -0.054 |
Token | of |
Token ID | 286 |
Feature activation | -2.55e-02 |
Pos logit contributions | |
xual | +0.070 |
relativity | +0.067 |
blank | +0.067 |
manship | +0.065 |
Lovecraft | +0.064 |
Neg logit contributions | |
utonium | -0.116 |
puter | -0.109 |
APH | -0.100 |
awei | -0.098 |
izoph | -0.097 |
Token | their |
Token ID | 511 |
Feature activation | +2.94e-02 |
Pos logit contributions | |
xual | +0.068 |
relativity | +0.067 |
blank | +0.067 |
manship | +0.065 |
Ples | +0.065 |
Neg logit contributions | |
utonium | -0.074 |
puter | -0.069 |
APH | -0.061 |
awei | -0.060 |
izoph | -0.060 |
Token | daughter |
Token ID | 4957 |
Feature activation | +8.66e-02 |
Pos logit contributions | |
utonium | +0.090 |
puter | +0.084 |
awei | +0.075 |
APH | +0.075 |
izoph | +0.073 |
Neg logit contributions | |
xual | -0.074 |
relativity | -0.073 |
blank | -0.072 |
manship | -0.071 |
Ples | -0.071 |
Token | 3 |
Token ID | 18 |
Feature activation | +5.28e-02 |
Pos logit contributions | |
utonium | +0.121 |
puter | +0.113 |
APH | +0.101 |
awei | +0.101 |
ordable | +0.099 |
Neg logit contributions | |
xual | -0.093 |
relativity | -0.092 |
blank | -0.089 |
Ples | -0.088 |
manship | -0.088 |
Token | s |
Token ID | 82 |
Feature activation | +5.55e-03 |
Pos logit contributions | |
utonium | +0.204 |
puter | +0.192 |
APH | +0.176 |
awei | +0.175 |
ordable | +0.173 |
Neg logit contributions | |
xual | -0.092 |
relativity | -0.090 |
blank | -0.088 |
manship | -0.086 |
Ples | -0.085 |
Token | )} |
Token ID | 38165 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
utonium | +0.018 |
puter | +0.016 |
APH | +0.015 |
awei | +0.015 |
ordable | +0.014 |
Neg logit contributions | |
xual | -0.014 |
relativity | -0.013 |
blank | -0.013 |
manship | -0.013 |
Ples | -0.013 |
Token | 52 |
Token ID | 6740 |
Feature activation | +3.15e-02 |
Pos logit contributions | |
xual | +0.349 |
relativity | +0.341 |
blank | +0.339 |
manship | +0.332 |
Ples | +0.329 |
Neg logit contributions | |
utonium | -0.368 |
puter | -0.343 |
APH | -0.301 |
awei | -0.300 |
ordable | -0.293 |
Token | . |
Token ID | 13 |
Feature activation | +6.02e-02 |
Pos logit contributions | |
utonium | +0.107 |
puter | +0.101 |
awei | +0.091 |
APH | +0.090 |
izoph | +0.089 |
Neg logit contributions | |
xual | -0.069 |
relativity | -0.068 |
blank | -0.067 |
manship | -0.066 |
Ples | -0.065 |
Token | Q |
Token ID | 1195 |
Feature activation | -5.14e-02 |
Pos logit contributions | |
utonium | +0.177 |
puter | +0.166 |
APH | +0.146 |
awei | +0.145 |
ordable | +0.142 |
Neg logit contributions | |
xual | -0.161 |
relativity | -0.156 |
blank | -0.155 |
manship | -0.153 |
Ples | -0.149 |
Token | xf |
Token ID | 26152 |
Feature activation | -4.38e-02 |
Pos logit contributions | |
xual | +0.117 |
relativity | +0.116 |
blank | +0.112 |
manship | +0.111 |
Ples | +0.111 |
Neg logit contributions | |
utonium | -0.170 |
puter | -0.161 |
APH | -0.144 |
awei | -0.143 |
ordable | -0.141 |
Token | 7 |
Token ID | 22 |
Feature activation | -9.47e-04 |
Pos logit contributions | |
xual | +0.097 |
relativity | +0.097 |
blank | +0.093 |
Ples | +0.092 |
manship | +0.092 |
Neg logit contributions | |
utonium | -0.148 |
puter | -0.139 |
APH | -0.125 |
awei | -0.124 |
ordable | -0.122 |
Token | + |
Token ID | 10 |
Feature activation | +1.22e-02 |
Pos logit contributions | |
xual | +0.003 |
relativity | +0.003 |
blank | +0.003 |
manship | +0.003 |
Ples | +0.002 |
Neg logit contributions | |
utonium | -0.003 |
puter | -0.002 |
APH | -0.002 |
awei | -0.002 |
ordable | -0.002 |
Token | { |
Token ID | 1391 |
Feature activation | -2.37e-02 |
Pos logit contributions | |
utonium | +0.034 |
puter | +0.031 |
APH | +0.027 |
awei | +0.027 |
ordable | +0.026 |
Neg logit contributions | |
xual | -0.035 |
relativity | -0.034 |
blank | -0.034 |
manship | -0.033 |
Ples | -0.033 |
Token | ( |
Token ID | 7 |
Feature activation | +4.25e-02 |
Pos logit contributions | |
xual | +0.048 |
relativity | +0.047 |
blank | +0.045 |
Ples | +0.045 |
manship | +0.045 |
Neg logit contributions | |
utonium | -0.085 |
puter | -0.080 |
APH | -0.073 |
awei | -0.072 |
ordable | -0.071 |
Token | Film |
Token ID | 39750 |
