Token | very |
Token ID | 845 |
Feature activation | -5.94e-01 |
Pos logit contributions | |
strangers | +0.217 |
tresp | +0.191 |
vern | +0.185 |
unts | +0.174 |
cruel | +0.173 |
Neg logit contributions | |
Of | -0.197 |
cy | -0.196 |
girl | -0.186 |
sc | -0.183 |
Sure | -0.177 |
Token | brave |
Token ID | 14802 |
Feature activation | -3.75e+00 |
Pos logit contributions | |
strangers | +0.030 |
tresp | +0.026 |
vern | +0.024 |
supposed | +0.022 |
cruel | +0.022 |
Neg logit contributions | |
Of | -0.037 |
cy | -0.037 |
girl | -0.035 |
sc | -0.035 |
Sure | -0.034 |
Token | and |
Token ID | 290 |
Feature activation | -2.53e+00 |
Pos logit contributions | |
strangers | +0.231 |
tresp | +0.206 |
vern | +0.194 |
cruel | +0.187 |
supposed | +0.185 |
Neg logit contributions | |
Of | -0.194 |
cy | -0.193 |
sc | -0.181 |
Sure | -0.177 |
girl | -0.175 |
Token | smart |
Token ID | 4451 |
Feature activation | -2.88e+00 |
Pos logit contributions | |
strangers | +0.110 |
tresp | +0.095 |
vern | +0.088 |
cruel | +0.088 |
supposed | +0.083 |
Neg logit contributions | |
cy | -0.176 |
Of | -0.173 |
sc | -0.167 |
girl | -0.163 |
Sure | -0.162 |
Token | . |
Token ID | 13 |
Feature activation | -1.21e-02 |
Pos logit contributions | |
strangers | +0.187 |
tresp | +0.168 |
vern | +0.160 |
cruel | +0.153 |
supposed | +0.153 |
Neg logit contributions | |
Of | -0.139 |
cy | -0.138 |
sc | -0.128 |
Sure | -0.126 |
girl | -0.125 |
Token | Of |
Token ID | 3226 |
Feature activation | +1.49e+01 |
Pos logit contributions | |
strangers | +0.001 |
tresp | +0.001 |
isdom | +0.001 |
vern | +0.001 |
unts | +0.001 |
Neg logit contributions | |
cy | -0.001 |
mixture | -0.000 |
sc | -0.000 |
girl | -0.000 |
tin | -0.000 |
Token | course |
Token ID | 1781 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
cy | +0.768 |
Of | +0.767 |
girl | +0.759 |
sc | +0.688 |
tin | +0.678 |
Neg logit contributions | |
strangers | -0.848 |
tresp | -0.752 |
vern | -0.747 |
supposed | -0.735 |
cod | -0.712 |
Token | you |
Token ID | 345 |
Feature activation | +5.73e-01 |
Pos logit contributions | |
strangers | +0.091 |
tresp | +0.081 |
vern | +0.076 |
cruel | +0.074 |
supposed | +0.072 |
Neg logit contributions | |
cy | -0.073 |
Of | -0.073 |
sc | -0.070 |
Sure | -0.067 |
girl | -0.066 |
Token | can |
Token ID | 460 |
Feature activation | -4.46e+00 |
Pos logit contributions | |
cy | +0.028 |
girl | +0.027 |
Of | +0.025 |
sc | +0.025 |
tin | +0.025 |
Neg logit contributions | |
strangers | -0.038 |
tresp | -0.032 |
vern | -0.032 |
Days | -0.031 |
eping | -0.030 |
Token | have |
Token ID | 423 |
Feature activation | -3.06e+00 |
Pos logit contributions | |
strangers | +0.273 |
tresp | +0.247 |
cruel | +0.229 |
vern | +0.227 |
cod | +0.222 |
Neg logit contributions | |
cy | -0.233 |
Of | -0.230 |
girl | -0.214 |
tin | -0.209 |
sc | -0.207 |
Token | your |
Token ID | 534 |
Feature activation | +6.88e-01 |
Pos logit contributions | |
strangers | +0.214 |
tresp | +0.196 |
vern | +0.188 |
cruel | +0.180 |
supposed | +0.179 |
Neg logit contributions | |
Of | -0.131 |
cy | -0.130 |
sc | -0.120 |
girl | -0.120 |
Sure | -0.116 |
Token | tomorrow |
Token ID | 9439 |
Feature activation | -5.81e-02 |
Pos logit contributions | |
strangers | +0.067 |
tresp | +0.059 |
vern | +0.057 |
supposed | +0.054 |
cruel | +0.053 |
Neg logit contributions | |
Of | -0.055 |
cy | -0.053 |
sc | -0.052 |
girl | -0.051 |
Sure | -0.049 |
Token | and |
Token ID | 290 |
Feature activation | -2.28e+00 |
Pos logit contributions | |
strangers | +0.004 |
tresp | +0.003 |
vern | +0.003 |
supposed | +0.003 |
cruel | +0.003 |
Neg logit contributions | |
Of | -0.003 |
cy | -0.003 |
sc | -0.003 |
girl | -0.003 |
Sure | -0.003 |
Token | play |
Token ID | 711 |
Feature activation | -6.94e-01 |
Pos logit contributions | |
strangers | +0.127 |
tresp | +0.110 |
cruel | +0.100 |
vern | +0.099 |
never | +0.097 |
Neg logit contributions | |
cy | -0.130 |
Of | -0.130 |
sc | -0.126 |
Sure | -0.120 |
girl | -0.119 |
Token | again |
Token ID | 757 |
Feature activation | +4.83e+00 |
Pos logit contributions | |
strangers | +0.052 |
tresp | +0.048 |
vern | +0.046 |
enemies | +0.044 |
cruel | +0.044 |
Neg logit contributions | |
Of | -0.026 |
cy | -0.025 |
Sure | -0.023 |
girl | -0.022 |
sc | -0.021 |
Token | . |
Token ID | 13 |
Feature activation | +3.58e-01 |
Pos logit contributions | |
Of | +0.237 |
cy | +0.233 |
sc | +0.221 |
girl | +0.216 |
Sure | +0.213 |
Neg logit contributions | |
strangers | -0.311 |
tresp | -0.276 |
vern | -0.264 |
cruel | -0.253 |
supposed | -0.252 |
Token | Of |
Token ID | 3226 |
Feature activation | +1.47e+01 |
Pos logit contributions | |
cy | +0.019 |
sc | +0.019 |
tin | +0.018 |
girl | +0.018 |
mixture | +0.018 |
Neg logit contributions | |
strangers | -0.020 |
tresp | -0.017 |
unts | -0.016 |
vern | -0.016 |
isdom | -0.016 |
Token | course |
Token ID | 1781 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
cy | +0.782 |
Of | +0.771 |
girl | +0.766 |
sc | +0.701 |
Sure | +0.675 |
Neg logit contributions | |
strangers | -0.841 |
vern | -0.768 |
tresp | -0.760 |
supposed | -0.739 |
unts | -0.696 |
Token | , |
Token ID | 11 |
Feature activation | +8.50e-01 |
Pos logit contributions | |
strangers | +0.096 |
tresp | +0.085 |
vern | +0.080 |
cruel | +0.078 |
supposed | +0.076 |
Neg logit contributions | |
Of | -0.081 |
cy | -0.080 |
sc | -0.077 |
girl | -0.074 |
Sure | -0.074 |
Token | she |
Token ID | 673 |
Feature activation | +1.95e+00 |
Pos logit contributions | |
cy | +0.047 |
sc | +0.046 |
Of | +0.046 |
Sure | +0.043 |
suit | +0.042 |
Neg logit contributions | |
strangers | -0.049 |
tresp | -0.042 |
never | -0.039 |
cruel | -0.038 |
vern | -0.038 |
Token | did |
Token ID | 750 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
cy | +0.102 |
Of | +0.097 |
girl | +0.096 |
sc | +0.094 |
onto | +0.089 |
Neg logit contributions | |
strangers | -0.121 |
tresp | -0.107 |
vern | -0.105 |
cruel | -0.099 |
cod | -0.098 |
Token | and |
Token ID | 290 |
Feature activation | -2.22e+00 |
Pos logit contributions | |
strangers | +0.127 |
tresp | +0.115 |
vern | +0.110 |
cruel | +0.108 |
unts | +0.107 |
Neg logit contributions | |
Of | -0.082 |
cy | -0.078 |
girl | -0.074 |
sc | -0.073 |
Sure | -0.071 |
Token | an |
Token ID | 281 |
Feature activation | -8.29e-01 |
Pos logit contributions | |
Of | +0.164 |
cy | +0.163 |
sc | +0.152 |
girl | +0.151 |
Sure | +0.147 |
Neg logit contributions | |
strangers | -0.252 |
tresp | -0.228 |
vern | -0.221 |
cruel | -0.211 |
supposed | -0.209 |
Token | ugly |
Token ID | 13400 |
Feature activation | -3.30e+00 |
Pos logit contributions | |
strangers | +0.046 |
vern | +0.042 |
tresp | +0.041 |
unts | +0.039 |
cruel | +0.037 |
Neg logit contributions | |
girl | -0.045 |
Of | -0.044 |
cy | -0.043 |
up | -0.041 |
tin | -0.040 |
Token | little |
Token ID | 1310 |
Feature activation | +8.62e-01 |
Pos logit contributions | |
strangers | +0.209 |
tresp | +0.188 |
vern | +0.178 |
cruel | +0.172 |
supposed | +0.169 |
Neg logit contributions | |
Of | -0.164 |
cy | -0.163 |
sc | -0.154 |
girl | -0.149 |
Sure | -0.148 |
Token | mouse |
Token ID | 10211 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
Of | +0.043 |
cy | +0.040 |
sc | +0.040 |
Sure | +0.039 |
onto | +0.035 |
Neg logit contributions | |
strangers | -0.056 |
tresp | -0.050 |
cruel | -0.046 |
mean | -0.045 |
liar | -0.044 |
Token | . |
Token ID | 13 |
Feature activation | +2.40e-01 |
Pos logit contributions | |
cy | +0.062 |
Of | +0.060 |
girl | +0.059 |
sc | +0.058 |
onto | +0.055 |
Neg logit contributions | |
strangers | -0.087 |
vern | -0.081 |
tresp | -0.079 |
cruel | -0.074 |
unts | -0.073 |
Token | Of |
Token ID | 3226 |
Feature activation | +1.46e+01 |
Pos logit contributions | |
cy | +0.011 |
Of | +0.010 |
sc | +0.010 |
girl | +0.010 |
Sure | +0.009 |
Neg logit contributions | |
strangers | -0.016 |
tresp | -0.014 |
vern | -0.014 |
unts | -0.013 |
cruel | -0.013 |
Token | course |
Token ID | 1781 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
Of | +0.847 |
cy | +0.842 |
girl | +0.806 |
sc | +0.776 |
Sure | +0.762 |
Neg logit contributions | |
strangers | -0.803 |
tresp | -0.712 |
vern | -0.694 |
supposed | -0.656 |
unts | -0.642 |
Token | , |
Token ID | 11 |
Feature activation | +5.89e-01 |
Pos logit contributions | |
strangers | +0.105 |
tresp | +0.095 |
vern | +0.088 |
cruel | +0.086 |
supposed | +0.084 |
Neg logit contributions | |
cy | -0.086 |
Of | -0.086 |
sc | -0.082 |
girl | -0.078 |
Sure | -0.078 |
Token | Joy |
Token ID | 14087 |
Feature activation | +5.00e+00 |
Pos logit contributions | |
cy | +0.031 |
Of | +0.030 |
sc | +0.030 |
Sure | +0.027 |
girl | +0.027 |
Neg logit contributions | |
strangers | -0.036 |
tresp | -0.032 |
vern | -0.029 |
cruel | -0.029 |
never | -0.028 |
Token | couldn |
Token ID | 3521 |
Feature activation | -5.93e+00 |
Pos logit contributions | |
cy | +0.242 |
girl | +0.228 |
Of | +0.226 |
sc | +0.220 |
onto | +0.208 |
Neg logit contributions | |
strangers | -0.326 |
tresp | -0.293 |
vern | -0.292 |
supposed | -0.270 |
cruel | -0.270 |
Token | 't |
Token ID | 470 |
Feature activation | -2.98e+00 |
Pos logit contributions | |
strangers | +0.329 |
tresp | +0.288 |
vern | +0.273 |
cruel | +0.263 |
unts | +0.259 |
Neg logit contributions | |
Of | -0.343 |
cy | -0.338 |
sc | -0.325 |
girl | -0.315 |
Sure | -0.314 |
Token | to |
Token ID | 284 |
Feature activation | -7.32e-01 |
Pos logit contributions | |
strangers | +0.273 |
vern | +0.248 |
tresp | +0.247 |
unts | +0.226 |
cruel | +0.225 |
Neg logit contributions | |
Of | -0.244 |
cy | -0.243 |
girl | -0.230 |
sc | -0.224 |
Sure | -0.219 |
Token | run |
Token ID | 1057 |
Feature activation | -4.48e+00 |
Pos logit contributions | |
vern | +0.042 |
strangers | +0.041 |
tresp | +0.040 |
unts | +0.037 |
cruel | +0.037 |
Neg logit contributions | |
cy | -0.035 |
Of | -0.035 |
girl | -0.034 |
down | -0.033 |
up | -0.032 |
Token | too |
Token ID | 1165 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
strangers | +0.348 |
tresp | +0.327 |
vern | +0.324 |
isdom | +0.310 |
unts | +0.307 |
Neg logit contributions | |
cy | -0.147 |
sc | -0.142 |
Of | -0.141 |
girl | -0.132 |
down | -0.131 |
Token | fast |
Token ID | 3049 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
down | +0.009 |
cy | +0.009 |
onto | +0.008 |
up | +0.008 |
sc | +0.008 |
Neg logit contributions | |
strangers | -0.009 |
tresp | -0.009 |
isdom | -0.009 |
cod | -0.009 |
vern | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | +2.66e-01 |
Pos logit contributions | |
strangers | +0.095 |
tresp | +0.088 |
vern | +0.086 |
cruel | +0.082 |
unts | +0.081 |
Neg logit contributions | |
Of | -0.056 |
cy | -0.056 |
sc | -0.053 |
girl | -0.052 |
down | -0.050 |
Token | Of |
Token ID | 3226 |
Feature activation | +1.45e+01 |
Pos logit contributions | |
cy | +0.012 |
sc | +0.012 |
Of | +0.011 |
girl | +0.011 |
tin | +0.010 |
Neg logit contributions | |
strangers | -0.018 |
tresp | -0.016 |
vern | -0.015 |
hated | -0.015 |
unts | -0.015 |
Token | course |
Token ID | 1781 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
girl | +0.659 |
Of | +0.658 |
cy | +0.626 |
sc | +0.549 |
cash | +0.547 |
Neg logit contributions | |
strangers | -0.878 |
vern | -0.855 |
supposed | -0.824 |
tresp | -0.812 |
unts | -0.796 |
Token | , |
Token ID | 11 |
Feature activation | +7.04e-01 |
Pos logit contributions | |
strangers | +0.109 |
tresp | +0.097 |
vern | +0.091 |
cruel | +0.088 |
supposed | +0.087 |
Neg logit contributions | |
cy | -0.090 |
Of | -0.089 |
sc | -0.085 |
girl | -0.082 |
Sure | -0.081 |
Token | Tommy |
Token ID | 19919 |
Feature activation | -2.48e+00 |
Pos logit contributions | |
cy | +0.039 |
sc | +0.038 |
Of | +0.037 |
girl | +0.035 |
Sure | +0.035 |
Neg logit contributions | |
strangers | -0.042 |
tresp | -0.036 |
vern | -0.033 |
hated | -0.032 |
never | -0.032 |
Token | was |
Token ID | 373 |
Feature activation | +3.00e+00 |
Pos logit contributions | |
strangers | +0.161 |
tresp | +0.144 |
vern | +0.143 |
cod | +0.134 |
cruel | +0.132 |
Neg logit contributions | |
cy | -0.122 |
girl | -0.116 |
Of | -0.113 |
down | -0.110 |
up | -0.109 |
Token | still |
Token ID | 991 |
Feature activation | -2.42e+00 |
Pos logit contributions | |
up | +0.165 |
Of | +0.164 |
down | +0.162 |
girl | +0.160 |
cy | +0.160 |
Neg logit contributions | |
strangers | -0.167 |
tresp | -0.147 |
vern | -0.139 |
unts | -0.135 |
cod | -0.135 |
Token | to |
Token ID | 284 |
Feature activation | -8.91e-01 |
Pos logit contributions | |
strangers | +0.186 |
tresp | +0.169 |
vern | +0.162 |
cruel | +0.155 |
supposed | +0.154 |
Neg logit contributions | |
Of | -0.127 |
cy | -0.126 |
sc | -0.118 |
girl | -0.117 |
Sure | -0.114 |
Token | go |
Token ID | 467 |
Feature activation | -2.55e+00 |
Pos logit contributions | |
strangers | +0.058 |
tresp | +0.053 |
vern | +0.049 |
cod | +0.049 |
cruel | +0.049 |
Neg logit contributions | |
Of | -0.043 |
cy | -0.042 |
girl | -0.039 |
sc | -0.038 |
onto | -0.038 |
Token | golf |
Token ID | 13126 |
Feature activation | -3.15e+00 |
Pos logit contributions | |
strangers | +0.170 |
tresp | +0.152 |
vern | +0.146 |
supposed | +0.141 |
cruel | +0.138 |
Neg logit contributions | |
Of | -0.118 |
cy | -0.116 |
sc | -0.109 |
girl | -0.108 |
Sure | -0.107 |
Token | ing |
Token ID | 278 |
Feature activation | +4.31e+00 |
Pos logit contributions | |
strangers | +0.212 |
tresp | +0.190 |
vern | +0.187 |
enemies | +0.174 |
cruel | +0.172 |
Neg logit contributions | |
Of | -0.140 |
cy | -0.135 |
Sure | -0.132 |
girl | -0.125 |
Me | -0.122 |
Token | . |
Token ID | 13 |
Feature activation | +4.69e-02 |
Pos logit contributions | |
Of | +0.215 |
cy | +0.211 |
Sure | +0.202 |
girl | +0.195 |
sc | +0.194 |
Neg logit contributions | |
strangers | -0.276 |
tresp | -0.241 |
vern | -0.225 |
cruel | -0.218 |
unts | -0.216 |
Token | Of |
Token ID | 3226 |
Feature activation | +1.44e+01 |
Pos logit contributions | |
cy | +0.003 |
sc | +0.003 |
tin | +0.002 |
fl | +0.002 |
cer | +0.002 |
Neg logit contributions | |
strangers | -0.002 |
hated | -0.002 |
shouldn | -0.002 |
lee | -0.002 |
tresp | -0.002 |
Token | course |
Token ID | 1781 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
cy | +0.848 |
Of | +0.848 |
girl | +0.808 |
sc | +0.783 |
Sure | +0.761 |
Neg logit contributions | |
strangers | -0.775 |
tresp | -0.694 |
vern | -0.671 |
supposed | -0.632 |
unts | -0.619 |
Token | she |
Token ID | 673 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
strangers | +0.108 |
tresp | +0.093 |
vern | +0.086 |
cruel | +0.085 |
hated | +0.084 |
Neg logit contributions | |
cy | -0.094 |
sc | -0.094 |
Of | -0.094 |
Sure | -0.089 |
tin | -0.087 |
Token | said |
Token ID | 531 |
Feature activation | +3.96e+00 |
Pos logit contributions | |
cy | +0.077 |
Of | +0.076 |
girl | +0.071 |
sc | +0.071 |
Sure | +0.068 |
Neg logit contributions | |
strangers | -0.108 |
tresp | -0.097 |
vern | -0.093 |
cruel | -0.089 |
supposed | -0.088 |
Token | yes |
Token ID | 3763 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
Of | +0.212 |
cy | +0.206 |
sc | +0.196 |
girl | +0.196 |
Sure | +0.191 |
Neg logit contributions | |
strangers | -0.236 |
tresp | -0.211 |
vern | -0.200 |
supposed | -0.192 |
unts | -0.191 |
Token | , |
Token ID | 11 |
Feature activation | +5.92e-01 |
Pos logit contributions | |
Of | +0.007 |
cy | +0.007 |
sc | +0.007 |
girl | +0.007 |
Sure | +0.006 |
Neg logit contributions | |
strangers | -0.010 |
tresp | -0.009 |
vern | -0.008 |
cruel | -0.008 |
supposed | -0.008 |
Token | folded |
Token ID | 24650 |
Feature activation | +4.21e+00 |
Pos logit contributions | |
strangers | +0.110 |
never | +0.097 |
tresp | +0.097 |
eping | +0.096 |
hated | +0.093 |
Neg logit contributions | |
Of | -0.167 |
umm | -0.158 |
cy | -0.157 |
Me | -0.145 |
Sure | -0.144 |
Token | it |
Token ID | 340 |
Feature activation | -3.72e-01 |
Pos logit contributions | |
cy | +0.300 |
Of | +0.288 |
girl | +0.278 |
Sure | +0.277 |
umm | +0.274 |
Neg logit contributions | |
strangers | -0.155 |
eping | -0.133 |
eps | -0.124 |
ills | -0.119 |
vern | -0.116 |
Token | in |
Token ID | 287 |
Feature activation | +2.72e+00 |
Pos logit contributions | |
strangers | +0.020 |
never | +0.020 |
often | +0.019 |
supposed | +0.019 |
Days | +0.018 |
Neg logit contributions | |
cy | -0.020 |
Of | -0.019 |
girl | -0.019 |
therapist | -0.017 |
Sure | -0.017 |
Token | two |
Token ID | 734 |
Feature activation | +5.57e+00 |
Pos logit contributions | |
Of | +0.153 |
cy | +0.153 |
sc | +0.145 |
Sure | +0.139 |
girl | +0.135 |
Neg logit contributions | |
strangers | -0.152 |
tresp | -0.137 |
vern | -0.130 |
unts | -0.127 |
supposed | -0.124 |
Token | . |
Token ID | 13 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
Of | +0.222 |
cy | +0.222 |
sc | +0.205 |
girl | +0.203 |
Sure | +0.195 |
Neg logit contributions | |
strangers | -0.406 |
tresp | -0.371 |
vern | -0.357 |
cruel | -0.344 |
supposed | -0.342 |
Token | Of |
Token ID | 3226 |
Feature activation | +1.44e+01 |
Pos logit contributions | |
cy | +0.009 |
girl | +0.008 |
sc | +0.007 |
cer | +0.007 |
Of | +0.007 |
Neg logit contributions | |
strangers | -0.008 |
tresp | -0.007 |
unts | -0.007 |
isdom | -0.007 |
hated | -0.007 |
Token | course |
Token ID | 1781 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
cy | +0.764 |
Of | +0.759 |
girl | +0.752 |
sc | +0.692 |
Sure | +0.664 |
Neg logit contributions | |
strangers | -0.821 |
vern | -0.743 |
tresp | -0.735 |
supposed | -0.707 |
unts | -0.674 |
Token | , |
Token ID | 11 |
Feature activation | +6.95e-01 |
Pos logit contributions | |
strangers | +0.109 |
tresp | +0.098 |
vern | +0.092 |
cruel | +0.089 |
supposed | +0.087 |
Neg logit contributions | |
Of | -0.093 |
cy | -0.093 |
sc | -0.089 |
girl | -0.086 |
Sure | -0.084 |
Token | it |
Token ID | 340 |
Feature activation | -3.15e-01 |
Pos logit contributions | |
cy | +0.037 |
sc | +0.036 |
Of | +0.035 |
Sure | +0.032 |
suit | +0.032 |
Neg logit contributions | |
strangers | -0.043 |
tresp | -0.038 |
never | -0.034 |
cruel | -0.034 |
enemies | -0.033 |
Token | didn |
Token ID | 1422 |
Feature activation | -5.63e+00 |
Pos logit contributions | |
strangers | +0.019 |
tresp | +0.017 |
vern | +0.016 |
supposed | +0.016 |
hated | +0.015 |
Neg logit contributions | |
Of | -0.017 |
cy | -0.016 |
Sure | -0.015 |
sc | -0.015 |
girl | -0.015 |
Token | 't |
Token ID | 470 |
Feature activation | -3.06e+00 |
Pos logit contributions | |
strangers | +0.301 |
tresp | +0.263 |
vern | +0.245 |
cruel | +0.240 |
cod | +0.234 |
Neg logit contributions | |
Of | -0.337 |
cy | -0.326 |
sc | -0.321 |
Sure | -0.308 |
girl | -0.307 |
Token | moment |
Token ID | 2589 |
Feature activation | +1.00e+01 |
Pos logit contributions | |
cy | +0.036 |
Of | +0.034 |
sc | +0.027 |
onto | +0.025 |
Sure | +0.024 |
Neg logit contributions | |
strangers | -0.154 |
tresp | -0.145 |
vern | -0.140 |
cruel | -0.137 |
supposed | -0.134 |
Token | . |
Token ID | 13 |
Feature activation | +3.80e-01 |
Pos logit contributions | |
Of | +0.508 |
cy | +0.506 |
sc | +0.474 |
girl | +0.470 |
Sure | +0.459 |
Neg logit contributions | |
strangers | -0.627 |
tresp | -0.563 |
vern | -0.538 |
cruel | -0.513 |
supposed | -0.509 |
Token | " |
Token ID | 366 |
Feature activation | -2.67e+00 |
Pos logit contributions | |
cy | +0.022 |
sc | +0.020 |
mixture | +0.020 |
tin | +0.019 |
Of | +0.019 |
Neg logit contributions | |
strangers | -0.018 |
shouldn | -0.016 |
tresp | -0.016 |
unts | -0.016 |
never | -0.016 |
Token | Yes |
Token ID | 5297 |
Feature activation | +1.14e+01 |
Pos logit contributions | |
strangers | +0.161 |
Days | +0.152 |
never | +0.149 |
understand | +0.146 |
respected | +0.144 |
Neg logit contributions | |
up | -0.114 |
cy | -0.114 |
onto | -0.112 |
down | -0.111 |
mixture | -0.109 |
Token | ! |
Token ID | 0 |
Feature activation | -7.96e-01 |
Pos logit contributions | |
Of | +0.542 |
cy | +0.535 |
girl | +0.505 |
sc | +0.497 |
Sure | +0.484 |
Neg logit contributions | |
strangers | -0.745 |
tresp | -0.675 |
vern | -0.647 |
supposed | -0.625 |
cruel | -0.620 |
Token | Of |
Token ID | 3226 |
Feature activation | +1.44e+01 |
Pos logit contributions | |
strangers | +0.048 |
tresp | +0.043 |
isdom | +0.043 |
shouldn | +0.042 |
vern | +0.041 |
Neg logit contributions | |
cy | -0.036 |
sc | -0.034 |
tin | -0.034 |
mixture | -0.034 |
girl | -0.032 |
Token | course |
Token ID | 1781 |
Feature activation | -1.83e+00 |
Pos logit contributions | |
Of | +0.728 |
cy | +0.710 |
girl | +0.701 |
sc | +0.662 |
onto | +0.642 |
Neg logit contributions | |
strangers | -0.848 |
tresp | -0.726 |
vern | -0.724 |
supposed | -0.709 |
hated | -0.708 |
Token | ," |
Token ID | 553 |
Feature activation | -3.08e-01 |
Pos logit contributions | |
strangers | +0.113 |
tresp | +0.102 |
vern | +0.096 |
cruel | +0.092 |
supposed | +0.090 |
Neg logit contributions | |
cy | -0.094 |
Of | -0.093 |
sc | -0.089 |
Sure | -0.085 |
girl | -0.085 |
Token | he |
Token ID | 339 |
Feature activation | +1.86e+00 |
Pos logit contributions | |
strangers | +0.016 |
tresp | +0.014 |
cruel | +0.013 |
understand | +0.013 |
shouldn | +0.013 |
Neg logit contributions | |
cy | -0.017 |
Of | -0.016 |
umm | -0.016 |
sc | -0.016 |
suit | -0.016 |
Token | said |
Token ID | 531 |
Feature activation | +4.14e+00 |
Pos logit contributions | |
cy | +0.106 |
Of | +0.100 |
Sure | +0.093 |
sc | +0.093 |
mixture | +0.091 |
Neg logit contributions | |
strangers | -0.102 |
tresp | -0.094 |
cruel | -0.088 |
vern | -0.088 |
never | -0.086 |
Token | . |
Token ID | 13 |
Feature activation | +4.07e-01 |
Pos logit contributions | |
cy | +0.251 |
Of | +0.228 |
sc | +0.225 |
girl | +0.214 |
Sure | +0.212 |
Neg logit contributions | |
strangers | -0.215 |
vern | -0.197 |
tresp | -0.191 |
understand | -0.189 |
never | -0.181 |
Token | a |
Token ID | 257 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
strangers | +0.232 |
vern | +0.203 |
tresp | +0.200 |
unts | +0.193 |
isdom | +0.189 |
Neg logit contributions | |
Of | -0.222 |
girl | -0.219 |
cy | -0.216 |
up | -0.212 |
down | -0.206 |
Token | good |
Token ID | 922 |
Feature activation | +2.37e+00 |
Pos logit contributions | |
girl | +0.076 |
cy | +0.075 |
Of | +0.074 |
sc | +0.070 |
Sure | +0.068 |
Neg logit contributions | |
strangers | -0.073 |
tresp | -0.063 |
vern | -0.061 |
isdom | -0.059 |
supposed | -0.058 |
Token | brother |
Token ID | 3956 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
Of | +0.132 |
sc | +0.128 |
cy | +0.127 |
Sure | +0.121 |
onto | +0.119 |
Neg logit contributions | |
strangers | -0.137 |
tresp | -0.121 |
unts | -0.115 |
enemies | -0.112 |
cruel | -0.111 |
Token | too |
Token ID | 1165 |
Feature activation | -1.72e-01 |
Pos logit contributions | |
strangers | +0.109 |
tresp | +0.100 |
vern | +0.097 |
supposed | +0.092 |
cruel | +0.092 |
Neg logit contributions | |
cy | -0.069 |
Of | -0.068 |
girl | -0.066 |
sc | -0.065 |
Sure | -0.059 |
Token | . |
Token ID | 13 |
Feature activation | -6.20e-01 |
Pos logit contributions | |
strangers | +0.013 |
tresp | +0.012 |
vern | +0.012 |
Days | +0.012 |
isdom | +0.012 |
Neg logit contributions | |
Of | -0.005 |
girl | -0.005 |
cy | -0.005 |
sc | -0.005 |
down | -0.005 |
Token | Of |
Token ID | 3226 |
Feature activation | +1.43e+01 |
Pos logit contributions | |
strangers | +0.041 |
tresp | +0.038 |
cruel | +0.035 |
