Token | be |
Token ID | 307 |
Feature activation | +1.94e-02 |
Pos logit contributions | |
sizes | +0.014 |
bows | +0.012 |
planets | +0.012 |
cultures | +0.012 |
ABC | +0.012 |
Neg logit contributions | |
late | -0.014 |
Start | -0.012 |
aback | -0.012 |
O | -0.012 |
sm | -0.012 |
Token | cow |
Token ID | 9875 |
Feature activation | +3.58e-02 |
Pos logit contributions | |
sizes | +0.039 |
planets | +0.036 |
bows | +0.034 |
clubs | +0.034 |
toes | +0.033 |
Neg logit contributions | |
late | -0.028 |
aback | -0.025 |
O | -0.025 |
Start | -0.025 |
sm | -0.023 |
Token | boys |
Token ID | 13202 |
Feature activation | +9.04e-02 |
Pos logit contributions | |
sizes | +0.041 |
planets | +0.033 |
ABC | +0.033 |
cultures | +0.033 |
hips | +0.032 |
Neg logit contributions | |
late | -0.079 |
sm | -0.072 |
aback | -0.069 |
severe | -0.067 |
poisonous | -0.067 |
Token | and |
Token ID | 290 |
Feature activation | +5.23e-03 |
Pos logit contributions | |
sizes | +0.150 |
planets | +0.128 |
ABC | +0.127 |
cultures | +0.125 |
toes | +0.123 |
Neg logit contributions | |
late | -0.167 |
aback | -0.142 |
sm | -0.139 |
O | -0.134 |
Start | -0.134 |
Token | cow |
Token ID | 9875 |
Feature activation | +3.68e-02 |
Pos logit contributions | |
sizes | +0.008 |
planets | +0.007 |
clubs | +0.007 |
ABC | +0.007 |
bows | +0.007 |
Neg logit contributions | |
late | -0.010 |
aback | -0.009 |
Start | -0.009 |
sm | -0.009 |
O | -0.009 |
Token | girls |
Token ID | 36960 |
Feature activation | +2.33e-01 |
Pos logit contributions | |
sizes | +0.041 |
ABC | +0.035 |
cultures | +0.032 |
bows | +0.032 |
planets | +0.032 |
Neg logit contributions | |
late | -0.082 |
sm | -0.075 |
aback | -0.071 |
heaven | -0.069 |
another | -0.069 |
Token | . |
Token ID | 13 |
Feature activation | +1.22e-02 |
Pos logit contributions | |
sizes | +0.455 |
cultures | +0.389 |
ABC | +0.386 |
planets | +0.381 |
bows | +0.379 |
Neg logit contributions | |
late | -0.328 |
another | -0.272 |
here | -0.270 |
aback | -0.268 |
sm | -0.265 |
Token | They |
Token ID | 1119 |
Feature activation | +6.15e-02 |
Pos logit contributions | |
sizes | +0.019 |
toes | +0.016 |
necks | +0.016 |
planets | +0.015 |
clubs | +0.015 |
Neg logit contributions | |
late | -0.024 |
severe | -0.021 |
sm | -0.021 |
aback | -0.021 |
poisonous | -0.020 |
Token | put |
Token ID | 1234 |
Feature activation | -5.47e-02 |
Pos logit contributions | |
sizes | +0.112 |
planets | +0.098 |
bows | +0.096 |
ABC | +0.095 |
clubs | +0.094 |
Neg logit contributions | |
late | -0.104 |
aback | -0.089 |
Start | -0.087 |
sm | -0.086 |
O | -0.086 |
Token | on |
Token ID | 319 |
Feature activation | -7.42e-03 |
Pos logit contributions | |
late | +0.094 |
Start | +0.083 |
aback | +0.082 |
O | +0.079 |
sm | +0.078 |
Neg logit contributions | |
sizes | -0.098 |
planets | -0.087 |
clubs | -0.085 |
bows | -0.084 |
toes | -0.082 |
Token | hats |
Token ID | 23910 |
Feature activation | +8.32e-02 |
Pos logit contributions | |
late | +0.011 |
aback | +0.010 |
sm | +0.009 |
Start | +0.009 |
O | +0.009 |
Neg logit contributions | |
sizes | -0.014 |
bows | -0.013 |
planets | -0.013 |
ABC | -0.012 |
cultures | -0.012 |
Token | my |
Token ID | 616 |
Feature activation | -6.20e-03 |
Pos logit contributions | |
sizes | +0.131 |
planets | +0.117 |
bows | +0.116 |
ABC | +0.115 |
clubs | +0.113 |
Neg logit contributions | |
late | -0.079 |
aback | -0.065 |
Start | -0.062 |
sm | -0.062 |
O | -0.062 |
Token | cow |
Token ID | 9875 |
Feature activation | +3.49e-02 |
Pos logit contributions | |
late | +0.010 |
aback | +0.009 |
Start | +0.009 |
sm | +0.009 |
O | +0.009 |
Neg logit contributions | |
sizes | -0.011 |
planets | -0.010 |
bows | -0.010 |
ABC | -0.010 |
clubs | -0.010 |
Token | boys |
Token ID | 13202 |
Feature activation | +9.28e-02 |
Pos logit contributions | |
sizes | +0.056 |
bows | +0.049 |
planets | +0.048 |
ABC | +0.047 |
toes | +0.045 |
Neg logit contributions | |
late | -0.067 |
aback | -0.059 |
Start | -0.059 |
O | -0.058 |
izz | -0.056 |
Token | and |
Token ID | 290 |
Feature activation | +3.29e-03 |
Pos logit contributions | |
sizes | +0.136 |
bows | +0.119 |
planets | +0.115 |
ABC | +0.112 |
clubs | +0.109 |
Neg logit contributions | |
late | -0.188 |
Start | -0.165 |
aback | -0.164 |
O | -0.162 |
sm | -0.158 |
Token | cow |
Token ID | 9875 |
Feature activation | +3.26e-02 |
Pos logit contributions | |
sizes | +0.006 |
planets | +0.005 |
clubs | +0.005 |
toes | +0.005 |
ABC | +0.005 |
Neg logit contributions | |
late | -0.006 |
aback | -0.005 |
Start | -0.005 |
izz | -0.005 |
sm | -0.005 |
Token | girls |
Token ID | 36960 |
Feature activation | +2.30e-01 |
Pos logit contributions | |
sizes | +0.053 |
bows | +0.045 |
planets | +0.045 |
ABC | +0.044 |
clubs | +0.043 |
Neg logit contributions | |
late | -0.062 |
aback | -0.054 |
Start | -0.054 |
O | -0.053 |
sm | -0.051 |
Token | . |
Token ID | 13 |
Feature activation | +2.66e-02 |
Pos logit contributions | |
sizes | +0.433 |
planets | +0.381 |
bows | +0.374 |
ABC | +0.372 |
clubs | +0.367 |
Neg logit contributions | |
late | -0.369 |
aback | -0.313 |
Start | -0.304 |
sm | -0.304 |
O | -0.302 |
Token | I |
Token ID | 314 |
Feature activation | -6.05e-02 |
Pos logit contributions | |
sizes | +0.045 |
planets | +0.039 |
bows | +0.038 |
ABC | +0.037 |
cultures | +0.037 |
Neg logit contributions | |
late | -0.047 |
aback | -0.042 |
Start | -0.041 |
sm | -0.041 |
O | -0.040 |
Token | love |
Token ID | 1842 |
Feature activation | +3.20e-02 |
Pos logit contributions | |
late | +0.124 |
aback | +0.111 |
O | +0.109 |
Start | +0.109 |
izz | +0.107 |
Neg logit contributions | |
sizes | -0.078 |
bows | -0.071 |
ABC | -0.063 |
neck | -0.059 |
pretending | -0.059 |
Token | you |
Token ID | 345 |
Feature activation | +1.70e-03 |
Pos logit contributions | |
sizes | +0.066 |
planets | +0.060 |
ABC | +0.058 |
cultures | +0.057 |
toes | +0.057 |
Neg logit contributions | |
late | -0.044 |
aback | -0.041 |
Start | -0.040 |
O | -0.037 |
izz | -0.037 |
Token | ." |
Token ID | 526 |
Feature activation | -2.21e-02 |
Pos logit contributions | |
sizes | +0.003 |
planets | +0.003 |
ABC | +0.002 |
bows | +0.002 |
toes | +0.002 |
Neg logit contributions | |
late | -0.003 |
aback | -0.003 |
Start | -0.003 |
O | -0.003 |
sm | -0.003 |
Token | play |
Token ID | 711 |
Feature activation | +5.29e-02 |
Pos logit contributions | |
sizes | +0.014 |
planets | +0.012 |
bows | +0.012 |
ABC | +0.011 |
cultures | +0.011 |
Neg logit contributions | |
late | -0.018 |
aback | -0.015 |
O | -0.015 |
Start | -0.015 |
sm | -0.015 |
Token | cow |
Token ID | 9875 |
Feature activation | +3.80e-02 |
Pos logit contributions | |
sizes | +0.066 |
planets | +0.063 |
bows | +0.060 |
ABC | +0.060 |
clubs | +0.060 |
Neg logit contributions | |
late | -0.108 |
izz | -0.103 |
severe | -0.101 |
aback | -0.100 |
O | -0.098 |
Token | boys |
Token ID | 13202 |
Feature activation | +9.31e-02 |
Pos logit contributions | |
sizes | +0.052 |
planets | +0.043 |
ABC | +0.042 |
cultures | +0.041 |
bows | +0.041 |
Neg logit contributions | |
late | -0.079 |
aback | -0.070 |
sm | -0.069 |
Start | -0.067 |
O | -0.066 |
Token | and |
Token ID | 290 |
Feature activation | +2.83e-03 |
Pos logit contributions | |
sizes | +0.147 |
planets | +0.125 |
ABC | +0.122 |
cultures | +0.121 |
bows | +0.120 |
Neg logit contributions | |
late | -0.177 |
aback | -0.156 |
sm | -0.150 |
Start | -0.148 |
O | -0.148 |
Token | cow |
Token ID | 9875 |
Feature activation | +3.87e-02 |
Pos logit contributions | |
sizes | +0.004 |
planets | +0.004 |
bows | +0.004 |
ABC | +0.004 |
clubs | +0.004 |
Neg logit contributions | |
late | -0.006 |
aback | -0.005 |
Start | -0.005 |
sm | -0.005 |
O | -0.005 |
Token | girls |
Token ID | 36960 |
Feature activation | +2.30e-01 |