Feature activation | +2.72e-02 |
Pos logit contributions | |
utonium | +0.048 |
puter | +0.046 |
APH | +0.042 |
awei | +0.041 |
ritten | +0.040 |
Neg logit contributions | |
xual | -0.037 |
relativity | -0.036 |
Ples | -0.035 |
manship | -0.035 |
blank | -0.035 |
Token | ography |
Token ID | 4867 |
Feature activation | +5.07e-02 |
Pos logit contributions | |
utonium | +0.082 |
puter | +0.077 |
APH | +0.068 |
awei | +0.067 |
ritten | +0.066 |
Neg logit contributions | |
xual | -0.071 |
blank | -0.069 |
relativity | -0.068 |
manship | -0.066 |
Ples | -0.066 |
Token | [ |
Token ID | 685 |
Feature activation | -2.68e-02 |
Pos logit contributions | |
utonium | +0.156 |
puter | +0.146 |
APH | +0.131 |
awei | +0.129 |
ritten | +0.127 |
Neg logit contributions | |
xual | -0.128 |
relativity | -0.124 |
blank | -0.124 |
manship | -0.121 |
Ples | -0.120 |
Token | edit |
Token ID | 4370 |
Feature activation | +8.33e-04 |
Pos logit contributions | |
xual | +0.075 |
relativity | +0.074 |
blank | +0.073 |
manship | +0.072 |
Ples | +0.071 |
Neg logit contributions | |
utonium | -0.075 |
puter | -0.070 |
awei | -0.061 |
APH | -0.061 |
izoph | -0.060 |
Token | ] |
Token ID | 2361 |
Feature activation | -8.19e-02 |
Pos logit contributions | |
utonium | +0.003 |
puter | +0.003 |
APH | +0.003 |
awei | +0.003 |
ritten | +0.003 |
Neg logit contributions | |
xual | -0.002 |
relativity | -0.002 |
blank | -0.002 |
manship | -0.002 |
Ples | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | -4.75e-02 |
Pos logit contributions | |
xual | +0.187 |
relativity | +0.185 |
blank | +0.183 |
manship | +0.178 |
Ples | +0.178 |
Neg logit contributions | |
utonium | -0.271 |
puter | -0.254 |
awei | -0.228 |
APH | -0.227 |
izoph | -0.223 |
Token |
|
Token ID | 198 |
Feature activation | -2.27e-02 |
Pos logit contributions | |
blank | +0.102 |
xual | +0.102 |
relativity | +0.101 |
manship | +0.099 |
Ples | +0.098 |
Neg logit contributions | |
utonium | -0.163 |
puter | -0.154 |
awei | -0.139 |
APH | -0.137 |
izoph | -0.136 |
Token | Al |
Token ID | 2348 |
Feature activation | +5.37e-02 |
Pos logit contributions | |
xual | +0.058 |
relativity | +0.056 |
manship | +0.054 |
Ples | +0.054 |
blank | +0.054 |
Neg logit contributions | |
utonium | -0.070 |
puter | -0.066 |
APH | -0.060 |
awei | -0.058 |
ritten | -0.058 |
Token | bum |
Token ID | 4435 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
utonium | +0.178 |
puter | +0.168 |
awei | +0.147 |
APH | +0.146 |
ritten | +0.146 |
Neg logit contributions | |
xual | -0.126 |
relativity | -0.123 |
blank | -0.118 |
manship | -0.118 |
eering | -0.115 |
Token | [ |
Token ID | 685 |
Feature activation | -1.77e-02 |
Pos logit contributions | |
xual | +0.239 |
relativity | +0.232 |
blank | +0.231 |
Ples | +0.222 |
manship | +0.221 |
Neg logit contributions | |
utonium | -0.330 |
puter | -0.310 |
APH | -0.278 |
awei | -0.277 |
ritten | -0.273 |
Token | edit |
Token ID | 4370 |
Feature activation | -2.53e-02 |
Pos logit contributions | |
xual | +0.048 |
blank | +0.047 |
relativity | +0.047 |
manship | +0.046 |
Lovecraft | +0.045 |
Neg logit contributions | |
utonium | -0.051 |
puter | -0.048 |
awei | -0.042 |
APH | -0.041 |
izoph | -0.041 |
Token | . |
Token ID | 13 |
Feature activation | -8.62e-03 |
Pos logit contributions | |
utonium | +0.147 |
puter | +0.138 |
APH | +0.124 |
awei | +0.124 |
ordable | +0.121 |
Neg logit contributions | |
xual | -0.110 |
relativity | -0.108 |
blank | -0.106 |
Ples | -0.105 |
manship | -0.104 |
Token |
|
Token ID | 198 |
Feature activation | -1.00e-02 |
Pos logit contributions | |
xual | +0.021 |
relativity | +0.021 |
blank | +0.020 |
manship | +0.020 |
Ples | +0.020 |
Neg logit contributions | |
utonium | -0.027 |
puter | -0.025 |
APH | -0.023 |
awei | -0.023 |
ordable | -0.022 |
Token |
|
Token ID | 198 |
Feature activation | -7.17e-03 |
Pos logit contributions | |
xual | +0.022 |
relativity | +0.022 |
blank | +0.022 |
manship | +0.021 |
Ples | +0.021 |
Neg logit contributions | |
utonium | -0.034 |
puter | -0.032 |
awei | -0.029 |
APH | -0.029 |
izoph | -0.028 |
Token | It |
Token ID | 1026 |
Feature activation | -2.42e-02 |
Pos logit contributions | |
xual | +0.018 |