isdom | +0.035 |
vern | +0.034 |
Neg logit contributions | |
cy | -0.028 |
mixture | -0.026 |
sc | -0.026 |
girl | -0.025 |
tin | -0.024 |
Token | course |
Token ID | 1781 |
Feature activation | -1.99e+00 |
Pos logit contributions | |
girl | +0.749 |
cy | +0.746 |
Of | +0.744 |
sc | +0.661 |
tin | +0.652 |
Neg logit contributions | |
strangers | -0.818 |
tresp | -0.736 |
vern | -0.730 |
supposed | -0.712 |
cod | -0.683 |
Token | we |
Token ID | 356 |
Feature activation | +8.25e-01 |
Pos logit contributions | |
strangers | +0.122 |
tresp | +0.108 |
vern | +0.100 |
cruel | +0.099 |
unts | +0.094 |
Neg logit contributions | |
cy | -0.104 |
Of | -0.103 |
sc | -0.100 |
Sure | -0.095 |
girl | -0.093 |
Token | can |
Token ID | 460 |
Feature activation | -4.94e+00 |
Pos logit contributions | |
cy | +0.036 |
girl | +0.033 |
down | +0.030 |
up | +0.029 |
sc | +0.028 |
Neg logit contributions | |
strangers | -0.059 |
vern | -0.053 |
tresp | -0.051 |
opl | -0.051 |
cod | -0.051 |
Token | still |
Token ID | 991 |
Feature activation | -2.69e+00 |
Pos logit contributions | |
strangers | +0.318 |
tresp | +0.294 |
cruel | +0.271 |
vern | +0.268 |
supposed | +0.267 |
Neg logit contributions | |
cy | -0.247 |
Of | -0.235 |
up | -0.223 |
girl | -0.221 |
down | -0.211 |
Token | be |
Token ID | 307 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
strangers | +0.179 |
tresp | +0.165 |
vern | +0.156 |
supposed | +0.153 |
cruel | +0.152 |
Neg logit contributions | |
cy | -0.128 |
Of | -0.121 |
girl | -0.116 |
sc | -0.107 |
down | -0.107 |
Token | are |
Token ID | 389 |
Feature activation | -4.24e+00 |
Pos logit contributions | |
cy | +0.277 |
girl | +0.263 |
sc | +0.251 |
fits | +0.250 |
Of | +0.244 |
Neg logit contributions | |
strangers | -0.305 |
vern | -0.267 |
tresp | -0.262 |
Days | -0.252 |
isdom | -0.248 |
Token | my |
Token ID | 616 |
Feature activation | +2.79e+00 |
Pos logit contributions | |
strangers | +0.293 |
tresp | +0.263 |
vern | +0.261 |
unts | +0.247 |
cod | +0.244 |
Neg logit contributions | |
Of | -0.177 |
cy | -0.173 |
girl | -0.170 |
up | -0.156 |
sc | -0.155 |
Token | best |
Token ID | 1266 |
Feature activation | +6.19e+00 |
Pos logit contributions | |
Of | +0.142 |
cy | +0.140 |
sc | +0.135 |
Sure | +0.129 |
onto | +0.123 |
Neg logit contributions | |
strangers | -0.175 |
tresp | -0.159 |
vern | -0.152 |
cruel | -0.144 |
supposed | -0.141 |
Token | friend |
Token ID | 1545 |
Feature activation | +2.98e+00 |
Pos logit contributions | |
Of | +0.322 |
cy | +0.321 |
sc | +0.306 |
Sure | +0.293 |
girl | +0.284 |
Neg logit contributions | |
strangers | -0.378 |
tresp | -0.343 |
vern | -0.321 |
supposed | -0.308 |
unts | -0.307 |
Token | . |
Token ID | 13 |
Feature activation | -5.11e-01 |
Pos logit contributions | |
cy | +0.131 |
Of | +0.129 |
girl | +0.123 |
sc | +0.121 |
Sure | +0.113 |
Neg logit contributions | |
strangers | -0.204 |
tresp | -0.185 |
vern | -0.180 |
cruel | -0.172 |
supposed | -0.170 |
Token | Of |
Token ID | 3226 |
Feature activation | +1.43e+01 |
Pos logit contributions | |
strangers | +0.033 |
tresp | +0.030 |
isdom | +0.028 |
unts | +0.027 |
vern | +0.027 |
Neg logit contributions | |
cy | -0.024 |
mixture | -0.023 |
tin | -0.022 |
sc | -0.021 |
girl | -0.021 |
Token | course |
Token ID | 1781 |
Feature activation | -2.04e+00 |
Pos logit contributions | |
cy | +0.760 |
Of | +0.750 |
girl | +0.748 |
sc | +0.672 |
tin | +0.660 |
Neg logit contributions | |
strangers | -0.815 |
tresp | -0.724 |
vern | -0.722 |
supposed | -0.694 |
cod | -0.678 |
Token | I |
Token ID | 314 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
strangers | +0.123 |
tresp | +0.109 |
vern | +0.101 |
cruel | +0.099 |
supposed | +0.095 |
Neg logit contributions | |
cy | -0.107 |
Of | -0.107 |
sc | -0.103 |
Sure | -0.099 |
girl | -0.096 |
Token | include |
Token ID | 2291 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
cy | +0.056 |
girl | +0.050 |
sc | +0.049 |
Of | +0.048 |
Sure | +0.044 |
Neg logit contributions | |
strangers | -0.082 |
tresp | -0.070 |
vern | -0.068 |
cruel | -0.066 |
isdom | -0.066 |
Token | you |
Token ID | 345 |
Feature activation | +1.44e-02 |
Pos logit contributions | |
cy | +0.057 |
Of | +0.057 |
sc | +0.054 |
Sure | +0.053 |
girl | +0.053 |
Neg logit contributions | |
strangers | -0.070 |
tresp | -0.062 |
vern | -0.059 |
cruel | -0.056 |
supposed | -0.056 |
Token | in |
Token ID | 287 |
Feature activation | +2.48e+00 |
Pos logit contributions | |
cy | +0.001 |
Of | +0.001 |
girl | +0.001 |
sc | +0.001 |
Sure | +0.001 |
Neg logit contributions | |
strangers | -0.001 |
tresp | -0.001 |
vern | -0.001 |
cruel | -0.001 |
unts | -0.001 |
Token | his |
Token ID | 465 |
Feature activation | +8.89e-01 |
Pos logit contributions | |
cy | +0.157 |
Of | +0.151 |
girl | +0.143 |
sc | +0.142 |
Sure | +0.141 |
Neg logit contributions | |
strangers | -0.163 |
tresp | -0.147 |
supposed | -0.132 |
vern | -0.130 |
eping | -0.127 |
Token | fish |
Token ID | 5916 |
Feature activation | -2.60e-01 |
Pos logit contributions | |
Of | +0.042 |
cy | +0.042 |
sc | +0.039 |
girl | +0.039 |
Sure | +0.038 |
Neg logit contributions | |
strangers | -0.058 |
tresp | -0.053 |
vern | -0.050 |
cruel | -0.048 |
supposed | -0.048 |
Token | with |
Token ID | 351 |
Feature activation | +9.56e+00 |
Pos logit contributions | |
strangers | +0.018 |
tresp | +0.016 |
vern | +0.016 |
supposed | +0.015 |
cruel | +0.015 |
Neg logit contributions | |
Of | -0.011 |
cy | -0.011 |
sc | -0.010 |
Sure | -0.010 |
girl | -0.010 |
Token | him |
Token ID | 683 |
Feature activation | -5.12e+00 |
Pos logit contributions | |
Of | +0.597 |
cy | +0.591 |
sc | +0.565 |
onto | +0.555 |
girl | +0.553 |
Neg logit contributions | |
strangers | -0.473 |
tresp | -0.422 |
vern | -0.408 |
cruel | -0.383 |
supposed | -0.374 |
Token | ! |
Token ID | 0 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
strangers | +0.342 |
tresp | +0.311 |
vern | +0.301 |
cruel | +0.288 |
unts | +0.285 |
Neg logit contributions | |
Of | -0.234 |
cy | -0.233 |
sc | -0.217 |
girl | -0.215 |
Sure | -0.209 |
Token | Of |
Token ID | 3226 |
Feature activation | +1.43e+01 |
Pos logit contributions | |
strangers | +0.067 |
tresp | +0.060 |
unts | +0.058 |
vern | +0.056 |
supposed | +0.056 |
Neg logit contributions | |
cy | -0.058 |
girl | -0.055 |
Of | -0.055 |
sc | -0.054 |
tin | -0.052 |
Token | course |
Token ID | 1781 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
Of | +0.755 |
cy | +0.742 |
girl | +0.735 |
sc | +0.680 |
onto | +0.658 |
Neg logit contributions | |
strangers | -0.821 |
vern | -0.745 |
tresp | -0.734 |
supposed | -0.705 |
unts | -0.687 |
Token | , |
Token ID | 11 |
Feature activation | +4.18e-01 |
Pos logit contributions | |
strangers | +0.121 |
tresp | +0.109 |
vern | +0.102 |
cruel | +0.099 |
supposed | +0.098 |
Neg logit contributions | |
cy | -0.098 |
Of | -0.098 |
sc | -0.093 |
girl | -0.090 |
Sure | -0.089 |
Token | it |
Token ID | 340 |
Feature activation | -4.47e-01 |
Pos logit contributions | |
cy | +0.022 |
Of | +0.021 |
sc | +0.021 |
girl | +0.020 |
Sure | +0.019 |
Neg logit contributions | |
strangers | -0.026 |
tresp | -0.023 |
vern | -0.021 |
cruel | -0.021 |
supposed | -0.020 |
Token | wasn |
Token ID | 2492 |
Feature activation | -3.19e+00 |
Pos logit contributions | |
strangers | +0.028 |
tresp | +0.025 |
vern | +0.024 |
cruel | +0.023 |
supposed | +0.023 |
Neg logit contributions | |
Of | -0.023 |
cy | -0.022 |
sc | -0.021 |
Sure | -0.020 |
girl | -0.020 |
Token | 't |
Token ID | 470 |
Feature activation | -3.23e+00 |
Pos logit contributions | |
strangers | +0.206 |
tresp | +0.181 |
cod | +0.180 |
isdom | +0.178 |
enemies | +0.173 |
Neg logit contributions | |
Of | -0.151 |
onto | -0.149 |
sc | -0.149 |
up | -0.141 |
cy | -0.139 |
Token | said |
Token ID | 531 |
Feature activation | +3.92e+00 |
Pos logit contributions | |
strangers | +0.136 |
tresp | +0.116 |
hated | +0.115 |
cruel | +0.114 |
never | +0.109 |
Neg logit contributions | |
sc | -0.139 |
cy | -0.138 |
Of | -0.134 |
Sure | -0.124 |
suit | -0.122 |
Token | , |
Token ID | 11 |
Feature activation | +5.48e-01 |
Pos logit contributions | |
cy | +0.194 |
Of | +0.194 |
sc | +0.182 |
girl | +0.180 |
Sure | +0.176 |
Neg logit contributions | |
strangers | -0.247 |
tresp | -0.223 |
vern | -0.213 |
cruel | -0.203 |
supposed | -0.201 |
Token | " |
Token ID | 366 |
Feature activation | -2.84e+00 |
Pos logit contributions | |
Of | +0.026 |
cy | +0.026 |
sc | +0.024 |
girl | +0.024 |
Sure | +0.024 |
Neg logit contributions | |
strangers | -0.035 |
tresp | -0.032 |
vern | -0.031 |
cruel | -0.029 |
supposed | -0.029 |
Token | Yes |
Token ID | 5297 |
Feature activation | +1.13e+01 |
Pos logit contributions | |
strangers | +0.182 |
Days | +0.174 |
never | +0.171 |
understand | +0.167 |
vern | +0.164 |
Neg logit contributions | |
up | -0.105 |
cy | -0.104 |
onto | -0.100 |
down | -0.099 |
into | -0.095 |
Token | ! |
Token ID | 0 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
Of | +0.533 |
cy | +0.527 |
girl | +0.495 |
sc | +0.490 |
Sure | +0.473 |
Neg logit contributions | |
strangers | -0.742 |
tresp | -0.673 |
vern | -0.647 |
supposed | -0.622 |
cruel | -0.618 |
Token | Of |
Token ID | 3226 |
Feature activation | +1.43e+01 |
Pos logit contributions | |
strangers | +0.062 |
tresp | +0.056 |
isdom | +0.055 |
shouldn | +0.054 |
unts | +0.053 |
Neg logit contributions | |
cy | -0.042 |
mixture | -0.039 |
sc | -0.039 |
girl | -0.038 |
tin | -0.038 |
Token | course |
Token ID | 1781 |
Feature activation | -1.93e+00 |
Pos logit contributions | |
Of | +0.711 |
cy | +0.707 |
girl | +0.690 |
sc | +0.642 |
tin | +0.624 |
Neg logit contributions | |
strangers | -0.848 |
tresp | -0.742 |
vern | -0.738 |
ache | -0.718 |
supposed | -0.713 |
Token | . |
Token ID | 13 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
strangers | +0.125 |
tresp | +0.113 |
vern | +0.107 |
cruel | +0.103 |
supposed | +0.102 |
Neg logit contributions | |
cy | -0.093 |
Of | -0.092 |
sc | -0.087 |
girl | -0.084 |
Sure | -0.084 |
Token | I |
Token ID | 314 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
cy | +0.005 |
girl | +0.005 |
mixture | +0.005 |
tin | +0.005 |
sc | +0.005 |
Neg logit contributions | |
strangers | -0.008 |
tresp | -0.007 |
isdom | -0.007 |
shouldn | -0.007 |
never | -0.007 |
Token | have |
Token ID | 423 |
Feature activation | -3.38e+00 |
Pos logit contributions | |
cy | +0.072 |
Of | +0.066 |
girl | +0.065 |
sc | +0.065 |
Sure | +0.062 |
Neg logit contributions | |
strangers | -0.083 |
tresp | -0.070 |
vern | -0.067 |
cruel | -0.065 |
supposed | -0.062 |
Token | a |
Token ID | 257 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
strangers | +0.248 |
tresp | +0.226 |
vern | +0.220 |
unts | +0.212 |
cruel | +0.211 |
Neg logit contributions | |
Of | -0.131 |
cy | -0.127 |
girl | -0.121 |
sc | -0.121 |
Sure | -0.114 |
Token | you |
Token ID | 345 |
Feature activation | -5.09e-02 |
Pos logit contributions | |
Of | +0.001 |
cy | +0.001 |
girl | +0.001 |
sc | +0.001 |
Sure | +0.001 |
Neg logit contributions | |
strangers | -0.002 |
tresp | -0.002 |
vern | -0.002 |
supposed | -0.002 |
unts | -0.002 |
Token | are |
Token ID | 389 |
Feature activation | -4.27e+00 |
Pos logit contributions | |
strangers | +0.003 |
tresp | +0.002 |
vern | +0.002 |
cruel | +0.002 |
cod | +0.002 |
Neg logit contributions | |
Of | -0.003 |
cy | -0.003 |
girl | -0.003 |
sc | -0.003 |
Sure | -0.003 |
Token | very |
Token ID | 845 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
strangers | +0.252 |
tresp | +0.224 |
vern | +0.214 |
cruel | +0.203 |
unts | +0.201 |
Neg logit contributions | |
Of | -0.232 |
cy | -0.231 |
girl | -0.217 |
sc | -0.217 |
Sure | -0.211 |
Token | kind |
Token ID | 1611 |
Feature activation | -3.91e+00 |
Pos logit contributions | |
strangers | +0.049 |
tresp | +0.043 |
vern | +0.041 |
cruel | +0.038 |
supposed | +0.038 |
Neg logit contributions | |
cy | -0.072 |
Of | -0.072 |
sc | -0.070 |
Sure | -0.068 |
girl | -0.068 |
Token | . |
Token ID | 13 |
Feature activation | -5.40e-01 |
Pos logit contributions | |
strangers | +0.225 |
tresp | +0.196 |
vern | +0.183 |
unts | +0.178 |
supposed | +0.174 |
Neg logit contributions | |
Of | -0.218 |
cy | -0.218 |
Sure | -0.206 |
sc | -0.205 |
mixture | -0.196 |
Token | Of |
Token ID | 3226 |
Feature activation | +1.43e+01 |
Pos logit contributions | |
strangers | +0.035 |
tresp | +0.032 |
isdom | +0.030 |
vern | +0.029 |
unts | +0.029 |
Neg logit contributions | |
cy | -0.024 |
mixture | -0.023 |
sc | -0.023 |
girl | -0.022 |
tin | -0.022 |
Token | course |
Token ID | 1781 |
Feature activation | -2.06e+00 |
Pos logit contributions | |
cy | +0.761 |
Of | +0.754 |
girl | +0.743 |
sc | +0.682 |
tin | +0.658 |
Neg logit contributions | |
strangers | -0.804 |
tresp | -0.715 |
vern | -0.708 |
supposed | -0.686 |
ache | -0.674 |
Token | you |
Token ID | 345 |
Feature activation | -3.58e-02 |
Pos logit contributions | |
strangers | +0.127 |
tresp | +0.113 |
vern | +0.105 |
cruel | +0.102 |
supposed | +0.099 |
Neg logit contributions | |
cy | -0.107 |
Of | -0.106 |
sc | -0.102 |
Sure | -0.098 |
girl | -0.095 |
Token | can |
Token ID | 460 |
Feature activation | -5.07e+00 |
Pos logit contributions | |
strangers | +0.002 |
tresp | +0.002 |
vern | +0.002 |
Days | +0.002 |
eping | +0.002 |
Neg logit contributions | |
cy | -0.002 |
girl | -0.002 |
sc | -0.002 |
Of | -0.002 |
up | -0.001 |
Token | touch |
Token ID | 3638 |
Feature activation | +2.44e+00 |
Pos logit contributions | |
strangers | +0.334 |
tresp | +0.306 |
cruel | +0.290 |
vern | +0.285 |
enemies | +0.279 |
Neg logit contributions | |
cy | -0.251 |
Of | -0.239 |
girl | -0.222 |
up | -0.216 |
onto | -0.214 |
Token | it |
Token ID | 340 |
Feature activation | -6.33e-01 |
Pos logit contributions | |
Of | +0.117 |
cy | +0.116 |
sc | +0.109 |
girl | +0.107 |
Sure | +0.106 |
Neg logit contributions | |
strangers | -0.160 |
tresp | -0.143 |
vern | -0.137 |
cruel | -0.132 |
supposed | -0.130 |
Token | You |
Token ID | 1639 |
Feature activation | +2.94e+00 |
Pos logit contributions | |
strangers | +0.166 |
never | +0.151 |
hated | +0.151 |
cruel | +0.149 |
vern | +0.146 |
Neg logit contributions | |
cy | -0.153 |
onto | -0.145 |
down | -0.144 |
Of | -0.143 |
girl | -0.139 |
Token | can |
Token ID | 460 |
Feature activation | -5.05e+00 |
Pos logit contributions | |
cy | +0.162 |
girl | +0.156 |
Of | +0.156 |
sc | +0.145 |
down | +0.143 |
Neg logit contributions | |
strangers | -0.173 |
tresp | -0.149 |
vern | -0.148 |
cod | -0.140 |
Days | -0.140 |
Token | , |
Token ID | 11 |
Feature activation | +2.85e-01 |
Pos logit contributions | |
strangers | +0.311 |
tresp | +0.282 |
vern | +0.264 |
cruel | +0.260 |
supposed | +0.256 |
Neg logit contributions | |
cy | -0.268 |
Of | -0.263 |
sc | -0.241 |
girl | -0.238 |
Sure | -0.234 |
Token | Max |
Token ID | 5436 |
Feature activation | -2.88e+00 |
Pos logit contributions | |
Of | +0.012 |
cy | +0.012 |
girl | +0.011 |
sc | +0.011 |
Sure | +0.010 |
Neg logit contributions | |
strangers | -0.020 |
tresp | -0.018 |
vern | -0.018 |
supposed | -0.017 |
unts | -0.017 |
Token | . |
Token ID | 13 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
strangers | +0.188 |
tresp | +0.170 |
vern | +0.162 |
cruel | +0.155 |
supposed | +0.154 |
Neg logit contributions | |
Of | -0.138 |
cy | -0.137 |
sc | -0.128 |
girl | -0.126 |
Sure | -0.124 |
Token | Of |
Token ID | 3226 |
Feature activation | +1.42e+01 |
Pos logit contributions | |
strangers | +0.015 |
tresp | +0.014 |
isdom | +0.013 |
shouldn | +0.013 |
cruel | +0.013 |
Neg logit contributions | |
cy | -0.010 |
girl | -0.010 |
sc | -0.009 |
mixture | -0.009 |
tin | -0.009 |
Token | course |
Token ID | 1781 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
Of | +0.738 |
cy | +0.730 |
girl | +0.725 |
sc | +0.656 |
tin | +0.641 |
Neg logit contributions | |
strangers | -0.824 |
vern | -0.723 |
tresp | -0.722 |
supposed | -0.695 |
cod | -0.684 |
Token | you |
Token ID | 345 |
Feature activation | -3.32e-02 |
Pos logit contributions | |
strangers | +0.136 |
tresp | +0.122 |
vern | +0.115 |
cruel | +0.112 |
supposed | +0.109 |
Neg logit contributions | |
cy | -0.102 |
Of | -0.100 |
sc | -0.096 |
girl | -0.092 |
Sure | -0.091 |
Token | can |
Token ID | 460 |
Feature activation | -5.04e+00 |
Pos logit contributions | |
strangers | +0.002 |
tresp | +0.002 |
vern | +0.002 |
cod | +0.002 |
eping | +0.002 |
Neg logit contributions | |
cy | -0.002 |
sc | -0.001 |
girl | -0.001 |
Of | -0.001 |
up | -0.001 |
Token | , |
Token ID | 11 |
Feature activation | +2.66e-01 |
Pos logit contributions | |
strangers | +0.328 |
tresp | +0.297 |
cruel | +0.278 |
vern | +0.277 |
supposed | +0.268 |
Neg logit contributions | |
cy | -0.252 |
Of | -0.243 |
girl | -0.225 |
sc | -0.224 |
up | -0.220 |
Token | it |
Token ID | 340 |
Feature activation | -5.94e-01 |
Pos logit contributions | |
Of | +0.012 |
cy | +0.012 |
girl | +0.011 |
sc | +0.011 |
Sure | +0.010 |
Neg logit contributions | |
strangers | -0.018 |
tresp | -0.017 |
vern | -0.016 |
supposed | -0.015 |
cruel | -0.015 |
Token | said |
Token ID | 531 |
Feature activation | +3.78e+00 |
Pos logit contributions | |
strangers | +0.080 |
tresp | +0.072 |
vern | +0.069 |
cruel | +0.066 |
supposed | +0.066 |
Neg logit contributions | |
Of | -0.058 |
cy | -0.058 |
sc | -0.054 |
girl | -0.054 |
Sure | -0.052 |
Token | , |
Token ID | 11 |
Feature activation | +3.56e-01 |
Pos logit contributions | |
cy | +0.191 |
Of | +0.191 |
sc | +0.179 |
girl | +0.177 |
Sure | +0.173 |
Neg logit contributions | |
strangers | -0.235 |
tresp | -0.211 |
vern | -0.202 |
cruel | -0.193 |
supposed | -0.190 |
Token | " |
Token ID | 366 |
Feature activation | -2.96e+00 |
Pos logit contributions | |
cy | +0.018 |
Of | +0.018 |
sc | +0.017 |
girl | +0.017 |
Sure | +0.016 |
Neg logit contributions | |
strangers | -0.022 |
tresp | -0.019 |
vern | -0.019 |
cruel | -0.018 |
unts | -0.018 |
Token | Yes |
Token ID | 5297 |
Feature activation | +1.12e+01 |
Pos logit contributions | |
strangers | +0.171 |
understand | +0.151 |
never | +0.149 |
Days | +0.147 |
cod | +0.144 |
Neg logit contributions | |
up | -0.136 |
down | -0.130 |
onto | -0.129 |
cy | -0.128 |
Of | -0.128 |
Token | ! |
Token ID | 0 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
Of | +0.501 |
cy | +0.493 |
girl | +0.469 |
sc | +0.451 |
Sure | +0.441 |
Neg logit contributions | |
strangers | -0.759 |
tresp | -0.690 |
vern | -0.666 |
supposed | -0.647 |
cruel | -0.638 |
Token | Of |
Token ID | 3226 |
Feature activation | +1.42e+01 |
Pos logit contributions | |
strangers | +0.082 |
tresp | +0.075 |
isdom | +0.074 |
shouldn | +0.071 |
vern | +0.070 |
Neg logit contributions | |
cy | -0.055 |
sc | -0.053 |
girl | -0.050 |
tin | -0.049 |
mixture | -0.049 |
Token | course |
Token ID | 1781 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
Of | +0.686 |
cy | +0.671 |
girl | +0.664 |
sc | +0.608 |
onto | +0.602 |
Neg logit contributions | |
strangers | -0.857 |
vern | -0.752 |
tresp | -0.738 |
ache | -0.735 |
hated | -0.728 |
Token | you |
Token ID | 345 |
Feature activation | -2.09e-02 |
Pos logit contributions | |
strangers | +0.129 |
tresp | +0.116 |
vern | +0.109 |
cruel | +0.105 |
supposed | +0.104 |
Neg logit contributions | |
cy | -0.107 |
Of | -0.107 |
sc | -0.101 |
girl | -0.097 |
Sure | -0.097 |
Token | can |
Token ID | 460 |
Feature activation | -5.07e+00 |
Pos logit contributions | |
strangers | +0.001 |
vern | +0.001 |
tresp | +0.001 |
cod | +0.001 |
eping | +0.001 |
Neg logit contributions | |
cy | -0.001 |
girl | -0.001 |
sc | -0.001 |
tin | -0.001 |
Of | -0.001 |
Token | borrow |
Token ID | 8804 |
Feature activation | -2.20e+00 |
Pos logit contributions | |
strangers | +0.315 |
tresp | +0.281 |
cruel | +0.262 |
vern | +0.261 |
supposed | +0.252 |
Neg logit contributions | |
cy | -0.265 |
Of | -0.263 |
sc | -0.246 |
girl | -0.242 |
Sure | -0.236 |
Token | some |
Token ID | 617 |
Feature activation | +3.18e+00 |
Pos logit contributions | |
strangers | +0.152 |
tresp | +0.139 |
vern | +0.133 |
cruel | +0.128 |
supposed | +0.128 |
Neg logit contributions | |
Of | -0.096 |
cy | -0.095 |
sc | -0.088 |
girl | -0.087 |
Sure | -0.084 |
Token | could |
Token ID | 714 |
Feature activation | -5.22e+00 |
Pos logit contributions | |
cy | +0.071 |
Of | +0.070 |
girl | +0.069 |
sc | +0.068 |
Sure | +0.065 |
Neg logit contributions | |
strangers | -0.089 |
vern | -0.078 |
tresp | -0.078 |
cruel | -0.071 |
unts | -0.071 |
Token | hardly |
Token ID | 8941 |
Feature activation | -4.12e+00 |
Pos logit contributions | |
strangers | +0.302 |
tresp | +0.278 |
cod | +0.269 |
ills | +0.253 |
cruel | +0.252 |
Neg logit contributions | |
Of | -0.293 |
onto | -0.277 |
cy | -0.269 |
Sure | -0.267 |
down | -0.265 |
Token | stand |
Token ID | 1302 |
Feature activation | +3.06e+00 |
Pos logit contributions | |
strangers | +0.226 |
tresp | +0.197 |
vern | +0.188 |
cruel | +0.179 |
supposed | +0.177 |
Neg logit contributions | |
cy | -0.238 |
Of | -0.238 |
sc | -0.226 |
girl | -0.224 |
Sure | -0.218 |
Token | it |
Token ID | 340 |
Feature activation | -6.11e-01 |
Pos logit contributions | |
cy | +0.073 |
Of | +0.072 |
girl | +0.062 |
sc | +0.061 |
Sure | +0.056 |
Neg logit contributions | |
strangers | -0.271 |
tresp | -0.252 |
vern | -0.246 |
unts | -0.237 |
cruel | -0.236 |
Token | ! |
Token ID | 0 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
strangers | +0.038 |
tresp | +0.033 |
vern | +0.032 |
supposed | +0.032 |
cruel | +0.031 |
Neg logit contributions | |
Of | -0.031 |
cy | -0.030 |
girl | -0.028 |
Sure | -0.028 |
sc | -0.027 |
Token | Of |
Token ID | 3226 |
Feature activation | +1.42e+01 |
Pos logit contributions | |
strangers | +0.074 |
hated | +0.061 |
tresp | +0.060 |
unts | +0.059 |
isdom | +0.059 |
Neg logit contributions | |
cy | -0.069 |
sc | -0.067 |
Of | -0.061 |
cer | -0.060 |
mixture | -0.060 |
Token | course |
Token ID | 1781 |
Feature activation | -2.10e+00 |
Pos logit contributions | |
Of | +0.768 |
cy | +0.767 |
girl | +0.753 |
sc | +0.696 |
Sure | +0.671 |
Neg logit contributions | |
strangers | -0.793 |
tresp | -0.718 |
vern | -0.711 |
supposed | -0.681 |
unts | -0.657 |
Token | she |
Token ID | 673 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
strangers | +0.123 |
tresp | +0.108 |
vern | +0.100 |
cruel | +0.098 |
supposed | +0.097 |
Neg logit contributions | |
cy | -0.114 |
Of | -0.114 |
sc | -0.112 |
Sure | -0.104 |
tin | -0.103 |
Token | wanted |
Token ID | 2227 |
Feature activation | -2.84e+00 |
Pos logit contributions | |
cy | +0.075 |
girl | +0.070 |
Of | +0.070 |
sc | +0.067 |
Sure | +0.066 |
Neg logit contributions | |
strangers | -0.093 |
vern | -0.081 |
tresp | -0.080 |
cruel | -0.075 |
unts | -0.073 |
Token | to |
Token ID | 284 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
strangers | +0.189 |
tresp | +0.171 |
vern | +0.164 |
cruel | +0.157 |
supposed | +0.156 |
Neg logit contributions | |
Of | -0.134 |
cy | -0.134 |
sc | -0.124 |
girl | -0.123 |
Sure | -0.120 |
Token | go |
Token ID | 467 |
Feature activation | -2.64e+00 |
Pos logit contributions | |
strangers | +0.066 |
tresp | +0.060 |
cruel | +0.058 |
vern | +0.057 |
cod | +0.056 |
Neg logit contributions | |
Of | -0.048 |
cy | -0.046 |
girl | -0.044 |
onto | -0.042 |
down | -0.041 |
Token | ride |
Token ID | 6594 |