Pos logit contributions | |
sizes | +0.048 |
ABC | +0.040 |
planets | +0.040 |
cultures | +0.039 |
bows | +0.039 |
Neg logit contributions | |
late | -0.081 |
sm | -0.072 |
aback | -0.071 |
poisoned | -0.068 |
severe | -0.067 |
Token | , |
Token ID | 11 |
Feature activation | +4.39e-02 |
Pos logit contributions | |
sizes | +0.406 |
cultures | +0.348 |
planets | +0.343 |
ABC | +0.339 |
azes | +0.336 |
Neg logit contributions | |
late | -0.355 |
aback | -0.306 |
another | -0.303 |
here | -0.301 |
sm | -0.287 |
Token | and |
Token ID | 290 |
Feature activation | -2.90e-03 |
Pos logit contributions | |
sizes | +0.072 |
planets | +0.062 |
bows | +0.062 |
ABC | +0.061 |
cultures | +0.060 |
Neg logit contributions | |
late | -0.081 |
aback | -0.069 |
sm | -0.068 |
Start | -0.067 |
O | -0.067 |
Token | pretend |
Token ID | 16614 |
Feature activation | +6.99e-02 |
Pos logit contributions | |
late | +0.005 |
aback | +0.005 |
Start | +0.005 |
O | +0.004 |
sm | +0.004 |
Neg logit contributions | |
sizes | -0.005 |
planets | -0.004 |
bows | -0.004 |
ABC | -0.004 |
clubs | -0.004 |
Token | to |
Token ID | 284 |
Feature activation | +1.48e-02 |
Pos logit contributions | |
sizes | +0.118 |
planets | +0.102 |
bows | +0.100 |
ABC | +0.099 |
clubs | +0.098 |
Neg logit contributions | |
late | -0.125 |
aback | -0.116 |
Start | -0.111 |
O | -0.111 |
izz | -0.107 |
Token | ride |
Token ID | 6594 |
Feature activation | +1.65e-02 |
Pos logit contributions | |
sizes | +0.021 |
planets | +0.018 |
bows | +0.017 |
ABC | +0.017 |
clubs | +0.017 |
Neg logit contributions | |
late | -0.031 |
aback | -0.028 |
sm | -0.027 |
Start | -0.027 |
izz | -0.027 |
Token | the |
Token ID | 262 |
Feature activation | +3.77e-02 |
Pos logit contributions | |
sizes | +0.151 |
planets | +0.136 |
ABC | +0.131 |
bows | +0.131 |
clubs | +0.128 |
Neg logit contributions | |
late | -0.119 |
aback | -0.106 |
Start | -0.102 |
O | -0.102 |
sm | -0.099 |
Token | blocks |
Token ID | 7021 |
Feature activation | +3.93e-02 |
Pos logit contributions | |
sizes | +0.047 |
bows | +0.041 |
cultures | +0.040 |
clubs | +0.038 |
necks | +0.038 |
Neg logit contributions | |
late | -0.080 |
aback | -0.067 |
sm | -0.067 |
Start | -0.066 |
O | -0.064 |
Token | , |
Token ID | 11 |
Feature activation | +5.48e-02 |
Pos logit contributions | |
sizes | +0.062 |
bows | +0.053 |
planets | +0.052 |
ABC | +0.050 |
toes | +0.050 |
Neg logit contributions | |
late | -0.074 |
O | -0.070 |
aback | -0.070 |
Start | -0.070 |
severe | -0.067 |
Token | compare |
Token ID | 8996 |
Feature activation | +4.10e-02 |
Pos logit contributions | |
sizes | +0.095 |
planets | +0.083 |
bows | +0.082 |
ABC | +0.081 |
clubs | +0.079 |
Neg logit contributions | |
late | -0.096 |
aback | -0.083 |
Start | -0.081 |
O | -0.081 |
sm | -0.080 |
Token | the |
Token ID | 262 |
Feature activation | +4.30e-02 |
Pos logit contributions | |
sizes | +0.077 |
planets | +0.068 |
bows | +0.066 |
ABC | +0.066 |
clubs | +0.065 |
Neg logit contributions | |
late | -0.067 |
aback | -0.058 |
Start | -0.056 |
O | -0.056 |
sm | -0.056 |
Token | sizes |
Token ID | 10620 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
sizes | +0.054 |
bows | +0.048 |
cultures | +0.047 |
planets | +0.046 |
clubs | +0.046 |
Neg logit contributions | |
late | -0.089 |
aback | -0.078 |
Start | -0.075 |
sm | -0.074 |
O | -0.072 |
Token | , |
Token ID | 11 |
Feature activation | +6.17e-02 |
Pos logit contributions | |
sizes | +0.320 |
planets | +0.278 |
bows | +0.277 |
ABC | +0.269 |
clubs | +0.269 |
Neg logit contributions | |
late | -0.271 |
aback | -0.236 |
Start | -0.230 |
O | -0.229 |
sm | -0.222 |
Token | and |
Token ID | 290 |
Feature activation | -4.82e-04 |
Pos logit contributions | |
sizes | +0.093 |
bows | +0.082 |
ABC | +0.081 |
planets | +0.080 |
cultures | +0.080 |
Neg logit contributions | |
late | -0.116 |
aback | -0.097 |
Start | -0.094 |
O | -0.094 |
sm | -0.093 |
Token | sort |
Token ID | 3297 |
Feature activation | +1.73e-02 |
Pos logit contributions | |
late | +0.001 |
aback | +0.001 |
Start | +0.001 |
sm | +0.001 |
O | +0.001 |
Neg logit contributions | |
sizes | -0.001 |
bows | -0.001 |
ABC | -0.001 |
planets | -0.001 |
clubs | -0.001 |
Token | the |
Token ID | 262 |
Feature activation | +3.60e-02 |
Pos logit contributions | |
sizes | +0.032 |
planets | +0.028 |
bows | +0.028 |
ABC | +0.027 |
clubs | +0.027 |
Neg logit contributions | |
late | -0.029 |
O | -0.025 |
aback | -0.025 |
Start | -0.025 |
severe | -0.025 |
Token | colors |
Token ID | 7577 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
sizes | +0.043 |
bows | +0.038 |
cultures | +0.037 |
inas | +0.036 |
clubs | +0.036 |
Neg logit contributions | |
late | -0.076 |
aback | -0.066 |
Start | -0.064 |
sm | -0.064 |
my | -0.062 |
Token | shoot |
Token ID | 2686 |
Feature activation | +4.02e-02 |
Pos logit contributions | |
sizes | +0.116 |
planets | +0.099 |
bows | +0.099 |
ABC | +0.098 |
cultures | +0.096 |
Neg logit contributions | |
late | -0.136 |
aback | -0.118 |
Start | -0.116 |
O | -0.115 |
sm | -0.114 |
Token | ac |
Token ID | 936 |
Feature activation | -5.64e-03 |
Pos logit contributions | |
sizes | +0.075 |
planets | +0.067 |
clubs | +0.065 |
languages | +0.063 |
nations | +0.063 |
Neg logit contributions | |
late | -0.066 |
izz | -0.058 |
severe | -0.056 |
aback | -0.056 |
O | -0.055 |
Token | orns |
Token ID | 19942 |
Feature activation | +2.39e-02 |
Pos logit contributions | |
late | +0.010 |
aback | +0.008 |
Start | +0.008 |
sm | +0.008 |
severe | +0.008 |
Neg logit contributions | |
sizes | -0.010 |
bows | -0.009 |
clubs | -0.009 |
planets | -0.009 |
ABC | -0.009 |
Token | with |
Token ID | 351 |
Feature activation | -6.95e-03 |
Pos logit contributions | |
sizes | +0.041 |
planets | +0.036 |
bows | +0.035 |
ABC | +0.035 |
cultures | +0.035 |
Neg logit contributions | |
late | -0.042 |
aback | -0.037 |
sm | -0.036 |
Start | -0.035 |
O | -0.035 |
Token | their |
Token ID | 511 |
Feature activation | +5.23e-02 |
Pos logit contributions | |
late | +0.009 |
aback | +0.008 |
Start | +0.007 |
O | +0.007 |
sm | +0.007 |
Neg logit contributions | |
sizes | -0.015 |
planets | -0.014 |
clubs | -0.013 |
bows | -0.013 |
ABC | -0.013 |
Token | tails |
Token ID | 30514 |
Feature activation | +1.67e-01 |
Pos logit contributions | |
sizes | +0.080 |
bows | +0.072 |
planets | +0.072 |
ABC | +0.070 |
cultures | +0.070 |
Neg logit contributions | |
late | -0.092 |
sm | -0.083 |
aback | -0.083 |
O | -0.082 |
poisonous | -0.082 |
Token | . |
Token ID | 13 |
Feature activation | +2.03e-02 |
Pos logit contributions | |
sizes | +0.312 |
ABC | +0.302 |
cultures | +0.301 |
bows | +0.290 |
planets | +0.285 |
Neg logit contributions | |
late | -0.241 |
aback | -0.200 |
sm | -0.190 |
another | -0.187 |
poisoned | -0.183 |
Token | The |
Token ID | 383 |
Feature activation | +2.98e-02 |
Pos logit contributions | |
sizes | +0.039 |
planets | +0.034 |
bows | +0.034 |
ABC | +0.034 |
clubs | +0.033 |
Neg logit contributions | |
late | -0.032 |
aback | -0.028 |
Start | -0.027 |
sm | -0.027 |
O | -0.027 |
Token | ac |
Token ID | 936 |
Feature activation | -1.90e-02 |
Pos logit contributions | |
sizes | +0.057 |
planets | +0.049 |
bows | +0.049 |
ABC | +0.048 |
cultures | +0.048 |
Neg logit contributions | |
late | -0.049 |
O | -0.043 |
Start | -0.041 |
aback | -0.041 |
sm | -0.040 |
Token | orns |
Token ID | 19942 |
Feature activation | +1.32e-03 |
Pos logit contributions | |
late | +0.032 |
aback | +0.027 |
Start | +0.026 |
sm | +0.025 |
severe | +0.025 |
Neg logit contributions | |
sizes | -0.035 |
bows | -0.031 |
planets | -0.030 |
clubs | -0.030 |
ABC | -0.029 |
Token | flew |
Token ID | 13112 |
Feature activation | -5.52e-03 |
Pos logit contributions | |
sizes | +0.002 |