relativity | +0.017 |
Ples | +0.017 |
blank | +0.017 |
manship | +0.017 |
Neg logit contributions | |
utonium | -0.022 |
puter | -0.021 |
APH | -0.019 |
awei | -0.019 |
ritten | -0.018 |
Token | also |
Token ID | 635 |
Feature activation | +1.64e-02 |
Pos logit contributions | |
xual | +0.059 |
relativity | +0.058 |
blank | +0.057 |
Ples | +0.056 |
manship | +0.056 |
Neg logit contributions | |
utonium | -0.076 |
puter | -0.071 |
awei | -0.064 |
APH | -0.064 |
ritten | -0.063 |
Token | makes |
Token ID | 1838 |
Feature activation | -2.58e-02 |
Pos logit contributions | |
utonium | +0.050 |
puter | +0.046 |
awei | +0.041 |
APH | +0.041 |
ritten | +0.040 |
Neg logit contributions | |
xual | -0.042 |
blank | -0.041 |
relativity | -0.041 |
Ples | -0.040 |
manship | -0.040 |
Token | it |
Token ID | 340 |
Feature activation | +1.93e-02 |
Pos logit contributions | |
xual | +0.073 |
relativity | +0.071 |
blank | +0.071 |
manship | +0.070 |
Ples | +0.070 |
Neg logit contributions | |
utonium | -0.072 |
puter | -0.067 |
awei | -0.058 |
APH | -0.058 |
izoph | -0.057 |
Token | mandatory |
Token ID | 13677 |
Feature activation | +9.03e-02 |
Pos logit contributions | |
utonium | +0.054 |
puter | +0.051 |
awei | +0.044 |
APH | +0.044 |
ordable | +0.043 |
Neg logit contributions | |
xual | -0.054 |
relativity | -0.053 |
blank | -0.052 |
Ples | -0.051 |
manship | -0.051 |
Token | for |
Token ID | 329 |
Feature activation | -5.98e-02 |
Pos logit contributions | |
utonium | +0.275 |
puter | +0.260 |
awei | +0.230 |
APH | +0.229 |
ritten | +0.223 |
Neg logit contributions | |
xual | -0.229 |
relativity | -0.223 |
blank | -0.222 |
Ples | -0.218 |
manship | -0.217 |
Token | all |
Token ID | 477 |
Feature activation | -3.07e-02 |
Pos logit contributions | |
xual | +0.163 |
relativity | +0.160 |
blank | +0.159 |
manship | +0.156 |
Ples | +0.155 |
Neg logit contributions | |
utonium | -0.171 |
puter | -0.160 |
awei | -0.141 |
APH | -0.140 |
izoph | -0.137 |
Token | operators |
Token ID | 12879 |
Feature activation | +4.27e-02 |
Pos logit contributions | |
xual | +0.090 |
relativity | +0.088 |
blank | +0.088 |
manship | +0.086 |
Ples | +0.085 |
Neg logit contributions | |
utonium | -0.082 |
puter | -0.076 |
awei | -0.066 |
APH | -0.066 |
ordable | -0.064 |
Token | blur |
Token ID | 23671 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
utonium | +0.069 |
puter | +0.065 |
APH | +0.058 |
awei | +0.058 |
izoph | +0.057 |
Neg logit contributions | |
xual | -0.054 |
blank | -0.052 |
relativity | -0.052 |
manship | -0.051 |
Ples | -0.051 |
Token | the |
Token ID | 262 |
Feature activation | +1.52e-02 |
Pos logit contributions | |
xual | +0.269 |
relativity | +0.260 |
blank | +0.260 |
manship | +0.254 |
Ples | +0.253 |
Neg logit contributions | |
utonium | -0.298 |
puter | -0.278 |
APH | -0.248 |
awei | -0.244 |
ritten | -0.242 |
Token | boundary |
Token ID | 18645 |
Feature activation | +6.30e-02 |
Pos logit contributions | |
utonium | +0.052 |
puter | +0.049 |
APH | +0.044 |
awei | +0.044 |
ritten | +0.044 |
Neg logit contributions | |
xual | -0.033 |
blank | -0.031 |
relativity | -0.031 |
manship | -0.031 |
Ples | -0.030 |
Token | lines |
Token ID | 3951 |
Feature activation | +9.15e-03 |
Pos logit contributions | |
utonium | +0.193 |
puter | +0.181 |
APH | +0.160 |
awei | +0.160 |
ritten | +0.156 |
Neg logit contributions | |
xual | -0.159 |
relativity | -0.154 |
blank | -0.153 |
manship | -0.149 |
Lovecraft | -0.149 |
Token | between |
Token ID | 1022 |
Feature activation | -2.04e-02 |
Pos logit contributions | |
utonium | +0.028 |
puter | +0.026 |
APH | +0.023 |
awei | +0.023 |
ordable | +0.023 |
Neg logit contributions | |
xual | -0.023 |
relativity | -0.022 |
blank | -0.022 |
Ples | -0.021 |
Lovecraft | -0.021 |
Token | sovereign |
Token ID | 18901 |
Feature activation | -5.26e-04 |
Pos logit contributions | |
xual | +0.053 |
relativity | +0.052 |
blank | +0.052 |
manship | +0.051 |
Ples | +0.050 |
Neg logit contributions | |
utonium | -0.061 |
puter | -0.057 |
APH | -0.050 |
awei | -0.050 |
ritten | -0.049 |
Token | Israel |
Token ID | 2692 |
Feature activation | -5.70e-02 |
Pos logit contributions | |
xual | +0.001 |