Feature activation | -2.06e+00 |
Pos logit contributions | |
strangers | +0.049 |
tresp | +0.046 |
vern | +0.044 |
supposed | +0.044 |
cruel | +0.043 |
Neg logit contributions | |
Of | -0.035 |
cy | -0.034 |
girl | -0.032 |
tin | -0.031 |
sc | -0.030 |
Token | in |
Token ID | 287 |
Feature activation | +2.62e+00 |
Pos logit contributions | |
strangers | +0.137 |
tresp | +0.118 |
vern | +0.111 |
cruel | +0.107 |
enemies | +0.105 |
Neg logit contributions | |
Of | -0.095 |
cy | -0.092 |
Sure | -0.088 |
sc | -0.088 |
mixture | -0.086 |
Token | the |
Token ID | 262 |
Feature activation | -9.95e-01 |
Pos logit contributions | |
Of | +0.122 |
cy | +0.122 |
sc | +0.113 |
girl | +0.113 |
Sure | +0.109 |
Neg logit contributions | |
strangers | -0.173 |
tresp | -0.157 |
vern | -0.151 |
cruel | -0.145 |
supposed | -0.143 |
Token | wagon |
Token ID | 31860 |
Feature activation | -4.45e+00 |
Pos logit contributions | |
strangers | +0.062 |
tresp | +0.055 |
vern | +0.053 |
cruel | +0.050 |
supposed | +0.050 |
Neg logit contributions | |
Of | -0.051 |
cy | -0.051 |
sc | -0.048 |
girl | -0.047 |
Sure | -0.046 |
Token | . |
Token ID | 13 |
Feature activation | +2.39e-03 |
Pos logit contributions | |
strangers | +0.275 |
tresp | +0.239 |
vern | +0.230 |
cruel | +0.218 |
never | +0.217 |
Neg logit contributions | |
Of | -0.222 |
cy | -0.213 |
Sure | -0.201 |
sc | -0.201 |
girl | -0.197 |
Token | Of |
Token ID | 3226 |
Feature activation | +1.41e+01 |
Pos logit contributions | |
cy | +0.000 |
sc | +0.000 |
girl | +0.000 |
mixture | +0.000 |
Of | +0.000 |
Neg logit contributions | |
strangers | -0.000 |
tresp | -0.000 |
unts | -0.000 |
vern | -0.000 |
isdom | -0.000 |
Token | course |
Token ID | 1781 |
Feature activation | -2.14e+00 |
Pos logit contributions | |
Of | +0.795 |
cy | +0.783 |
girl | +0.754 |
sc | +0.706 |
Sure | +0.698 |
Neg logit contributions | |
strangers | -0.783 |
tresp | -0.708 |
vern | -0.681 |
supposed | -0.664 |
unts | -0.641 |
Token | , |
Token ID | 11 |
Feature activation | +4.91e-01 |
Pos logit contributions | |
strangers | +0.124 |
tresp | +0.108 |
never | +0.099 |
cruel | +0.095 |
vern | +0.094 |
Neg logit contributions | |
cy | -0.115 |
sc | -0.114 |
Of | -0.111 |
mixture | -0.106 |
Sure | -0.105 |
Token | Molly |
Token ID | 30236 |
Feature activation | +7.34e+00 |
Pos logit contributions | |
cy | +0.024 |
sc | +0.023 |
mixture | +0.022 |
Of | +0.021 |
umm | +0.021 |
Neg logit contributions | |
strangers | -0.031 |
tresp | -0.027 |
never | -0.026 |
understand | -0.025 |
cruel | -0.024 |
Token | and |
Token ID | 290 |
Feature activation | -2.64e+00 |
Pos logit contributions | |
cy | +0.335 |
Of | +0.330 |
girl | +0.314 |
sc | +0.304 |
Sure | +0.297 |
Neg logit contributions | |
strangers | -0.497 |
tresp | -0.449 |
vern | -0.433 |
supposed | -0.415 |
cruel | -0.413 |
Token | Sam |
Token ID | 3409 |
Feature activation | -3.16e+00 |
Pos logit contributions | |
strangers | +0.162 |
tresp | +0.140 |
vern | +0.126 |
cruel | +0.125 |
isdom | +0.123 |
Neg logit contributions | |
sc | -0.139 |
cy | -0.139 |
Of | -0.137 |
Sure | -0.127 |
mixture | -0.126 |
Token | said |
Token ID | 531 |
Feature activation | +3.66e+00 |
Pos logit contributions | |
Of | +0.066 |
cy | +0.066 |
girl | +0.063 |
sc | +0.061 |
Sure | +0.060 |
Neg logit contributions | |
strangers | -0.093 |
tresp | -0.084 |
vern | -0.082 |
supposed | -0.077 |
cruel | -0.075 |
Token | , |
Token ID | 11 |
Feature activation | +3.05e-01 |
Pos logit contributions | |
cy | +0.190 |
Of | +0.186 |
sc | +0.177 |
girl | +0.174 |
Sure | +0.170 |
Neg logit contributions | |
strangers | -0.224 |
tresp | -0.202 |
vern | -0.193 |
cruel | -0.185 |
supposed | -0.180 |
Token | " |
Token ID | 366 |
Feature activation | -3.09e+00 |
Pos logit contributions | |
Of | +0.014 |
cy | +0.014 |
sc | +0.013 |
girl | +0.013 |
Sure | +0.013 |
Neg logit contributions | |
strangers | -0.020 |
tresp | -0.018 |
vern | -0.018 |
cruel | -0.017 |
supposed | -0.017 |
Token | Yes |
Token ID | 5297 |
Feature activation | +1.11e+01 |
Pos logit contributions | |
strangers | +0.181 |
understand | +0.159 |
never | +0.158 |
Days | +0.155 |
respected | +0.155 |
Neg logit contributions | |
cy | -0.137 |
up | -0.134 |
Of | -0.132 |
onto | -0.132 |
sc | -0.131 |
Token | ! |
Token ID | 0 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
Of | +0.514 |
cy | +0.504 |
girl | +0.479 |
sc | +0.458 |
Sure | +0.452 |
Neg logit contributions | |
strangers | -0.736 |
tresp | -0.665 |
vern | -0.645 |
supposed | -0.625 |
unts | -0.618 |
Token | Of |
Token ID | 3226 |
Feature activation | +1.41e+01 |
Pos logit contributions | |
strangers | +0.079 |
tresp | +0.072 |
isdom | +0.069 |
shouldn | +0.067 |
cruel | +0.067 |
Neg logit contributions | |
cy | -0.057 |
sc | -0.056 |
mixture | -0.052 |
girl | -0.052 |
tin | -0.051 |
Token | course |
Token ID | 1781 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
Of | +0.701 |
cy | +0.691 |
girl | +0.676 |
onto | +0.615 |
tin | +0.611 |
Neg logit contributions | |
strangers | -0.844 |
vern | -0.740 |
tresp | -0.723 |
supposed | -0.713 |
hated | -0.709 |
Token | ." |
Token ID | 526 |
Feature activation | -5.01e-01 |
Pos logit contributions | |
strangers | +0.137 |
tresp | +0.124 |
vern | +0.116 |
cruel | +0.112 |
supposed | +0.110 |
Neg logit contributions | |
cy | -0.111 |
Of | -0.110 |
sc | -0.105 |
girl | -0.101 |
Sure | -0.101 |
Token |
|
Token ID | 198 |
Feature activation | +6.24e-01 |
Pos logit contributions | |
strangers | +0.022 |
unts | +0.019 |
tresp | +0.019 |
never | +0.019 |
understand | +0.018 |
Neg logit contributions | |
cy | -0.031 |
mixture | -0.028 |
sc | -0.028 |
fl | -0.027 |
girl | -0.027 |
Token |
|
Token ID | 198 |
Feature activation | +6.21e-01 |
Pos logit contributions | |
Of | +0.025 |
cy | +0.024 |
sc | +0.023 |
girl | +0.022 |
Sure | +0.022 |
Neg logit contributions | |
strangers | -0.046 |
tresp | -0.042 |
vern | -0.040 |
cruel | -0.039 |
supposed | -0.039 |
Token | The |
Token ID | 464 |
Feature activation | -3.18e+00 |
Pos logit contributions | |
Of | +0.034 |
cy | +0.034 |
sc | +0.032 |
girl | +0.032 |
Sure | +0.031 |
Neg logit contributions | |
strangers | -0.036 |
tresp | -0.032 |
vern | -0.030 |
cruel | -0.029 |
supposed | -0.029 |
Token | friends |
Token ID | 2460 |
Feature activation | -7.81e-01 |
Pos logit contributions | |
girl | +0.045 |
Of | +0.042 |
cy | +0.042 |
moment | +0.039 |
mixture | +0.039 |
Neg logit contributions | |
strangers | -0.053 |
tresp | -0.050 |
cod | -0.048 |
isdom | -0.047 |
unts | -0.047 |
Token | to |
Token ID | 284 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
strangers | +0.054 |
tresp | +0.049 |
vern | +0.047 |
cruel | +0.046 |
unts | +0.045 |
Neg logit contributions | |
cy | -0.034 |
Of | -0.034 |
sc | -0.032 |
girl | -0.031 |
Sure | -0.030 |
Token | go |
Token ID | 467 |
Feature activation | -2.78e+00 |
Pos logit contributions | |
strangers | +0.067 |
cruel | +0.062 |
tresp | +0.062 |
hated | +0.062 |
cod | +0.061 |
Neg logit contributions | |
cy | -0.048 |
onto | -0.047 |
up | -0.046 |
down | -0.046 |
girl | -0.045 |
Token | home |
Token ID | 1363 |
Feature activation | +2.68e+00 |
Pos logit contributions | |
strangers | +0.204 |
tresp | +0.186 |
vern | +0.179 |
cruel | +0.172 |
supposed | +0.171 |
Neg logit contributions | |
Of | -0.110 |
cy | -0.109 |
sc | -0.101 |
girl | -0.099 |
Sure | -0.097 |
Token | . |
Token ID | 13 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
cy | +0.115 |
Of | +0.115 |
girl | +0.106 |
sc | +0.106 |
Sure | +0.102 |
Neg logit contributions | |
strangers | -0.187 |
tresp | -0.170 |
vern | -0.162 |
cruel | -0.157 |
unts | -0.155 |
Token | Of |
Token ID | 3226 |
Feature activation | +1.41e+01 |
Pos logit contributions | |
strangers | +0.007 |
tresp | +0.007 |
vern | +0.006 |
unts | +0.006 |
hated | +0.006 |
Neg logit contributions | |
cy | -0.006 |
sc | -0.006 |
girl | -0.006 |
Of | -0.006 |
tin | -0.006 |
Token | course |
Token ID | 1781 |
Feature activation | -2.16e+00 |
Pos logit contributions | |
cy | +0.732 |
girl | +0.728 |
Of | +0.726 |
sc | +0.653 |
Sure | +0.630 |
Neg logit contributions | |
strangers | -0.819 |
vern | -0.745 |
tresp | -0.740 |
supposed | -0.723 |
unts | -0.686 |
Token | , |
Token ID | 11 |
Feature activation | +3.17e-01 |
Pos logit contributions | |
strangers | +0.133 |
tresp | +0.119 |
vern | +0.111 |
cruel | +0.108 |
supposed | +0.105 |
Neg logit contributions | |
cy | -0.111 |
Of | -0.111 |
sc | -0.106 |
girl | -0.102 |
Sure | -0.101 |
Token | they |
Token ID | 484 |
Feature activation | -2.65e-01 |
Pos logit contributions | |
cy | +0.017 |
sc | +0.016 |
Of | +0.016 |
Sure | +0.015 |
girl | +0.015 |
Neg logit contributions | |
strangers | -0.019 |
tresp | -0.017 |
never | -0.015 |
cruel | -0.015 |
vern | -0.015 |
Token | had |
Token ID | 550 |
Feature activation | -4.73e+00 |
Pos logit contributions | |
strangers | +0.017 |
tresp | +0.015 |
vern | +0.015 |
cod | +0.015 |
cruel | +0.015 |
Neg logit contributions | |
cy | -0.014 |
girl | -0.013 |
down | -0.013 |
onto | -0.012 |
up | -0.012 |
Token | a |
Token ID | 257 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
strangers | +0.337 |
tresp | +0.297 |
vern | +0.287 |
cruel | +0.284 |
cod | +0.281 |
Neg logit contributions | |
Of | -0.197 |
cy | -0.196 |
girl | -0.184 |
sc | -0.182 |
Sure | -0.180 |
Token | my |
Token ID | 616 |
Feature activation | +2.73e+00 |
Pos logit contributions | |
Of | +0.014 |
cy | +0.013 |
sc | +0.013 |
girl | +0.012 |
Sure | +0.012 |
Neg logit contributions | |
strangers | -0.019 |
tresp | -0.017 |
vern | -0.016 |
cruel | -0.015 |
supposed | -0.015 |
Token | cute |
Token ID | 13779 |
Feature activation | -2.41e+00 |
Pos logit contributions | |
cy | +0.148 |
sc | +0.146 |
Of | +0.146 |
girl | +0.132 |
Sure | +0.132 |
Neg logit contributions | |
strangers | -0.156 |
tresp | -0.141 |
vern | -0.135 |
cruel | -0.128 |
hated | -0.127 |
Token | little |
Token ID | 1310 |
Feature activation | +1.98e-01 |
Pos logit contributions | |
strangers | +0.161 |
tresp | +0.144 |
vern | +0.137 |
supposed | +0.132 |
cruel | +0.132 |
Neg logit contributions | |
Of | -0.111 |
cy | -0.109 |
sc | -0.106 |
Sure | -0.099 |
girl | -0.098 |
Token | girl |
Token ID | 2576 |
Feature activation | +1.06e+01 |
Pos logit contributions | |
sc | +0.007 |
Of | +0.007 |
antly | +0.006 |
ipt | +0.006 |
iffs | +0.006 |
Neg logit contributions | |
strangers | -0.015 |
tresp | -0.013 |
mean | -0.013 |
enemies | -0.012 |
liar | -0.012 |
Token | ! |
Token ID | 0 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
cy | +0.507 |
Of | +0.504 |
girl | +0.468 |
sc | +0.467 |
Sure | +0.453 |
Neg logit contributions | |
strangers | -0.689 |
tresp | -0.619 |
vern | -0.597 |
cruel | -0.571 |
unts | -0.561 |
Token | Of |
Token ID | 3226 |
Feature activation | +1.41e+01 |
Pos logit contributions | |
strangers | +0.075 |
isdom | +0.070 |
shouldn | +0.070 |
tresp | +0.069 |
never | +0.068 |
Neg logit contributions | |
cy | -0.054 |
mixture | -0.053 |
tin | -0.052 |
sc | -0.051 |
up | -0.048 |
Token | course |
Token ID | 1781 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
cy | +0.653 |
girl | +0.652 |
Of | +0.650 |
tin | +0.568 |
sc | +0.567 |
Neg logit contributions | |
strangers | -0.868 |
vern | -0.765 |
tresp | -0.765 |
ache | -0.761 |
supposed | -0.754 |
Token | you |
Token ID | 345 |
Feature activation | -9.24e-02 |
Pos logit contributions | |
strangers | +0.137 |
tresp | +0.123 |
vern | +0.115 |
cruel | +0.111 |
supposed | +0.110 |
Neg logit contributions | |
cy | -0.110 |
Of | -0.110 |
sc | -0.106 |
Sure | -0.101 |
girl | -0.100 |
Token | can |
Token ID | 460 |
Feature activation | -5.17e+00 |
Pos logit contributions | |
strangers | +0.007 |
tresp | +0.006 |
vern | +0.006 |
cod | +0.006 |
cruel | +0.005 |
Neg logit contributions | |
cy | -0.004 |
girl | -0.004 |
sc | -0.004 |
Of | -0.004 |
up | -0.004 |
Token | have |
Token ID | 423 |
Feature activation | -3.74e+00 |
Pos logit contributions | |
strangers | +0.343 |
tresp | +0.309 |
cruel | +0.296 |
vern | +0.285 |
cod | +0.283 |
Neg logit contributions | |
cy | -0.255 |
Of | -0.250 |
girl | -0.229 |
onto | -0.224 |
Sure | -0.223 |
Token | a |
Token ID | 257 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
strangers | +0.279 |
tresp | +0.262 |
vern | +0.251 |
unts | +0.247 |
cruel | +0.243 |
Neg logit contributions | |
Of | -0.137 |
cy | -0.125 |
girl | -0.124 |
sc | -0.120 |
onto | -0.118 |
Token | they |
Token ID | 484 |
Feature activation | -2.37e-01 |
Pos logit contributions | |
cy | +0.123 |
Of | +0.120 |
sc | +0.115 |
girl | +0.110 |
Sure | +0.109 |
Neg logit contributions | |
strangers | -0.199 |
tresp | -0.177 |
vern | -0.168 |
cruel | -0.164 |
supposed | -0.160 |
Token | could |
Token ID | 714 |
Feature activation | -5.25e+00 |
Pos logit contributions | |
strangers | +0.015 |
vern | +0.014 |
tresp | +0.014 |
opl | +0.014 |
cod | +0.014 |
Neg logit contributions | |
cy | -0.012 |
Of | -0.011 |
girl | -0.011 |
onto | -0.010 |
ed | -0.010 |
Token | join |
Token ID | 4654 |
Feature activation | +3.03e+00 |
Pos logit contributions | |
strangers | +0.335 |
tresp | +0.308 |
cod | +0.290 |
vern | +0.289 |
cruel | +0.287 |
Neg logit contributions | |
cy | -0.255 |
Of | -0.254 |
onto | -0.233 |
up | -0.231 |
sc | -0.228 |
Token | her |
Token ID | 607 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
cy | +0.144 |
Of | +0.144 |
sc | +0.135 |
girl | +0.133 |
Sure | +0.133 |
Neg logit contributions | |
strangers | -0.199 |
tresp | -0.176 |
vern | -0.166 |
cruel | -0.160 |
supposed | -0.159 |
Token | . |
Token ID | 13 |
Feature activation | -8.38e-02 |
Pos logit contributions | |
strangers | +0.011 |
tresp | +0.010 |
vern | +0.009 |
supposed | +0.009 |
cruel | +0.009 |
Neg logit contributions | |
Of | -0.008 |
cy | -0.008 |
sc | -0.008 |
Sure | -0.008 |
girl | -0.007 |
Token | Of |
Token ID | 3226 |
Feature activation | +1.41e+01 |
Pos logit contributions | |
strangers | +0.005 |
unts | +0.004 |
hated | +0.004 |
tresp | +0.004 |
vern | +0.004 |
Neg logit contributions | |
cy | -0.005 |
tin | -0.004 |
girl | -0.004 |
mixture | -0.004 |
sc | -0.004 |
Token | course |
Token ID | 1781 |
Feature activation | -2.24e+00 |
Pos logit contributions | |
Of | +0.850 |
cy | +0.848 |
girl | +0.803 |
sc | +0.801 |
Sure | +0.774 |
Neg logit contributions | |
strangers | -0.733 |
tresp | -0.648 |
vern | -0.620 |
supposed | -0.583 |
cruel | -0.574 |
Token | , |
Token ID | 11 |
Feature activation | +4.30e-01 |
Pos logit contributions | |
strangers | +0.138 |
tresp | +0.119 |
cruel | +0.108 |
never | +0.107 |
hated | +0.106 |
Neg logit contributions | |
cy | -0.115 |
Of | -0.114 |
sc | -0.110 |
Sure | -0.110 |
tin | -0.108 |
Token | she |
Token ID | 673 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
cy | +0.024 |
ASH | +0.024 |
Sure | +0.022 |
tin | +0.022 |
sc | +0.022 |
Neg logit contributions | |
strangers | -0.025 |
tresp | -0.020 |
never | -0.020 |
cruel | -0.019 |
mean | -0.019 |
Token | said |
Token ID | 531 |
Feature activation | +3.81e+00 |
Pos logit contributions | |
cy | +0.076 |
Of | +0.074 |
girl | +0.072 |
sc | +0.071 |
Sure | +0.068 |
Neg logit contributions | |
strangers | -0.090 |
tresp | -0.080 |
vern | -0.077 |
supposed | -0.072 |
cruel | -0.072 |
Token | yes |
Token ID | 3763 |
Feature activation | -2.79e-01 |
Pos logit contributions | |
Of | +0.199 |
cy | +0.190 |
girl | +0.182 |
sc | +0.182 |
Sure | +0.178 |
Neg logit contributions | |
strangers | -0.233 |
tresp | -0.209 |
vern | -0.198 |
supposed | -0.191 |
unts | -0.190 |
Token | give |
Token ID | 1577 |
Feature activation | +3.83e+00 |
Pos logit contributions | |
strangers | +0.384 |
tresp | +0.344 |
vern | +0.330 |
cruel | +0.310 |
supposed | +0.308 |
Neg logit contributions | |
Of | -0.374 |
cy | -0.372 |
girl | -0.350 |
sc | -0.349 |
Sure | -0.339 |
Token | away |
Token ID | 1497 |
Feature activation | +7.40e+00 |
Pos logit contributions | |
Of | +0.137 |
cy | +0.134 |
sc | +0.125 |
girl | +0.120 |
Sure | +0.120 |
Neg logit contributions | |
strangers | -0.300 |
tresp | -0.271 |
vern | -0.260 |
cruel | -0.253 |
supposed | -0.252 |
Token | her |
Token ID | 607 |
Feature activation | -4.29e-01 |
Pos logit contributions | |
Of | +0.335 |
girl | +0.333 |
cy | +0.333 |
down | +0.304 |
up | +0.298 |
Neg logit contributions | |
strangers | -0.460 |
vern | -0.435 |
tresp | -0.434 |
unts | -0.417 |
supposed | -0.413 |
Token | things |
Token ID | 1243 |
Feature activation | +1.85e+00 |
Pos logit contributions | |
strangers | +0.030 |
tresp | +0.028 |
vern | +0.027 |
cruel | +0.026 |
supposed | +0.026 |
Neg logit contributions | |
cy | -0.018 |
Of | -0.018 |
girl | -0.017 |
sc | -0.016 |
Sure | -0.016 |
Token | to |
Token ID | 284 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
cy | +0.079 |
Of | +0.079 |
sc | +0.073 |
girl | +0.073 |
Sure | +0.069 |
Neg logit contributions | |
strangers | -0.129 |
tresp | -0.118 |
vern | -0.113 |
cruel | -0.109 |
unts | -0.109 |
Token | strangers |
Token ID | 18981 |
Feature activation | -1.59e+01 |
Pos logit contributions | |
strangers | +0.069 |
tresp | +0.069 |
vern | +0.066 |
unts | +0.064 |
supposed | +0.063 |
Neg logit contributions | |
Of | -0.058 |
cy | -0.056 |
girl | -0.055 |
up | -0.049 |
down | -0.049 |
Token | again |
Token ID | 757 |
Feature activation | +4.10e+00 |
Pos logit contributions | |
strangers | +1.149 |
tresp | +1.058 |
vern | +1.022 |
cruel | +0.978 |
supposed | +0.973 |
Neg logit contributions | |
cy | -0.643 |
Of | -0.638 |
sc | -0.590 |
girl | -0.587 |
Sure | -0.562 |
Token | . |
Token ID | 13 |
Feature activation | -3.39e-01 |
Pos logit contributions | |
cy | +0.155 |
Of | +0.153 |
girl | +0.145 |
down | +0.132 |
sc | +0.131 |
Neg logit contributions | |
strangers | -0.298 |
tresp | -0.283 |
vern | -0.275 |
cruel | -0.258 |
supposed | -0.257 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -7.19e+00 |
Pos logit contributions | |
strangers | +0.020 |
tresp | +0.018 |
vern | +0.017 |
unts | +0.017 |
supposed | +0.017 |
Neg logit contributions | |
cy | -0.018 |
Of | -0.017 |
sc | -0.017 |
girl | -0.016 |
tin | -0.016 |
Token | Once |
Token ID | 7454 |
Feature activation | -2.89e-01 |
Pos logit contributions | |
strangers | +0.417 |
tresp | +0.366 |
vern | +0.353 |
unts | +0.345 |
supposed | +0.333 |
Neg logit contributions | |
Of | -0.374 |
cy | -0.367 |
girl | -0.350 |
mixture | -0.346 |
sc | -0.346 |
Token | upon |
Token ID | 2402 |
Feature activation | -4.20e-01 |
Pos logit contributions | |
strangers | +0.022 |
tresp | +0.021 |
vern | +0.019 |
cod | +0.019 |
cruel | +0.019 |
Neg logit contributions | |
cy | -0.011 |
Of | -0.011 |
girl | -0.010 |
Sure | -0.009 |
down | -0.009 |
Token | rules |
Token ID | 3173 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
strangers | +0.022 |
tresp | +0.019 |
vern | +0.018 |
cruel | +0.018 |
enemies | +0.017 |
Neg logit contributions | |
cy | -0.016 |
Of | -0.015 |
sc | -0.015 |
Sure | -0.014 |
girl | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | -3.59e-01 |
Pos logit contributions | |
cy | +0.041 |
Of | +0.040 |
sc | +0.039 |
girl | +0.038 |
down | +0.036 |
Neg logit contributions | |
strangers | -0.073 |
tresp | -0.068 |
vern | -0.064 |
cruel | -0.064 |
cod | -0.063 |
Token | She |
Token ID | 1375 |
Feature activation | -6.22e-02 |
Pos logit contributions | |
strangers | +0.022 |
tresp | +0.019 |
vern | +0.019 |
unts | +0.019 |
isdom | +0.018 |
Neg logit contributions | |
cy | -0.018 |
sc | -0.018 |
Of | -0.017 |
mixture | -0.017 |
tin | -0.016 |
Token | knew |
Token ID | 2993 |
Feature activation | -4.30e+00 |
Pos logit contributions | |
strangers | +0.003 |
tresp | +0.003 |
vern | +0.003 |
supposed | +0.003 |
cruel | +0.003 |
Neg logit contributions | |
cy | -0.004 |
girl | -0.004 |
Of | -0.003 |
sc | -0.003 |
Sure | -0.003 |
Token | that |
Token ID | 326 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
strangers | +0.252 |
tresp | +0.228 |
vern | +0.217 |
unts | +0.207 |
cruel | +0.206 |
Neg logit contributions | |
Of | -0.233 |
cy | -0.228 |
girl | -0.217 |
sc | -0.213 |
Sure | -0.211 |
Token | strangers |
Token ID | 18981 |
Feature activation | -1.59e+01 |
Pos logit contributions | |
strangers | +0.096 |
tresp | +0.086 |
vern | +0.082 |
cruel | +0.079 |
supposed | +0.079 |
Neg logit contributions | |
cy | -0.070 |
Of | -0.070 |
sc | -0.066 |
girl | -0.065 |
Sure | -0.063 |
Token | could |
Token ID | 714 |
Feature activation | -5.28e+00 |
Pos logit contributions | |
strangers | +0.948 |
vern | +0.947 |
tresp | +0.901 |
unts | +0.884 |
cod | +0.860 |
Neg logit contributions | |
cy | -0.821 |
girl | -0.751 |
sc | -0.745 |
Of | -0.733 |
up | -0.718 |
Token | be |
Token ID | 307 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
strangers | +0.291 |
ills | +0.286 |
lee | +0.281 |
tresp | +0.281 |
eping | +0.281 |
Neg logit contributions | |
up | -0.242 |
cy | -0.238 |
Of | -0.236 |
with | -0.229 |
girl | -0.228 |
Token | dangerous |
Token ID | 4923 |
Feature activation | -1.02e+01 |
Pos logit contributions | |
girl | +0.069 |
up | +0.068 |
down | +0.067 |
cy | +0.067 |
Of | +0.065 |
Neg logit contributions | |
strangers | -0.065 |
tresp | -0.059 |
vern | -0.059 |
unts | -0.056 |
isdom | -0.054 |
Token | and |
Token ID | 290 |
Feature activation | -2.90e+00 |
Pos logit contributions | |
strangers | +0.640 |
tresp | +0.578 |
vern | +0.555 |
cruel | +0.528 |
supposed | +0.523 |
Neg logit contributions | |
Of | -0.508 |
cy | -0.507 |
sc | -0.475 |
girl | -0.473 |
Sure | -0.458 |
Token | that |
Token ID | 326 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
strangers | +0.143 |
vern | +0.141 |
tresp | +0.138 |
unts | +0.131 |
eping | +0.126 |
Neg logit contributions | |
Of | -0.164 |
girl | -0.164 |
cy | -0.157 |
down | -0.156 |
up | -0.153 |
Token | feelings |
Token ID | 7666 |
Feature activation | -3.21e+00 |
Pos logit contributions | |
strangers | +0.143 |
tresp | +0.136 |
eping | +0.134 |
vern | +0.133 |
supposed | +0.132 |
Neg logit contributions | |
girl | -0.092 |
cy | -0.086 |
Of | -0.083 |
up | -0.074 |
Sure | -0.074 |
Token | and |
Token ID | 290 |
Feature activation | -3.06e+00 |
Pos logit contributions | |
strangers | +0.210 |
tresp | +0.195 |
vern | +0.184 |
cruel | +0.178 |
supposed | +0.178 |
Neg logit contributions | |
Of | -0.147 |
cy | -0.145 |
sc | -0.140 |
girl | -0.139 |
onto | -0.130 |
Token | not |
Token ID | 407 |
Feature activation | -5.09e+00 |
Pos logit contributions | |
strangers | +0.155 |
tresp | +0.140 |
vern | +0.137 |
unts | +0.127 |
eping | +0.125 |
Neg logit contributions | |
Of | -0.184 |
cy | -0.178 |
girl | -0.176 |
Sure | -0.167 |
sc | -0.166 |
Token | to |
Token ID | 284 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
strangers | +0.308 |
vern | +0.285 |
tresp | +0.282 |
unts | +0.256 |
cruel | +0.255 |
Neg logit contributions | |
Of | -0.255 |
cy | -0.254 |
girl | -0.239 |
sc | -0.233 |
down | -0.229 |
Token | follow |
Token ID | 1061 |
Feature activation | +2.88e+00 |
Pos logit contributions | |
vern | +0.063 |
strangers | +0.062 |
tresp | +0.061 |
eping | +0.057 |
supposed | +0.056 |
Neg logit contributions | |
cy | -0.052 |
Of | -0.051 |
girl | -0.050 |
down | -0.047 |
up | -0.046 |
Token | strangers |
Token ID | 18981 |
Feature activation | -1.59e+01 |
Pos logit contributions | |
Of | +0.132 |
cy | +0.130 |
up | +0.128 |
down | +0.127 |