planets | +0.002 |
ABC | +0.002 |
bows | +0.002 |
cultures | +0.002 |
Neg logit contributions | |
late | -0.002 |
aback | -0.002 |
sm | -0.002 |
Start | -0.002 |
O | -0.002 |
Token | them |
Token ID | 606 |
Feature activation | +9.22e-03 |
Pos logit contributions | |
sizes | +0.016 |
clubs | +0.015 |
planets | +0.014 |
patterns | +0.014 |
languages | +0.014 |
Neg logit contributions | |
late | -0.017 |
severe | -0.015 |
Start | -0.015 |
sm | -0.014 |
O | -0.014 |
Token | how |
Token ID | 703 |
Feature activation | -5.55e-03 |
Pos logit contributions | |
sizes | +0.021 |
planets | +0.019 |
bows | +0.018 |
ABC | +0.018 |
clubs | +0.018 |
Neg logit contributions | |
late | -0.012 |
aback | -0.010 |
Start | -0.009 |
O | -0.009 |
sm | -0.009 |
Token | to |
Token ID | 284 |
Feature activation | +7.79e-03 |
Pos logit contributions | |
late | +0.009 |
aback | +0.008 |
O | +0.008 |
Start | +0.008 |
izz | +0.008 |
Neg logit contributions | |
sizes | -0.010 |
planets | -0.009 |
clubs | -0.009 |
cultures | -0.009 |
toes | -0.008 |
Token | move |
Token ID | 1445 |
Feature activation | +1.54e-02 |
Pos logit contributions | |
sizes | +0.012 |
planets | +0.011 |
bows | +0.010 |
ABC | +0.010 |
clubs | +0.010 |
Neg logit contributions | |
late | -0.015 |
aback | -0.013 |
sm | -0.013 |
Start | -0.013 |
O | -0.013 |
Token | their |
Token ID | 511 |
Feature activation | +5.19e-02 |
Pos logit contributions | |
sizes | +0.032 |
planets | +0.028 |
bows | +0.028 |
clubs | +0.028 |
ABC | +0.027 |
Neg logit contributions | |
late | -0.022 |
aback | -0.018 |
Start | -0.018 |
O | -0.018 |
sm | -0.018 |
Token | tails |
Token ID | 30514 |
Feature activation | +1.67e-01 |
Pos logit contributions | |
sizes | +0.075 |
bows | +0.070 |
planets | +0.061 |
ABC | +0.061 |
inas | +0.061 |
Neg logit contributions | |
late | -0.098 |
aback | -0.087 |
poisoned | -0.085 |
Start | -0.085 |
sm | -0.084 |
Token | in |
Token ID | 287 |
Feature activation | +2.55e-02 |
Pos logit contributions | |
sizes | +0.304 |
ABC | +0.271 |
bows | +0.270 |
cultures | +0.265 |
planets | +0.265 |
Neg logit contributions | |
late | -0.278 |
aback | -0.238 |
Start | -0.223 |
sm | -0.221 |
O | -0.215 |
Token | the |
Token ID | 262 |
Feature activation | +2.71e-02 |
Pos logit contributions | |
sizes | +0.060 |
planets | +0.054 |
clubs | +0.053 |
ABC | +0.053 |
bows | +0.053 |
Neg logit contributions | |
late | -0.029 |
aback | -0.023 |
sm | -0.023 |
Start | -0.022 |
O | -0.022 |
Token | water |
Token ID | 1660 |
Feature activation | +5.37e-02 |
Pos logit contributions | |
sizes | +0.049 |
planets | +0.043 |
bows | +0.042 |
ABC | +0.041 |
clubs | +0.041 |
Neg logit contributions | |
late | -0.046 |
aback | -0.040 |
sm | -0.039 |
Start | -0.039 |
O | -0.039 |
Token | and |
Token ID | 290 |
Feature activation | +1.17e-03 |
Pos logit contributions | |
sizes | +0.083 |
planets | +0.073 |
ABC | +0.073 |
bows | +0.071 |
cultures | +0.071 |
Neg logit contributions | |
late | -0.104 |
aback | -0.091 |
sm | -0.086 |
Start | -0.086 |
O | -0.084 |
Token | soon |
Token ID | 2582 |
Feature activation | -1.68e-02 |
Pos logit contributions | |
sizes | +0.002 |
ABC | +0.002 |
bows | +0.002 |
planets | +0.002 |
cultures | +0.002 |
Neg logit contributions | |
late | -0.002 |
aback | -0.002 |
Start | -0.002 |
sm | -0.002 |
O | -0.002 |
Token | " |
Token ID | 366 |
Feature activation | -3.40e-03 |
Pos logit contributions | |
sizes | +0.041 |
planets | +0.034 |
bows | +0.033 |
ABC | +0.033 |
clubs | +0.032 |
Neg logit contributions | |
late | -0.083 |
aback | -0.074 |
Start | -0.073 |
O | -0.073 |
sm | -0.073 |
Token | Let |
Token ID | 5756 |
Feature activation | -3.00e-03 |
Pos logit contributions | |
late | +0.005 |
poisonous | +0.004 |
severe | +0.004 |
aback | +0.004 |
poisoned | +0.004 |
Neg logit contributions | |
sizes | -0.007 |
bows | -0.006 |
planets | -0.006 |
cultures | -0.006 |
ABC | -0.006 |
Token | 's |
Token ID | 338 |
Feature activation | +6.47e-02 |
Pos logit contributions | |
late | +0.007 |
sm | +0.006 |
izz | +0.006 |
poisonous | +0.006 |
plug | +0.006 |
Neg logit contributions | |
sizes | -0.003 |
ABC | -0.003 |
clubs | -0.003 |
languages | -0.003 |
patterns | -0.003 |
Token | hold |
Token ID | 1745 |
Feature activation | +3.78e-03 |
Pos logit contributions | |
sizes | +0.109 |
planets | +0.094 |
bows | +0.093 |
ABC | +0.092 |
clubs | +0.090 |
Neg logit contributions | |
late | -0.118 |
aback | -0.102 |
Start | -0.100 |
sm | -0.099 |
O | -0.099 |
Token | our |
Token ID | 674 |
Feature activation | +5.24e-02 |
Pos logit contributions | |
sizes | +0.007 |
clubs | +0.006 |
toes | +0.006 |
planets | +0.006 |
patterns | +0.006 |
Neg logit contributions | |
late | -0.006 |
severe | -0.005 |
Start | -0.005 |
O | -0.005 |
poisonous | -0.005 |
Token | tails |
Token ID | 30514 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
sizes | +0.081 |
bows | +0.073 |
planets | +0.068 |
ABC | +0.067 |
cultures | +0.066 |
Neg logit contributions | |
late | -0.097 |
aback | -0.086 |
sm | -0.084 |
Start | -0.082 |
severe | -0.082 |
Token | together |
Token ID | 1978 |
Feature activation | +5.44e-02 |
Pos logit contributions | |
sizes | +0.296 |
planets | +0.259 |
bows | +0.255 |
ABC | +0.252 |
clubs | +0.249 |
Neg logit contributions | |
late | -0.284 |
aback | -0.244 |
Start | -0.240 |
O | -0.238 |
sm | -0.237 |
Token | . |
Token ID | 13 |
Feature activation | +3.98e-02 |
Pos logit contributions | |
sizes | +0.095 |
planets | +0.082 |
bows | +0.081 |
ABC | +0.080 |
clubs | +0.079 |
Neg logit contributions | |
late | -0.095 |
aback | -0.082 |
O | -0.081 |
Start | -0.081 |
sm | -0.080 |
Token | That |
Token ID | 1320 |
Feature activation | +5.22e-03 |
Pos logit contributions | |
sizes | +0.074 |
planets | +0.065 |
bows | +0.064 |
ABC | +0.064 |
clubs | +0.062 |
Neg logit contributions | |
late | -0.065 |
aback | -0.055 |
sm | -0.054 |
Start | -0.054 |
O | -0.054 |
Token | way |
Token ID | 835 |
Feature activation | +2.88e-02 |
Pos logit contributions | |
sizes | +0.007 |
planets | +0.006 |
bows | +0.006 |
ABC | +0.006 |
clubs | +0.006 |
Neg logit contributions | |
late | -0.011 |
aback | -0.010 |
Start | -0.010 |
O | -0.010 |
sm | -0.010 |
Token | , |
Token ID | 11 |
Feature activation | +4.91e-02 |
Pos logit contributions | |
sizes | +0.050 |
planets | +0.043 |
bows | +0.042 |
ABC | +0.042 |
clubs | +0.042 |
Neg logit contributions | |
late | -0.051 |
aback | -0.044 |
O | -0.044 |
Start | -0.044 |
sm | -0.044 |
Token | jumped |
Token ID | 11687 |
Feature activation | +1.72e-02 |
Pos logit contributions | |
late | +0.006 |
aback | +0.006 |
O | +0.005 |
Start | +0.005 |
sm | +0.005 |
Neg logit contributions | |
sizes | -0.007 |
ABC | -0.006 |
bows | -0.006 |
cultures | -0.006 |
planets | -0.006 |
Token | , |
Token ID | 11 |
Feature activation | +5.89e-02 |
Pos logit contributions | |
sizes | +0.031 |
cultures | +0.028 |
ABC | +0.028 |
planets | +0.027 |
hobbies | +0.027 |
Neg logit contributions | |
late | -0.031 |
aback | -0.027 |
Start | -0.025 |
O | -0.025 |
sm | -0.024 |
Token | w |
Token ID | 266 |
Feature activation | +3.27e-02 |
Pos logit contributions | |
sizes | +0.099 |
cultures | +0.093 |
planets | +0.091 |
ABC | +0.091 |
languages | +0.089 |
Neg logit contributions | |
late | -0.105 |
aback | -0.091 |
Start | -0.087 |
sm | -0.085 |
O | -0.083 |
Token | agging |
Token ID | 16406 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
sizes | +0.040 |
planets | +0.033 |
bows | +0.033 |
ABC | +0.032 |
cultures | +0.031 |
Neg logit contributions | |
late | -0.074 |
aback | -0.067 |
Start | -0.066 |
O | -0.065 |
sm | -0.065 |
Token | their |
Token ID | 511 |
Feature activation | +5.71e-02 |
Pos logit contributions | |
sizes | +0.242 |
ABC | +0.233 |
cultures | +0.230 |
bows | +0.223 |