relativity | +0.001 |
blank | +0.001 |
Ples | +0.001 |
manship | +0.001 |
Neg logit contributions | |
utonium | -0.002 |
puter | -0.001 |
APH | -0.001 |
awei | -0.001 |
ritten | -0.001 |
Token | and |
Token ID | 290 |
Feature activation | -4.29e-02 |
Pos logit contributions | |
xual | +0.143 |
relativity | +0.140 |
blank | +0.138 |
Ples | +0.135 |
manship | +0.134 |
Neg logit contributions | |
utonium | -0.176 |
puter | -0.165 |
APH | -0.147 |
awei | -0.146 |
ritten | -0.144 |
Token | the |
Token ID | 262 |
Feature activation | -2.47e-02 |
Pos logit contributions | |
xual | +0.116 |
relativity | +0.113 |
blank | +0.112 |
manship | +0.110 |
Ples | +0.109 |
Neg logit contributions | |
utonium | -0.125 |
puter | -0.116 |
APH | -0.103 |
awei | -0.102 |
ritten | -0.100 |
Token | settlements |
Token ID | 18573 |
Feature activation | -3.25e-02 |
Pos logit contributions | |
xual | +0.065 |
relativity | +0.063 |
blank | +0.062 |
manship | +0.061 |
Ples | +0.061 |
Neg logit contributions | |
utonium | -0.074 |
puter | -0.069 |
APH | -0.061 |
awei | -0.061 |
izoph | -0.059 |
Token | in |
Token ID | 287 |
Feature activation | -4.14e-02 |
Pos logit contributions | |
xual | +0.082 |
relativity | +0.079 |
blank | +0.079 |
Ples | +0.077 |
Lovecraft | +0.076 |
Neg logit contributions | |
utonium | -0.100 |
puter | -0.093 |
APH | -0.083 |
awei | -0.082 |
ordable | -0.081 |
Token | have |
Token ID | 423 |
Feature activation | +1.81e-03 |
Pos logit contributions | |
utonium | +0.147 |
puter | +0.138 |
APH | +0.123 |
awei | +0.121 |
ritten | +0.120 |
Neg logit contributions | |
xual | -0.133 |
relativity | -0.131 |
blank | -0.130 |
Ples | -0.127 |
manship | -0.126 |
Token | been |
Token ID | 587 |
Feature activation | -1.66e-02 |
Pos logit contributions | |
utonium | +0.005 |
puter | +0.004 |
awei | +0.004 |
APH | +0.004 |
ritten | +0.004 |
Neg logit contributions | |
xual | -0.005 |
relativity | -0.005 |
blank | -0.005 |
Ples | -0.005 |
manship | -0.005 |
Token | MS |
Token ID | 6579 |
Feature activation | +1.78e-02 |
Pos logit contributions | |
xual | +0.044 |
blank | +0.043 |
relativity | +0.043 |
Ples | +0.042 |
manship | +0.042 |
Neg logit contributions | |
utonium | -0.049 |
puter | -0.045 |
APH | -0.040 |
awei | -0.040 |
ritten | -0.039 |
Token | F |
Token ID | 37 |
Feature activation | +8.13e-02 |
Pos logit contributions | |
utonium | +0.050 |
puter | +0.046 |
awei | +0.041 |
izoph | +0.040 |
APH | +0.039 |
Neg logit contributions | |
xual | -0.050 |
relativity | -0.049 |
blank | -0.049 |
manship | -0.048 |
Ples | -0.048 |
Token | 's |
Token ID | 338 |
Feature activation | +3.32e-02 |
Pos logit contributions | |
utonium | +0.281 |
puter | +0.265 |
APH | +0.240 |
awei | +0.239 |
ordable | +0.234 |
Neg logit contributions | |
xual | -0.173 |
relativity | -0.168 |
blank | -0.168 |
Ples | -0.163 |
manship | -0.162 |
Token | statement |
Token ID | 2643 |
Feature activation | -1.00e-01 |
Pos logit contributions | |
utonium | +0.102 |
puter | +0.095 |
awei | +0.085 |
APH | +0.084 |
izoph | +0.083 |
Neg logit contributions | |
xual | -0.084 |
blank | -0.082 |
relativity | -0.082 |
manship | -0.080 |
Ples | -0.079 |
Token | a |
Token ID | 257 |
Feature activation | -1.20e-02 |
Pos logit contributions | |
xual | +0.255 |
relativity | +0.250 |
blank | +0.248 |
Ples | +0.243 |
manship | +0.243 |
Neg logit contributions | |
utonium | -0.302 |
puter | -0.282 |
awei | -0.251 |
APH | -0.250 |
ordable | -0.245 |
Token | month |
Token ID | 1227 |
Feature activation | -1.96e-02 |
Pos logit contributions | |
xual | +0.031 |
relativity | +0.031 |
blank | +0.030 |
manship | +0.030 |
Ples | +0.030 |
Neg logit contributions | |
utonium | -0.036 |
puter | -0.033 |
APH | -0.029 |
awei | -0.029 |
ritten | -0.029 |
Token | ago |
Token ID | 2084 |
Feature activation | -2.35e-02 |
Pos logit contributions | |
xual | +0.052 |
relativity | +0.051 |
blank | +0.050 |
manship | +0.049 |
Ples | +0.049 |
Neg logit contributions | |
utonium | -0.058 |
puter | -0.054 |
APH | -0.048 |
awei | -0.047 |
ritten | -0.046 |
Token | that |
Token ID | 326 |
Feature activation | +7.86e-04 |
Pos logit contributions | |
xual | +0.060 |
relativity | +0.059 |
blank | +0.058 |