girl | +0.124 |
Neg logit contributions | |
vern | -0.171 |
strangers | -0.167 |
tresp | -0.166 |
unts | -0.159 |
supposed | -0.158 |
Token | . |
Token ID | 13 |
Feature activation | -5.62e-01 |
Pos logit contributions | |
strangers | +1.083 |
tresp | +0.994 |
vern | +0.959 |
cruel | +0.917 |
supposed | +0.910 |
Neg logit contributions | |
cy | -0.700 |
Of | -0.695 |
sc | -0.651 |
girl | -0.642 |
Sure | -0.619 |
Token | They |
Token ID | 1119 |
Feature activation | +4.38e-01 |
Pos logit contributions | |
strangers | +0.037 |
tresp | +0.034 |
vern | +0.032 |
unts | +0.031 |
cruel | +0.031 |
Neg logit contributions | |
cy | -0.026 |
Of | -0.026 |
sc | -0.025 |
girl | -0.024 |
Sure | -0.023 |
Token | learned |
Token ID | 4499 |
Feature activation | -6.45e+00 |
Pos logit contributions | |
cy | +0.027 |
girl | +0.026 |
Of | +0.023 |
cash | +0.023 |
boy | +0.023 |
Neg logit contributions | |
strangers | -0.022 |
ills | -0.020 |
vern | -0.020 |
eping | -0.020 |
tresp | -0.020 |
Token | to |
Token ID | 284 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
strangers | +0.393 |
tresp | +0.357 |
vern | +0.336 |
cod | +0.328 |
unts | +0.328 |
Neg logit contributions | |
Of | -0.329 |
cy | -0.309 |
girl | -0.303 |
sc | -0.297 |
Sure | -0.295 |
Token | stay |
Token ID | 2652 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
strangers | +0.058 |
tresp | +0.052 |
vern | +0.049 |
cruel | +0.048 |
eping | +0.047 |
Neg logit contributions | |
Of | -0.059 |
cy | -0.059 |
girl | -0.057 |
sc | -0.054 |
Sure | -0.053 |
Token | that |
Token ID | 326 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
strangers | +0.379 |
tresp | +0.342 |
cod | +0.320 |
vern | +0.319 |
supposed | +0.311 |
Neg logit contributions | |
Of | -0.347 |
girl | -0.318 |
cy | -0.315 |
up | -0.312 |
Sure | -0.311 |
Token | they |
Token ID | 484 |
Feature activation | -2.45e-01 |
Pos logit contributions | |
strangers | +0.079 |
tresp | +0.071 |
vern | +0.069 |
cruel | +0.064 |
unts | +0.064 |
Neg logit contributions | |
Of | -0.081 |
cy | -0.078 |
girl | -0.075 |
sc | -0.074 |
Sure | -0.073 |
Token | should |
Token ID | 815 |
Feature activation | -7.59e+00 |
Pos logit contributions | |
strangers | +0.013 |
tresp | +0.013 |
ules | +0.012 |
vern | +0.012 |
eping | +0.012 |
Neg logit contributions | |
cy | -0.014 |
girl | -0.013 |
fits | -0.013 |
up | -0.013 |
Of | -0.012 |
Token | not |
Token ID | 407 |
Feature activation | -5.02e+00 |
Pos logit contributions | |
strangers | +0.390 |
eping | +0.365 |
tresp | +0.361 |
cod | +0.355 |
ache | +0.337 |
Neg logit contributions | |
Of | -0.412 |
girl | -0.394 |
cy | -0.393 |
up | -0.384 |
with | -0.383 |
Token | trust |
Token ID | 3774 |
Feature activation | -1.78e+00 |
Pos logit contributions | |
strangers | +0.290 |
vern | +0.281 |
tresp | +0.273 |
eping | +0.260 |
cod | +0.253 |
Neg logit contributions | |
Of | -0.256 |
cy | -0.249 |
girl | -0.232 |
down | -0.227 |
sc | -0.223 |
Token | strangers |
Token ID | 18981 |
Feature activation | -1.59e+01 |
Pos logit contributions | |
vern | +0.098 |
tresp | +0.092 |
Days | +0.090 |
strangers | +0.088 |
ache | +0.087 |
Neg logit contributions | |
cy | -0.094 |
Of | -0.091 |
up | -0.090 |
down | -0.090 |
girl | -0.089 |
Token | . |
Token ID | 13 |
Feature activation | -5.60e-01 |
Pos logit contributions | |
strangers | +1.063 |
tresp | +1.040 |
vern | +1.038 |
eping | +1.004 |
unts | +0.998 |
Neg logit contributions | |
cy | -0.650 |
sc | -0.608 |
Of | -0.605 |
girl | -0.597 |
up | -0.585 |
Token | They |
Token ID | 1119 |
Feature activation | +4.68e-01 |
Pos logit contributions | |
strangers | +0.039 |
tresp | +0.036 |
vern | +0.034 |
cruel | +0.033 |
supposed | +0.033 |
Neg logit contributions | |
Of | -0.024 |
cy | -0.024 |
sc | -0.022 |
girl | -0.022 |
Sure | -0.022 |
Token | learned |
Token ID | 4499 |
Feature activation | -6.45e+00 |
Pos logit contributions | |
girl | +0.029 |
cy | +0.029 |
Of | +0.027 |
boy | +0.026 |
up | +0.025 |
Neg logit contributions | |
strangers | -0.023 |
eping | -0.021 |
tresp | -0.021 |
ills | -0.020 |
supposed | -0.019 |
Token | that |
Token ID | 326 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
strangers | +0.373 |
tresp | +0.337 |
vern | +0.314 |
cod | +0.313 |
supposed | +0.307 |
Neg logit contributions | |
Of | -0.350 |
girl | -0.321 |
cy | -0.320 |
Sure | -0.315 |
up | -0.315 |
Token | they |
Token ID | 484 |
Feature activation | -2.26e-01 |
Pos logit contributions | |
strangers | +0.080 |
tresp | +0.073 |
vern | +0.072 |
unts | +0.066 |
cruel | +0.065 |
Neg logit contributions | |
Of | -0.079 |
cy | -0.076 |
girl | -0.073 |
sc | -0.071 |
Sure | -0.071 |
Token | promised |
Token ID | 8072 |
Feature activation | -1.98e+00 |
Pos logit contributions | |
strangers | +0.157 |
tresp | +0.140 |
vern | +0.132 |
cruel | +0.126 |
supposed | +0.125 |
Neg logit contributions | |
Of | -0.145 |
cy | -0.144 |
sc | -0.136 |
girl | -0.135 |
Sure | -0.132 |
Token | never |
Token ID | 1239 |
Feature activation | -6.67e+00 |
Pos logit contributions | |
strangers | +0.130 |
tresp | +0.119 |
vern | +0.114 |
cruel | +0.109 |
supposed | +0.108 |
Neg logit contributions | |
Of | -0.093 |
cy | -0.091 |
girl | -0.085 |
sc | -0.085 |
Sure | -0.083 |
Token | to |
Token ID | 284 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
strangers | +0.429 |
tresp | +0.383 |
vern | +0.362 |
cruel | +0.352 |
supposed | +0.351 |
Neg logit contributions | |
cy | -0.328 |
Of | -0.326 |
sc | -0.309 |
girl | -0.300 |
Sure | -0.297 |
Token | frown |
Token ID | 22002 |
Feature activation | -2.00e+00 |
Pos logit contributions | |
strangers | +0.064 |
tresp | +0.059 |
vern | +0.058 |
cod | +0.054 |
cruel | +0.053 |
Neg logit contributions | |
Of | -0.057 |
cy | -0.056 |
girl | -0.053 |
down | -0.050 |
sc | -0.050 |
Token | on |
Token ID | 319 |
Feature activation | +3.59e+00 |
Pos logit contributions | |
strangers | +0.147 |
tresp | +0.131 |
vern | +0.126 |
cruel | +0.124 |
supposed | +0.123 |
Neg logit contributions | |
Of | -0.080 |
cy | -0.079 |
sc | -0.073 |
Sure | -0.072 |
girl | -0.071 |
Token | strangers |
Token ID | 18981 |
Feature activation | -1.59e+01 |
Pos logit contributions | |
Of | +0.162 |
cy | +0.159 |
girl | +0.151 |
sc | +0.147 |
up | +0.144 |
Neg logit contributions | |
strangers | -0.226 |
vern | -0.213 |
tresp | -0.212 |
unts | -0.200 |
supposed | -0.200 |
Token | again |
Token ID | 757 |
Feature activation | +4.24e+00 |
Pos logit contributions | |
strangers | +1.224 |
tresp | +1.105 |
vern | +1.062 |
cruel | +1.028 |
supposed | +1.022 |
Neg logit contributions | |
Of | -0.577 |
cy | -0.567 |
sc | -0.518 |
girl | -0.511 |
Sure | -0.506 |
Token | . |
Token ID | 13 |
Feature activation | -6.46e-02 |
Pos logit contributions | |
Of | +0.183 |
cy | +0.182 |
girl | +0.168 |
sc | +0.166 |
Sure | +0.161 |
Neg logit contributions | |
strangers | -0.291 |
tresp | -0.269 |
vern | -0.260 |
cruel | -0.247 |
supposed | -0.245 |
Token | They |
Token ID | 1119 |
Feature activation | +6.48e-01 |
Pos logit contributions | |
strangers | +0.005 |
tresp | +0.004 |
vern | +0.004 |
unts | +0.004 |
supposed | +0.004 |
Neg logit contributions | |
cy | -0.003 |
Of | -0.003 |
sc | -0.002 |
girl | -0.002 |
tin | -0.002 |
Token | also |
Token ID | 635 |
Feature activation | -2.46e+00 |
Pos logit contributions | |
cy | +0.036 |
girl | +0.032 |
Of | +0.031 |
onto | +0.031 |
down | +0.030 |
Neg logit contributions | |
strangers | -0.039 |
vern | -0.036 |
tresp | -0.036 |
supposed | -0.033 |
cod | -0.033 |
Token | promised |
Token ID | 8072 |
Feature activation | -1.98e+00 |
Pos logit contributions | |
strangers | +0.142 |
vern | +0.127 |
tresp | +0.124 |
supposed | +0.115 |
Days | +0.113 |
Neg logit contributions | |
cy | -0.142 |
Of | -0.131 |
girl | -0.131 |
tin | -0.122 |
onto | -0.120 |
Token | to |
Token ID | 284 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
strangers | +0.073 |
tresp | +0.066 |
vern | +0.064 |
cruel | +0.061 |
supposed | +0.060 |
Neg logit contributions | |
cy | -0.059 |
Of | -0.059 |
girl | -0.056 |
sc | -0.055 |
Sure | -0.053 |
Token | their |
Token ID | 511 |
Feature activation | -2.08e+00 |
Pos logit contributions | |
vern | +0.064 |
ache | +0.062 |
tresp | +0.060 |
eping | +0.059 |
strangers | +0.058 |
Neg logit contributions | |
Of | -0.048 |
girl | -0.045 |
up | -0.043 |
cy | -0.043 |
down | -0.041 |
Token | friends |
Token ID | 2460 |
Feature activation | -8.33e-01 |
Pos logit contributions | |
strangers | +0.119 |
tresp | +0.109 |
vern | +0.106 |
supposed | +0.101 |
cruel | +0.099 |
Neg logit contributions | |
cy | -0.113 |
Of | -0.111 |
girl | -0.108 |
sc | -0.100 |
Sure | -0.100 |
Token | and |
Token ID | 290 |
Feature activation | -2.98e+00 |
Pos logit contributions | |
strangers | +0.056 |
tresp | +0.053 |
vern | +0.050 |
cruel | +0.049 |
supposed | +0.049 |
Neg logit contributions | |
cy | -0.036 |
Of | -0.036 |
sc | -0.034 |
girl | -0.034 |
down | -0.031 |
Token | to |
Token ID | 284 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
strangers | +0.165 |
tresp | +0.150 |
vern | +0.145 |
eping | +0.138 |
cod | +0.136 |
Neg logit contributions | |
Of | -0.166 |
cy | -0.161 |
girl | -0.159 |
Sure | -0.149 |
sc | -0.148 |
Token | strangers |
Token ID | 18981 |
Feature activation | -1.59e+01 |
Pos logit contributions | |
strangers | +0.056 |
vern | +0.056 |
ache | +0.056 |
tresp | +0.055 |
eping | +0.054 |
Neg logit contributions | |
Of | -0.053 |
girl | -0.050 |
cy | -0.049 |
up | -0.048 |
down | -0.048 |
Token | . |
Token ID | 13 |
Feature activation | -4.76e-01 |
Pos logit contributions | |
strangers | +1.130 |
tresp | +1.069 |
vern | +1.040 |
supposed | +0.993 |
cruel | +0.985 |
Neg logit contributions | |
cy | -0.634 |
Of | -0.613 |
girl | -0.581 |
sc | -0.578 |
down | -0.540 |
Token | They |
Token ID | 1119 |
Feature activation | +5.67e-01 |
Pos logit contributions | |
strangers | +0.033 |
tresp | +0.030 |
vern | +0.029 |
cruel | +0.028 |
supposed | +0.028 |
Neg logit contributions | |
Of | -0.021 |
cy | -0.021 |
sc | -0.019 |
girl | -0.019 |
Sure | -0.019 |
Token | hugged |
Token ID | 41130 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
cy | +0.035 |
girl | +0.034 |
Of | +0.030 |
sc | +0.029 |
boy | +0.029 |
Neg logit contributions | |
strangers | -0.029 |
eping | -0.026 |
ills | -0.026 |
tresp | -0.025 |
supposed | -0.025 |
Token | each |
Token ID | 1123 |
Feature activation | -4.57e+00 |
Pos logit contributions | |
strangers | +0.116 |
vern | +0.114 |
tresp | +0.114 |
supposed | +0.109 |
cruel | +0.102 |
Neg logit contributions | |
cy | -0.097 |
Of | -0.097 |
girl | -0.095 |
down | -0.088 |
sc | -0.088 |
Token | other |
Token ID | 584 |
Feature activation | -2.85e-01 |
Pos logit contributions | |
strangers | +0.302 |
tresp | +0.281 |
vern | +0.272 |
cruel | +0.259 |
supposed | +0.257 |
Neg logit contributions | |
cy | -0.206 |
Of | -0.205 |
girl | -0.200 |
sc | -0.193 |
Sure | -0.182 |
Token | friends |
Token ID | 2460 |
Feature activation | -7.38e-01 |
Pos logit contributions | |
strangers | +0.023 |
tresp | +0.021 |
vern | +0.019 |
supposed | +0.019 |
cruel | +0.019 |
Neg logit contributions | |
Of | -0.018 |
cy | -0.018 |
sc | -0.017 |
Sure | -0.016 |
girl | -0.016 |
Token | and |
Token ID | 290 |
Feature activation | -2.86e+00 |
Pos logit contributions | |
strangers | +0.050 |
tresp | +0.046 |
vern | +0.044 |
cruel | +0.042 |
unts | +0.042 |
Neg logit contributions | |
cy | -0.033 |
Of | -0.033 |
sc | -0.031 |
girl | -0.030 |
Sure | -0.029 |
Token | not |
Token ID | 407 |
Feature activation | -5.05e+00 |
Pos logit contributions | |
strangers | +0.153 |
tresp | +0.136 |
vern | +0.131 |
cruel | +0.122 |
unts | +0.121 |
Neg logit contributions | |
Of | -0.167 |
cy | -0.166 |
girl | -0.158 |
sc | -0.157 |
Sure | -0.153 |
Token | talking |
Token ID | 3375 |
Feature activation | -6.06e-01 |
Pos logit contributions | |
strangers | +0.263 |
vern | +0.238 |
tresp | +0.235 |
unts | +0.212 |
cruel | +0.211 |
Neg logit contributions | |
Of | -0.293 |
cy | -0.290 |
girl | -0.284 |
sc | -0.271 |
down | -0.270 |
Token | to |
Token ID | 284 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
strangers | +0.041 |
tresp | +0.039 |
vern | +0.038 |
cod | +0.036 |
unts | +0.036 |
Neg logit contributions | |
Of | -0.025 |
cy | -0.024 |
sc | -0.023 |
down | -0.023 |
girl | -0.023 |
Token | strangers |
Token ID | 18981 |
Feature activation | -1.59e+01 |
Pos logit contributions | |
vern | +0.064 |
tresp | +0.059 |
eping | +0.055 |
strangers | +0.055 |
unts | +0.055 |
Neg logit contributions | |
girl | -0.054 |
Of | -0.054 |
down | -0.050 |
cy | -0.050 |
up | -0.050 |
Token | . |
Token ID | 13 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
strangers | +1.102 |
tresp | +1.032 |
vern | +1.014 |
unts | +0.962 |
cruel | +0.958 |
Neg logit contributions | |
cy | -0.658 |
Of | -0.642 |
sc | -0.614 |
girl | -0.608 |
down | -0.576 |
Token | Lily |
Token ID | 20037 |
Feature activation | +3.84e+00 |
Pos logit contributions | |
strangers | +0.011 |
hated | +0.010 |
shouldn | +0.009 |
never | +0.009 |
unts | +0.009 |
Neg logit contributions | |
cy | -0.008 |
cer | -0.008 |
sc | -0.007 |
mixture | -0.007 |
fl | -0.007 |
Token | thought |
Token ID | 1807 |
Feature activation | +3.38e+00 |
Pos logit contributions | |
cy | +0.209 |
Of | +0.207 |
girl | +0.200 |
sc | +0.194 |
Sure | +0.187 |
Neg logit contributions | |
strangers | -0.224 |
tresp | -0.202 |
vern | -0.195 |
supposed | -0.183 |
cruel | -0.180 |
Token | that |
Token ID | 326 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
up | +0.159 |
Of | +0.141 |
onto | +0.138 |
girl | +0.133 |
down | +0.131 |
Neg logit contributions | |
cod | -0.211 |
unts | -0.209 |
tresp | -0.205 |
vern | -0.201 |
liar | -0.196 |
Token | was |
Token ID | 373 |
Feature activation | +2.58e+00 |
Pos logit contributions | |
strangers | +0.097 |
tresp | +0.088 |
vern | +0.086 |
cruel | +0.081 |
unts | +0.081 |
Neg logit contributions | |
Of | -0.069 |
cy | -0.067 |
girl | -0.064 |
sc | -0.063 |
Sure | -0.061 |
Token | " |
Token ID | 366 |
Feature activation | -3.12e+00 |
Pos logit contributions | |
Of | +0.013 |
cy | +0.012 |
girl | +0.011 |
sc | +0.011 |
Sure | +0.011 |
Neg logit contributions | |
strangers | -0.019 |
tresp | -0.017 |
vern | -0.016 |
supposed | -0.016 |
cruel | -0.015 |
Token | You |
Token ID | 1639 |
Feature activation | +2.87e+00 |
Pos logit contributions | |
strangers | +0.195 |
tresp | +0.168 |
never | +0.167 |
vern | +0.166 |
cruel | +0.164 |
Neg logit contributions | |
cy | -0.142 |
Of | -0.141 |
sc | -0.140 |
onto | -0.136 |
suit | -0.135 |
Token | shouldn |
Token ID | 6584 |
Feature activation | -1.24e+01 |
Pos logit contributions | |
cy | +0.167 |
girl | +0.160 |
Of | +0.157 |
onto | +0.147 |
fits | +0.147 |
Neg logit contributions | |
strangers | -0.161 |
vern | -0.134 |
tresp | -0.132 |
Days | -0.132 |
cod | -0.132 |
Token | 't |
Token ID | 470 |
Feature activation | -3.55e+00 |
Pos logit contributions | |
strangers | +0.671 |
tresp | +0.591 |
vern | +0.556 |
cod | +0.539 |
cruel | +0.537 |
Neg logit contributions | |
Of | -0.739 |
cy | -0.720 |
girl | -0.687 |
sc | -0.678 |
Sure | -0.663 |
Token | trust |
Token ID | 3774 |
Feature activation | -1.83e+00 |
Pos logit contributions | |
strangers | +0.201 |
tresp | +0.181 |
vern | +0.175 |
cruel | +0.164 |
supposed | +0.162 |
Neg logit contributions | |
Of | -0.201 |
cy | -0.199 |
girl | -0.186 |
sc | -0.184 |
Sure | -0.179 |
Token | strangers |
Token ID | 18981 |
Feature activation | -1.59e+01 |
Pos logit contributions | |
vern | +0.118 |
tresp | +0.115 |
strangers | +0.112 |
cod | +0.110 |
unts | +0.110 |
Neg logit contributions | |
Of | -0.076 |
cy | -0.073 |
up | -0.073 |
down | -0.073 |
girl | -0.073 |
Token | !" |
Token ID | 2474 |
Feature activation | -6.94e-01 |
Pos logit contributions | |
strangers | +1.075 |
tresp | +1.004 |
vern | +1.003 |
unts | +0.953 |
cruel | +0.943 |
Neg logit contributions | |
cy | -0.675 |
Of | -0.657 |
sc | -0.632 |
girl | -0.621 |
down | -0.599 |
Token | in |
Token ID | 287 |
Feature activation | +2.37e+00 |
Pos logit contributions | |
strangers | +0.042 |
hated | +0.037 |
unts | +0.036 |
never | +0.036 |
tresp | +0.035 |
Neg logit contributions | |
cy | -0.033 |
sc | -0.032 |
suit | -0.030 |
tin | -0.030 |
Of | -0.030 |
Token | a |
Token ID | 257 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
Of | +0.117 |
cy | +0.117 |
sc | +0.110 |
girl | +0.108 |
Sure | +0.106 |
Neg logit contributions | |
strangers | -0.152 |
tresp | -0.136 |
vern | -0.130 |
cruel | -0.125 |
supposed | -0.123 |
Token | harsh |
Token ID | 11859 |
Feature activation | -5.57e+00 |
Pos logit contributions | |
Of | +0.074 |
cy | +0.073 |
girl | +0.072 |
sc | +0.070 |
Sure | +0.067 |
Neg logit contributions | |
strangers | -0.076 |
tresp | -0.068 |
vern | -0.064 |
supposed | -0.063 |
isdom | -0.060 |
Token | voice |
Token ID | 3809 |
Feature activation | +2.52e+00 |
Pos logit contributions | |
strangers | +0.391 |
tresp | +0.359 |
vern | +0.348 |
supposed | +0.332 |
cruel | +0.330 |
Neg logit contributions | |
Of | -0.235 |
cy | -0.232 |
girl | -0.218 |
sc | -0.213 |
Sure | -0.206 |
Token | be |
Token ID | 307 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
strangers | +0.070 |
tresp | +0.067 |
vern | +0.067 |
unts | +0.066 |
eping | +0.064 |
Neg logit contributions | |
cy | -0.047 |
Of | -0.046 |
girl | -0.045 |
up | -0.042 |
down | -0.039 |
Token | patient |
Token ID | 5827 |
Feature activation | +5.88e-01 |
Pos logit contributions | |
Of | +0.079 |
cy | +0.079 |
girl | +0.077 |
sc | +0.074 |
down | +0.073 |
Neg logit contributions | |
strangers | -0.063 |
tresp | -0.054 |
vern | -0.052 |
unts | -0.048 |
supposed | -0.047 |
Token | and |
Token ID | 290 |
Feature activation | -2.88e+00 |
Pos logit contributions | |
cy | +0.029 |
Of | +0.029 |
girl | +0.027 |
sc | +0.027 |
Sure | +0.026 |
Neg logit contributions | |
strangers | -0.037 |
tresp | -0.033 |
vern | -0.032 |
cruel | -0.031 |
unts | -0.030 |
Token | not |
Token ID | 407 |
Feature activation | -5.01e+00 |
Pos logit contributions | |
strangers | +0.137 |
tresp | +0.120 |
vern | +0.114 |
unts | +0.105 |
supposed | +0.103 |
Neg logit contributions | |
Of | -0.186 |
cy | -0.183 |
girl | -0.177 |
sc | -0.174 |
Sure | -0.172 |
Token | trust |
Token ID | 3774 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
strangers | +0.289 |
vern | +0.287 |
tresp | +0.265 |
isdom | +0.250 |
eping | +0.249 |
Neg logit contributions | |
Of | -0.248 |
cy | -0.247 |
girl | -0.239 |
down | -0.235 |
sc | -0.223 |
Token | strangers |
Token ID | 18981 |
Feature activation | -1.59e+01 |
Pos logit contributions | |
vern | +0.090 |
tresp | +0.081 |
Days | +0.079 |
cod | +0.077 |
strangers | +0.077 |
Neg logit contributions | |
down | -0.098 |
cy | -0.097 |
up | -0.096 |
into | -0.094 |
girl | -0.092 |
Token | . |
Token ID | 13 |
Feature activation | -2.27e-01 |
Pos logit contributions | |
strangers | +1.106 |
tresp | +1.042 |
vern | +1.039 |
unts | +0.992 |
cruel | +0.979 |
Neg logit contributions | |
cy | -0.639 |
Of | -0.607 |
sc | -0.594 |
girl | -0.580 |
down | -0.560 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -7.11e+00 |
Pos logit contributions | |
strangers | +0.014 |
tresp | +0.012 |
vern | +0.012 |
unts | +0.011 |
hated | +0.011 |
Neg logit contributions | |
cy | -0.012 |
Of | -0.011 |
sc | -0.011 |
girl | -0.011 |
tin | -0.010 |
Token | Once |
Token ID | 7454 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
strangers | +0.417 |
tresp | +0.372 |
vern | +0.353 |
unts | +0.345 |
supposed | +0.337 |
Neg logit contributions | |
Of | -0.366 |
cy | -0.359 |
girl | -0.343 |
sc | -0.338 |
mixture | -0.337 |
Token | upon |
Token ID | 2402 |
Feature activation | -3.53e-01 |
Pos logit contributions | |
strangers | +0.013 |
tresp | +0.012 |
cod | +0.011 |
vern | +0.011 |
cruel | +0.011 |
Neg logit contributions | |
cy | -0.006 |
Of | -0.006 |
girl | -0.005 |
Sure | -0.005 |
up | -0.005 |
Token | a |
Token ID | 257 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
strangers | +0.027 |
tresp | +0.025 |
vern | +0.024 |
cruel | +0.023 |
isdom | +0.023 |
Neg logit contributions | |
Of | -0.012 |
cy | -0.012 |
girl | -0.012 |
sc | -0.011 |
Sure | -0.011 |
Token | shy |
Token ID | 15800 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
strangers | +0.060 |
tresp | +0.053 |
vern | +0.051 |
isdom | +0.048 |
Days | +0.047 |
Neg logit contributions | |
cy | -0.063 |
Of | -0.062 |
girl | -0.061 |
sc | -0.058 |
tin | -0.057 |
Token | and |
Token ID | 290 |
Feature activation | -3.14e+00 |
Pos logit contributions | |
strangers | +0.105 |
tresp | +0.096 |
vern | +0.093 |
cruel | +0.088 |
supposed | +0.087 |
Neg logit contributions | |
Of | -0.074 |
cy | -0.074 |
girl | -0.069 |
sc | -0.069 |
Sure | -0.066 |
Token | does |
Token ID | 857 |
Feature activation | +7.49e-03 |
Pos logit contributions | |
strangers | +0.155 |
vern | +0.139 |
tresp | +0.138 |
unts | +0.124 |
supposed | +0.122 |
Neg logit contributions | |
Of | -0.191 |
cy | -0.189 |
girl | -0.184 |
sc | -0.180 |
down | -0.176 |
Token | not |
Token ID | 407 |
Feature activation | -5.00e+00 |
Pos logit contributions | |
up | +0.001 |
Of | +0.001 |
down | +0.001 |
onto | +0.000 |
girl | +0.000 |
Neg logit contributions | |
strangers | -0.000 |
tresp | -0.000 |
vern | -0.000 |
unts | -0.000 |
ills | -0.000 |
Token | like |
Token ID | 588 |
Feature activation | -6.43e-01 |
Pos logit contributions | |
strangers | +0.239 |
vern | +0.224 |
tresp | +0.222 |
Days | +0.198 |
isdom | +0.195 |
Neg logit contributions | |
cy | -0.300 |
girl | -0.298 |
Of | -0.294 |
down | -0.281 |
sc | -0.277 |
Token | strangers |
Token ID | 18981 |
Feature activation | -1.59e+01 |
Pos logit contributions | |
strangers | +0.038 |
vern | +0.038 |
tresp | +0.037 |
unts | +0.035 |
cod | +0.034 |
Neg logit contributions | |
Of | -0.030 |
girl | -0.029 |
cy | -0.028 |
down | -0.027 |
up | -0.027 |
Token | ." |
Token ID | 526 |
Feature activation | -7.24e-01 |
Pos logit contributions | |
strangers | +1.086 |
vern | +1.073 |
tresp | +1.056 |
Days | +1.010 |
unts | +1.000 |
Neg logit contributions | |
cy | -0.625 |
Of | -0.589 |
down | -0.585 |
girl | -0.583 |
sc | -0.583 |
Token |
|
Token ID | 198 |
Feature activation | +3.78e-01 |
Pos logit contributions | |
strangers | +0.040 |
tresp | +0.032 |
unts | +0.032 |
vern | +0.031 |
understand | +0.031 |
Neg logit contributions | |
cy | -0.041 |
sc | -0.041 |
mixture | -0.040 |
tin | -0.037 |
umm | -0.036 |
Token |
|
Token ID | 198 |
Feature activation | +3.79e-01 |
Pos logit contributions | |
Of | +0.014 |
cy | +0.013 |
girl | +0.012 |
Sure | +0.012 |
sc | +0.012 |
Neg logit contributions | |
strangers | -0.029 |
tresp | -0.028 |
supposed | -0.026 |
vern | -0.026 |
cruel | -0.025 |
Token | " |
Token ID | 1 |
Feature activation | -5.91e+00 |
Pos logit contributions | |
Of | +0.018 |
cy | +0.018 |
sc | +0.017 |
girl | +0.017 |
Sure | +0.016 |
Neg logit contributions | |
strangers | -0.025 |
tresp | -0.022 |
vern | -0.022 |
cruel | -0.021 |
supposed | -0.020 |
Token | Thank |
Token ID | 10449 |
Feature activation | +4.77e+00 |
Pos logit contributions | |
strangers | +0.376 |
cruel | +0.333 |
Days | +0.323 |
vern | +0.316 |
tresp | +0.314 |
Neg logit contributions | |
cy | -0.280 |
onto | -0.278 |
down | -0.277 |
up | -0.275 |
into | -0.258 |
Token | . |