planets | +0.216 |
Neg logit contributions | |
late | -0.198 |
sm | -0.165 |
aback | -0.164 |
Start | -0.155 |
O | -0.154 |
Token | tails |
Token ID | 30514 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
sizes | +0.060 |
bows | +0.057 |
hips | +0.056 |
ABC | +0.056 |
cultures | +0.056 |
Neg logit contributions | |
late | -0.120 |
sm | -0.112 |
poisonous | -0.108 |
O | -0.105 |
severe | -0.104 |
Token | . |
Token ID | 13 |
Feature activation | +2.29e-02 |
Pos logit contributions | |
cultures | +0.314 |
ABC | +0.311 |
sizes | +0.298 |
hobbies | +0.291 |
azes | +0.286 |
Neg logit contributions | |
late | -0.231 |
aback | -0.194 |
another | -0.191 |
sm | -0.182 |
away | -0.181 |
Token |
|
Token ID | 198 |
Feature activation | -1.42e-02 |
Pos logit contributions | |
sizes | +0.042 |
planets | +0.037 |
bows | +0.037 |
ABC | +0.036 |
clubs | +0.036 |
Neg logit contributions | |
late | -0.038 |
aback | -0.033 |
sm | -0.032 |
Start | -0.032 |
O | -0.032 |
Token |
|
Token ID | 198 |
Feature activation | -1.87e-02 |
Pos logit contributions | |
late | +0.024 |
aback | +0.022 |
sm | +0.020 |
poisoned | +0.020 |
Start | +0.020 |
Neg logit contributions | |
sizes | -0.024 |
ABC | -0.021 |
planets | -0.021 |
clubs | -0.020 |
bows | -0.020 |
Token | Then |
Token ID | 6423 |
Feature activation | +4.45e-02 |
Pos logit contributions | |
aback | +0.033 |
late | +0.033 |
sm | +0.029 |
poisonous | +0.029 |
poisoned | +0.029 |
Neg logit contributions | |
sizes | -0.029 |
planets | -0.025 |
clubs | -0.025 |
necks | -0.025 |
ABC | -0.024 |
Token | , |
Token ID | 11 |
Feature activation | +1.69e-02 |
Pos logit contributions | |
sizes | +0.077 |
bows | +0.067 |
cultures | +0.065 |
ABC | +0.065 |
planets | +0.062 |
Neg logit contributions | |
late | -0.081 |
O | -0.069 |
aback | -0.068 |
Start | -0.067 |
sm | -0.065 |
Token | cars |
Token ID | 5006 |
Feature activation | +4.73e-02 |
Pos logit contributions | |
late | +0.078 |
sm | +0.069 |
aback | +0.068 |
my | +0.067 |
O | +0.066 |
Neg logit contributions | |
bows | -0.047 |
sizes | -0.044 |
hips | -0.042 |
cultures | -0.042 |
azes | -0.040 |
Token | of |
Token ID | 286 |
Feature activation | -1.47e-02 |
Pos logit contributions | |
sizes | +0.071 |
planets | +0.061 |
cultures | +0.060 |
ABC | +0.059 |
toes | +0.059 |
Neg logit contributions | |
late | -0.095 |
aback | -0.083 |
sm | -0.081 |
Start | -0.079 |
O | -0.079 |
Token | different |
Token ID | 1180 |
Feature activation | +1.79e-02 |
Pos logit contributions | |
late | +0.023 |
aback | +0.019 |
O | +0.019 |
Start | +0.019 |
sm | +0.018 |
Neg logit contributions | |
sizes | -0.028 |
bows | -0.025 |
planets | -0.025 |
ABC | -0.024 |
cultures | -0.024 |
Token | colors |
Token ID | 7577 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
hips | +0.018 |
azes | +0.017 |
mast | +0.017 |
sing | +0.017 |
igo | +0.017 |
Neg logit contributions | |
late | -0.036 |
aback | -0.033 |
my | -0.031 |
sm | -0.031 |
another | -0.030 |
Token | and |
Token ID | 290 |
Feature activation | +5.96e-03 |
Pos logit contributions | |
sizes | +0.193 |
cultures | +0.184 |
ABC | +0.179 |
planets | +0.176 |
toes | +0.174 |
Neg logit contributions | |
late | -0.191 |
sm | -0.151 |
aback | -0.151 |
my | -0.141 |
Start | -0.140 |
Token | sizes |
Token ID | 10620 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
pit | +0.004 |
utes | +0.004 |
azes | +0.004 |
castle | +0.003 |
bles | +0.003 |
Neg logit contributions | |
late | -0.014 |
my | -0.013 |
another | -0.013 |
sm | -0.012 |
aback | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | +3.16e-02 |
Pos logit contributions | |
sizes | +0.279 |
ABC | +0.269 |
cultures | +0.265 |
planets | +0.263 |
cheeks | +0.254 |
Neg logit contributions | |
late | -0.258 |
sm | -0.218 |
aback | -0.209 |
Start | -0.196 |
O | -0.190 |
Token | They |
Token ID | 1119 |
Feature activation | +6.34e-02 |
Pos logit contributions | |
sizes | +0.062 |
bows | +0.055 |
planets | +0.055 |
ABC | +0.054 |
cultures | +0.054 |
Neg logit contributions | |
late | -0.050 |
O | -0.040 |
aback | -0.040 |
Start | -0.039 |
sm | -0.039 |
Token | make |
Token ID | 787 |
Feature activation | +2.87e-02 |
Pos logit contributions | |
sizes | +0.116 |
ABC | +0.108 |
bows | +0.105 |
cultures | +0.104 |
azes | +0.104 |
Neg logit contributions | |
late | -0.090 |
aback | -0.075 |
Start | -0.073 |
O | -0.072 |
sm | -0.071 |
Token | a |
Token ID | 257 |
Feature activation | +3.15e-02 |
Pos logit contributions | |
sizes | +0.048 |
cultures | +0.042 |
bows | +0.042 |
toes | +0.040 |
cheeks | +0.040 |
Neg logit contributions | |
late | -0.051 |
Start | -0.042 |
another | -0.041 |
aback | -0.040 |
sm | -0.040 |
Token | line |
Token ID | 1627 |
Feature activation | -4.86e-02 |
Pos logit contributions | |
sizes | +0.065 |
bows | +0.063 |
cultures | +0.059 |
aces | +0.058 |
azes | +0.057 |
Neg logit contributions | |
late | -0.043 |
my | -0.033 |
poisonous | -0.031 |
Start | -0.031 |
O | -0.031 |
Token | cubes |
Token ID | 34896 |
Feature activation | +1.38e-02 |
Pos logit contributions | |
late | +0.087 |
sm | +0.075 |
aback | +0.075 |
Start | +0.071 |
O | +0.070 |
Neg logit contributions | |
bows | -0.055 |
sizes | -0.054 |
cultures | -0.048 |
hips | -0.048 |
ABC | -0.048 |
Token | of |
Token ID | 286 |
Feature activation | -3.21e-02 |
Pos logit contributions | |
sizes | +0.026 |
planets | +0.023 |
bows | +0.023 |
ABC | +0.022 |
clubs | +0.022 |
Neg logit contributions | |
late | -0.022 |
aback | -0.019 |
Start | -0.019 |
O | -0.019 |
sm | -0.018 |
Token | different |
Token ID | 1180 |
Feature activation | +6.89e-03 |
Pos logit contributions | |
late | +0.044 |
aback | +0.036 |
O | +0.035 |
sm | +0.035 |
Start | +0.035 |
Neg logit contributions | |
sizes | -0.067 |
bows | -0.061 |
planets | -0.061 |
ABC | -0.060 |
cultures | -0.059 |
Token | colors |
Token ID | 7577 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
bows | +0.008 |
hips | +0.007 |
sizes | +0.007 |
ABC | +0.007 |
tails | +0.007 |
Neg logit contributions | |
late | -0.015 |
aback | -0.013 |
sm | -0.012 |
another | -0.012 |
my | -0.012 |
Token | and |
Token ID | 290 |
Feature activation | +5.39e-03 |
Pos logit contributions | |
sizes | +0.190 |
cultures | +0.178 |
ABC | +0.175 |
planets | +0.174 |
necks | +0.169 |
Neg logit contributions | |
late | -0.195 |
sm | -0.158 |
aback | -0.156 |
O | -0.147 |
izz | -0.146 |
Token | sizes |
Token ID | 10620 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
utes | +0.004 |
azes | +0.004 |
ABC | +0.004 |
hips | +0.004 |
bows | +0.004 |
Neg logit contributions | |
late | -0.013 |
my | -0.011 |
sm | -0.011 |
another | -0.011 |
aback | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | +3.08e-02 |
Pos logit contributions | |
sizes | +0.274 |
ABC | +0.261 |
planets | +0.257 |
cultures | +0.255 |
necks | +0.245 |
Neg logit contributions | |
late | -0.267 |
sm | -0.226 |
aback | -0.218 |
Start | -0.206 |
O | -0.202 |
Token | They |
Token ID | 1119 |
Feature activation | +6.33e-02 |
Pos logit contributions | |
sizes | +0.058 |
planets | +0.052 |
bows | +0.051 |
ABC | +0.050 |
cultures | +0.050 |
Neg logit contributions | |
late | -0.050 |
aback | -0.042 |
Start | -0.041 |
O | -0.041 |
sm | -0.040 |
Token | build |
Token ID | 1382 |
Feature activation | +3.49e-02 |
Pos logit contributions | |
sizes | +0.112 |
ABC | +0.102 |
bows | +0.101 |
planets | +0.099 |
cultures | +0.098 |
Neg logit contributions | |
late | -0.099 |
aback | -0.083 |
Start | -0.081 |
sm | -0.081 |
O | -0.080 |
Token | towers |
Token ID | 18028 |
Feature activation | +8.35e-02 |
Pos logit contributions | |
sizes | +0.068 |
inas | +0.065 |
bows | +0.065 |
cultures | +0.064 |
cheeks | +0.063 |
Neg logit contributions | |
late | -0.051 |
another | -0.043 |
aback | -0.036 |