Ples | +0.057 |
manship | +0.057 |
Neg logit contributions | |
utonium | -0.071 |
puter | -0.066 |
awei | -0.059 |
APH | -0.059 |
ordable | -0.058 |
Token | they |
Token ID | 484 |
Feature activation | +5.07e-02 |
Pos logit contributions | |
utonium | +0.002 |
puter | +0.002 |
awei | +0.002 |
APH | +0.002 |
izoph | +0.002 |
Neg logit contributions | |
xual | -0.002 |
relativity | -0.002 |
blank | -0.002 |
Ples | -0.002 |
manship | -0.002 |
Token | � |
Token ID | 251 |
Feature activation | +3.27e-02 |
Pos logit contributions | |
utonium | +0.012 |
puter | +0.011 |
awei | +0.010 |
APH | +0.010 |
izoph | +0.010 |
Neg logit contributions | |
xual | -0.016 |
relativity | -0.016 |
blank | -0.016 |
manship | -0.015 |
Ples | -0.015 |
Token |
|
Token ID | 198 |
Feature activation | -1.24e-03 |
Pos logit contributions | |
utonium | +0.103 |
puter | +0.097 |
APH | +0.087 |
awei | +0.086 |
izoph | +0.084 |
Neg logit contributions | |
xual | -0.080 |
relativity | -0.079 |
blank | -0.077 |
manship | -0.075 |
Ples | -0.074 |
Token |
|
Token ID | 198 |
Feature activation | +3.00e-03 |
Pos logit contributions | |
xual | +0.003 |
blank | +0.003 |
relativity | +0.003 |
manship | +0.003 |
Ples | +0.003 |
Neg logit contributions | |
utonium | -0.004 |
puter | -0.004 |
awei | -0.004 |
APH | -0.004 |
izoph | -0.003 |
Token | S |
Token ID | 50 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
utonium | +0.009 |
puter | +0.009 |
APH | +0.008 |
awei | +0.008 |
ritten | +0.007 |
Neg logit contributions | |
xual | -0.008 |
relativity | -0.008 |
manship | -0.007 |
Ples | -0.007 |
blank | -0.007 |
Token | pen |
Token ID | 3617 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
xual | +0.235 |
relativity | +0.233 |
blank | +0.226 |
manship | +0.223 |
Ples | +0.222 |
Neg logit contributions | |
utonium | -0.368 |
puter | -0.346 |
APH | -0.313 |
awei | -0.313 |
ritten | -0.307 |
Token | cer |
Token ID | 2189 |
Feature activation | -3.02e-01 |
Pos logit contributions | |
utonium | +0.423 |
puter | +0.389 |
APH | +0.356 |
awei | +0.352 |
ritten | +0.348 |
Neg logit contributions | |
relativity | -0.312 |
xual | -0.311 |
blank | -0.298 |
Ples | -0.297 |
manship | -0.293 |
Token | said |
Token ID | 531 |
Feature activation | +1.17e-02 |
Pos logit contributions | |
xual | +0.779 |
relativity | +0.767 |
blank | +0.757 |
manship | +0.741 |
Ples | +0.740 |
Neg logit contributions | |
utonium | -0.913 |
puter | -0.854 |
awei | -0.759 |
APH | -0.755 |
ritten | -0.737 |
Token | that |
Token ID | 326 |
Feature activation | +6.47e-02 |
Pos logit contributions | |
utonium | +0.033 |
puter | +0.031 |
awei | +0.028 |
APH | +0.027 |
ordable | +0.027 |
Neg logit contributions | |
xual | -0.032 |
relativity | -0.031 |
blank | -0.030 |
manship | -0.030 |
Ples | -0.030 |
Token | ads |
Token ID | 9011 |
Feature activation | +2.36e-02 |
Pos logit contributions | |
utonium | +0.188 |
puter | +0.178 |
awei | +0.158 |
APH | +0.157 |
ordable | +0.153 |
Neg logit contributions | |
xual | -0.171 |
relativity | -0.167 |
blank | -0.165 |
manship | -0.162 |
Ples | -0.160 |
Token | pretending |
Token ID | 23662 |
Feature activation | +1.48e-02 |
Pos logit contributions | |
utonium | +0.071 |
puter | +0.067 |
APH | +0.059 |
awei | +0.059 |
ordable | +0.057 |
Neg logit contributions | |
xual | -0.061 |
relativity | -0.060 |
blank | -0.059 |
Ples | -0.058 |
manship | -0.057 |
Token | to |
Token ID | 284 |
Feature activation | +4.91e-03 |
Pos logit contributions | |
utonium | +0.046 |
puter | +0.043 |
APH | +0.038 |
awei | +0.038 |
ordable | +0.038 |
Neg logit contributions | |
xual | -0.037 |
relativity | -0.036 |
blank | -0.036 |
Ples | -0.035 |
manship | -0.035 |
Token | tele |
Token ID | 5735 |
Feature activation | +8.00e-02 |
Pos logit contributions | |
utonium | +0.028 |
puter | +0.026 |
APH | +0.023 |
awei | +0.023 |
ritten | +0.022 |
Neg logit contributions | |
xual | -0.026 |
relativity | -0.025 |
blank | -0.025 |
manship | -0.024 |
Ples | -0.024 |
Token | metry |
Token ID | 41935 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
utonium | +0.197 |
puter | +0.184 |
awei | +0.156 |
APH | +0.156 |
ordable | +0.150 |
Neg logit contributions | |