Token ID | 13 |
Feature activation | -7.23e-01 |
Pos logit contributions | |
cy | +0.157 |
Of | +0.156 |
girl | +0.146 |
sc | +0.134 |
Sure | +0.134 |
Neg logit contributions | |
strangers | -0.302 |
tresp | -0.284 |
vern | -0.277 |
cruel | -0.264 |
supposed | -0.259 |
Token | They |
Token ID | 1119 |
Feature activation | +2.56e-02 |
Pos logit contributions | |
strangers | +0.042 |
tresp | +0.036 |
unts | +0.035 |
hated | +0.034 |
vern | +0.033 |
Neg logit contributions | |
cy | -0.040 |
sc | -0.039 |
Of | -0.037 |
mixture | -0.037 |
girl | -0.036 |
Token | do |
Token ID | 466 |
Feature activation | -2.30e+00 |
Pos logit contributions | |
cy | +0.001 |
girl | +0.001 |
tin | +0.001 |
Of | +0.001 |
up | +0.001 |
Neg logit contributions | |
strangers | -0.002 |
vern | -0.001 |
eping | -0.001 |
ills | -0.001 |
supposed | -0.001 |
Token | not |
Token ID | 407 |
Feature activation | -5.09e+00 |
Pos logit contributions | |
strangers | +0.089 |
tresp | +0.079 |
vern | +0.071 |
cod | +0.067 |
ache | +0.065 |
Neg logit contributions | |
up | -0.162 |
Of | -0.160 |
cy | -0.153 |
girl | -0.151 |
with | -0.150 |
Token | follow |
Token ID | 1061 |
Feature activation | +2.99e+00 |
Pos logit contributions | |
vern | +0.274 |
strangers | +0.268 |
tresp | +0.260 |
Days | +0.241 |
cod | +0.236 |
Neg logit contributions | |
cy | -0.286 |
girl | -0.270 |
Of | -0.257 |
down | -0.253 |
with | -0.240 |
Token | strangers |
Token ID | 18981 |
Feature activation | -1.59e+01 |
Pos logit contributions | |
Of | +0.159 |
cy | +0.157 |
girl | +0.150 |
sc | +0.146 |
down | +0.142 |
Neg logit contributions | |
strangers | -0.168 |
tresp | -0.158 |
vern | -0.156 |
supposed | -0.144 |
cruel | -0.143 |
Token | . |
Token ID | 13 |
Feature activation | -7.18e-01 |
Pos logit contributions | |
strangers | +1.075 |
tresp | +0.997 |
vern | +0.969 |
cruel | +0.922 |
unts | +0.915 |
Neg logit contributions | |
cy | -0.695 |
Of | -0.683 |
sc | -0.644 |
girl | -0.636 |
Sure | -0.608 |
Token | They |
Token ID | 1119 |
Feature activation | +5.15e-02 |
Pos logit contributions | |
strangers | +0.045 |
tresp | +0.039 |
unts | +0.037 |
vern | +0.037 |
hated | +0.036 |
Neg logit contributions | |
cy | -0.037 |
sc | -0.036 |
Of | -0.035 |
girl | -0.034 |
mixture | -0.033 |
Token | are |
Token ID | 389 |
Feature activation | -4.34e+00 |
Pos logit contributions | |
cy | +0.003 |
girl | +0.002 |
Of | +0.002 |
up | +0.002 |
tin | +0.002 |
Neg logit contributions | |
strangers | -0.003 |
vern | -0.003 |
ills | -0.003 |
eping | -0.003 |
supposed | -0.003 |
Token | polite |
Token ID | 23507 |
Feature activation | -2.36e+00 |
Pos logit contributions | |
strangers | +0.219 |
vern | +0.213 |
isdom | +0.204 |
tresp | +0.201 |
cod | +0.198 |
Neg logit contributions | |
up | -0.242 |
girl | -0.238 |
down | -0.230 |
into | -0.227 |
cy | -0.220 |
Token | and |
Token ID | 290 |
Feature activation | -3.28e+00 |
Pos logit contributions | |
strangers | +0.156 |
tresp | +0.143 |
vern | +0.140 |
cruel | +0.132 |
supposed | +0.131 |
Neg logit contributions | |
cy | -0.107 |
Of | -0.107 |
girl | -0.103 |
sc | -0.098 |
Sure | -0.094 |
Token | it |
Token ID | 340 |
Feature activation | -5.83e-01 |
Pos logit contributions | |
Of | +0.048 |
cy | +0.047 |
sc | +0.044 |
girl | +0.043 |
Sure | +0.042 |
Neg logit contributions | |
strangers | -0.065 |
tresp | -0.058 |
vern | -0.053 |
cruel | -0.052 |
never | -0.051 |
Token | . |
Token ID | 13 |
Feature activation | -2.43e-02 |
Pos logit contributions | |
strangers | +0.041 |
tresp | +0.037 |
vern | +0.036 |
supposed | +0.034 |
cruel | +0.034 |
Neg logit contributions | |
Of | -0.026 |
cy | -0.024 |
girl | -0.022 |
Sure | -0.022 |
sc | -0.021 |
Token | Finally |
Token ID | 9461 |
Feature activation | +6.34e+00 |
Pos logit contributions | |
strangers | +0.001 |
tresp | +0.001 |
hated | +0.001 |
never | +0.001 |
shouldn | +0.001 |
Neg logit contributions | |
cy | -0.001 |
sc | -0.001 |
girl | -0.001 |
fl | -0.001 |
cer | -0.001 |
Token | , |
Token ID | 11 |
Feature activation | +4.94e-01 |
Pos logit contributions | |
cy | +0.348 |
Of | +0.342 |
sc | +0.330 |
girl | +0.315 |
Sure | +0.311 |
Neg logit contributions | |
strangers | -0.378 |
tresp | -0.341 |
vern | -0.311 |
cruel | -0.302 |
hated | -0.291 |
Token | the |
Token ID | 262 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
cy | +0.028 |
sc | +0.028 |
Of | +0.027 |
suit | +0.025 |
girl | +0.025 |
Neg logit contributions | |
strangers | -0.028 |
tresp | -0.024 |
never | -0.023 |
cruel | -0.021 |
understand | -0.020 |
Token | strangers |
Token ID | 18981 |
Feature activation | -1.58e+01 |
Pos logit contributions | |
strangers | +0.064 |
tresp | +0.056 |
vern | +0.052 |
cruel | +0.051 |
supposed | +0.049 |
Neg logit contributions | |
Of | -0.065 |
cy | -0.065 |
sc | -0.062 |
Sure | -0.060 |
girl | -0.058 |
Token | got |
Token ID | 1392 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
strangers | +0.909 |
vern | +0.884 |
tresp | +0.828 |
isdom | +0.795 |
supposed | +0.787 |
Neg logit contributions | |
cy | -0.856 |
sc | -0.811 |
girl | -0.805 |
Of | -0.801 |
onto | -0.775 |
Token | angry |
Token ID | 7954 |
Feature activation | -5.42e+00 |
Pos logit contributions | |
strangers | +0.086 |
tresp | +0.078 |
vern | +0.073 |
cruel | +0.072 |
supposed | +0.072 |
Neg logit contributions | |
Of | -0.050 |
cy | -0.049 |
sc | -0.045 |
Sure | -0.044 |
girl | -0.044 |
Token | . |
Token ID | 13 |
Feature activation | +2.15e-02 |
Pos logit contributions | |
strangers | +0.325 |
tresp | +0.291 |
vern | +0.277 |
cruel | +0.264 |
supposed | +0.262 |
Neg logit contributions | |
Of | -0.287 |
cy | -0.286 |
sc | -0.268 |
girl | -0.266 |
Sure | -0.261 |
Token | They |
Token ID | 1119 |
Feature activation | +5.70e-01 |
Pos logit contributions | |
cy | +0.001 |
sc | +0.001 |
girl | +0.001 |
Of | +0.001 |
tin | +0.001 |
Neg logit contributions | |
strangers | -0.001 |
tresp | -0.001 |
unts | -0.001 |
hated | -0.001 |
vern | -0.001 |
Token | started |
Token ID | 2067 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
cy | +0.027 |
onto | +0.026 |
girl | +0.025 |
down | +0.025 |
into | +0.024 |
Neg logit contributions | |
vern | -0.037 |
strangers | -0.035 |
isdom | -0.034 |
opl | -0.033 |
supposed | -0.032 |
Token | day |
Token ID | 1110 |
Feature activation | +3.74e+00 |
Pos logit contributions | |
strangers | +0.105 |
tresp | +0.094 |
vern | +0.089 |
supposed | +0.089 |
cruel | +0.088 |
Neg logit contributions | |
cy | -0.062 |
Of | -0.060 |
sc | -0.056 |
Sure | -0.054 |
girl | -0.054 |
Token | to |
Token ID | 284 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
Of | +0.175 |
onto | +0.161 |
cy | +0.161 |
Sure | +0.158 |
down | +0.156 |
Neg logit contributions | |
strangers | -0.236 |
tresp | -0.221 |
vern | -0.219 |
cod | -0.217 |
cruel | -0.206 |
Token | be |
Token ID | 307 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
strangers | +0.063 |
tresp | +0.058 |
vern | +0.055 |
supposed | +0.054 |
eping | +0.054 |
Neg logit contributions | |
cy | -0.057 |
Of | -0.056 |
girl | -0.054 |
up | -0.051 |
tin | -0.050 |
Token | careful |
Token ID | 8161 |
Feature activation | -9.81e-01 |
Pos logit contributions | |
girl | +0.075 |
cy | +0.074 |
Of | +0.073 |
down | +0.070 |
up | +0.069 |
Neg logit contributions | |
strangers | -0.065 |
tresp | -0.057 |
vern | -0.055 |
unts | -0.052 |
isdom | -0.050 |
Token | with |
Token ID | 351 |
Feature activation | +9.40e+00 |
Pos logit contributions | |
strangers | +0.072 |
tresp | +0.068 |
vern | +0.065 |
cod | +0.063 |
cruel | +0.062 |
Neg logit contributions | |
cy | -0.036 |
Of | -0.036 |
up | -0.035 |
girl | -0.034 |
sc | -0.034 |
Token | strangers |
Token ID | 18981 |
Feature activation | -1.58e+01 |
Pos logit contributions | |
Of | +0.397 |
girl | +0.396 |
up | +0.396 |
cy | +0.373 |
down | +0.371 |
Neg logit contributions | |
vern | -0.549 |
unts | -0.543 |
strangers | -0.535 |
tresp | -0.529 |
ache | -0.503 |
Token | and |
Token ID | 290 |
Feature activation | -2.87e+00 |
Pos logit contributions | |
strangers | +1.052 |
tresp | +0.978 |
vern | +0.963 |
unts | +0.920 |
cruel | +0.908 |
Neg logit contributions | |
cy | -0.713 |
Of | -0.689 |
sc | -0.663 |
girl | -0.656 |
down | -0.619 |
Token | to |
Token ID | 284 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
strangers | +0.152 |
vern | +0.145 |
tresp | +0.143 |
unts | +0.133 |
eping | +0.133 |
Neg logit contributions | |
Of | -0.158 |
girl | -0.154 |
cy | -0.150 |
Sure | -0.143 |
down | -0.142 |
Token | not |
Token ID | 407 |
Feature activation | -5.00e+00 |
Pos logit contributions | |
strangers | +0.059 |
vern | +0.058 |
tresp | +0.057 |
unts | +0.053 |
eping | +0.053 |
Neg logit contributions | |
Of | -0.055 |
cy | -0.054 |
girl | -0.053 |
up | -0.050 |
down | -0.049 |
Token | trust |
Token ID | 3774 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
strangers | +0.297 |
vern | +0.287 |
tresp | +0.281 |
eping | +0.264 |
cruel | +0.257 |
Neg logit contributions | |
Of | -0.242 |
cy | -0.240 |
girl | -0.228 |
down | -0.218 |
sc | -0.214 |
Token | them |
Token ID | 606 |
Feature activation | -7.24e+00 |
Pos logit contributions | |
vern | +0.090 |
tresp | +0.085 |
strangers | +0.082 |
unts | +0.080 |
eping | +0.079 |
Neg logit contributions | |
cy | -0.099 |
down | -0.097 |
Of | -0.096 |
girl | -0.095 |
up | -0.095 |
Token | match |
Token ID | 2872 |
Feature activation | +7.32e+00 |
Pos logit contributions | |
strangers | +0.157 |
tresp | +0.137 |
vern | +0.130 |
cruel | +0.128 |
supposed | +0.125 |
Neg logit contributions | |
Of | -0.133 |
cy | -0.130 |
sc | -0.128 |
Sure | -0.123 |
suit | -0.116 |
Token | for |
Token ID | 329 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
cy | +0.329 |
Of | +0.324 |
girl | +0.307 |
sc | +0.304 |
down | +0.288 |
Neg logit contributions | |
strangers | -0.483 |
tresp | -0.441 |
vern | -0.429 |
unts | -0.410 |
cruel | -0.408 |
Token | the |
Token ID | 262 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
Of | +0.062 |
girl | +0.057 |
cy | +0.055 |
Me | +0.055 |
onto | +0.055 |
Neg logit contributions | |
strangers | -0.092 |
tresp | -0.089 |
vern | -0.089 |
cod | -0.088 |
unts | -0.087 |
Token | group |
Token ID | 1448 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
strangers | +0.096 |
tresp | +0.086 |
cruel | +0.080 |
vern | +0.079 |
supposed | +0.077 |
Neg logit contributions | |
Of | -0.068 |
cy | -0.067 |
sc | -0.065 |
Sure | -0.063 |
onto | -0.059 |
Token | of |
Token ID | 286 |
Feature activation | -2.35e+00 |
Pos logit contributions | |
strangers | +0.101 |
tresp | +0.093 |
vern | +0.091 |
cruel | +0.086 |
isdom | +0.085 |
Neg logit contributions | |
Of | -0.077 |
cy | -0.077 |
sc | -0.074 |
girl | -0.074 |
onto | -0.068 |
Token | strangers |
Token ID | 18981 |
Feature activation | -1.58e+01 |
Pos logit contributions | |
vern | +0.133 |
strangers | +0.131 |
tresp | +0.128 |
ache | +0.123 |
supposed | +0.123 |
Neg logit contributions | |
girl | -0.114 |
Of | -0.113 |
cy | -0.104 |
up | -0.098 |
tin | -0.098 |
Token | . |
Token ID | 13 |
Feature activation | -2.70e-01 |
Pos logit contributions | |
strangers | +1.089 |
tresp | +1.008 |
vern | +1.002 |
cruel | +0.944 |
unts | +0.939 |
Neg logit contributions | |
cy | -0.680 |
Of | -0.651 |
sc | -0.634 |
girl | -0.624 |
down | -0.595 |
Token | She |
Token ID | 1375 |
Feature activation | -3.15e-01 |
Pos logit contributions | |
strangers | +0.018 |
tresp | +0.016 |
vern | +0.015 |
unts | +0.015 |
supposed | +0.015 |
Neg logit contributions | |
cy | -0.012 |
Of | -0.012 |
sc | -0.012 |
girl | -0.011 |
tin | -0.011 |
Token | realized |
Token ID | 6939 |
Feature activation | -5.14e+00 |
Pos logit contributions | |
strangers | +0.019 |
vern | +0.017 |
tresp | +0.017 |
supposed | +0.016 |
unts | +0.015 |
Neg logit contributions | |
cy | -0.017 |
girl | -0.016 |
Of | -0.016 |
sc | -0.015 |
onto | -0.015 |
Token | that |
Token ID | 326 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
strangers | +0.298 |
tresp | +0.284 |
vern | +0.283 |
unts | +0.282 |
cod | +0.272 |
Neg logit contributions | |
Of | -0.256 |
girl | -0.243 |
up | -0.233 |
onto | -0.232 |
cy | -0.230 |
Token | in |
Token ID | 287 |
Feature activation | +2.43e+00 |
Pos logit contributions | |
strangers | +0.088 |
tresp | +0.080 |
vern | +0.077 |
cruel | +0.073 |
unts | +0.073 |
Neg logit contributions | |
Of | -0.072 |
cy | -0.071 |
girl | -0.067 |
sc | -0.066 |
Sure | -0.064 |
Token | € |
Token ID | 26391 |
Feature activation | +5.30e-01 |
Pos logit contributions | |
strangers | +0.204 |
tresp | +0.186 |
vern | +0.178 |
supposed | +0.175 |
hated | +0.168 |
Neg logit contributions | |
girl | -0.159 |
Of | -0.158 |
cy | -0.155 |
sc | -0.148 |
Sure | -0.148 |
Token | â„¢ |
Token ID | 8151 |
Feature activation | -7.06e+00 |
Pos logit contributions | |
Of | +0.030 |
cy | +0.029 |
Sure | +0.028 |
sc | +0.027 |
girl | +0.026 |
Neg logit contributions | |
strangers | -0.031 |
tresp | -0.027 |
vern | -0.026 |
cruel | -0.026 |
supposed | -0.024 |
Token | t |
Token ID | 83 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
strangers | +0.465 |
tresp | +0.416 |
vern | +0.391 |
cruel | +0.387 |
isdom | +0.375 |
Neg logit contributions | |
cy | -0.342 |
Of | -0.338 |
sc | -0.323 |
Sure | -0.305 |
girl | -0.303 |
Token | scared |
Token ID | 12008 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
strangers | +0.090 |
tresp | +0.080 |
vern | +0.079 |
cruel | +0.072 |
isdom | +0.072 |
Neg logit contributions | |
Of | -0.090 |
cy | -0.089 |
girl | -0.087 |
sc | -0.084 |
down | -0.083 |
Token | of |
Token ID | 286 |
Feature activation | -2.20e+00 |
Pos logit contributions | |
strangers | +0.113 |
tresp | +0.102 |
vern | +0.098 |
cruel | +0.093 |
supposed | +0.092 |
Neg logit contributions | |
Of | -0.087 |
cy | -0.086 |
sc | -0.081 |
girl | -0.080 |
Sure | -0.078 |
Token | strangers |
Token ID | 18981 |
Feature activation | -1.58e+01 |
Pos logit contributions | |
strangers | +0.132 |
vern | +0.124 |
tresp | +0.121 |
unts | +0.117 |
cruel | +0.114 |
Neg logit contributions | |
Of | -0.109 |
cy | -0.101 |
girl | -0.099 |
sc | -0.096 |
Me | -0.096 |
Token | anymore |
Token ID | 7471 |
Feature activation | -5.30e+00 |
Pos logit contributions | |
strangers | +1.044 |
tresp | +0.950 |
vern | +0.921 |
cruel | +0.878 |
unts | +0.870 |
Neg logit contributions | |
cy | -0.730 |
Of | -0.730 |
sc | -0.681 |
girl | -0.674 |
Sure | -0.650 |
Token | - |
Token ID | 532 |
Feature activation | -3.38e+00 |
Pos logit contributions | |
strangers | +0.357 |
tresp | +0.325 |
vern | +0.317 |
cruel | +0.304 |
unts | +0.299 |
Neg logit contributions | |
Of | -0.237 |
cy | -0.232 |
girl | -0.217 |
sc | -0.217 |
Sure | -0.209 |
Token | he |
Token ID | 339 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
strangers | +0.230 |
tresp | +0.210 |
vern | +0.206 |
unts | +0.195 |
cruel | +0.195 |
Neg logit contributions | |
Of | -0.150 |
cy | -0.145 |
girl | -0.137 |
sc | -0.136 |
Sure | -0.132 |
Token | was |
Token ID | 373 |
Feature activation | +2.65e+00 |
Pos logit contributions | |
cy | +0.080 |
Of | +0.077 |
girl | +0.077 |
sc | +0.073 |
Sure | +0.071 |
Neg logit contributions | |
strangers | -0.095 |
vern | -0.090 |
tresp | -0.086 |
unts | -0.080 |
cod | -0.079 |
Token | very |
Token ID | 845 |
Feature activation | -8.82e-01 |
Pos logit contributions | |
Of | +0.139 |
up | +0.137 |
cy | +0.135 |
girl | +0.135 |
down | +0.134 |
Neg logit contributions | |
strangers | -0.143 |
vern | -0.135 |
tresp | -0.128 |
isdom | -0.124 |
cod | -0.123 |
Token | you |
Token ID | 345 |
Feature activation | -9.36e-02 |
Pos logit contributions | |
strangers | +0.238 |
tresp | +0.226 |
vern | +0.219 |
unts | +0.214 |
cruel | +0.208 |
Neg logit contributions | |
cy | -0.175 |
Of | -0.166 |
girl | -0.164 |
sc | -0.160 |
down | -0.158 |
Token | know |
Token ID | 760 |
Feature activation | -4.26e+00 |
Pos logit contributions | |
vern | +0.005 |
Days | +0.005 |
strangers | +0.005 |
tresp | +0.005 |
eping | +0.005 |
Neg logit contributions | |
cy | -0.004 |
down | -0.004 |
up | -0.004 |
into | -0.004 |
girl | -0.004 |
Token | and |
Token ID | 290 |
Feature activation | -2.76e+00 |
Pos logit contributions | |
strangers | +0.283 |
tresp | +0.276 |
unts | +0.275 |
cod | +0.268 |
vern | +0.266 |
Neg logit contributions | |
Of | -0.154 |
up | -0.153 |
girl | -0.151 |
cy | -0.147 |
sc | -0.146 |
Token | not |
Token ID | 407 |
Feature activation | -4.98e+00 |
Pos logit contributions | |
strangers | +0.128 |
tresp | +0.113 |
vern | +0.108 |
cod | +0.099 |
unts | +0.099 |
Neg logit contributions | |
Of | -0.180 |
cy | -0.175 |
girl | -0.172 |
Sure | -0.165 |
sc | -0.165 |
Token | follow |
Token ID | 1061 |
Feature activation | +2.84e+00 |
Pos logit contributions | |
strangers | +0.270 |
vern | +0.255 |
tresp | +0.247 |
cod | +0.225 |
unts | +0.225 |
Neg logit contributions | |
Of | -0.275 |
cy | -0.270 |
girl | -0.264 |
down | -0.251 |
sc | -0.249 |
Token | strangers |
Token ID | 18981 |
Feature activation | -1.58e+01 |
Pos logit contributions | |
Of | +0.133 |
up | +0.131 |
cy | +0.130 |
girl | +0.130 |
down | +0.128 |
Neg logit contributions | |
strangers | -0.159 |
vern | -0.159 |
tresp | -0.158 |
cod | -0.151 |
unts | -0.149 |
Token | , |
Token ID | 11 |
Feature activation | +2.83e-01 |
Pos logit contributions | |
strangers | +1.088 |
tresp | +1.015 |
vern | +0.994 |
unts | +0.951 |
cruel | +0.949 |
Neg logit contributions | |
cy | -0.668 |
Of | -0.648 |
sc | -0.626 |
girl | -0.607 |
down | -0.580 |
Token | even |
Token ID | 772 |
Feature activation | -2.98e+00 |
Pos logit contributions | |
Of | +0.013 |
girl | +0.013 |
cy | +0.012 |
sc | +0.012 |
down | +0.012 |
Neg logit contributions | |
strangers | -0.017 |
vern | -0.017 |
tresp | -0.016 |
unts | -0.016 |
eping | -0.015 |
Token | if |
Token ID | 611 |
Feature activation | +2.79e+00 |
Pos logit contributions | |
strangers | +0.201 |
tresp | +0.176 |
vern | +0.164 |
cruel | +0.164 |
supposed | +0.162 |
Neg logit contributions | |
cy | -0.143 |
Of | -0.141 |
sc | -0.132 |
Sure | -0.129 |
girl | -0.126 |
Token | it |
Token ID | 340 |
Feature activation | -6.81e-01 |
Pos logit contributions | |
Of | +0.111 |
girl | +0.104 |
cy | +0.103 |
sc | +0.096 |
Sure | +0.094 |
Neg logit contributions | |
strangers | -0.191 |
tresp | -0.182 |
vern | -0.181 |
unts | -0.175 |
cod | -0.173 |
Token | 's |
Token ID | 338 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
strangers | +0.048 |
tresp | +0.044 |
vern | +0.044 |
unts | +0.041 |
cruel | +0.041 |
Neg logit contributions | |
cy | -0.028 |
Of | -0.028 |
sc | -0.026 |
girl | -0.026 |
Sure | -0.024 |
Token | . |
Token ID | 13 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
strangers | +0.231 |
tresp | +0.210 |
vern | +0.200 |
supposed | +0.193 |
cruel | +0.192 |
Neg logit contributions | |
cy | -0.155 |
Of | -0.154 |
sc | -0.145 |
girl | -0.139 |
Sure | -0.137 |
Token | Lily |
Token ID | 20037 |
Feature activation | +3.80e+00 |
Pos logit contributions | |
strangers | +0.009 |
hated | +0.007 |
unts | +0.007 |
tresp | +0.007 |
lee | +0.007 |
Neg logit contributions | |
cy | -0.009 |
sc | -0.008 |
Of | -0.008 |
girl | -0.008 |
tin | -0.008 |
Token | learned |
Token ID | 4499 |
Feature activation | -6.43e+00 |
Pos logit contributions | |
cy | +0.173 |
girl | +0.167 |
Of | +0.155 |
up | +0.149 |
sc | +0.149 |
Neg logit contributions | |
strangers | -0.270 |
tresp | -0.239 |
vern | -0.237 |
supposed | -0.223 |
cruel | -0.220 |
Token | that |
Token ID | 326 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
strangers | +0.380 |
tresp | +0.348 |
unts | +0.328 |
cod | +0.325 |
vern | +0.323 |
Neg logit contributions | |
Of | -0.338 |
up | -0.309 |
girl | -0.308 |
cy | -0.301 |
onto | -0.301 |
Token | sometimes |
Token ID | 3360 |
Feature activation | -7.34e-01 |
Pos logit contributions | |
strangers | +0.085 |
tresp | +0.075 |
vern | +0.071 |
cruel | +0.068 |
supposed | +0.068 |
Neg logit contributions | |
cy | -0.081 |
Of | -0.080 |
sc | -0.076 |
girl | -0.075 |
Sure | -0.074 |
Token | strangers |
Token ID | 18981 |
Feature activation | -1.58e+01 |
Pos logit contributions | |
strangers | +0.051 |
tresp | +0.047 |
vern | +0.046 |
unts | +0.044 |
supposed | +0.044 |
Neg logit contributions | |
Of | -0.031 |
cy | -0.029 |
girl | -0.029 |
sc | -0.027 |
down | -0.026 |
Token | can |
Token ID | 460 |
Feature activation | -5.10e+00 |
Pos logit contributions | |
strangers | +0.902 |
vern | +0.869 |
tresp | +0.841 |
Days | +0.797 |
unts | +0.788 |
Neg logit contributions | |
cy | -0.866 |
sc | -0.805 |
Of | -0.796 |
up | -0.781 |
girl | -0.779 |
Token | be |
Token ID | 307 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
strangers | +0.319 |
tresp | +0.304 |
eping | +0.296 |
supposed | +0.292 |
isdom | +0.290 |
Neg logit contributions | |
cy | -0.221 |
up | -0.216 |
Of | -0.209 |
girl | -0.206 |
down | -0.201 |
Token | nice |
Token ID | 3621 |
Feature activation | -5.83e-01 |
Pos logit contributions | |
girl | +0.074 |
down | +0.072 |
up | +0.072 |
cy | +0.071 |
into | +0.069 |
Neg logit contributions | |
strangers | -0.064 |
vern | -0.059 |
tresp | -0.057 |
avi | -0.054 |
asts | -0.054 |
Token | , |
Token ID | 11 |
Feature activation | +2.84e-01 |
Pos logit contributions | |
strangers | +0.036 |
tresp | +0.032 |
vern | +0.031 |
cruel | +0.029 |
supposed | +0.029 |
Neg logit contributions | |
Of | -0.030 |
cy | -0.030 |
sc | -0.028 |
girl | -0.027 |
Sure | -0.027 |
Token | but |
Token ID | 475 |
Feature activation | +4.03e+00 |
Pos logit contributions | |
Of | +0.011 |
cy | +0.010 |
girl | +0.010 |
sc | +0.010 |
Sure | +0.009 |
Neg logit contributions | |
strangers | -0.021 |
tresp | -0.020 |
vern | -0.019 |
unts | -0.018 |
supposed | -0.018 |
Token | is |
Token ID | 318 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
Of | +0.116 |
cy | +0.115 |
sc | +0.108 |
girl | +0.108 |
Sure | +0.101 |
Neg logit contributions | |
strangers | -0.188 |
tresp | -0.173 |
vern | -0.167 |
cruel | -0.158 |
supposed | -0.158 |
Token | dangerous |
Token ID | 4923 |
Feature activation | -1.01e+01 |
Pos logit contributions | |
Of | +0.072 |
girl | +0.069 |
cy | +0.066 |
sc | +0.065 |
up | +0.064 |
Neg logit contributions | |
strangers | -0.066 |
tresp | -0.058 |
vern | -0.057 |
cod | -0.052 |
unts | -0.052 |
Token | . |
Token ID | 13 |
Feature activation | -6.31e-01 |
Pos logit contributions | |
strangers | +0.674 |
tresp | +0.614 |
vern | +0.592 |
cruel | +0.564 |
supposed | +0.559 |
Neg logit contributions | |
Of | -0.462 |
cy | -0.459 |
sc | -0.432 |
girl | -0.431 |
Sure | -0.407 |
Token | You |
Token ID | 921 |
Feature activation | +5.14e+00 |
Pos logit contributions | |
strangers | +0.044 |
tresp | +0.040 |
vern | +0.038 |
unts | +0.037 |
cruel | +0.037 |
Neg logit contributions | |
cy | -0.027 |
Of | -0.025 |
girl | -0.024 |
sc | -0.024 |
mixture | -0.023 |
Token | are |
Token ID | 389 |
Feature activation | -4.20e+00 |
Pos logit contributions | |
cy | +0.280 |
girl | +0.265 |
Of | +0.262 |
fits | +0.257 |
sc | +0.255 |
Neg logit contributions | |
strangers | -0.289 |
vern | -0.267 |
tresp | -0.256 |
Days | -0.249 |
ules | -0.247 |
Token | strangers |
Token ID | 18981 |
Feature activation | -1.58e+01 |
Pos logit contributions | |
strangers | +0.223 |
vern | +0.198 |
tresp | +0.194 |
unts | +0.180 |
cod | +0.177 |
Neg logit contributions | |
Of | -0.236 |