my | -0.036 |
Start | -0.035 |
Token | and |
Token ID | 290 |
Feature activation | -5.53e-03 |
Pos logit contributions | |
sizes | +0.167 |
cultures | +0.160 |
hobbies | +0.159 |
cheeks | +0.157 |
habitats | +0.154 |
Neg logit contributions | |
late | -0.123 |
another | -0.097 |
sm | -0.083 |
here | -0.080 |
my | -0.080 |
Token | cars |
Token ID | 5006 |
Feature activation | +4.58e-02 |
Pos logit contributions | |
late | +0.080 |
sm | +0.071 |
aback | +0.070 |
Start | +0.068 |
my | +0.067 |
Neg logit contributions | |
bows | -0.048 |
sizes | -0.048 |
hips | -0.042 |
cultures | -0.042 |
ABC | -0.041 |
Token | of |
Token ID | 286 |
Feature activation | -1.58e-02 |
Pos logit contributions | |
sizes | +0.072 |
planets | +0.063 |
ABC | +0.061 |
cultures | +0.061 |
toes | +0.060 |
Neg logit contributions | |
late | -0.088 |
aback | -0.076 |
sm | -0.075 |
Start | -0.073 |
O | -0.072 |
Token | different |
Token ID | 1180 |
Feature activation | +1.81e-02 |
Pos logit contributions | |
late | +0.025 |
aback | +0.020 |
Start | +0.020 |
O | +0.020 |
sm | +0.020 |
Neg logit contributions | |
sizes | -0.030 |
bows | -0.027 |
planets | -0.026 |
ABC | -0.026 |
cultures | -0.026 |
Token | colors |
Token ID | 7577 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
hips | +0.018 |
mast | +0.017 |
sing | +0.017 |
igo | +0.017 |
azes | +0.017 |
Neg logit contributions | |
late | -0.037 |
aback | -0.034 |
sm | -0.032 |
my | -0.032 |
another | -0.030 |
Token | and |
Token ID | 290 |
Feature activation | +6.48e-03 |
Pos logit contributions | |
sizes | +0.187 |
cultures | +0.176 |
ABC | +0.173 |
planets | +0.170 |
necks | +0.169 |
Neg logit contributions | |
late | -0.190 |
sm | -0.152 |
aback | -0.151 |
my | -0.143 |
Start | -0.140 |
Token | sizes |
Token ID | 10620 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
pit | +0.004 |
utes | +0.004 |
azes | +0.004 |
ahs | +0.004 |
bles | +0.004 |
Neg logit contributions | |
late | -0.016 |
my | -0.015 |
another | -0.014 |
sm | -0.014 |
aback | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | +2.89e-02 |
Pos logit contributions | |
sizes | +0.276 |
ABC | +0.263 |
planets | +0.258 |
cultures | +0.257 |
necks | +0.249 |
Neg logit contributions | |
late | -0.260 |
sm | -0.221 |
aback | -0.210 |
Start | -0.198 |
O | -0.191 |
Token | They |
Token ID | 1119 |
Feature activation | +6.24e-02 |
Pos logit contributions | |
sizes | +0.055 |
bows | +0.049 |
planets | +0.049 |
ABC | +0.048 |
clubs | +0.048 |
Neg logit contributions | |
late | -0.047 |
O | -0.038 |
aback | -0.038 |
Start | -0.037 |
sm | -0.037 |
Token | like |
Token ID | 588 |
Feature activation | +5.61e-02 |
Pos logit contributions | |
sizes | +0.112 |
ABC | +0.102 |
toes | +0.099 |
bows | +0.099 |
cultures | +0.098 |
Neg logit contributions | |
late | -0.095 |
aback | -0.079 |
Start | -0.077 |
sm | -0.076 |
O | -0.076 |
Token | to |
Token ID | 284 |
Feature activation | +1.27e-02 |
Pos logit contributions | |
sizes | +0.125 |
bows | +0.117 |
cheeks | +0.114 |
necks | +0.114 |
planets | +0.114 |
Neg logit contributions | |
late | -0.067 |
sm | -0.047 |
my | -0.044 |
another | -0.043 |
Start | -0.042 |
Token | drive |
Token ID | 3708 |
Feature activation | +2.31e-04 |
Pos logit contributions | |
sizes | +0.021 |
planets | +0.019 |
bows | +0.018 |
ABC | +0.018 |
cultures | +0.018 |
Neg logit contributions | |
late | -0.022 |
O | -0.019 |
Start | -0.019 |
aback | -0.019 |
sm | -0.018 |
Token | cars |
Token ID | 5006 |
Feature activation | +4.88e-02 |
Pos logit contributions | |
late | +0.074 |
sm | +0.067 |
aback | +0.063 |
Start | +0.062 |
my | +0.062 |
Neg logit contributions | |
bows | -0.042 |
sizes | -0.040 |
hips | -0.037 |
cultures | -0.037 |
inas | -0.036 |
Token | of |
Token ID | 286 |
Feature activation | -1.69e-02 |
Pos logit contributions | |
sizes | +0.082 |
cultures | +0.075 |
planets | +0.075 |
toes | +0.073 |
ABC | +0.073 |
Neg logit contributions | |
late | -0.086 |
sm | -0.072 |
aback | -0.070 |
Start | -0.065 |
O | -0.064 |
Token | different |
Token ID | 1180 |
Feature activation | +1.92e-02 |
Pos logit contributions | |
late | +0.023 |
aback | +0.018 |
Start | +0.018 |
O | +0.017 |
sm | +0.017 |
Neg logit contributions | |
sizes | -0.035 |
bows | -0.032 |
planets | -0.032 |
cheeks | -0.031 |
cultures | -0.031 |
Token | colors |
Token ID | 7577 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
mast | +0.019 |
hips | +0.019 |
sing | +0.018 |
cheeks | +0.018 |
disco | +0.018 |
Neg logit contributions | |
late | -0.039 |
aback | -0.035 |
sm | -0.034 |
my | -0.033 |
another | -0.032 |
Token | and |
Token ID | 290 |
Feature activation | +1.04e-02 |
Pos logit contributions | |
cultures | +0.213 |
sizes | +0.211 |
habitats | +0.205 |
cheeks | +0.203 |
necks | +0.203 |
Neg logit contributions | |
late | -0.173 |
sm | -0.135 |
another | -0.126 |
aback | -0.126 |
my | -0.123 |
Token | sizes |
Token ID | 10620 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
pit | +0.009 |
castle | +0.008 |
utes | +0.007 |
azes | +0.007 |
iked | +0.007 |
Neg logit contributions | |
late | -0.023 |
my | -0.022 |
the | -0.021 |
another | -0.021 |
Start | -0.020 |
Token | . |
Token ID | 13 |
Feature activation | +2.17e-02 |
Pos logit contributions | |
sizes | +0.289 |
ABC | +0.281 |
planets | +0.278 |
cultures | +0.277 |
habitats | +0.269 |
Neg logit contributions | |
late | -0.234 |
sm | -0.201 |
aback | -0.184 |
Start | -0.175 |
another | -0.172 |
Token | They |
Token ID | 1119 |
Feature activation | +6.74e-02 |
Pos logit contributions | |
sizes | +0.044 |
bows | +0.041 |
planets | +0.040 |
ABC | +0.039 |
cultures | +0.039 |
Neg logit contributions | |
late | -0.032 |
O | -0.026 |
aback | -0.025 |
Start | -0.024 |
sm | -0.024 |
Token | make |
Token ID | 787 |
Feature activation | +2.88e-02 |
Pos logit contributions | |
sizes | +0.132 |
ABC | +0.124 |
bows | +0.122 |
azes | +0.121 |
cultures | +0.121 |
Neg logit contributions | |
late | -0.086 |
aback | -0.070 |
O | -0.068 |
Start | -0.067 |
sm | -0.066 |
Token | zoom |
Token ID | 19792 |
Feature activation | +2.52e-02 |
Pos logit contributions | |
sizes | +0.046 |
cultures | +0.042 |
bows | +0.042 |
cheeks | +0.040 |
toes | +0.040 |
Neg logit contributions | |
late | -0.051 |
Start | -0.042 |
another | -0.041 |
aback | -0.041 |
O | -0.040 |
Token | sounds |
Token ID | 5238 |
Feature activation | +8.80e-02 |
Pos logit contributions | |
sizes | +0.040 |
cultures | +0.036 |
toes | +0.035 |
planets | +0.035 |
necks | +0.035 |
Neg logit contributions | |
late | -0.045 |
aback | -0.039 |
Start | -0.038 |
sm | -0.037 |
O | -0.037 |
Token | cubes |
Token ID | 34896 |
Feature activation | +1.45e-02 |
Pos logit contributions | |
late | +0.078 |
sm | +0.067 |
aback | +0.067 |
O | +0.065 |
Start | +0.065 |
Neg logit contributions | |
bows | -0.047 |
sizes | -0.046 |
cultures | -0.041 |
hips | -0.041 |
inas | -0.041 |
Token | of |
Token ID | 286 |
Feature activation | -3.04e-02 |
Pos logit contributions | |
sizes | +0.028 |
planets | +0.026 |
ABC | +0.025 |
cultures | +0.025 |
bows | +0.025 |
Neg logit contributions | |
late | -0.023 |
aback | -0.018 |
sm | -0.018 |
Start | -0.017 |
O | -0.017 |
Token | different |
Token ID | 1180 |
Feature activation | +1.06e-02 |
Pos logit contributions | |
late | +0.044 |
aback | +0.036 |
Start | +0.035 |
O | +0.035 |
sm | +0.035 |
Neg logit contributions | |
sizes | -0.061 |
planets | -0.055 |
bows | -0.055 |
ABC | -0.054 |
cultures | -0.054 |
Token | colors |
Token ID | 7577 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
bows | +0.011 |
hips | +0.011 |
tails | +0.011 |
inas | +0.011 |
cheeks | +0.011 |
Neg logit contributions | |
late | -0.023 |
aback | -0.020 |
sm | -0.019 |
another | -0.018 |
Start | -0.018 |
Token | and |
Token ID | 290 |