xual | -0.254 |
relativity | -0.248 |
Ples | -0.242 |
blank | -0.242 |
manship | -0.239 |
Token | channel |
Token ID | 6518 |
Feature activation | +7.19e-02 |
Pos logit contributions | |
xual | +0.415 |
relativity | +0.396 |
blank | +0.395 |
manship | +0.389 |
Ples | +0.386 |
Neg logit contributions | |
utonium | -0.571 |
puter | -0.541 |
APH | -0.482 |
awei | -0.481 |
izoph | -0.472 |
Token | that |
Token ID | 326 |
Feature activation | +5.54e-02 |
Pos logit contributions | |
utonium | +0.230 |
puter | +0.217 |
APH | +0.193 |
awei | +0.193 |
ritten | +0.189 |
Neg logit contributions | |
xual | -0.172 |
relativity | -0.168 |
blank | -0.166 |
Ples | -0.163 |
manship | -0.162 |
Token | inexpl |
Token ID | 33199 |
Feature activation | +6.66e-02 |
Pos logit contributions | |
utonium | +0.167 |
puter | +0.157 |
awei | +0.139 |
APH | +0.138 |
izoph | +0.134 |
Neg logit contributions | |
xual | -0.144 |
relativity | -0.139 |
blank | -0.138 |
manship | -0.135 |
Ples | -0.134 |
Token | icably |
Token ID | 41685 |
Feature activation | -3.08e-01 |
Pos logit contributions | |
utonium | +0.172 |
puter | +0.158 |
awei | +0.137 |
APH | +0.136 |
ritten | +0.133 |
Neg logit contributions | |
xual | -0.202 |
relativity | -0.199 |
blank | -0.197 |
manship | -0.194 |
Ples | -0.193 |
Token | switched |
Token ID | 15293 |
Feature activation | +5.43e-02 |
Pos logit contributions | |
xual | +0.800 |
relativity | +0.778 |
blank | +0.772 |
manship | +0.756 |
Ples | +0.752 |
Neg logit contributions | |
utonium | -0.928 |
puter | -0.869 |
awei | -0.768 |
APH | -0.767 |
ritten | -0.750 |
Token | into |
Token ID | 656 |
Feature activation | -4.09e-04 |
Pos logit contributions | |
utonium | +0.164 |
puter | +0.154 |
awei | +0.136 |
APH | +0.136 |
izoph | +0.133 |
Neg logit contributions | |
xual | -0.140 |
blank | -0.135 |
relativity | -0.135 |
manship | -0.132 |
Ples | -0.131 |
Token | an |
Token ID | 281 |
Feature activation | +4.98e-03 |
Pos logit contributions | |
xual | +0.001 |
relativity | +0.001 |
blank | +0.001 |
manship | +0.001 |
Ples | +0.001 |
Neg logit contributions | |
utonium | -0.001 |
puter | -0.001 |
APH | -0.001 |
awei | -0.001 |
izoph | -0.001 |
Token | unsc |
Token ID | 28594 |
Feature activation | +5.21e-02 |
Pos logit contributions | |
utonium | +0.015 |
puter | +0.014 |
awei | +0.012 |
APH | +0.012 |
izoph | +0.012 |
Neg logit contributions | |
xual | -0.013 |
relativity | -0.013 |
blank | -0.013 |
manship | -0.013 |
Ples | -0.012 |
Token | hed |
Token ID | 704 |
Feature activation | -2.10e-02 |
Pos logit contributions | |
utonium | +0.161 |
puter | +0.151 |
awei | +0.134 |
APH | +0.134 |
ritten | +0.131 |
Neg logit contributions | |
xual | -0.130 |
relativity | -0.129 |
blank | -0.127 |
manship | -0.125 |
Ples | -0.125 |
Token | u |
Token ID | 84 |
Feature activation | -5.21e-02 |
Pos logit contributions | |
utonium | +0.165 |
puter | +0.156 |
awei | +0.141 |
APH | +0.141 |
izoph | +0.139 |
Neg logit contributions | |
xual | -0.092 |
relativity | -0.090 |
blank | -0.090 |
manship | -0.087 |
Ples | -0.086 |
Token | will |
Token ID | 481 |
Feature activation | -3.27e-02 |
Pos logit contributions | |
xual | +0.113 |
relativity | +0.109 |
blank | +0.108 |
Ples | +0.105 |
manship | +0.104 |
Neg logit contributions | |
utonium | -0.179 |
puter | -0.168 |
APH | -0.152 |
awei | -0.152 |
ordable | -0.148 |
Token | lose |
Token ID | 4425 |
Feature activation | -1.09e-02 |
Pos logit contributions | |
xual | +0.080 |
relativity | +0.078 |
blank | +0.078 |
manship | +0.076 |
Ples | +0.075 |
Neg logit contributions | |
utonium | -0.102 |
puter | -0.096 |
APH | -0.085 |
awei | -0.085 |
ritten | -0.083 |
Token | her |
Token ID | 607 |
Feature activation | -3.32e-03 |
Pos logit contributions | |
xual | +0.028 |
relativity | +0.028 |
blank | +0.027 |
manship | +0.027 |
Ples | +0.027 |
Neg logit contributions | |
utonium | -0.033 |
puter | -0.031 |
awei | -0.027 |
APH | -0.027 |
ordable | -0.027 |
Token | chair |
Token ID | 5118 |
Feature activation | -1.47e-02 |
Pos logit contributions | |
xual | +0.008 |
relativity | +0.008 |
blank | +0.008 |
Ples | +0.008 |
manship | +0.008 |
Neg logit contributions | |
utonium | -0.010 |