girl | -0.231 |
cy | -0.227 |
up | -0.217 |
tin | -0.214 |
Token | . |
Token ID | 13 |
Feature activation | -7.38e-01 |
Pos logit contributions | |
strangers | +1.105 |
vern | +1.042 |
tresp | +1.032 |
Days | +0.983 |
isdom | +0.979 |
Neg logit contributions | |
cy | -0.637 |
girl | -0.620 |
Of | -0.606 |
sc | -0.601 |
down | -0.572 |
Token | You |
Token ID | 921 |
Feature activation | +5.13e+00 |
Pos logit contributions | |
strangers | +0.053 |
tresp | +0.048 |
unts | +0.044 |
vern | +0.044 |
cruel | +0.043 |
Neg logit contributions | |
cy | -0.031 |
Of | -0.029 |
sc | -0.028 |
girl | -0.028 |
mixture | -0.028 |
Token | are |
Token ID | 389 |
Feature activation | -4.20e+00 |
Pos logit contributions | |
cy | +0.272 |
girl | +0.251 |
sc | +0.249 |
fits | +0.249 |
Of | +0.237 |
Neg logit contributions | |
strangers | -0.290 |
vern | -0.278 |
ules | -0.262 |
Days | -0.258 |
David | -0.255 |
Token | big |
Token ID | 1263 |
Feature activation | -4.37e+00 |
Pos logit contributions | |
strangers | +0.213 |
vern | +0.196 |
tresp | +0.182 |
isdom | +0.175 |
cod | +0.174 |
Neg logit contributions | |
girl | -0.234 |
Of | -0.234 |
up | -0.224 |
cy | -0.223 |
tin | -0.217 |
Token | and |
Token ID | 290 |
Feature activation | -3.24e+00 |
Pos logit contributions | |
strangers | +0.271 |
vern | +0.250 |
tresp | +0.245 |
supposed | +0.231 |
cruel | +0.228 |
Neg logit contributions | |
girl | -0.213 |
cy | -0.210 |
Of | -0.205 |
sc | -0.193 |
down | -0.186 |
Token | away |
Token ID | 1497 |
Feature activation | +7.46e+00 |
Pos logit contributions | |
strangers | +0.267 |
tresp | +0.243 |
vern | +0.228 |
never | +0.226 |
supposed | +0.225 |
Neg logit contributions | |
Of | -0.097 |
cy | -0.091 |
girl | -0.077 |
Sure | -0.076 |
sc | -0.075 |
Token | . |
Token ID | 13 |
Feature activation | +3.01e-03 |
Pos logit contributions | |
cy | +0.391 |
Of | +0.385 |
sc | +0.363 |
girl | +0.349 |
Sure | +0.346 |
Neg logit contributions | |
strangers | -0.467 |
tresp | -0.422 |
vern | -0.391 |
cruel | -0.377 |
supposed | -0.373 |
Token |
|
Token ID | 198 |
Feature activation | +8.93e-01 |
Pos logit contributions | |
cy | +0.000 |
sc | +0.000 |
girl | +0.000 |
Of | +0.000 |
tin | +0.000 |
Neg logit contributions | |
strangers | -0.000 |
tresp | -0.000 |
hated | -0.000 |
unts | -0.000 |
never | -0.000 |
Token |
|
Token ID | 198 |
Feature activation | +8.88e-01 |
Pos logit contributions | |
Of | +0.025 |
Sure | +0.023 |
cy | +0.022 |
sc | +0.022 |
onto | +0.019 |
Neg logit contributions | |
strangers | -0.077 |
tresp | -0.072 |
cruel | -0.068 |
isdom | -0.067 |
vern | -0.067 |
Token | The |
Token ID | 464 |
Feature activation | -2.93e+00 |
Pos logit contributions | |
sc | +0.036 |
Of | +0.036 |
cy | +0.034 |
girl | +0.033 |
Sure | +0.033 |
Neg logit contributions | |
strangers | -0.063 |
tresp | -0.057 |
supposed | -0.054 |
isdom | -0.054 |
vern | -0.054 |
Token | strangers |
Token ID | 18981 |
Feature activation | -1.58e+01 |
Pos logit contributions | |
strangers | +0.158 |
tresp | +0.145 |
vern | +0.143 |
supposed | +0.133 |
unts | +0.133 |
Neg logit contributions | |
girl | -0.166 |
cy | -0.166 |
Of | -0.165 |
sc | -0.152 |
Sure | -0.149 |
Token | began |
Token ID | 2540 |
Feature activation | +2.87e+00 |
Pos logit contributions | |
strangers | +0.956 |
vern | +0.890 |
tresp | +0.872 |
supposed | +0.818 |
isdom | +0.807 |
Neg logit contributions | |
cy | -0.824 |
Of | -0.790 |
girl | -0.776 |
sc | -0.768 |
onto | -0.725 |
Token | to |
Token ID | 284 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
Of | +0.113 |
cy | +0.106 |
girl | +0.102 |
onto | +0.101 |
sc | +0.100 |
Neg logit contributions | |
strangers | -0.203 |
vern | -0.188 |
tresp | -0.186 |
cod | -0.178 |
isdom | -0.176 |
Token | get |
Token ID | 651 |
Feature activation | +8.15e-01 |
Pos logit contributions | |
strangers | +0.056 |
vern | +0.050 |
tresp | +0.049 |
isdom | +0.047 |
supposed | +0.046 |
Neg logit contributions | |
cy | -0.056 |
Of | -0.055 |
girl | -0.054 |
sc | -0.051 |
down | -0.051 |
Token | dangerous |
Token ID | 4923 |
Feature activation | -1.02e+01 |
Pos logit contributions | |
Of | +0.046 |
cy | +0.045 |
sc | +0.043 |
Sure | +0.042 |
girl | +0.041 |
Neg logit contributions | |
strangers | -0.048 |
tresp | -0.042 |
cruel | -0.039 |
vern | -0.038 |
supposed | -0.037 |
Token | . |
Token ID | 13 |
Feature activation | +4.31e-02 |
Pos logit contributions | |
strangers | +0.649 |
tresp | +0.584 |
vern | +0.559 |
cruel | +0.534 |
supposed | +0.530 |
Neg logit contributions | |
Of | -0.498 |
cy | -0.497 |
sc | -0.464 |
girl | -0.460 |
Sure | -0.450 |
Token | them |
Token ID | 606 |
Feature activation | -7.19e+00 |
Pos logit contributions | |
vern | +0.032 |
tresp | +0.032 |
strangers | +0.031 |
supposed | +0.030 |
cod | +0.029 |
Neg logit contributions | |
Of | -0.025 |
girl | -0.024 |
up | -0.023 |
Me | -0.023 |
cy | -0.022 |
Token | to |
Token ID | 284 |
Feature activation | -8.01e-01 |
Pos logit contributions | |
strangers | +0.480 |
tresp | +0.470 |
cod | +0.465 |
opl | +0.462 |
eping | +0.461 |
Neg logit contributions | |
up | -0.286 |
Of | -0.273 |
girl | -0.268 |
down | -0.261 |
into | -0.245 |
Token | stay |
Token ID | 2652 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
strangers | +0.045 |
tresp | +0.043 |
cod | +0.041 |
vern | +0.041 |
supposed | +0.040 |
Neg logit contributions | |
cy | -0.040 |
girl | -0.039 |
Of | -0.038 |
up | -0.037 |
tin | -0.036 |
Token | away |
Token ID | 1497 |
Feature activation | +7.60e+00 |
Pos logit contributions | |
strangers | +0.069 |
tresp | +0.062 |
vern | +0.059 |
cruel | +0.057 |
supposed | +0.056 |
Neg logit contributions | |
Of | -0.050 |
cy | -0.047 |
sc | -0.046 |
Sure | -0.044 |
girl | -0.043 |
Token | from |
Token ID | 422 |
Feature activation | +5.89e+00 |
Pos logit contributions | |
Of | +0.271 |
cy | +0.270 |
sc | +0.245 |
girl | +0.243 |
Sure | +0.234 |
Neg logit contributions | |
strangers | -0.586 |
tresp | -0.539 |
vern | -0.520 |
cruel | -0.501 |
supposed | -0.498 |
Token | strangers |
Token ID | 18981 |
Feature activation | -1.58e+01 |
Pos logit contributions | |
cy | +0.254 |
girl | +0.249 |
Of | +0.244 |
up | +0.241 |
down | +0.239 |
Neg logit contributions | |
vern | -0.373 |
strangers | -0.365 |
tresp | -0.357 |
unts | -0.340 |
ache | -0.334 |
Token | . |
Token ID | 13 |
Feature activation | -3.86e-01 |
Pos logit contributions | |
strangers | +1.121 |
tresp | +1.070 |
vern | +1.063 |
cruel | +1.002 |
unts | +0.998 |
Neg logit contributions | |
cy | -0.622 |
sc | -0.581 |
Of | -0.577 |
girl | -0.571 |
down | -0.549 |
Token | But |
Token ID | 887 |
Feature activation | +8.88e+00 |
Pos logit contributions | |
strangers | +0.028 |
tresp | +0.026 |
vern | +0.025 |
cruel | +0.024 |
supposed | +0.024 |
Neg logit contributions | |
Of | -0.016 |
cy | -0.015 |
girl | -0.014 |
sc | -0.014 |
Sure | -0.014 |
Token | they |
Token ID | 484 |
Feature activation | -2.49e-01 |
Pos logit contributions | |
cy | +0.475 |
Of | +0.475 |
sc | +0.450 |
girl | +0.440 |
Sure | +0.432 |
Neg logit contributions | |
strangers | -0.531 |
tresp | -0.474 |
vern | -0.447 |
cruel | -0.430 |
supposed | -0.424 |
Token | did |
Token ID | 750 |
Feature activation | -2.31e+00 |
Pos logit contributions | |
vern | +0.015 |
opl | +0.015 |
strangers | +0.015 |
eping | +0.014 |
isdom | +0.014 |
Neg logit contributions | |
cy | -0.012 |
girl | -0.012 |
boy | -0.010 |
onto | -0.010 |
into | -0.009 |
Token | not |
Token ID | 407 |
Feature activation | -4.93e+00 |
Pos logit contributions | |
strangers | +0.087 |
tresp | +0.074 |
unts | +0.070 |
vern | +0.067 |
ills | +0.066 |
Neg logit contributions | |
up | -0.166 |
down | -0.160 |
Of | -0.158 |
onto | -0.156 |
cy | -0.156 |
Token | there |
Token ID | 612 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
Of | +0.036 |
sc | +0.035 |
cy | +0.034 |
Sure | +0.033 |
mixture | +0.032 |
Neg logit contributions | |
strangers | -0.044 |
tresp | -0.038 |
hated | -0.036 |
cruel | -0.036 |
vern | -0.036 |
Token | was |
Token ID | 373 |
Feature activation | +3.07e+00 |
Pos logit contributions | |
Of | +0.042 |
cy | +0.042 |
sc | +0.040 |
girl | +0.038 |
Sure | +0.037 |
Neg logit contributions | |
strangers | -0.078 |
tresp | -0.071 |
vern | -0.068 |
supposed | -0.065 |
hated | -0.065 |
Token | a |
Token ID | 257 |
Feature activation | +1.90e+00 |
Pos logit contributions | |
Of | +0.145 |
cy | +0.144 |
sc | +0.136 |
girl | +0.133 |
Sure | +0.131 |
Neg logit contributions | |
strangers | -0.200 |
tresp | -0.180 |
vern | -0.172 |
supposed | -0.166 |
cruel | -0.164 |
Token | happy |
Token ID | 3772 |
Feature activation | -2.93e+00 |
Pos logit contributions | |
girl | +0.087 |
cy | +0.087 |
Of | +0.085 |
Sure | +0.076 |
sc | +0.074 |
Neg logit contributions | |
strangers | -0.129 |
tresp | -0.118 |
vern | -0.116 |
supposed | -0.110 |
isdom | -0.106 |
Token | little |
Token ID | 1310 |
Feature activation | +7.33e-01 |
Pos logit contributions | |
strangers | +0.191 |
tresp | +0.173 |
vern | +0.165 |
cruel | +0.158 |
supposed | +0.157 |
Neg logit contributions | |
Of | -0.140 |
cy | -0.139 |
sc | -0.130 |
girl | -0.128 |
Sure | -0.125 |
Token | boy |
Token ID | 2933 |
Feature activation | +8.94e+00 |
Pos logit contributions | |
sc | +0.022 |
Of | +0.022 |
antly | +0.019 |
onto | +0.019 |
Sure | +0.019 |
Neg logit contributions | |
strangers | -0.059 |
tresp | -0.054 |
mean | -0.052 |
unts | -0.052 |
cruel | -0.052 |
Token | named |
Token ID | 3706 |
Feature activation | -5.00e+00 |
Pos logit contributions | |
cy | +0.685 |
Of | +0.675 |
girl | +0.648 |
sc | +0.637 |
Sure | +0.630 |
Neg logit contributions | |
strangers | -0.332 |
tresp | -0.275 |
vern | -0.274 |
cruel | -0.237 |
supposed | -0.229 |
Token | Tim |
Token ID | 5045 |
Feature activation | -2.46e+00 |
Pos logit contributions | |
strangers | +0.256 |
tresp | +0.223 |
vern | +0.202 |
supposed | +0.199 |
cruel | +0.193 |
Neg logit contributions | |
cy | -0.303 |
Of | -0.299 |
sc | -0.293 |
girl | -0.289 |
Sure | -0.278 |
Token | . |
Token ID | 13 |
Feature activation | +2.53e-01 |
Pos logit contributions | |
strangers | +0.189 |
tresp | +0.181 |
vern | +0.179 |
cruel | +0.169 |
Days | +0.165 |
Neg logit contributions | |
cy | -0.096 |
girl | -0.085 |
down | -0.080 |
Of | -0.078 |
up | -0.076 |
Token | Tim |
Token ID | 5045 |
Feature activation | -2.43e+00 |
Pos logit contributions | |
Of | +0.012 |
cy | +0.012 |
Sure | +0.011 |
girl | +0.011 |
sc | +0.011 |
Neg logit contributions | |
strangers | -0.017 |
tresp | -0.016 |
vern | -0.015 |
cruel | -0.014 |
supposed | -0.014 |
Token | loved |
Token ID | 6151 |
Feature activation | -5.70e+00 |
Pos logit contributions | |
strangers | +0.139 |
vern | +0.128 |
tresp | +0.124 |
cruel | +0.113 |
Days | +0.112 |
Neg logit contributions | |
cy | -0.151 |
girl | -0.139 |
up | -0.133 |
down | -0.130 |
Of | -0.127 |
Token | the |
Token ID | 262 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
strangers | +0.165 |
tresp | +0.147 |
vern | +0.136 |
supposed | +0.134 |
cruel | +0.132 |
Neg logit contributions | |
cy | -0.132 |
Of | -0.131 |
sc | -0.124 |
Sure | -0.119 |
girl | -0.117 |
Token | table |
Token ID | 3084 |
Feature activation | +4.15e+00 |
Pos logit contributions | |
strangers | +0.064 |
tresp | +0.058 |
vern | +0.055 |
cruel | +0.053 |
supposed | +0.053 |
Neg logit contributions | |
Of | -0.050 |
cy | -0.050 |
sc | -0.047 |
girl | -0.046 |
Sure | -0.045 |
Token | was |
Token ID | 373 |
Feature activation | +2.66e+00 |
Pos logit contributions | |
Of | +0.198 |
cy | +0.197 |
sc | +0.184 |
girl | +0.183 |
Sure | +0.178 |
Neg logit contributions | |
strangers | -0.269 |
tresp | -0.243 |
vern | -0.233 |
cruel | -0.223 |
supposed | -0.221 |
Token | set |
Token ID | 900 |
Feature activation | +5.65e+00 |
Pos logit contributions | |
cy | +0.125 |
Of | +0.124 |
up | +0.123 |
down | +0.123 |
onto | +0.122 |
Neg logit contributions | |
strangers | -0.171 |
tresp | -0.149 |
vern | -0.148 |
cod | -0.143 |
isdom | -0.139 |
Token | up |
Token ID | 510 |
Feature activation | +7.49e+00 |
Pos logit contributions | |
Of | +0.254 |
cy | +0.253 |
sc | +0.236 |
girl | +0.233 |
Sure | +0.227 |
Neg logit contributions | |
strangers | -0.383 |
tresp | -0.347 |
vern | -0.333 |
cruel | -0.319 |
supposed | -0.317 |
Token | with |
Token ID | 351 |
Feature activation | +9.48e+00 |
Pos logit contributions | |
Of | +0.339 |
cy | +0.334 |
sc | +0.312 |
girl | +0.308 |
Sure | +0.302 |
Neg logit contributions | |
strangers | -0.507 |
tresp | -0.462 |
vern | -0.440 |
supposed | -0.426 |
cruel | -0.419 |
Token | a |
Token ID | 257 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
Of | +0.462 |
cy | +0.458 |
girl | +0.432 |
sc | +0.421 |
Sure | +0.412 |
Neg logit contributions | |
strangers | -0.599 |
tresp | -0.544 |
vern | -0.525 |
cruel | -0.505 |
supposed | -0.496 |
Token | big |
Token ID | 1263 |
Feature activation | -4.13e+00 |
Pos logit contributions | |
Of | +0.075 |
cy | +0.075 |
girl | +0.071 |
sc | +0.071 |
Sure | +0.069 |
Neg logit contributions | |
strangers | -0.083 |
tresp | -0.074 |
vern | -0.070 |
cruel | -0.067 |
supposed | -0.067 |
Token | , |
Token ID | 11 |
Feature activation | +3.68e-01 |
Pos logit contributions | |
strangers | +0.258 |
tresp | +0.229 |
vern | +0.223 |
supposed | +0.214 |
cruel | +0.211 |
Neg logit contributions | |
cy | -0.210 |
Of | -0.207 |
girl | -0.201 |
sc | -0.193 |
Sure | -0.189 |
Token | red |
Token ID | 2266 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
Of | +0.019 |
cy | +0.019 |
sc | +0.018 |
girl | +0.018 |
Sure | +0.017 |
Neg logit contributions | |
strangers | -0.023 |
tresp | -0.020 |
vern | -0.019 |
cruel | -0.018 |
supposed | -0.018 |
Token | cake |
Token ID | 12187 |
Feature activation | +1.96e+00 |
Pos logit contributions | |
strangers | +0.012 |
tresp | +0.011 |
vern | +0.011 |
cruel | +0.010 |
unts | +0.010 |
Neg logit contributions | |
Of | -0.008 |
cy | -0.008 |
sc | -0.008 |
girl | -0.008 |
Sure | -0.008 |
Token | he |
Token ID | 339 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
Of | +0.019 |
cy | +0.019 |
sc | +0.017 |
girl | +0.017 |
Sure | +0.016 |
Neg logit contributions | |
strangers | -0.031 |
tresp | -0.029 |
vern | -0.027 |
cruel | -0.026 |
supposed | -0.026 |
Token | was |
Token ID | 373 |
Feature activation | +2.66e+00 |
Pos logit contributions | |
cy | +0.085 |
girl | +0.082 |
Of | +0.081 |
sc | +0.078 |
Sure | +0.076 |
Neg logit contributions | |
strangers | -0.096 |
tresp | -0.085 |
vern | -0.084 |
cod | -0.077 |
unts | -0.076 |
Token | climbing |
Token ID | 14281 |
Feature activation | -5.29e+00 |
Pos logit contributions | |
Of | +0.134 |
up | +0.132 |
cy | +0.131 |
down | +0.131 |
girl | +0.130 |
Neg logit contributions | |
strangers | -0.159 |
tresp | -0.139 |
vern | -0.137 |
cod | -0.130 |
unts | -0.129 |
Token | all |
Token ID | 477 |
Feature activation | -2.74e+00 |
Pos logit contributions | |
strangers | +0.396 |
tresp | +0.362 |
vern | +0.343 |
cruel | +0.331 |
supposed | +0.331 |
Neg logit contributions | |
Of | -0.206 |
cy | -0.200 |
girl | -0.180 |
sc | -0.179 |
Sure | -0.177 |
Token | the |
Token ID | 262 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
strangers | +0.178 |
tresp | +0.159 |
supposed | +0.158 |
never | +0.152 |
vern | +0.147 |
Neg logit contributions | |
Of | -0.126 |
Sure | -0.121 |
sc | -0.116 |
cy | -0.116 |
cash | -0.113 |
Token | way |
Token ID | 835 |
Feature activation | +8.69e+00 |
Pos logit contributions | |
strangers | +0.083 |
tresp | +0.076 |
vern | +0.073 |
cruel | +0.070 |
supposed | +0.070 |
Neg logit contributions | |
Of | -0.038 |
cy | -0.038 |
sc | -0.034 |
girl | -0.033 |
Sure | -0.033 |
Token | up |
Token ID | 510 |
Feature activation | +7.58e+00 |
Pos logit contributions | |
cy | +0.352 |
Of | +0.351 |
sc | +0.323 |
girl | +0.320 |
Sure | +0.311 |
Neg logit contributions | |
strangers | -0.627 |
tresp | -0.575 |
vern | -0.551 |
cruel | -0.532 |
supposed | -0.525 |
Token | to |
Token ID | 284 |
Feature activation | -9.90e-01 |
Pos logit contributions | |
Of | +0.363 |
cy | +0.360 |
sc | +0.335 |
girl | +0.333 |
Sure | +0.326 |
Neg logit contributions | |
strangers | -0.495 |
tresp | -0.445 |
vern | -0.424 |
cruel | -0.407 |
supposed | -0.405 |
Token | the |
Token ID | 262 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
strangers | +0.062 |
tresp | +0.054 |
vern | +0.051 |
supposed | +0.049 |
cruel | +0.049 |
Neg logit contributions | |
cy | -0.051 |
Of | -0.051 |
sc | -0.050 |
girl | -0.047 |
Sure | -0.046 |
Token | top |
Token ID | 1353 |
Feature activation | +4.93e+00 |
Pos logit contributions | |
strangers | +0.071 |
tresp | +0.064 |
vern | +0.060 |
cruel | +0.058 |
supposed | +0.058 |
Neg logit contributions | |
Of | -0.053 |
cy | -0.052 |
sc | -0.049 |
girl | -0.048 |
Sure | -0.047 |
Token | of |
Token ID | 286 |
Feature activation | -2.29e+00 |
Pos logit contributions | |
Of | +0.272 |
cy | +0.269 |
sc | +0.251 |
girl | +0.249 |
Sure | +0.248 |
Neg logit contributions | |
strangers | -0.284 |
tresp | -0.249 |
vern | -0.235 |
unts | -0.227 |
cruel | -0.225 |
Token | envelop |
Token ID | 16441 |
Feature activation | -1.90e+00 |
Pos logit contributions | |
strangers | +0.076 |
tresp | +0.069 |
vern | +0.065 |
cruel | +0.063 |
supposed | +0.062 |
Neg logit contributions | |
Of | -0.057 |
cy | -0.057 |
sc | -0.054 |
girl | -0.052 |
Sure | -0.052 |
Token | es |
Token ID | 274 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
strangers | +0.125 |
tresp | +0.112 |
vern | +0.108 |
cruel | +0.104 |
supposed | +0.102 |
Neg logit contributions | |
cy | -0.090 |
Of | -0.089 |
sc | -0.084 |
girl | -0.083 |
Sure | -0.079 |
Token | united |
Token ID | 16503 |
Feature activation | -2.57e+00 |
Pos logit contributions | |
strangers | +0.076 |
tresp | +0.070 |
vern | +0.069 |
supposed | +0.065 |
cruel | +0.065 |
Neg logit contributions | |
cy | -0.060 |
sc | -0.058 |
Of | -0.057 |
girl | -0.056 |
onto | -0.054 |
Token | and |
Token ID | 290 |
Feature activation | -2.31e+00 |
Pos logit contributions | |
strangers | +0.164 |
tresp | +0.149 |
vern | +0.144 |
cruel | +0.137 |
supposed | +0.135 |
Neg logit contributions | |
cy | -0.125 |
Of | -0.124 |
sc | -0.117 |
girl | -0.116 |
Sure | -0.111 |
Token | became |
Token ID | 2627 |
Feature activation | -3.10e+00 |
Pos logit contributions | |
strangers | +0.131 |
tresp | +0.116 |
vern | +0.112 |
cruel | +0.105 |
unts | +0.104 |
Neg logit contributions | |
Of | -0.129 |
cy | -0.128 |
girl | -0.121 |
sc | -0.121 |
Sure | -0.117 |
Token | one |
Token ID | 530 |
Feature activation | +8.30e+00 |
Pos logit contributions | |
strangers | +0.188 |
tresp | +0.169 |
vern | +0.161 |
cruel | +0.153 |
supposed | +0.152 |
Neg logit contributions | |
Of | -0.160 |
cy | -0.160 |
sc | -0.150 |
girl | -0.149 |
Sure | -0.145 |
Token | big |
Token ID | 1263 |
Feature activation | -3.71e+00 |
Pos logit contributions | |
Of | +0.505 |
cy | +0.499 |
sc | +0.486 |
Sure | +0.472 |
onto | +0.454 |
Neg logit contributions | |
strangers | -0.420 |
tresp | -0.370 |
vern | -0.349 |
cruel | -0.332 |
unts | -0.324 |
Token | , |
Token ID | 11 |
Feature activation | +7.49e-01 |
Pos logit contributions | |
strangers | +0.232 |
tresp | +0.209 |
vern | +0.201 |
cruel | +0.191 |
supposed | +0.190 |
Neg logit contributions | |
Of | -0.185 |
cy | -0.185 |
girl | -0.173 |
sc | -0.172 |
Sure | -0.167 |
Token | happy |
Token ID | 3772 |
Feature activation | -2.78e+00 |
Pos logit contributions | |
Of | +0.038 |
cy | +0.038 |
girl | +0.036 |
sc | +0.036 |
Sure | +0.035 |
Neg logit contributions | |
strangers | -0.046 |
tresp | -0.042 |
vern | -0.040 |
supposed | -0.038 |
cruel | -0.038 |
Token | family |
Token ID | 1641 |
Feature activation | -3.29e+00 |
Pos logit contributions | |
strangers | +0.171 |
tresp | +0.152 |
vern | +0.143 |
cruel | +0.138 |
unts | +0.137 |
Neg logit contributions | |
cy | -0.144 |
Of | -0.143 |
sc | -0.138 |
Sure | -0.130 |
girl | -0.130 |
Token | . |
Token ID | 13 |
Feature activation | +8.60e-02 |
Pos logit contributions | |
strangers | +0.213 |
tresp | +0.192 |
vern | +0.184 |
cruel | +0.176 |
supposed | +0.174 |
Neg logit contributions | |
Of | -0.158 |
cy | -0.158 |
girl | -0.147 |
sc | -0.146 |
Sure | -0.142 |
Token | to |
Token ID | 284 |
Feature activation | -7.36e-01 |
Pos logit contributions | |
Of | +0.087 |
cy | +0.084 |
girl | +0.079 |
sc | +0.079 |
Sure | +0.077 |
Neg logit contributions | |
strangers | -0.126 |
tresp | -0.115 |
vern | -0.113 |
cruel | -0.105 |
cod | -0.104 |
Token | become |
Token ID | 1716 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
strangers | +0.043 |
tresp | +0.039 |
vern | +0.038 |
cruel | +0.036 |
supposed | +0.035 |
Neg logit contributions | |
Of | -0.039 |
cy | -0.039 |
girl | -0.037 |
sc | -0.036 |
down | -0.035 |
Token | a |
Token ID | 257 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
strangers | +0.112 |
tresp | +0.101 |
vern | +0.096 |
cruel | +0.092 |
supposed | +0.091 |
Neg logit contributions | |
Of | -0.090 |
cy | -0.090 |
girl | -0.085 |
sc | -0.084 |
Sure | -0.081 |
Token | great |
Token ID | 1049 |
Feature activation | -2.70e+00 |
Pos logit contributions | |
Of | +0.093 |
cy | +0.091 |
sc | +0.087 |
Sure | +0.084 |
girl | +0.083 |
Neg logit contributions | |
strangers | -0.095 |
tresp | -0.086 |
vern | -0.081 |
cruel | -0.078 |
unts | -0.077 |
Token | basketball |
Token ID | 9669 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
strangers | +0.166 |
tresp | +0.148 |
vern | +0.140 |
unts | +0.136 |
supposed | +0.135 |
Neg logit contributions | |
Of | -0.138 |
cy | -0.136 |
sc | -0.131 |
Sure | -0.126 |
girl | -0.122 |
Token | player |
Token ID | 2137 |
Feature activation | +8.33e+00 |
Pos logit contributions | |
strangers | +0.100 |
tresp | +0.091 |
vern | +0.086 |
supposed | +0.082 |
cruel | +0.082 |
Neg logit contributions | |
Of | -0.076 |
cy | -0.076 |
sc | -0.070 |
girl | -0.070 |
Sure | -0.069 |
Token | . |
Token ID | 13 |
Feature activation | +3.21e-01 |
Pos logit contributions | |
Of | +0.392 |
cy | +0.391 |
sc | +0.365 |
girl | +0.362 |
Sure | +0.352 |
Neg logit contributions | |
strangers | -0.544 |
tresp | -0.491 |
vern | -0.472 |
cruel | -0.451 |
supposed | -0.447 |
Token | |
Token ID | 220 |
Feature activation | +3.36e+00 |
Pos logit contributions | |
cy | +0.014 |
Of | +0.014 |
sc | +0.013 |
girl | +0.013 |
Sure | +0.012 |
Neg logit contributions | |
strangers | -0.022 |
tresp | -0.020 |
vern | -0.020 |
unts | -0.019 |
cruel | -0.019 |
Token | Thanks |
Token ID | 6930 |
Feature activation | +7.60e+00 |
Pos logit contributions | |
Of | +0.136 |
cy | +0.134 |
sc | +0.124 |
girl | +0.122 |
Sure | +0.120 |
Neg logit contributions | |
strangers | -0.245 |
tresp | -0.223 |
vern | -0.213 |
cruel | -0.207 |
supposed | -0.204 |
Token | to |
Token ID | 284 |
Feature activation | -6.45e-01 |
Pos logit contributions | |
cy | +0.395 |
Of | +0.391 |
sc | +0.383 |
girl | +0.358 |
Sure | +0.354 |
Neg logit contributions | |
strangers | -0.463 |
tresp | -0.411 |
vern | -0.380 |
cruel | -0.373 |
supposed | -0.368 |
Token | the |
Token ID | 262 |
Feature activation | -8.15e-01 |
Pos logit contributions | |
strangers | +0.044 |
vern | +0.043 |
tresp | +0.041 |
ache | +0.040 |
cod | +0.039 |
Neg logit contributions | |
Of | -0.028 |
cy | -0.026 |
Me | -0.024 |
down | -0.024 |
Sure | -0.024 |
Token | reached |