Feature activation | +6.92e-03 |
Pos logit contributions | |
cultures | +0.214 |
sizes | +0.211 |
habitats | +0.209 |
ABC | +0.204 |
planets | +0.203 |
Neg logit contributions | |
late | -0.174 |
sm | -0.133 |
another | -0.126 |
izz | -0.123 |
aback | -0.121 |
Token | sizes |
Token ID | 10620 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
utes | +0.006 |
pit | +0.006 |
azes | +0.006 |
ahs | +0.005 |
habitats | +0.005 |
Neg logit contributions | |
late | -0.015 |
my | -0.014 |
another | -0.014 |
the | -0.013 |
some | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | +2.25e-02 |
Pos logit contributions | |
sizes | +0.291 |
ABC | +0.287 |
planets | +0.286 |
cultures | +0.282 |
habitats | +0.279 |
Neg logit contributions | |
late | -0.233 |
sm | -0.197 |
aback | -0.177 |
another | -0.170 |
Start | -0.170 |
Token | They |
Token ID | 1119 |
Feature activation | +6.65e-02 |
Pos logit contributions | |
sizes | +0.046 |
planets | +0.042 |
bows | +0.041 |
clubs | +0.041 |
cultures | +0.040 |
Neg logit contributions | |
late | -0.032 |
O | -0.026 |
Start | -0.026 |
aback | -0.026 |
sm | -0.025 |
Token | can |
Token ID | 460 |
Feature activation | +7.81e-02 |
Pos logit contributions | |
sizes | +0.125 |
ABC | +0.116 |
bows | +0.116 |
planets | +0.113 |
cultures | +0.112 |
Neg logit contributions | |
late | -0.093 |
aback | -0.076 |
O | -0.075 |
Start | -0.074 |
sm | -0.073 |
Token | make |
Token ID | 787 |
Feature activation | +3.21e-02 |
Pos logit contributions | |
sizes | +0.140 |
bows | +0.126 |
cultures | +0.124 |
planets | +0.124 |
languages | +0.120 |
Neg logit contributions | |
late | -0.126 |
O | -0.106 |
Start | -0.103 |
aback | -0.101 |
izz | -0.099 |
Token | towers |
Token ID | 18028 |
Feature activation | +9.38e-02 |
Pos logit contributions | |
sizes | +0.056 |
bows | +0.053 |
cultures | +0.052 |
cheeks | +0.050 |
habitats | +0.050 |
Neg logit contributions | |
late | -0.053 |
another | -0.043 |
aback | -0.041 |
Start | -0.041 |
my | -0.041 |
Token | they |
Token ID | 484 |
Feature activation | +3.27e-02 |
Pos logit contributions | |
sizes | +0.002 |
planets | +0.002 |
ABC | +0.002 |
cultures | +0.002 |
nations | +0.002 |
Neg logit contributions | |
late | -0.002 |
aback | -0.002 |
Start | -0.002 |
O | -0.002 |
sm | -0.002 |
Token | 're |
Token ID | 821 |
Feature activation | +6.83e-02 |
Pos logit contributions | |
sizes | +0.051 |
planets | +0.043 |
bows | +0.042 |
ABC | +0.040 |
cultures | +0.040 |
Neg logit contributions | |
late | -0.067 |
O | -0.058 |
aback | -0.058 |
Start | -0.057 |
sm | -0.057 |
Token | different |
Token ID | 1180 |
Feature activation | +2.25e-02 |
Pos logit contributions | |
sizes | +0.126 |
planets | +0.109 |
bows | +0.105 |
ABC | +0.103 |
toes | +0.102 |
Neg logit contributions | |
late | -0.114 |
aback | -0.103 |
O | -0.102 |
Start | -0.102 |
sm | -0.099 |
Token | colors |
Token ID | 7577 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
sizes | +0.039 |
clubs | +0.036 |
necks | +0.036 |
ABC | +0.035 |
planets | +0.035 |
Neg logit contributions | |
late | -0.037 |
aback | -0.030 |
sm | -0.029 |
my | -0.028 |
Start | -0.027 |
Token | and |
Token ID | 290 |
Feature activation | +2.91e-03 |
Pos logit contributions | |
sizes | +0.241 |
cultures | +0.221 |
ABC | +0.220 |
planets | +0.219 |
clubs | +0.219 |
Neg logit contributions | |
late | -0.182 |
aback | -0.142 |
sm | -0.141 |
Start | -0.132 |
O | -0.130 |
Token | sizes |
Token ID | 10620 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
sizes | +0.004 |
ABC | +0.003 |
bows | +0.003 |
clubs | +0.003 |
planets | +0.003 |
Neg logit contributions | |
late | -0.006 |
aback | -0.005 |
sm | -0.005 |
Start | -0.005 |
my | -0.005 |
Token | ." |
Token ID | 526 |
Feature activation | -1.91e-02 |
Pos logit contributions | |
sizes | +0.297 |
planets | +0.269 |
ABC | +0.267 |
cultures | +0.262 |
clubs | +0.261 |
Neg logit contributions | |
late | -0.256 |
aback | -0.216 |
sm | -0.212 |
Start | -0.206 |
O | -0.201 |
Token |
|
Token ID | 198 |
Feature activation | -1.24e-02 |
Pos logit contributions | |
late | +0.022 |
aback | +0.016 |
Start | +0.016 |
O | +0.016 |
sm | +0.014 |
Neg logit contributions | |
sizes | -0.048 |
planets | -0.043 |
cultures | -0.043 |
bows | -0.042 |
nations | -0.041 |
Token |
|
Token ID | 198 |
Feature activation | -1.66e-02 |
Pos logit contributions | |
late | +0.018 |
aback | +0.015 |
Start | +0.015 |
O | +0.015 |
sm | +0.015 |
Neg logit contributions | |
sizes | -0.025 |
planets | -0.022 |
bows | -0.022 |
ABC | -0.022 |
clubs | -0.022 |
Token | Max |
Token ID | 11518 |
Feature activation | +4.56e-02 |
Pos logit contributions | |
late | +0.025 |
O | +0.021 |
Start | +0.021 |
aback | +0.020 |
sm | +0.020 |
Neg logit contributions | |
sizes | -0.034 |
bows | -0.030 |
planets | -0.030 |
ABC | -0.029 |
toes | -0.029 |
Token | started |
Token ID | 2067 |
Feature activation | +9.45e-03 |
Pos logit contributions | |
sizes | +0.079 |
planets | +0.069 |
bows | +0.068 |
ABC | +0.067 |
cultures | +0.066 |
Neg logit contributions | |
late | -0.080 |
aback | -0.070 |
Start | -0.068 |
O | -0.068 |
sm | -0.067 |
Token | cars |
Token ID | 5006 |
Feature activation | +4.84e-02 |
Pos logit contributions | |
late | +0.079 |
sm | +0.072 |
aback | +0.067 |
my | +0.067 |
O | +0.067 |
Neg logit contributions | |
bows | -0.047 |
sizes | -0.044 |
hips | -0.042 |
cultures | -0.041 |
cheeks | -0.040 |
Token | of |
Token ID | 286 |
Feature activation | -1.45e-02 |
Pos logit contributions | |
sizes | +0.084 |
planets | +0.077 |
cultures | +0.077 |
toes | +0.077 |
cheeks | +0.074 |
Neg logit contributions | |
late | -0.083 |
sm | -0.070 |
aback | -0.067 |
Start | -0.062 |
O | -0.062 |
Token | different |
Token ID | 1180 |
Feature activation | +1.78e-02 |
Pos logit contributions | |
late | +0.021 |
Start | +0.017 |
aback | +0.017 |
O | +0.017 |
sm | +0.017 |
Neg logit contributions | |
sizes | -0.028 |
bows | -0.026 |
planets | -0.025 |
cultures | -0.025 |
ABC | -0.025 |
Token | colors |
Token ID | 7577 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
mast | +0.018 |
hips | +0.018 |
sing | +0.017 |
cheeks | +0.016 |
disco | +0.016 |
Neg logit contributions | |
late | -0.036 |
aback | -0.032 |
sm | -0.032 |
my | -0.030 |
another | -0.029 |
Token | and |
Token ID | 290 |
Feature activation | +7.41e-03 |
Pos logit contributions | |
cultures | +0.205 |
sizes | +0.205 |
antics | +0.197 |
habitats | +0.197 |
ABC | +0.195 |
Neg logit contributions | |
late | -0.170 |
sm | -0.132 |
aback | -0.123 |
another | -0.121 |
my | -0.119 |
Token | sizes |
Token ID | 10620 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
pit | +0.005 |
utes | +0.005 |
castle | +0.004 |
azes | +0.004 |
bles | +0.004 |
Neg logit contributions | |
late | -0.018 |
my | -0.016 |
another | -0.016 |
the | -0.016 |
Start | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | +2.25e-02 |
Pos logit contributions | |
sizes | +0.290 |
ABC | +0.289 |
planets | +0.284 |
cultures | +0.283 |
habitats | +0.278 |
Neg logit contributions | |
late | -0.227 |
sm | -0.194 |
aback | -0.175 |
another | -0.163 |
Start | -0.161 |
Token | They |
Token ID | 1119 |
Feature activation | +6.40e-02 |
Pos logit contributions | |
sizes | +0.040 |
planets | +0.035 |
ABC | +0.034 |
bows | +0.034 |
toes | +0.033 |
Neg logit contributions | |
late | -0.039 |
aback | -0.035 |
sm | -0.034 |
Start | -0.033 |
O | -0.033 |
Token | make |
Token ID | 787 |
Feature activation | +2.90e-02 |
Pos logit contributions | |
sizes | +0.120 |
ABC | +0.112 |
bows | +0.110 |
azes | +0.109 |
cultures | +0.108 |
Neg logit contributions | |
late | -0.088 |
aback | -0.071 |
O | -0.070 |
sm | -0.069 |
Start | -0.069 |
Token | roads |
Token ID | 9725 |
Feature activation | +6.36e-02 |