puter | -0.010 |
awei | -0.009 |
APH | -0.008 |
ordable | -0.008 |
Token | manship |
Token ID | 25428 |
Feature activation | -4.59e-01 |
Pos logit contributions | |
xual | +0.012 |
relativity | +0.011 |
blank | +0.010 |
Ples | +0.009 |
Lovecraft | +0.009 |
Neg logit contributions | |
utonium | -0.071 |
puter | -0.068 |
APH | -0.063 |
awei | -0.063 |
ordable | -0.063 |
Token | . |
Token ID | 13 |
Feature activation | -8.28e-02 |
Pos logit contributions | |
xual | +1.031 |
relativity | +1.013 |
blank | +1.001 |
Ples | +0.974 |
manship | +0.970 |
Neg logit contributions | |
utonium | -1.537 |
puter | -1.448 |
awei | -1.299 |
APH | -1.297 |
ordable | -1.271 |
Token | Throughout |
Token ID | 24581 |
Feature activation | -4.31e-02 |
Pos logit contributions | |
xual | +0.204 |
relativity | +0.199 |
blank | +0.196 |
manship | +0.190 |
Ples | +0.187 |
Neg logit contributions | |
utonium | -0.260 |
puter | -0.244 |
APH | -0.220 |
awei | -0.216 |
ordable | -0.213 |
Token | the |
Token ID | 262 |
Feature activation | -3.44e-02 |
Pos logit contributions | |
xual | +0.115 |
blank | +0.112 |
relativity | +0.112 |
manship | +0.108 |
Ples | +0.107 |
Neg logit contributions | |
utonium | -0.126 |
puter | -0.118 |
APH | -0.105 |
awei | -0.103 |
ordable | -0.103 |
Token | campaign |
Token ID | 1923 |
Feature activation | -2.27e-03 |
Pos logit contributions | |
xual | +0.086 |
relativity | +0.084 |
blank | +0.083 |
manship | +0.081 |
Ples | +0.081 |
Neg logit contributions | |
utonium | -0.106 |
puter | -0.099 |
APH | -0.088 |
awei | -0.088 |
ordable | -0.087 |
Token | , |
Token ID | 11 |
Feature activation | -1.73e-02 |
Pos logit contributions | |
xual | +0.005 |
relativity | +0.005 |
blank | +0.005 |
manship | +0.005 |
Ples | +0.005 |
Neg logit contributions | |
utonium | -0.007 |
puter | -0.007 |
APH | -0.006 |
awei | -0.006 |
ritten | -0.006 |
Token | un |
Token ID | 555 |
Feature activation | -8.67e-03 |
Pos logit contributions | |
xual | +0.050 |
relativity | +0.048 |
blank | +0.048 |
manship | +0.047 |
Ples | +0.047 |
Neg logit contributions | |
utonium | -0.067 |
puter | -0.063 |
awei | -0.056 |
APH | -0.056 |
ordable | -0.055 |
Token | earth |
Token ID | 16442 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
xual | +0.021 |
relativity | +0.021 |
Ples | +0.020 |
blank | +0.020 |
Lovecraft | +0.020 |
Neg logit contributions | |
utonium | -0.028 |
puter | -0.026 |
APH | -0.023 |
awei | -0.023 |
ritten | -0.023 |
Token | a |
Token ID | 257 |
Feature activation | -4.05e-02 |
Pos logit contributions | |
xual | +0.333 |
relativity | +0.324 |
blank | +0.323 |
Ples | +0.317 |
manship | +0.314 |
Neg logit contributions | |
utonium | -0.351 |
puter | -0.325 |
awei | -0.287 |
APH | -0.285 |
ordable | -0.281 |
Token | few |
Token ID | 1178 |
Feature activation | -2.94e-02 |
Pos logit contributions | |
xual | +0.099 |
relativity | +0.095 |
blank | +0.095 |
Ples | +0.093 |
manship | +0.093 |
Neg logit contributions | |
utonium | -0.129 |
puter | -0.120 |
awei | -0.107 |
APH | -0.106 |
ritten | -0.105 |
Token | barg |
Token ID | 12828 |
Feature activation | -8.33e-02 |
Pos logit contributions | |
xual | +0.077 |
relativity | +0.074 |
blank | +0.074 |
Ples | +0.073 |
manship | +0.073 |
Neg logit contributions | |
utonium | -0.088 |
puter | -0.082 |
awei | -0.073 |
APH | -0.072 |
ordable | -0.071 |
Token | ains |
Token ID | 1299 |
Feature activation | -3.01e-01 |
Pos logit contributions | |
relativity | +0.235 |
xual | +0.235 |
blank | +0.230 |
Ples | +0.229 |
manship | +0.226 |
Neg logit contributions | |
utonium | -0.234 |
puter | -0.212 |
awei | -0.190 |
ritten | -0.186 |
ordable | -0.185 |
Token | along |
Token ID | 1863 |
Feature activation | -8.37e-02 |
Pos logit contributions | |
xual | +0.732 |
relativity | +0.716 |
blank | +0.711 |
Ples | +0.697 |
manship | +0.686 |
Neg logit contributions | |
utonium | -0.954 |
puter | -0.894 |
awei | -0.798 |
APH | -0.794 |
ordable | -0.783 |
Token | the |
Token ID | 262 |
Feature activation | -6.32e-02 |
Pos logit contributions | |
xual | +0.242 |
relativity | +0.233 |
blank | +0.232 |
Ples | +0.229 |
manship | +0.227 |
Neg logit contributions | |
utonium | -0.228 |
puter | -0.212 |