Token ID | 4251 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
strangers | +0.114 |
never | +0.114 |
hated | +0.101 |
missed | +0.098 |
tresp | +0.093 |
Neg logit contributions | |
umm | -0.213 |
Of | -0.212 |
sc | -0.199 |
cy | -0.187 |
mixture | -0.186 |
Token | for |
Token ID | 329 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
strangers | +0.006 |
tresp | +0.005 |
supposed | +0.005 |
never | +0.005 |
vern | +0.005 |
Neg logit contributions | |
Of | -0.006 |
sc | -0.006 |
cy | -0.006 |
umm | -0.006 |
girl | -0.005 |
Token | the |
Token ID | 262 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
Of | +0.055 |
cy | +0.052 |
girl | +0.051 |
onto | +0.049 |
Sure | +0.048 |
Neg logit contributions | |
strangers | -0.103 |
tresp | -0.097 |
vern | -0.095 |
unts | -0.092 |
cruel | -0.092 |
Token | ball |
Token ID | 2613 |
Feature activation | +2.41e-03 |
Pos logit contributions | |
strangers | +0.090 |
tresp | +0.082 |
vern | +0.079 |
cruel | +0.076 |
supposed | +0.075 |
Neg logit contributions | |
Of | -0.059 |
cy | -0.059 |
girl | -0.055 |
sc | -0.054 |
Sure | -0.053 |
Token | . |
Token ID | 13 |
Feature activation | -4.80e-01 |
Pos logit contributions | |
Of | +0.000 |
cy | +0.000 |
girl | +0.000 |
sc | +0.000 |
Sure | +0.000 |
Neg logit contributions | |
strangers | -0.000 |
tresp | -0.000 |
vern | -0.000 |
supposed | -0.000 |
cruel | -0.000 |
Token | Suddenly |
Token ID | 24975 |
Feature activation | +7.21e+00 |
Pos logit contributions | |
strangers | +0.028 |
tresp | +0.024 |
unts | +0.023 |
hated | +0.023 |
isdom | +0.022 |
Neg logit contributions | |
cy | -0.025 |
sc | -0.024 |
girl | -0.023 |
mixture | -0.022 |
cer | -0.022 |
Token | , |
Token ID | 11 |
Feature activation | +2.93e-01 |
Pos logit contributions | |
Of | +0.359 |
cy | +0.358 |
sc | +0.335 |
girl | +0.330 |
Sure | +0.324 |
Neg logit contributions | |
strangers | -0.457 |
tresp | -0.411 |
vern | -0.392 |
cruel | -0.375 |
supposed | -0.371 |
Token | she |
Token ID | 673 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
sc | +0.017 |
cy | +0.017 |
Of | +0.017 |
umm | +0.016 |
suit | +0.016 |
Neg logit contributions | |
strangers | -0.016 |
tresp | -0.013 |
never | -0.012 |
cruel | -0.012 |
mean | -0.012 |
Token | saw |
Token ID | 2497 |
Feature activation | -2.54e+00 |
Pos logit contributions | |
cy | +0.061 |
girl | +0.061 |
into | +0.057 |
down | +0.057 |
onto | +0.056 |
Neg logit contributions | |
strangers | -0.078 |
vern | -0.075 |
tresp | -0.071 |
isdom | -0.067 |
supposed | -0.065 |
Token | a |
Token ID | 257 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
strangers | +0.171 |
tresp | +0.154 |
vern | +0.148 |
cruel | +0.142 |
supposed | +0.141 |
Neg logit contributions | |
Of | -0.117 |
cy | -0.117 |
sc | -0.109 |
girl | -0.107 |
Sure | -0.105 |
Token | cute |
Token ID | 13779 |
Feature activation | -2.38e+00 |
Pos logit contributions | |
girl | +0.066 |
cy | +0.066 |
Of | +0.065 |
sc | +0.061 |
Sure | +0.060 |
Neg logit contributions | |
strangers | -0.076 |
tresp | -0.067 |
vern | -0.066 |
supposed | -0.062 |
isdom | -0.061 |
Token | , |
Token ID | 11 |
Feature activation | +3.32e-01 |
Pos logit contributions | |
cy | +0.251 |
Of | +0.237 |
sc | +0.232 |
girl | +0.225 |
mixture | +0.223 |
Neg logit contributions | |
strangers | -0.214 |
tresp | -0.194 |
hated | -0.160 |
vern | -0.159 |
cruel | -0.157 |
Token | he |
Token ID | 339 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
cy | +0.019 |
sc | +0.018 |
Of | +0.018 |
fits | +0.017 |
umm | +0.017 |
Neg logit contributions | |
strangers | -0.019 |
tresp | -0.016 |
never | -0.015 |
hated | -0.014 |
enemies | -0.014 |
Token | saw |
Token ID | 2497 |
Feature activation | -2.31e+00 |
Pos logit contributions | |
cy | +0.083 |
girl | +0.078 |
sc | +0.078 |
Of | +0.077 |
Sure | +0.073 |
Neg logit contributions | |
strangers | -0.088 |
vern | -0.082 |
tresp | -0.080 |
supposed | -0.074 |
cruel | -0.073 |
Token | a |
Token ID | 257 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
strangers | +0.162 |
tresp | +0.149 |
vern | +0.144 |
supposed | +0.137 |
unts | +0.137 |
Neg logit contributions | |
Of | -0.098 |
cy | -0.096 |
girl | -0.091 |
sc | -0.089 |
Sure | -0.087 |
Token | big |
Token ID | 1263 |
Feature activation | -4.10e+00 |
Pos logit contributions | |
cy | +0.085 |
Of | +0.085 |
girl | +0.081 |
sc | +0.080 |
Sure | +0.077 |
Neg logit contributions | |
strangers | -0.088 |
tresp | -0.078 |
vern | -0.075 |
supposed | -0.071 |
cruel | -0.070 |
Token | , |
Token ID | 11 |
Feature activation | +2.89e-01 |
Pos logit contributions | |
strangers | +0.265 |
tresp | +0.240 |
vern | +0.235 |
supposed | +0.222 |
cruel | +0.220 |
Neg logit contributions | |
cy | -0.196 |
Of | -0.194 |
girl | -0.185 |
sc | -0.179 |
Sure | -0.174 |
Token | angry |
Token ID | 7954 |
Feature activation | -5.28e+00 |
Pos logit contributions | |
Of | +0.015 |
cy | +0.015 |
girl | +0.015 |
sc | +0.014 |
Sure | +0.014 |
Neg logit contributions | |
strangers | -0.017 |
tresp | -0.015 |
vern | -0.015 |
supposed | -0.014 |
unts | -0.014 |
Token | cat |
Token ID | 3797 |
Feature activation | -3.99e+00 |
Pos logit contributions | |
strangers | +0.311 |
tresp | +0.279 |
vern | +0.275 |
supposed | +0.257 |
cruel | +0.254 |
Neg logit contributions | |
Of | -0.280 |
cy | -0.278 |
girl | -0.268 |
sc | -0.255 |
Sure | -0.254 |
Token | coming |
Token ID | 2406 |
Feature activation | -3.79e+00 |
Pos logit contributions | |
strangers | +0.266 |
vern | +0.256 |
tresp | +0.242 |
cruel | +0.230 |
isdom | +0.229 |
Neg logit contributions | |
cy | -0.170 |
Of | -0.164 |
sc | -0.162 |
girl | -0.162 |
down | -0.158 |
Token | towards |
Token ID | 3371 |
Feature activation | +6.79e+00 |
Pos logit contributions | |
strangers | +0.310 |
tresp | +0.285 |
supposed | +0.265 |
vern | +0.264 |
cruel | +0.263 |
Neg logit contributions | |
Of | -0.124 |
cy | -0.116 |
sc | -0.104 |
girl | -0.103 |
mixture | -0.102 |
Token | him |
Token ID | 683 |
Feature activation | -5.18e+00 |
Pos logit contributions | |
Of | +0.405 |
cy | +0.397 |
girl | +0.382 |
down | +0.376 |
onto | +0.373 |
Neg logit contributions | |
strangers | -0.335 |
vern | -0.330 |
tresp | -0.320 |
cruel | -0.294 |
supposed | -0.291 |
Token | it |
Token ID | 340 |
Feature activation | -6.32e-01 |
Pos logit contributions | |
strangers | +0.108 |
tresp | +0.091 |
vern | +0.086 |
cruel | +0.082 |
unts | +0.082 |
Neg logit contributions | |
cy | -0.101 |
Of | -0.100 |
sc | -0.098 |
girl | -0.093 |
Sure | -0.092 |
Token | , |
Token ID | 11 |
Feature activation | +4.48e-01 |
Pos logit contributions | |
strangers | +0.034 |
never | +0.031 |
understand | +0.030 |
vern | +0.030 |
often | +0.029 |
Neg logit contributions | |
Of | -0.033 |
cy | -0.033 |
ASH | -0.031 |
Sure | -0.030 |
sc | -0.030 |
Token | before |
Token ID | 878 |
Feature activation | +5.83e+00 |
Pos logit contributions | |
Of | +0.024 |
cy | +0.024 |
girl | +0.023 |
Sure | +0.022 |
sc | +0.022 |
Neg logit contributions | |
strangers | -0.027 |
tresp | -0.024 |
vern | -0.023 |
cruel | -0.022 |
supposed | -0.022 |
Token | putting |
Token ID | 5137 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
Of | +0.296 |
girl | +0.281 |
cy | +0.276 |
Sure | +0.273 |
onto | +0.272 |
Neg logit contributions | |
strangers | -0.355 |
tresp | -0.323 |
vern | -0.308 |
cod | -0.307 |
cruel | -0.296 |
Token | on |
Token ID | 319 |
Feature activation | +3.70e+00 |
Pos logit contributions | |
Of | +0.065 |
cy | +0.063 |
Sure | +0.061 |
sc | +0.060 |
girl | +0.059 |
Neg logit contributions | |
strangers | -0.070 |
tresp | -0.060 |
vern | -0.057 |
cruel | -0.053 |
supposed | -0.053 |
Token | her |
Token ID | 607 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
cy | +0.166 |
Of | +0.165 |
girl | +0.155 |
sc | +0.155 |
onto | +0.147 |
Neg logit contributions | |
strangers | -0.244 |
tresp | -0.225 |
vern | -0.217 |
cruel | -0.209 |
supposed | -0.207 |
Token | shoes |
Token ID | 10012 |
Feature activation | +4.23e-01 |
Pos logit contributions | |
strangers | +0.010 |
tresp | +0.009 |
vern | +0.009 |
cruel | +0.008 |
supposed | +0.008 |
Neg logit contributions | |
Of | -0.006 |
cy | -0.006 |
sc | -0.005 |
girl | -0.005 |
Sure | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | -4.40e-02 |
Pos logit contributions | |
Of | +0.021 |
cy | +0.020 |
girl | +0.019 |
sc | +0.019 |
Sure | +0.019 |
Neg logit contributions | |
strangers | -0.027 |
tresp | -0.024 |
vern | -0.023 |
supposed | -0.022 |
cruel | -0.022 |
Token | She |
Token ID | 1375 |
Feature activation | +7.26e-03 |
Pos logit contributions | |
strangers | +0.003 |
unts | +0.002 |
vern | +0.002 |
tresp | +0.002 |
isdom | +0.002 |
Neg logit contributions | |
cy | -0.002 |
sc | -0.002 |
girl | -0.002 |
Of | -0.002 |
tin | -0.002 |
Token | waved |
Token ID | 26834 |
Feature activation | +3.21e+00 |
Pos logit contributions | |
cy | +0.000 |
Of | +0.000 |
girl | +0.000 |
sc | +0.000 |
Sure | +0.000 |
Neg logit contributions | |
strangers | -0.000 |
tresp | -0.000 |
vern | -0.000 |
supposed | -0.000 |
cruel | -0.000 |
Token | goodbye |
Token ID | 24829 |
Feature activation | +2.53e-01 |
Pos logit contributions | |
cy | +0.166 |
Of | +0.163 |
sc | +0.158 |
Sure | +0.149 |
girl | +0.149 |
Neg logit contributions | |
strangers | -0.198 |
tresp | -0.172 |
vern | -0.166 |
cruel | -0.160 |
unts | -0.156 |
Token | 't |
Token ID | 470 |
Feature activation | -3.24e+00 |
Pos logit contributions | |
strangers | +0.343 |
tresp | +0.305 |
cod | +0.296 |
cruel | +0.286 |
isdom | +0.277 |
Neg logit contributions | |
Of | -0.310 |
onto | -0.293 |
sc | -0.290 |
cy | -0.289 |
up | -0.288 |
Token | have |
Token ID | 423 |
Feature activation | -3.52e+00 |
Pos logit contributions | |
strangers | +0.153 |
tresp | +0.140 |
vern | +0.139 |
cruel | +0.123 |
isdom | +0.123 |
Neg logit contributions | |
cy | -0.207 |
girl | -0.202 |
Of | -0.198 |
down | -0.189 |
sc | -0.188 |
Token | any |
Token ID | 597 |
Feature activation | -6.60e-01 |
Pos logit contributions | |
strangers | +0.227 |
tresp | +0.213 |
vern | +0.211 |
cod | +0.201 |
unts | +0.199 |
Neg logit contributions | |
Of | -0.154 |
cy | -0.150 |
girl | -0.148 |
down | -0.139 |
sc | -0.138 |
Token | time |
Token ID | 640 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
strangers | +0.040 |
tresp | +0.034 |
vern | +0.033 |
supposed | +0.032 |
cruel | +0.031 |
Neg logit contributions | |
cy | -0.037 |
Of | -0.036 |
sc | -0.034 |
Sure | -0.034 |
girl | -0.032 |
Token | to |
Token ID | 284 |
Feature activation | -8.53e-01 |
Pos logit contributions | |
strangers | +0.132 |
tresp | +0.122 |
vern | +0.120 |
unts | +0.113 |
cruel | +0.113 |
Neg logit contributions | |
Of | -0.084 |
cy | -0.083 |
girl | -0.078 |
sc | -0.076 |
Sure | -0.074 |
Token | get |
Token ID | 651 |
Feature activation | +9.87e-01 |
Pos logit contributions | |
strangers | +0.050 |
tresp | +0.047 |
vern | +0.045 |
cruel | +0.044 |
unts | +0.043 |
Neg logit contributions | |
cy | -0.043 |
Of | -0.043 |
girl | -0.041 |
onto | -0.039 |
up | -0.039 |
Token | a |
Token ID | 257 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
Of | +0.050 |
cy | +0.049 |
sc | +0.048 |
Sure | +0.047 |
girl | +0.044 |
Neg logit contributions | |
strangers | -0.064 |
tresp | -0.055 |
supposed | -0.053 |
vern | -0.053 |
cruel | -0.052 |
Token | massage |
Token ID | 26900 |
Feature activation | +3.02e+00 |
Pos logit contributions | |
cy | +0.084 |
Of | +0.081 |
sc | +0.078 |
Sure | +0.074 |
ASH | +0.073 |
Neg logit contributions | |
strangers | -0.103 |
tresp | -0.088 |
vern | -0.087 |
cruel | -0.084 |
ache | -0.082 |
Token | . |
Token ID | 13 |
Feature activation | +5.85e-03 |
Pos logit contributions | |
Of | +0.172 |
cy | +0.163 |
Sure | +0.161 |
sc | +0.154 |
Wow | +0.142 |
Neg logit contributions | |
strangers | -0.177 |
tresp | -0.147 |
ache | -0.132 |
vern | -0.131 |
supposed | -0.128 |
Token | She |
Token ID | 1375 |
Feature activation | +8.72e-02 |
Pos logit contributions | |
cy | +0.000 |
sc | +0.000 |
Of | +0.000 |
girl | +0.000 |
tin | +0.000 |
Neg logit contributions | |
strangers | -0.000 |
tresp | -0.000 |
hated | -0.000 |
vern | -0.000 |
supposed | -0.000 |
Token | started |
Token ID | 2067 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
cy | +0.004 |
girl | +0.004 |
Of | +0.004 |
sc | +0.004 |
tin | +0.004 |
Neg logit contributions | |
strangers | -0.005 |
vern | -0.005 |
tresp | -0.005 |
supposed | -0.005 |
unts | -0.005 |
Token | and |
Token ID | 290 |
Feature activation | -2.60e+00 |
Pos logit contributions | |
Of | +0.050 |
cy | +0.049 |
sc | +0.046 |
girl | +0.046 |
Sure | +0.045 |
Neg logit contributions | |
strangers | -0.058 |
tresp | -0.052 |
vern | -0.049 |
cruel | -0.047 |
supposed | -0.047 |
Token | started |
Token ID | 2067 |
Feature activation | +1.70e+00 |
Pos logit contributions | |
strangers | +0.146 |
tresp | +0.131 |
never | +0.118 |
cruel | +0.117 |
unts | +0.115 |
Neg logit contributions | |
Of | -0.144 |
cy | -0.142 |
sc | -0.139 |
Sure | -0.133 |
girl | -0.130 |
Token | applaud |
Token ID | 22517 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
Of | +0.093 |
cy | +0.092 |
sc | +0.086 |
girl | +0.086 |
Sure | +0.084 |
Neg logit contributions | |
strangers | -0.099 |
tresp | -0.088 |
vern | -0.085 |
cruel | -0.080 |
supposed | -0.078 |
Token | ing |
Token ID | 278 |
Feature activation | +4.22e+00 |
Pos logit contributions | |
strangers | +0.088 |
tresp | +0.078 |
vern | +0.075 |
cruel | +0.073 |
unts | +0.073 |
Neg logit contributions | |
cy | -0.051 |
Of | -0.050 |
sc | -0.048 |
Sure | -0.047 |
girl | -0.046 |
Token | louder |
Token ID | 27089 |
Feature activation | +3.62e+00 |
Pos logit contributions | |
cy | +0.202 |
Of | +0.198 |
Sure | +0.188 |
sc | +0.185 |
girl | +0.182 |
Neg logit contributions | |
strangers | -0.276 |
tresp | -0.244 |
vern | -0.225 |
cruel | -0.224 |
unts | -0.222 |
Token | . |
Token ID | 13 |
Feature activation | +9.47e-02 |
Pos logit contributions | |
cy | +0.181 |
Of | +0.180 |
sc | +0.169 |
girl | +0.166 |
Sure | +0.164 |
Neg logit contributions | |
strangers | -0.228 |
tresp | -0.204 |
vern | -0.194 |
cruel | -0.187 |
unts | -0.185 |
Token | The |
Token ID | 383 |
Feature activation | -9.03e-01 |
Pos logit contributions | |
cy | +0.004 |
girl | +0.004 |
sc | +0.004 |
Of | +0.004 |
tin | +0.004 |
Neg logit contributions | |
strangers | -0.006 |
tresp | -0.006 |
unts | -0.005 |
vern | -0.005 |
hated | -0.005 |
Token | performer |
Token ID | 26960 |
Feature activation | +6.69e+00 |
Pos logit contributions | |
strangers | +0.048 |
vern | +0.048 |
tresp | +0.044 |
supposed | +0.042 |
unts | +0.041 |
Neg logit contributions | |
girl | -0.053 |
cy | -0.049 |
Of | -0.048 |
sc | -0.044 |
boy | -0.044 |
Token | was |
Token ID | 373 |
Feature activation | +2.82e+00 |
Pos logit contributions | |
cy | +0.342 |
Of | +0.340 |
girl | +0.321 |
sc | +0.319 |
Sure | +0.307 |
Neg logit contributions | |
strangers | -0.412 |
tresp | -0.369 |
vern | -0.357 |
supposed | -0.336 |
cruel | -0.336 |
Token | so |
Token ID | 523 |
Feature activation | +2.35e+00 |
Pos logit contributions | |
Of | +0.136 |
cy | +0.133 |
girl | +0.128 |
up | +0.127 |
onto | +0.125 |
Neg logit contributions | |
strangers | -0.181 |
tresp | -0.160 |
vern | -0.155 |
isdom | -0.148 |
cod | -0.148 |
Token | embarrassed |
Token ID | 21100 |
Feature activation | -2.99e+00 |
Pos logit contributions | |
Of | +0.146 |
cy | +0.143 |
girl | +0.138 |
sc | +0.132 |
down | +0.130 |
Neg logit contributions | |
strangers | -0.125 |
tresp | -0.108 |
vern | -0.099 |
cod | -0.093 |
isdom | -0.093 |
Token | sun |
Token ID | 4252 |
Feature activation | +2.18e+00 |
Pos logit contributions | |
strangers | +0.154 |
tresp | +0.128 |
vern | +0.120 |
cruel | +0.119 |
enemies | +0.114 |
Neg logit contributions | |
Of | -0.150 |
cy | -0.147 |
Sure | -0.142 |
sc | -0.141 |
girl | -0.135 |
Token | fl |
Token ID | 2704 |
Feature activation | +4.78e+00 |
Pos logit contributions | |
Of | +0.083 |
sc | +0.081 |
Sure | +0.076 |
cy | +0.071 |
girl | +0.067 |
Neg logit contributions | |
strangers | -0.158 |
tresp | -0.139 |
ache | -0.135 |
eping | -0.132 |
vern | -0.131 |
Token | owers |
Token ID | 3618 |
Feature activation | -5.13e+00 |
Pos logit contributions | |
Of | +0.289 |
girl | +0.277 |
sc | +0.274 |
Sure | +0.272 |
cy | +0.271 |
Neg logit contributions | |
strangers | -0.234 |
tresp | -0.206 |
vern | -0.199 |
supposed | -0.185 |
unts | -0.183 |
Token | again |
Token ID | 757 |
Feature activation | +4.56e+00 |
Pos logit contributions | |
strangers | +0.407 |
tresp | +0.380 |
vern | +0.368 |
unts | +0.354 |
cruel | +0.353 |
Neg logit contributions | |
cy | -0.169 |
Of | -0.165 |
sc | -0.151 |
girl | -0.150 |
Sure | -0.138 |
Token | . |
Token ID | 13 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
cy | +0.184 |
Of | +0.179 |
girl | +0.168 |
sc | +0.166 |
Sure | +0.156 |
Neg logit contributions | |
strangers | -0.324 |
tresp | -0.304 |
vern | -0.296 |
cruel | -0.281 |
supposed | -0.279 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -6.75e+00 |
Pos logit contributions | |
strangers | +0.011 |
tresp | +0.010 |
unts | +0.009 |
hated | +0.009 |
vern | +0.009 |
Neg logit contributions | |
cy | -0.010 |
sc | -0.010 |
mixture | -0.010 |
tin | -0.010 |
Of | -0.009 |
Token | L |
Token ID | 43 |
Feature activation | +3.75e+00 |
Pos logit contributions | |
strangers | +0.468 |
tresp | +0.422 |
unts | +0.395 |
vern | +0.393 |
supposed | +0.379 |
Neg logit contributions | |
Of | -0.276 |
cy | -0.257 |
Sure | -0.250 |
mixture | -0.244 |
sc | -0.244 |
Token | ily |
Token ID | 813 |
Feature activation | -1.83e+00 |
Pos logit contributions | |
cy | +0.206 |
Of | +0.202 |
girl | +0.194 |
sc | +0.190 |
Sure | +0.185 |
Neg logit contributions | |
strangers | -0.216 |
tresp | -0.196 |
vern | -0.186 |
cruel | -0.183 |
cod | -0.175 |
Token | and |
Token ID | 290 |
Feature activation | -2.50e+00 |
Pos logit contributions | |
strangers | +0.125 |
vern | +0.116 |
tresp | +0.113 |
cruel | +0.108 |
supposed | +0.104 |
Neg logit contributions | |
cy | -0.089 |
girl | -0.080 |
Of | -0.077 |
sc | -0.074 |
Sure | -0.073 |
Token | Ben |
Token ID | 3932 |
Feature activation | +2.55e+00 |
Pos logit contributions | |
strangers | +0.161 |
vern | +0.152 |
tresp | +0.152 |
cod | +0.142 |
cruel | +0.140 |
Neg logit contributions | |
Of | -0.120 |
cy | -0.118 |
girl | -0.112 |
Sure | -0.104 |
down | -0.103 |
Token | were |
Token ID | 547 |
Feature activation | -3.91e+00 |
Pos logit contributions | |
cy | +0.139 |
girl | +0.120 |
Of | +0.108 |
tin | +0.107 |
ed | +0.107 |
Neg logit contributions | |
strangers | -0.163 |
vern | -0.156 |
tresp | -0.146 |
cruel | -0.146 |
Days | -0.138 |
Token | ." |
Token ID | 526 |
Feature activation | -3.12e-01 |
Pos logit contributions | |
strangers | +0.380 |
tresp | +0.340 |
vern | +0.317 |
supposed | +0.310 |
cruel | +0.302 |
Neg logit contributions | |
cy | -0.314 |
Of | -0.305 |
girl | -0.286 |
sc | -0.283 |
Sure | -0.280 |
Token | |
Token ID | 220 |
Feature activation | +3.10e+00 |
Pos logit contributions | |
strangers | +0.020 |
tresp | +0.017 |
vern | +0.017 |
unts | +0.017 |
hated | +0.017 |
Neg logit contributions | |
cy | -0.015 |
sc | -0.015 |
tin | -0.014 |
Of | -0.013 |
girl | -0.013 |
Token |
|
Token ID | 198 |
Feature activation | +9.60e-01 |
Pos logit contributions | |
Of | +0.126 |
cy | +0.125 |
sc | +0.115 |
girl | +0.114 |
Sure | +0.112 |
Neg logit contributions | |
strangers | -0.224 |
tresp | -0.205 |
vern | -0.196 |
cruel | -0.190 |
supposed | -0.188 |
Token |
|
Token ID | 198 |
Feature activation | +9.64e-01 |
Pos logit contributions | |
cy | +0.041 |
Of | +0.041 |
sc | +0.038 |
girl | +0.037 |
Sure | +0.036 |
Neg logit contributions | |
strangers | -0.067 |
tresp | -0.061 |
vern | -0.059 |
cruel | -0.057 |
supposed | -0.056 |
Token | Her |
Token ID | 9360 |
Feature activation | -9.28e-01 |
Pos logit contributions | |
Of | +0.055 |
cy | +0.053 |
girl | +0.050 |
sc | +0.050 |
Sure | +0.050 |
Neg logit contributions | |
strangers | -0.055 |
tresp | -0.050 |
vern | -0.046 |
supposed | -0.044 |
cruel | -0.044 |
Token | mom |
Token ID | 1995 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
strangers | +0.057 |
tresp | +0.051 |
vern | +0.049 |
cruel | +0.047 |
supposed | +0.046 |
Neg logit contributions | |
Of | -0.048 |
cy | -0.048 |
girl | -0.045 |
sc | -0.045 |
Sure | -0.044 |
Token | smiled |
Token ID | 13541 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
strangers | +0.083 |
tresp | +0.075 |
vern | +0.073 |
supposed | +0.069 |
cruel | +0.069 |
Neg logit contributions | |
cy | -0.056 |
Of | -0.055 |
girl | -0.052 |
sc | -0.051 |
Sure | -0.049 |
Token | and |
Token ID | 290 |
Feature activation | -2.59e+00 |
Pos logit contributions | |
sc | +0.085 |
cy | +0.085 |
Of | +0.085 |
Sure | +0.080 |
Me | +0.076 |
Neg logit contributions | |
strangers | -0.065 |
tresp | -0.052 |
vern | -0.052 |
unts | -0.050 |
cruel | -0.050 |
Token | said |
Token ID | 531 |
Feature activation | +3.92e+00 |
Pos logit contributions | |
strangers | +0.132 |
tresp | +0.115 |
cruel | +0.111 |
hated | +0.110 |
never | +0.110 |
Neg logit contributions | |
cy | -0.150 |
sc | -0.149 |
Of | -0.142 |
suit | -0.136 |
umm | -0.133 |
Token | , |
Token ID | 11 |
Feature activation | +5.07e-01 |
Pos logit contributions | |
cy | +0.218 |
Of | +0.209 |
sc | +0.201 |
girl | +0.196 |
Sure | +0.193 |
Neg logit contributions | |
strangers | -0.226 |
tresp | -0.204 |
vern | -0.195 |
cruel | -0.185 |
unts | -0.178 |
Token | " |
Token ID | 366 |
Feature activation | -2.90e+00 |
Pos logit contributions | |
cy | +0.026 |
Of | +0.025 |
sc | +0.024 |
girl | +0.023 |
Sure | +0.023 |
Neg logit contributions | |
strangers | -0.031 |
tresp | -0.028 |
vern | -0.027 |
cruel | -0.026 |
supposed | -0.026 |
Token | , |
Token ID | 11 |
Feature activation | +4.45e-01 |
Pos logit contributions | |
Of | +0.512 |
cy | +0.508 |
girl | +0.480 |
sc | +0.465 |
Sure | +0.454 |
Neg logit contributions | |
strangers | -0.769 |
tresp | -0.702 |
vern | -0.673 |
supposed | -0.656 |
cruel | -0.649 |
Token | but |
Token ID | 475 |
Feature activation | +4.23e+00 |
Pos logit contributions | |
Of | +0.019 |
girl | +0.018 |
cy | +0.017 |
sc | +0.017 |
Sure | +0.016 |
Neg logit contributions | |
strangers | -0.031 |
tresp | -0.029 |
vern | -0.028 |
supposed | -0.027 |
unts | -0.027 |
Token | be |
Token ID | 307 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
cy | +0.227 |
Of | +0.226 |
sc | +0.215 |
girl | +0.210 |
Sure | +0.207 |
Neg logit contributions | |
strangers | -0.252 |
tresp | -0.224 |
vern | -0.211 |
cruel | -0.203 |
supposed | -0.200 |
Token | careful |
Token ID | 8161 |
Feature activation | -6.50e-01 |
Pos logit contributions | |
Of | +0.096 |
cy | +0.095 |
girl | +0.092 |
sc | +0.091 |
Sure | +0.089 |
Neg logit contributions | |
strangers | -0.074 |
tresp | -0.064 |
vern | -0.060 |
cruel | -0.056 |
unts | -0.055 |
Token | and |
Token ID | 290 |
Feature activation | -2.63e+00 |
Pos logit contributions | |
strangers | +0.046 |
tresp | +0.043 |
vern | +0.041 |
cruel | +0.040 |
unts | +0.039 |
Neg logit contributions | |
Of | -0.025 |
cy | -0.025 |
up | -0.024 |
girl | -0.024 |
down | -0.024 |
Token | don |
Token ID | 836 |
Feature activation | -3.97e+00 |
Pos logit contributions | |
strangers | +0.143 |
tresp | +0.128 |
vern | +0.125 |
unts | +0.118 |
cruel | +0.113 |
Neg logit contributions | |