Pos logit contributions | |
sizes | +0.045 |
cultures | +0.040 |
bows | +0.040 |
toes | +0.039 |
cheeks | +0.038 |
Neg logit contributions | |
late | -0.054 |
Start | -0.044 |
aback | -0.043 |
another | -0.043 |
sm | -0.043 |
Token | with |
Token ID | 351 |
Feature activation | -1.79e-02 |
Pos logit contributions | |
sizes | +0.117 |
cheeks | +0.112 |
toes | +0.112 |
habitats | +0.111 |
cultures | +0.111 |
Neg logit contributions | |
late | -0.093 |
another | -0.073 |
aback | -0.067 |
away | -0.065 |
my | -0.064 |
Token | it |
Token ID | 340 |
Feature activation | -4.57e-02 |
Pos logit contributions | |
sizes | +0.070 |
planets | +0.065 |
patterns | +0.063 |
ABC | +0.063 |
toes | +0.061 |
Neg logit contributions | |
late | -0.043 |
aback | -0.037 |
O | -0.035 |
sm | -0.035 |
severe | -0.035 |
Token | with |
Token ID | 351 |
Feature activation | -8.08e-03 |
Pos logit contributions | |
late | +0.077 |
aback | +0.066 |
Start | +0.065 |
O | +0.065 |
sm | +0.064 |
Neg logit contributions | |
sizes | -0.083 |
planets | -0.073 |
bows | -0.072 |
ABC | -0.071 |
clubs | -0.070 |
Token | holes |
Token ID | 10421 |
Feature activation | +4.16e-02 |
Pos logit contributions | |
late | +0.011 |
aback | +0.010 |
izz | +0.009 |
Start | +0.009 |
sm | +0.009 |
Neg logit contributions | |
sizes | -0.017 |
planets | -0.016 |
patterns | -0.015 |
toes | -0.015 |
clubs | -0.015 |
Token | of |
Token ID | 286 |
Feature activation | +9.36e-03 |
Pos logit contributions | |
sizes | +0.064 |
planets | +0.055 |
bows | +0.054 |
ABC | +0.053 |
clubs | +0.052 |
Neg logit contributions | |
late | -0.081 |
aback | -0.071 |
Start | -0.070 |
O | -0.070 |
sm | -0.069 |
Token | different |
Token ID | 1180 |
Feature activation | +3.26e-02 |
Pos logit contributions | |
sizes | +0.021 |
planets | +0.020 |
patterns | +0.019 |
clubs | +0.019 |
toes | +0.018 |
Neg logit contributions | |
late | -0.012 |
aback | -0.010 |
izz | -0.010 |
Start | -0.010 |
sm | -0.010 |
Token | sizes |
Token ID | 10620 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
sizes | +0.036 |
bows | +0.032 |
ABC | +0.032 |
hips | +0.030 |
planets | +0.030 |
Neg logit contributions | |
late | -0.072 |
aback | -0.065 |
sm | -0.063 |
Start | -0.063 |
O | -0.061 |
Token | . |
Token ID | 13 |
Feature activation | +2.42e-02 |
Pos logit contributions | |
sizes | +0.269 |
planets | +0.236 |
ABC | +0.234 |
bows | +0.233 |
cultures | +0.229 |
Neg logit contributions | |
late | -0.289 |
aback | -0.248 |
sm | -0.243 |
Start | -0.240 |
O | -0.238 |
Token | I |
Token ID | 314 |
Feature activation | -5.25e-02 |
Pos logit contributions | |
sizes | +0.048 |
planets | +0.043 |
bows | +0.042 |
ABC | +0.042 |
clubs | +0.041 |
Neg logit contributions | |
late | -0.036 |
aback | -0.031 |
Start | -0.030 |
sm | -0.030 |
O | -0.030 |
Token | will |
Token ID | 481 |
Feature activation | +7.58e-02 |
Pos logit contributions | |
late | +0.105 |
aback | +0.091 |
O | +0.091 |
severe | +0.090 |
Start | +0.089 |
Neg logit contributions | |
sizes | -0.078 |
bows | -0.067 |
planets | -0.062 |
ABC | -0.061 |
patterns | -0.060 |
Token | make |
Token ID | 787 |
Feature activation | +3.42e-02 |
Pos logit contributions | |
sizes | +0.138 |
planets | +0.121 |
bows | +0.121 |
ABC | +0.119 |
cultures | +0.117 |
Neg logit contributions | |
late | -0.126 |
aback | -0.106 |
Start | -0.106 |
O | -0.104 |
sm | -0.101 |
Token | it |
Token ID | 340 |
Feature activation | -4.53e-02 |
Pos logit contributions | |
sizes | +0.074 |
planets | +0.069 |
patterns | +0.067 |
ABC | +0.066 |
clubs | +0.065 |
Neg logit contributions | |
late | -0.045 |
aback | -0.038 |
O | -0.037 |
sm | -0.036 |
severe | -0.036 |
Token | cars |
Token ID | 5006 |
Feature activation | +5.01e-02 |
Pos logit contributions | |
late | +0.083 |
sm | +0.075 |
aback | +0.071 |
severe | +0.070 |
O | +0.070 |
Neg logit contributions | |
sizes | -0.045 |
bows | -0.044 |
hips | -0.039 |
cultures | -0.039 |
planets | -0.038 |
Token | of |
Token ID | 286 |
Feature activation | -1.27e-02 |
Pos logit contributions | |
sizes | +0.106 |
cultures | +0.099 |
planets | +0.099 |
toes | +0.097 |
cheeks | +0.095 |
Neg logit contributions | |
late | -0.067 |
sm | -0.053 |
aback | -0.051 |
Start | -0.044 |
O | -0.044 |
Token | different |
Token ID | 1180 |
Feature activation | +1.84e-02 |
Pos logit contributions | |
late | +0.017 |
aback | +0.014 |
Start | +0.014 |
O | +0.014 |
sm | +0.014 |
Neg logit contributions | |
sizes | -0.026 |
bows | -0.024 |
planets | -0.024 |
ABC | -0.023 |
cultures | -0.023 |
Token | colors |
Token ID | 7577 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
mast | +0.019 |
hips | +0.019 |
disco | +0.018 |
sing | +0.017 |
igo | +0.017 |
Neg logit contributions | |
late | -0.037 |
aback | -0.033 |
sm | -0.033 |
another | -0.030 |
my | -0.030 |
Token | and |
Token ID | 290 |
Feature activation | +6.62e-03 |
Pos logit contributions | |
cultures | +0.233 |
sizes | +0.225 |
habitats | +0.223 |
antics | +0.223 |
necks | +0.220 |
Neg logit contributions | |
late | -0.152 |
sm | -0.116 |
another | -0.107 |
aback | -0.103 |
out | -0.097 |
Token | sizes |
Token ID | 10620 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
pit | +0.005 |
utes | +0.005 |
castle | +0.005 |
azes | +0.005 |
spine | +0.004 |
Neg logit contributions | |
late | -0.015 |
sm | -0.013 |
the | -0.013 |
another | -0.013 |
my | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | +2.32e-02 |
Pos logit contributions | |
ABC | +0.306 |
planets | +0.304 |
cultures | +0.303 |
habitats | +0.300 |
sizes | +0.299 |
Neg logit contributions | |
late | -0.200 |
sm | -0.178 |
aback | -0.150 |
another | -0.148 |
out | -0.140 |
Token | They |
Token ID | 1119 |
Feature activation | +6.77e-02 |
Pos logit contributions | |
sizes | +0.044 |
bows | +0.039 |
planets | +0.039 |
ABC | +0.038 |
cultures | +0.038 |
Neg logit contributions | |
late | -0.037 |
O | -0.030 |
aback | -0.030 |
Start | -0.030 |
sm | -0.029 |
Token | liked |
Token ID | 8288 |
Feature activation | +5.72e-02 |
Pos logit contributions | |
sizes | +0.109 |
ABC | +0.099 |
bows | +0.099 |
cultures | +0.098 |
planets | +0.097 |
Neg logit contributions | |
late | -0.115 |
O | -0.099 |
sm | -0.099 |
aback | -0.095 |
Start | -0.094 |
Token | to |
Token ID | 284 |
Feature activation | +1.91e-02 |
Pos logit contributions | |
sizes | +0.134 |
bows | +0.123 |
planets | +0.121 |
hips | +0.119 |
toes | +0.119 |
Neg logit contributions | |
late | -0.065 |
sm | -0.047 |
O | -0.044 |
Start | -0.044 |
aback | -0.043 |
Token | zoom |
Token ID | 19792 |
Feature activation | +3.43e-02 |
Pos logit contributions | |
sizes | +0.032 |
planets | +0.029 |
bows | +0.028 |
cultures | +0.027 |
ABC | +0.027 |
Neg logit contributions | |
late | -0.032 |
aback | -0.028 |
Start | -0.028 |
O | -0.028 |
sm | -0.027 |
Token | took |
Token ID | 1718 |
Feature activation | -7.12e-02 |
Pos logit contributions | |
sizes | +0.037 |
planets | +0.033 |
bows | +0.032 |
ABC | +0.032 |
clubs | +0.031 |
Neg logit contributions | |
late | -0.037 |
aback | -0.032 |
Start | -0.031 |
O | -0.031 |
sm | -0.031 |
Token | turns |
Token ID | 4962 |
Feature activation | +4.22e-02 |
Pos logit contributions | |
late | +0.110 |
O | +0.095 |
Start | +0.094 |
severe | +0.093 |
sm | +0.093 |
Neg logit contributions | |
sizes | -0.140 |
planets | -0.128 |
clubs | -0.123 |
toes | -0.123 |
patterns | -0.121 |
Token | to |
Token ID | 284 |
Feature activation | -5.70e-04 |
Pos logit contributions | |
sizes | +0.072 |
cultures | +0.065 |
planets | +0.064 |
bows | +0.063 |
hobbies | +0.063 |
Neg logit contributions | |
late | -0.078 |
sm | -0.064 |
aback | -0.063 |
Start | -0.062 |
poisoned | -0.059 |
Token | measure |
Token ID | 3953 |
Feature activation | +1.58e-03 |
Pos logit contributions | |
late | +0.001 |