APH | -0.184 |
awei | -0.182 |
ritten | -0.181 |
Token | way |
Token ID | 835 |
Feature activation | -7.61e-02 |
Pos logit contributions | |
xual | +0.158 |
relativity | +0.153 |
blank | +0.152 |
manship | +0.150 |
Ples | +0.149 |
Neg logit contributions | |
utonium | -0.196 |
puter | -0.184 |
awei | -0.164 |
APH | -0.163 |
ritten | -0.161 |
Token | . |
Token ID | 13 |
Feature activation | +1.26e-03 |
Pos logit contributions | |
xual | +0.181 |
relativity | +0.176 |
blank | +0.175 |
Ples | +0.172 |
manship | +0.170 |
Neg logit contributions | |
utonium | -0.244 |
puter | -0.229 |
awei | -0.205 |
APH | -0.204 |
ordable | -0.200 |
Token |
|
Token ID | 198 |
Feature activation | +1.51e-03 |
Pos logit contributions | |
utonium | +0.004 |
puter | +0.004 |
APH | +0.003 |
awei | +0.003 |
ordable | +0.003 |
Neg logit contributions | |
xual | -0.003 |
relativity | -0.003 |
blank | -0.003 |
manship | -0.003 |
Ples | -0.003 |
Token | 2000 |
Token ID | 4751 |
Feature activation | -7.16e-02 |
Pos logit contributions | |
xual | +0.111 |
relativity | +0.109 |
blank | +0.107 |
manship | +0.105 |
Ples | +0.105 |
Neg logit contributions | |
utonium | -0.119 |
puter | -0.111 |
awei | -0.099 |
APH | -0.099 |
izoph | -0.096 |
Token | spears |
Token ID | 46842 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
xual | +0.167 |
relativity | +0.165 |
blank | +0.160 |
Ples | +0.158 |
manship | +0.157 |
Neg logit contributions | |
utonium | -0.233 |
puter | -0.218 |
awei | -0.197 |
APH | -0.196 |
izoph | -0.192 |
Token | , |
Token ID | 11 |
Feature activation | -2.47e-02 |
Pos logit contributions | |
xual | +0.247 |
relativity | +0.242 |
blank | +0.237 |
Ples | +0.233 |
manship | +0.229 |
Neg logit contributions | |
utonium | -0.350 |
puter | -0.329 |
APH | -0.296 |
awei | -0.295 |
ritten | -0.287 |
Token | 300 |
Token ID | 5867 |
Feature activation | -4.33e-03 |
Pos logit contributions | |
xual | +0.074 |
relativity | +0.073 |
blank | +0.072 |
manship | +0.071 |
Ples | +0.070 |
Neg logit contributions | |
utonium | -0.064 |
puter | -0.060 |
awei | -0.052 |
APH | -0.052 |
izoph | -0.050 |
Token | arm |
Token ID | 3211 |
Feature activation | -5.65e-02 |
Pos logit contributions | |
xual | +0.010 |
relativity | +0.010 |
blank | +0.010 |
Ples | +0.010 |
manship | +0.010 |
Neg logit contributions | |
utonium | -0.014 |
puter | -0.013 |
awei | -0.012 |
APH | -0.012 |
izoph | -0.012 |
Token | ours |
Token ID | 4662 |
Feature activation | -3.29e-01 |
Pos logit contributions | |
xual | +0.127 |
relativity | +0.124 |
blank | +0.119 |
Ples | +0.117 |
Lovecraft | +0.116 |
Neg logit contributions | |
utonium | -0.191 |
puter | -0.182 |
awei | -0.165 |
APH | -0.163 |
ordable | -0.158 |
Token | and |
Token ID | 290 |
Feature activation | -2.29e-02 |
Pos logit contributions | |
xual | +0.755 |
relativity | +0.744 |
blank | +0.730 |
Ples | +0.715 |
manship | +0.707 |
Neg logit contributions | |
utonium | -1.081 |
puter | -1.018 |
awei | -0.917 |
APH | -0.917 |
ritten | -0.888 |
Token | 500 |
Token ID | 5323 |
Feature activation | -6.90e-02 |
Pos logit contributions | |
xual | +0.067 |
relativity | +0.066 |
blank | +0.066 |
manship | +0.064 |
Ples | +0.064 |
Neg logit contributions | |
utonium | -0.060 |
puter | -0.056 |
awei | -0.049 |
APH | -0.049 |
izoph | -0.047 |
Token | shields |
Token ID | 21132 |
Feature activation | +2.71e-03 |
Pos logit contributions | |
xual | +0.163 |
relativity | +0.160 |
blank | +0.156 |
Ples | +0.153 |
manship | +0.153 |
Neg logit contributions | |
utonium | -0.223 |
puter | -0.208 |
awei | -0.189 |
APH | -0.187 |
izoph | -0.184 |
Token | , |
Token ID | 11 |
Feature activation | +9.94e-03 |
Pos logit contributions | |
utonium | +0.009 |
puter | +0.008 |
awei | +0.007 |
APH | +0.007 |
ordable | +0.007 |
Neg logit contributions | |
xual | -0.007 |
relativity | -0.007 |
blank | -0.006 |
Ples | -0.006 |
manship | -0.006 |
Token | were |
Token ID | 547 |
Feature activation | -4.25e-02 |
Pos logit contributions | |
utonium | +0.030 |
puter | +0.028 |
awei | +0.025 |
APH | +0.025 |
ordable | +0.024 |
Neg logit contributions | |
xual | -0.026 |
relativity | -0.025 |
blank | -0.025 |
manship | -0.024 |
Ples | -0.024 |