Of | -0.149 |
cy | -0.146 |
girl | -0.142 |
down | -0.142 |
Sure | -0.138 |
Token | 't |
Token ID | 470 |
Feature activation | -3.18e+00 |
Pos logit contributions | |
strangers | +0.257 |
tresp | +0.231 |
cod | +0.219 |
liar | +0.219 |
cruel | +0.219 |
Neg logit contributions | |
Of | -0.185 |
onto | -0.184 |
up | -0.178 |
sc | -0.177 |
cy | -0.175 |
Token | lean |
Token ID | 10904 |
Feature activation | -3.41e+00 |
Pos logit contributions | |
strangers | +0.189 |
tresp | +0.177 |
vern | +0.176 |
unts | +0.161 |
cruel | +0.160 |
Neg logit contributions | |
cy | -0.165 |
Of | -0.159 |
down | -0.154 |
girl | -0.154 |
onto | -0.145 |
Token | too |
Token ID | 1165 |
Feature activation | +2.40e-02 |
Pos logit contributions | |
strangers | +0.278 |
tresp | +0.260 |
vern | +0.256 |
unts | +0.244 |
cruel | +0.241 |
Neg logit contributions | |
cy | -0.105 |
Of | -0.099 |
sc | -0.095 |
down | -0.094 |
onto | -0.090 |
Token | far |
Token ID | 1290 |
Feature activation | -3.43e+00 |
Pos logit contributions | |
cy | +0.001 |
down | +0.001 |
girl | +0.001 |
Of | +0.001 |
sc | +0.001 |
Neg logit contributions | |
strangers | -0.001 |
tresp | -0.001 |
vern | -0.001 |
isdom | -0.001 |
cod | -0.001 |
Token | ," |
Token ID | 553 |
Feature activation | -5.02e-01 |
Pos logit contributions | |
strangers | +0.208 |
tresp | +0.176 |
vern | +0.166 |
cruel | +0.162 |
supposed | +0.159 |
Neg logit contributions | |
Of | -0.189 |
cy | -0.183 |
Sure | -0.174 |
Me | -0.165 |
sc | -0.165 |
Token | great |
Token ID | 1049 |
Feature activation | -3.01e+00 |
Pos logit contributions | |
cy | +0.071 |
girl | +0.069 |
Of | +0.069 |
sc | +0.066 |
Sure | +0.065 |
Neg logit contributions | |
strangers | -0.073 |
tresp | -0.062 |
vern | -0.059 |
isdom | -0.057 |
cruel | -0.057 |
Token | time |
Token ID | 640 |
Feature activation | -2.12e+00 |
Pos logit contributions | |
strangers | +0.160 |
tresp | +0.140 |
vern | +0.133 |
cruel | +0.127 |
supposed | +0.123 |
Neg logit contributions | |
cy | -0.183 |
Of | -0.182 |
girl | -0.173 |
sc | -0.172 |
Sure | -0.168 |
Token | at |
Token ID | 379 |
Feature activation | -4.09e-01 |
Pos logit contributions | |
strangers | +0.153 |
tresp | +0.135 |
vern | +0.133 |
cruel | +0.131 |
isdom | +0.125 |
Neg logit contributions | |
Of | -0.086 |
cy | -0.084 |
sc | -0.079 |
girl | -0.078 |
Sure | -0.077 |
Token | the |
Token ID | 262 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
strangers | +0.026 |
tresp | +0.023 |
vern | +0.022 |
supposed | +0.021 |
cruel | +0.021 |
Neg logit contributions | |
Of | -0.021 |
cy | -0.020 |
sc | -0.020 |
girl | -0.019 |
Sure | -0.019 |
Token | event |
Token ID | 1785 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
strangers | +0.087 |
tresp | +0.079 |
vern | +0.075 |
cruel | +0.072 |
supposed | +0.071 |
Neg logit contributions | |
Of | -0.069 |
cy | -0.068 |
sc | -0.064 |
girl | -0.063 |
Sure | -0.062 |
Token | . |
Token ID | 13 |
Feature activation | -4.33e-01 |
Pos logit contributions | |
strangers | +0.098 |
tresp | +0.089 |
vern | +0.085 |
cruel | +0.082 |
supposed | +0.081 |
Neg logit contributions | |
Of | -0.067 |
cy | -0.067 |
sc | -0.062 |
girl | -0.061 |
Sure | -0.060 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -7.15e+00 |
Pos logit contributions | |
strangers | +0.028 |
tresp | +0.025 |
vern | +0.024 |
supposed | +0.023 |
unts | +0.023 |
Neg logit contributions | |
cy | -0.021 |
Of | -0.021 |
sc | -0.020 |
girl | -0.020 |
Sure | -0.019 |
Token | Once |
Token ID | 7454 |
Feature activation | -9.96e-02 |
Pos logit contributions | |
strangers | +0.423 |
tresp | +0.377 |
vern | +0.356 |
unts | +0.353 |
supposed | +0.343 |
Neg logit contributions | |
Of | -0.364 |
cy | -0.354 |
girl | -0.337 |
sc | -0.336 |
mixture | -0.335 |
Token | upon |
Token ID | 2402 |
Feature activation | -2.51e-01 |
Pos logit contributions | |
strangers | +0.008 |
tresp | +0.007 |
vern | +0.007 |
cod | +0.007 |
cruel | +0.007 |
Neg logit contributions | |
cy | -0.004 |
Of | -0.004 |
girl | -0.003 |
down | -0.003 |
Sure | -0.003 |
Token | a |
Token ID | 257 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
strangers | +0.019 |
tresp | +0.018 |
vern | +0.017 |
cruel | +0.017 |
isdom | +0.016 |
Neg logit contributions | |
Of | -0.009 |
cy | -0.009 |
girl | -0.008 |
sc | -0.008 |
Sure | -0.008 |
Token | time |
Token ID | 640 |
Feature activation | -2.11e+00 |
Pos logit contributions | |
cy | +0.071 |
Of | +0.066 |
sc | +0.064 |
Sure | +0.063 |
girl | +0.063 |
Neg logit contributions | |
strangers | -0.085 |
tresp | -0.077 |
cruel | -0.071 |
vern | -0.070 |
reckless | -0.068 |
Token | All |
Token ID | 3237 |
Feature activation | -8.04e-03 |
Pos logit contributions | |
Of | +0.077 |
cy | +0.075 |
sc | +0.072 |
girl | +0.071 |
Sure | +0.071 |
Neg logit contributions | |
strangers | -0.088 |
tresp | -0.079 |
vern | -0.072 |
cruel | -0.071 |
supposed | -0.071 |
Token | of |
Token ID | 286 |
Feature activation | -1.95e+00 |
Pos logit contributions | |
strangers | +0.000 |
tresp | +0.000 |
vern | +0.000 |
cruel | +0.000 |
unts | +0.000 |
Neg logit contributions | |
Of | -0.000 |
cy | -0.000 |
sc | -0.000 |
Sure | -0.000 |
tin | -0.000 |
Token | Bella |
Token ID | 39304 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
strangers | +0.135 |
tresp | +0.125 |
vern | +0.124 |
supposed | +0.117 |
cruel | +0.116 |
Neg logit contributions | |
Of | -0.082 |
cy | -0.081 |
girl | -0.078 |
Sure | -0.073 |
sc | -0.072 |
Token | 's |
Token ID | 338 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
cy | +0.059 |
Of | +0.055 |
girl | +0.054 |
sc | +0.053 |
Sure | +0.051 |
Neg logit contributions | |
strangers | -0.079 |
vern | -0.072 |
tresp | -0.072 |
cruel | -0.067 |
supposed | -0.066 |
Token | friends |
Token ID | 2460 |
Feature activation | -2.94e-01 |
Pos logit contributions | |
Of | +0.082 |
cy | +0.081 |
girl | +0.081 |
Sure | +0.074 |
mixture | +0.073 |
Neg logit contributions | |
strangers | -0.098 |
tresp | -0.091 |
vern | -0.087 |
cod | -0.085 |
supposed | -0.084 |
Token | wanted |
Token ID | 2227 |
Feature activation | -2.58e+00 |
Pos logit contributions | |
strangers | +0.017 |
vern | +0.016 |
tresp | +0.016 |
cruel | +0.014 |
cod | +0.014 |
Neg logit contributions | |
cy | -0.016 |
Of | -0.016 |
girl | -0.015 |
sc | -0.014 |
down | -0.014 |
Token | to |
Token ID | 284 |
Feature activation | -7.54e-01 |
Pos logit contributions | |
strangers | +0.173 |
tresp | +0.159 |
vern | +0.154 |
cruel | +0.147 |
unts | +0.146 |
Neg logit contributions | |
Of | -0.116 |
cy | -0.113 |
girl | -0.106 |
sc | -0.105 |
Sure | -0.103 |
Token | see |
Token ID | 766 |
Feature activation | -3.48e+00 |
Pos logit contributions | |
strangers | +0.045 |
tresp | +0.041 |
cruel | +0.040 |
cod | +0.040 |
vern | +0.039 |
Neg logit contributions | |
Of | -0.038 |
cy | -0.037 |
girl | -0.035 |
onto | -0.034 |
up | -0.034 |
Token | the |
Token ID | 262 |
Feature activation | -8.93e-01 |
Pos logit contributions | |
strangers | +0.206 |
tresp | +0.192 |
vern | +0.187 |
unts | +0.178 |
supposed | +0.176 |
Neg logit contributions | |
Of | -0.180 |
cy | -0.177 |
girl | -0.170 |
sc | -0.164 |
down | -0.159 |
Token | triangle |
Token ID | 22950 |
Feature activation | +5.00e+00 |
Pos logit contributions | |
strangers | +0.054 |
tresp | +0.049 |
vern | +0.047 |
supposed | +0.045 |
cruel | +0.044 |
Neg logit contributions | |
cy | -0.046 |
Of | -0.046 |
girl | -0.044 |
sc | -0.043 |
Sure | -0.041 |
Token | in |
Token ID | 287 |
Feature activation | +2.63e+00 |
Pos logit contributions | |
Of | +0.235 |
cy | +0.234 |
sc | +0.218 |
girl | +0.214 |
Sure | +0.211 |
Neg logit contributions | |
strangers | -0.329 |
tresp | -0.296 |
vern | -0.283 |
cruel | -0.272 |
supposed | -0.269 |
Token | Then |
Token ID | 6423 |
Feature activation | +2.74e+00 |
Pos logit contributions | |
Of | +0.040 |
cy | +0.039 |
sc | +0.038 |
girl | +0.037 |
Sure | +0.037 |
Neg logit contributions | |
strangers | -0.059 |
tresp | -0.053 |
vern | -0.050 |
supposed | -0.049 |
cruel | -0.048 |
Token | , |
Token ID | 11 |
Feature activation | +5.51e-01 |
Pos logit contributions | |
sc | +0.164 |
cy | +0.160 |
Of | +0.155 |
Sure | +0.143 |
suit | +0.142 |
Neg logit contributions | |
strangers | -0.152 |
tresp | -0.133 |
never | -0.120 |
cruel | -0.114 |
enemies | -0.111 |
Token | it |
Token ID | 340 |
Feature activation | -5.16e-01 |
Pos logit contributions | |
sc | +0.032 |
cy | +0.032 |
Of | +0.030 |
suit | +0.029 |
umm | +0.029 |
Neg logit contributions | |
strangers | -0.031 |
tresp | -0.027 |
never | -0.024 |
cruel | -0.024 |
enemies | -0.023 |
Token | started |
Token ID | 2067 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
strangers | +0.032 |
tresp | +0.029 |
vern | +0.027 |
cruel | +0.027 |
hated | +0.027 |
Neg logit contributions | |
Of | -0.026 |
cy | -0.026 |
sc | -0.024 |
Sure | -0.024 |
girl | -0.023 |
Token | to |
Token ID | 284 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
Of | +0.069 |
cy | +0.068 |
sc | +0.063 |
girl | +0.063 |
Sure | +0.062 |
Neg logit contributions | |
strangers | -0.106 |
tresp | -0.096 |
vern | -0.093 |
cruel | -0.088 |
unts | -0.087 |
Token | rain |
Token ID | 6290 |
Feature activation | -8.20e+00 |
Pos logit contributions | |
strangers | +0.059 |
tresp | +0.054 |
vern | +0.052 |
supposed | +0.049 |
unts | +0.049 |
Neg logit contributions | |
cy | -0.053 |
Of | -0.052 |
girl | -0.051 |
sc | -0.049 |
tin | -0.049 |
Token | . |
Token ID | 13 |
Feature activation | +1.52e-02 |
Pos logit contributions | |
strangers | +0.525 |
tresp | +0.473 |
vern | +0.451 |
supposed | +0.432 |
cruel | +0.430 |
Neg logit contributions | |
Of | -0.403 |
cy | -0.396 |
sc | -0.368 |
girl | -0.367 |
Sure | -0.362 |
Token | The |
Token ID | 383 |
Feature activation | -6.60e-01 |
Pos logit contributions | |
cy | +0.001 |
Of | +0.001 |
sc | +0.001 |
girl | +0.001 |
tin | +0.001 |
Neg logit contributions | |
strangers | -0.001 |
tresp | -0.001 |
hated | -0.001 |
cruel | -0.001 |
unts | -0.001 |
Token | bunny |
Token ID | 44915 |
Feature activation | +2.42e+00 |
Pos logit contributions | |
strangers | +0.042 |
tresp | +0.037 |
cruel | +0.035 |
vern | +0.034 |
enemies | +0.033 |
Neg logit contributions | |
Of | -0.034 |
cy | -0.032 |
sc | -0.032 |
Sure | -0.031 |
onto | -0.028 |
Token | looked |
Token ID | 3114 |
Feature activation | +3.84e+00 |
Pos logit contributions | |
cy | +0.112 |
girl | +0.107 |
Of | +0.106 |
sc | +0.104 |
Sure | +0.097 |
Neg logit contributions | |
strangers | -0.163 |
tresp | -0.149 |
vern | -0.149 |
supposed | -0.139 |
cruel | -0.135 |
Token | up |
Token ID | 510 |
Feature activation | +7.49e+00 |
Pos logit contributions | |
cy | +0.117 |
Of | +0.116 |
sc | +0.104 |
girl | +0.104 |
Sure | +0.098 |
Neg logit contributions | |
strangers | -0.316 |
tresp | -0.293 |
vern | -0.285 |
cruel | -0.273 |
supposed | -0.272 |
Token | the |
Token ID | 262 |
Feature activation | -7.39e-01 |
Pos logit contributions | |
Of | +0.129 |
cy | +0.126 |
girl | +0.125 |
Sure | +0.115 |
Me | +0.112 |
Neg logit contributions | |
strangers | -0.242 |
tresp | -0.228 |
vern | -0.224 |
supposed | -0.215 |
cod | -0.210 |
Token | lion |
Token ID | 18744 |
Feature activation | -2.75e+00 |
Pos logit contributions | |
strangers | +0.039 |
vern | +0.035 |
tresp | +0.035 |
supposed | +0.032 |
unts | +0.031 |
Neg logit contributions | |
Of | -0.043 |
girl | -0.042 |
cy | -0.042 |
sc | -0.040 |
Sure | -0.039 |
Token | flex |
Token ID | 7059 |
Feature activation | +4.99e+00 |
Pos logit contributions | |
strangers | +0.164 |
tresp | +0.147 |
vern | +0.144 |
supposed | +0.136 |
cruel | +0.133 |
Neg logit contributions | |
cy | -0.145 |
Of | -0.143 |
sc | -0.137 |
girl | -0.136 |
Sure | -0.131 |
Token | ed |
Token ID | 276 |
Feature activation | +6.93e+00 |
Pos logit contributions | |
cy | +0.122 |
Of | +0.119 |
sc | +0.105 |
girl | +0.101 |
Sure | +0.093 |
Neg logit contributions | |
strangers | -0.443 |
tresp | -0.413 |
vern | -0.401 |
supposed | -0.388 |
cruel | -0.388 |
Token | his |
Token ID | 465 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
cy | +0.371 |
Of | +0.361 |
sc | +0.346 |
girl | +0.341 |
Sure | +0.333 |
Neg logit contributions | |
strangers | -0.420 |
tresp | -0.365 |
vern | -0.335 |
cruel | -0.332 |
enemies | -0.326 |
Token | muscles |
Token ID | 12749 |
Feature activation | -9.16e+00 |
Pos logit contributions | |
Of | +0.054 |
girl | +0.053 |
onto | +0.053 |
down | +0.052 |
mixture | +0.050 |
Neg logit contributions | |
strangers | -0.086 |
tresp | -0.080 |
supposed | -0.077 |
unts | -0.076 |
cod | -0.076 |
Token | and |
Token ID | 290 |
Feature activation | -2.29e+00 |
Pos logit contributions | |
strangers | +0.632 |
tresp | +0.573 |
vern | +0.549 |
cruel | +0.530 |
supposed | +0.522 |
Neg logit contributions | |
Of | -0.396 |
cy | -0.396 |
sc | -0.378 |
girl | -0.365 |
Sure | -0.353 |
Token | roared |
Token ID | 45615 |
Feature activation | -8.39e-01 |
Pos logit contributions | |
strangers | +0.120 |
tresp | +0.106 |
never | +0.104 |
cruel | +0.100 |
hated | +0.098 |
Neg logit contributions | |
cy | -0.139 |
Of | -0.136 |
sc | -0.134 |
Sure | -0.122 |
girl | -0.122 |
Token | . |
Token ID | 13 |
Feature activation | +2.66e-01 |
Pos logit contributions | |
strangers | +0.052 |
tresp | +0.046 |
vern | +0.044 |
cruel | +0.043 |
enemies | +0.042 |
Neg logit contributions | |
cy | -0.043 |
Of | -0.042 |
sc | -0.040 |
girl | -0.039 |
Sure | -0.039 |
Token |
|
Token ID | 198 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
cy | +0.013 |
sc | +0.012 |
Of | +0.012 |
girl | +0.012 |
tin | +0.011 |
Neg logit contributions | |
strangers | -0.016 |
tresp | -0.015 |
unts | -0.014 |
vern | -0.014 |
hated | -0.014 |
Token |
|
Token ID | 198 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
Of | +0.031 |
Sure | +0.029 |
sc | +0.028 |
cy | +0.027 |
up | +0.024 |
Neg logit contributions | |
strangers | -0.095 |
tresp | -0.088 |
cruel | -0.084 |
liar | -0.081 |
supposed | -0.081 |
Token | So |
Token ID | 2396 |
Feature activation | +3.09e+00 |
Pos logit contributions | |
Of | +0.044 |
cy | +0.044 |
sc | +0.042 |
girl | +0.041 |
Sure | +0.040 |
Neg logit contributions | |
strangers | -0.057 |
tresp | -0.052 |
vern | -0.048 |
supposed | -0.048 |
cruel | -0.047 |
Token | , |
Token ID | 11 |
Feature activation | +5.45e-01 |
Pos logit contributions | |
sc | +0.188 |
cy | +0.176 |
Of | +0.174 |
Sure | +0.171 |
mixture | +0.168 |
Neg logit contributions | |
strangers | -0.164 |
tresp | -0.136 |
never | -0.133 |
cruel | -0.116 |
mean | -0.115 |
Token | one |
Token ID | 530 |
Feature activation | +8.05e+00 |
Pos logit contributions | |
sc | +0.029 |
cy | +0.029 |
Of | +0.028 |
suit | +0.027 |
umm | +0.027 |
Neg logit contributions | |
strangers | -0.032 |
tresp | -0.026 |
never | -0.025 |
enemies | -0.023 |
understand | -0.023 |
Token | of |
Token ID | 286 |
Feature activation | -2.21e+00 |
Pos logit contributions | |
sc | +0.448 |
Of | +0.439 |
cy | +0.439 |
Sure | +0.419 |
ASH | +0.408 |
Neg logit contributions | |
strangers | -0.461 |
tresp | -0.395 |
cruel | -0.394 |
mean | -0.385 |
unts | -0.365 |
Token | the |
Token ID | 262 |
Feature activation | -9.45e-01 |
Pos logit contributions | |
strangers | +0.140 |
tresp | +0.126 |
vern | +0.121 |
cruel | +0.116 |
supposed | +0.115 |
Neg logit contributions | |
Of | -0.110 |
cy | -0.109 |
sc | -0.102 |
girl | -0.102 |
Sure | -0.099 |
Token | cows |
Token ID | 22575 |
Feature activation | -1.10e+01 |
Pos logit contributions | |
strangers | +0.054 |
tresp | +0.047 |
vern | +0.044 |
cruel | +0.043 |
unts | +0.041 |
Neg logit contributions | |
Of | -0.055 |
cy | -0.054 |
sc | -0.052 |
Sure | -0.051 |
onto | -0.048 |
Token | offered |
Token ID | 4438 |
Feature activation | +2.08e+00 |
Pos logit contributions | |
strangers | +0.681 |
vern | +0.654 |
tresp | +0.635 |
supposed | +0.597 |
unts | +0.582 |
Neg logit contributions | |
cy | -0.549 |
girl | -0.528 |
Of | -0.510 |
down | -0.486 |
sc | -0.481 |
Token | to |
Token ID | 284 |
Feature activation | -9.07e-01 |
Pos logit contributions | |
Of | +0.096 |
cy | +0.095 |
girl | +0.089 |
sc | +0.089 |
Sure | +0.086 |
Neg logit contributions | |
strangers | -0.136 |
tresp | -0.125 |
vern | -0.121 |
cruel | -0.115 |
supposed | -0.114 |
Token | carry |
Token ID | 3283 |
Feature activation | +2.81e+00 |
Pos logit contributions | |
strangers | +0.052 |
tresp | +0.048 |
vern | +0.048 |
supposed | +0.045 |
unts | +0.045 |
Neg logit contributions | |
Of | -0.048 |
cy | -0.047 |
girl | -0.045 |
sc | -0.043 |
Sure | -0.043 |
Token | her |
Token ID | 607 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
Of | +0.149 |
cy | +0.146 |
Sure | +0.139 |
girl | +0.135 |
sc | +0.134 |
Neg logit contributions | |
strangers | -0.174 |
tresp | -0.149 |
vern | -0.139 |
cruel | -0.132 |
supposed | -0.130 |
Token | out |
Token ID | 503 |
Feature activation | +4.65e+00 |
Pos logit contributions | |
strangers | +0.010 |
tresp | +0.009 |
vern | +0.008 |
cruel | +0.008 |
supposed | +0.008 |
Neg logit contributions | |
Of | -0.006 |
cy | -0.006 |
sc | -0.006 |
girl | -0.005 |
Sure | -0.005 |
Token | ride |
Token ID | 6594 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
strangers | +0.015 |
tresp | +0.013 |
vern | +0.012 |
cruel | +0.011 |
supposed | +0.011 |
Neg logit contributions | |
Of | -0.022 |
cy | -0.022 |
sc | -0.021 |
girl | -0.021 |
Sure | -0.021 |
Token | together |
Token ID | 1978 |
Feature activation | +7.04e+00 |
Pos logit contributions | |
strangers | +0.126 |
tresp | +0.112 |
vern | +0.106 |
supposed | +0.102 |
cruel | +0.101 |
Neg logit contributions | |
Of | -0.083 |
cy | -0.081 |
Sure | -0.075 |
girl | -0.075 |
sc | -0.074 |
Token | . |
Token ID | 13 |
Feature activation | -2.51e-02 |
Pos logit contributions | |
Of | +0.317 |
cy | +0.316 |
sc | +0.294 |
girl | +0.291 |
Sure | +0.282 |
Neg logit contributions | |
strangers | -0.476 |
tresp | -0.433 |
vern | -0.416 |
cruel | -0.399 |
supposed | -0.395 |
Token | The |
Token ID | 383 |
Feature activation | -7.74e-01 |
Pos logit contributions | |
strangers | +0.001 |
tresp | +0.001 |
hated | +0.001 |
shouldn | +0.001 |
supposed | +0.001 |
Neg logit contributions | |
cy | -0.001 |
tin | -0.001 |
mixture | -0.001 |
sc | -0.001 |
Of | -0.001 |
Token | two |
Token ID | 734 |
Feature activation | +5.47e+00 |
Pos logit contributions | |
strangers | +0.050 |
tresp | +0.046 |
vern | +0.044 |
unts | +0.042 |
supposed | +0.042 |
Neg logit contributions | |
Of | -0.037 |
girl | -0.036 |
cy | -0.036 |
sc | -0.034 |
Sure | -0.032 |
Token | ponies |
Token ID | 46370 |
Feature activation | -9.77e+00 |
Pos logit contributions | |
girl | +0.318 |
cy | +0.285 |
Of | +0.283 |
down | +0.265 |
sc | +0.259 |
Neg logit contributions | |
vern | -0.293 |
tresp | -0.291 |
strangers | -0.289 |
isdom | -0.281 |
supposed | -0.279 |
Token | ran |
Token ID | 4966 |
Feature activation | -2.98e+00 |
Pos logit contributions | |
strangers | +0.544 |
vern | +0.499 |
tresp | +0.489 |
cruel | +0.458 |
supposed | +0.453 |
Neg logit contributions | |
cy | -0.582 |
Of | -0.543 |
girl | -0.542 |
sc | -0.533 |
onto | -0.510 |
Token | through |
Token ID | 832 |
Feature activation | +5.36e+00 |
Pos logit contributions | |
strangers | +0.199 |
tresp | +0.180 |
vern | +0.167 |
supposed | +0.163 |
unts | +0.162 |
Neg logit contributions | |
Of | -0.136 |
cy | -0.133 |
girl | -0.121 |
Sure | -0.119 |
mixture | -0.118 |
Token | the |
Token ID | 262 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
Of | +0.211 |
cy | +0.209 |
girl | +0.200 |
sc | +0.191 |
onto | +0.186 |
Neg logit contributions | |
strangers | -0.378 |
vern | -0.367 |
tresp | -0.354 |
cruel | -0.343 |
supposed | -0.341 |
Token | me |
Token ID | 502 |
Feature activation | -2.55e+00 |
Pos logit contributions | |
strangers | +0.068 |
tresp | +0.061 |
vern | +0.059 |
cruel | +0.056 |
supposed | +0.056 |
Neg logit contributions | |
cy | -0.055 |
Of | -0.055 |
girl | -0.052 |
sc | -0.051 |
Sure | -0.050 |
Token | adow |
Token ID | 4584 |
Feature activation | -6.87e+00 |
Pos logit contributions | |
strangers | +0.150 |
cruel | +0.136 |
tresp | +0.135 |
liar | +0.126 |
bullies | +0.122 |
Neg logit contributions | |
cy | -0.141 |
down | -0.126 |
Of | -0.123 |
up | -0.122 |
Sure | -0.120 |
Token | so |
Token ID | 523 |
Feature activation | +4.35e+00 |
Pos logit contributions | |
Of | +0.079 |
girl | +0.068 |
cy | +0.065 |
Sure | +0.063 |
down | +0.063 |
Neg logit contributions | |
strangers | -0.228 |
tresp | -0.222 |
vern | -0.216 |
supposed | -0.212 |
unts | -0.210 |
Token | happy |
Token ID | 3772 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
Of | +0.241 |
cy | +0.236 |
girl | +0.227 |
sc | +0.221 |
Sure | +0.218 |
Neg logit contributions | |
strangers | -0.249 |
tresp | -0.225 |
vern | -0.213 |
cruel | -0.198 |
cod | -0.198 |
Token | and |
Token ID | 290 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
strangers | +0.078 |
tresp | +0.069 |
vern | +0.064 |
supposed | +0.062 |
cruel | +0.062 |
Neg logit contributions | |
cy | -0.069 |
Of | -0.068 |
sc | -0.065 |
Sure | -0.062 |
girl | -0.062 |
Token | smiled |
Token ID | 13541 |
Feature activation | +2.51e+00 |
Pos logit contributions | |
strangers | +0.067 |
tresp | +0.059 |
vern | +0.056 |
cruel | +0.054 |
supposed | +0.054 |
Neg logit contributions | |
cy | -0.070 |
Of | -0.069 |
sc | -0.066 |
girl | -0.064 |
Sure | -0.064 |
Token | at |
Token ID | 379 |
Feature activation | +6.41e-01 |
Pos logit contributions | |
sc | +0.130 |
cy | +0.130 |
Of | +0.128 |
Sure | +0.120 |
tin | +0.113 |
Neg logit contributions | |
strangers | -0.150 |
tresp | -0.131 |
vern | -0.127 |
cruel | -0.121 |
unts | -0.121 |
Token | Billy |
Token ID | 15890 |
Feature activation | -8.99e+00 |
Pos logit contributions | |
Of | +0.031 |
cy | +0.030 |
girl | +0.028 |
Sure | +0.027 |
sc | +0.026 |
Neg logit contributions | |
strangers | -0.041 |
tresp | -0.038 |
vern | -0.037 |
cod | -0.035 |
cruel | -0.035 |
Token | . |
Token ID | 13 |
Feature activation | +7.89e-01 |
Pos logit contributions | |
strangers | +0.507 |
tresp | +0.427 |
vern | +0.405 |
supposed | +0.400 |
understand | +0.398 |
Neg logit contributions | |
Of | -0.491 |
cy | -0.483 |
sc | -0.472 |
Sure | -0.461 |
girl | -0.436 |
Token | His |
Token ID | 2399 |
Feature activation | +2.44e+00 |
Pos logit contributions | |
Of | +0.033 |
cy | +0.032 |
sc | +0.029 |
girl | +0.029 |
Sure | +0.029 |
Neg logit contributions | |
strangers | -0.057 |
tresp | -0.052 |
vern | -0.050 |
cruel | -0.049 |
supposed | -0.048 |
Token | mother |
Token ID | 2802 |
Feature activation | -9.12e-01 |
Pos logit contributions | |
Of | +0.123 |
cy | +0.121 |
girl | +0.117 |
Sure | +0.111 |
sc | +0.106 |
Neg logit contributions | |
strangers | -0.153 |
tresp | -0.138 |
vern | -0.133 |
supposed | -0.127 |
cod | -0.125 |
Token | hugged |
Token ID | 41130 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
strangers | +0.066 |
tresp | +0.061 |
vern | +0.060 |
supposed | +0.056 |
cruel | +0.055 |
Neg logit contributions | |
cy | -0.039 |
girl | -0.037 |
Of | -0.037 |
sc | -0.032 |
Sure | -0.032 |
Token | him |
Token ID | 683 |
Feature activation | -4.73e+00 |
Pos logit contributions | |
strangers | +0.060 |
tresp | +0.056 |
vern | +0.054 |
supposed | +0.050 |
cruel | +0.049 |
Neg logit contributions | |
Of | -0.077 |
cy | -0.075 |
girl | -0.073 |
down | -0.070 |
sc | -0.069 |