aback | +0.001 |
sm | +0.001 |
Start | +0.001 |
O | +0.001 |
Neg logit contributions | |
sizes | -0.001 |
planets | -0.001 |
bows | -0.001 |
ABC | -0.001 |
clubs | -0.001 |
Token | their |
Token ID | 511 |
Feature activation | +4.84e-02 |
Pos logit contributions | |
sizes | +0.004 |
planets | +0.003 |
bows | +0.003 |
ABC | +0.003 |
clubs | +0.003 |
Neg logit contributions | |
late | -0.002 |
aback | -0.002 |
Start | -0.001 |
sm | -0.001 |
O | -0.001 |
Token | tails |
Token ID | 30514 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
sizes | +0.068 |
bows | +0.058 |
planets | +0.057 |
cultures | +0.057 |
hips | +0.056 |
Neg logit contributions | |
late | -0.096 |
aback | -0.083 |
sm | -0.081 |
Start | -0.080 |
poisonous | -0.080 |
Token | . |
Token ID | 13 |
Feature activation | +1.71e-02 |
Pos logit contributions | |
sizes | +0.295 |
cultures | +0.277 |
ABC | +0.273 |
hobbies | +0.265 |
bows | +0.265 |
Neg logit contributions | |
late | -0.247 |
aback | -0.195 |
another | -0.190 |
sm | -0.185 |
Start | -0.181 |
Token | The |
Token ID | 383 |
Feature activation | +3.07e-02 |
Pos logit contributions | |
sizes | +0.030 |
planets | +0.027 |
bows | +0.026 |
ABC | +0.026 |
clubs | +0.025 |
Neg logit contributions | |
late | -0.030 |
aback | -0.026 |
sm | -0.025 |
Start | -0.025 |
O | -0.025 |
Token | mouse |
Token ID | 10211 |
Feature activation | -2.40e-03 |
Pos logit contributions | |
sizes | +0.063 |
bows | +0.055 |
clubs | +0.054 |
toes | +0.054 |
planets | +0.054 |
Neg logit contributions | |
late | -0.046 |
O | -0.037 |
Start | -0.037 |
sm | -0.037 |
aback | -0.036 |
Token | 's |
Token ID | 338 |
Feature activation | +5.12e-02 |
Pos logit contributions | |
late | +0.004 |
aback | +0.004 |
Start | +0.004 |
sm | +0.004 |
O | +0.004 |
Neg logit contributions | |
sizes | -0.004 |
planets | -0.004 |
bows | -0.004 |
ABC | -0.003 |
cultures | -0.003 |
Token | tail |
Token ID | 7894 |
Feature activation | +6.55e-02 |
Pos logit contributions | |
sizes | +0.077 |
cultures | +0.066 |
planets | +0.065 |
bows | +0.064 |
hips | +0.063 |
Neg logit contributions | |
late | -0.096 |
aback | -0.080 |
another | -0.079 |
poisonous | -0.079 |
poisoned | -0.078 |
Token | boats |
Token ID | 16659 |
Feature activation | +3.19e-02 |
Pos logit contributions | |
late | +0.077 |
sm | +0.069 |
aback | +0.066 |
O | +0.064 |
Start | +0.064 |
Neg logit contributions | |
bows | -0.053 |
sizes | -0.051 |
ABC | -0.047 |
hips | -0.047 |
azes | -0.045 |
Token | of |
Token ID | 286 |
Feature activation | -1.90e-02 |
Pos logit contributions | |
sizes | +0.063 |
ABC | +0.060 |
planets | +0.058 |
cheeks | +0.057 |
igo | +0.057 |
Neg logit contributions | |
late | -0.045 |
sm | -0.037 |
aback | -0.036 |
poisoned | -0.031 |
Start | -0.030 |
Token | different |
Token ID | 1180 |
Feature activation | +1.54e-02 |
Pos logit contributions | |
late | +0.026 |
aback | +0.021 |
O | +0.021 |
sm | +0.021 |
Start | +0.021 |
Neg logit contributions | |
sizes | -0.039 |
bows | -0.036 |
ABC | -0.035 |
planets | -0.035 |
cultures | -0.034 |
Token | colors |
Token ID | 7577 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
bows | +0.016 |
azes | +0.016 |
hips | +0.016 |
sing | +0.015 |
igo | +0.015 |
Neg logit contributions | |
late | -0.031 |
sm | -0.028 |
aback | -0.028 |
my | -0.026 |
Start | -0.026 |
Token | and |
Token ID | 290 |
Feature activation | +7.96e-03 |
Pos logit contributions | |
cultures | +0.215 |
sizes | +0.214 |
ABC | +0.214 |
antics | +0.205 |
cheeks | +0.205 |
Neg logit contributions | |
late | -0.157 |
sm | -0.132 |
aback | -0.117 |
another | -0.115 |
here | -0.110 |
Token | sizes |
Token ID | 10620 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
pit | +0.005 |
azes | +0.004 |
hips | +0.004 |
ABC | +0.004 |
iece | +0.004 |
Neg logit contributions | |
late | -0.020 |
sm | -0.018 |
aback | -0.017 |
my | -0.017 |
another | -0.017 |
Token | . |
Token ID | 13 |
Feature activation | +2.35e-02 |
Pos logit contributions | |
ABC | +0.293 |
sizes | +0.287 |
planets | +0.280 |
cultures | +0.278 |
azes | +0.271 |
Neg logit contributions | |
late | -0.217 |
sm | -0.201 |
aback | -0.176 |
another | -0.163 |
here | -0.160 |
Token | They |
Token ID | 1119 |
Feature activation | +6.65e-02 |
Pos logit contributions | |
sizes | +0.043 |
planets | +0.037 |
bows | +0.037 |
ABC | +0.037 |
clubs | +0.036 |
Neg logit contributions | |
late | -0.040 |
aback | -0.034 |
Start | -0.033 |
O | -0.033 |
sm | -0.033 |
Token | liked |
Token ID | 8288 |
Feature activation | +5.79e-02 |
Pos logit contributions | |
sizes | +0.104 |
ABC | +0.094 |
bows | +0.094 |
cultures | +0.090 |
planets | +0.090 |
Neg logit contributions | |
late | -0.117 |
sm | -0.103 |
O | -0.102 |
aback | -0.101 |
Start | -0.098 |
Token | to |
Token ID | 284 |
Feature activation | +1.73e-02 |
Pos logit contributions | |
sizes | +0.134 |
bows | +0.123 |
planets | +0.120 |
hips | +0.119 |
ABC | +0.118 |
Neg logit contributions | |
late | -0.068 |
sm | -0.050 |
aback | -0.048 |
O | -0.048 |
Start | -0.048 |
Token | make |
Token ID | 787 |
Feature activation | +4.07e-02 |
Pos logit contributions | |
sizes | +0.029 |
bows | +0.025 |
planets | +0.025 |
ABC | +0.025 |
cultures | +0.024 |
Neg logit contributions | |
late | -0.029 |
aback | -0.025 |
O | -0.025 |
Start | -0.025 |
sm | -0.025 |
Token | Jack |
Token ID | 3619 |
Feature activation | +3.89e-02 |
Pos logit contributions | |
late | +0.020 |
aback | +0.017 |
sm | +0.017 |
Start | +0.017 |
O | +0.017 |
Neg logit contributions | |
sizes | -0.023 |
planets | -0.020 |
clubs | -0.020 |
toes | -0.020 |
ABC | -0.020 |
Token | and |
Token ID | 290 |
Feature activation | -1.60e-02 |
Pos logit contributions | |
sizes | +0.061 |
planets | +0.053 |
bows | +0.053 |
ABC | +0.052 |
cultures | +0.051 |
Neg logit contributions | |
late | -0.075 |
aback | -0.066 |
Start | -0.064 |
sm | -0.063 |
O | -0.062 |
Token | w |
Token ID | 266 |
Feature activation | +3.55e-02 |
Pos logit contributions | |
late | +0.031 |
sm | +0.029 |
O | +0.029 |
izz | +0.028 |
aback | +0.027 |
Neg logit contributions | |
sizes | -0.022 |
neck | -0.019 |
toes | -0.019 |
planets | -0.018 |
clubs | -0.018 |
Token | agged |
Token ID | 14655 |
Feature activation | +5.77e-02 |
Pos logit contributions | |
sizes | +0.070 |
planets | +0.062 |
bows | +0.062 |
ABC | +0.061 |
cultures | +0.060 |
Neg logit contributions | |
late | -0.054 |
aback | -0.047 |
Start | -0.045 |
sm | -0.045 |
O | -0.045 |
Token | their |
Token ID | 511 |
Feature activation | +5.81e-02 |
Pos logit contributions | |
sizes | +0.134 |
ABC | +0.124 |
bows | +0.124 |
planets | +0.123 |
cultures | +0.120 |
Neg logit contributions | |
late | -0.067 |
aback | -0.053 |
Start | -0.049 |
sm | -0.049 |
O | -0.047 |
Token | tails |
Token ID | 30514 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
sizes | +0.065 |
bows | +0.060 |
ABC | +0.057 |
planets | +0.055 |
cultures | +0.054 |
Neg logit contributions | |
late | -0.130 |
sm | -0.115 |
aback | -0.113 |
poisonous | -0.113 |
O | -0.113 |
Token | . |
Token ID | 13 |
Feature activation | +1.94e-02 |
Pos logit contributions | |
sizes | +0.314 |
cultures | +0.298 |
ABC | +0.297 |
bows | +0.291 |
planets | +0.290 |
Neg logit contributions | |
late | -0.249 |
aback | -0.200 |
sm | -0.194 |
another | -0.185 |
Start | -0.185 |
Token | Jack |
Token ID | 3619 |
Feature activation | +2.39e-02 |
Pos logit contributions | |
sizes | +0.034 |
planets | +0.030 |
bows | +0.030 |
ABC | +0.029 |
clubs | +0.029 |
Neg logit contributions | |
late | -0.034 |
aback | -0.029 |
Start | -0.029 |
O | -0.028 |
sm | -0.028 |
Token | was |
Token ID | 373 |
Feature activation | +2.47e-02 |
Pos logit contributions | |
sizes | +0.039 |
planets | +0.034 |
bows | +0.034 |
ABC | +0.033 |
clubs | +0.033 |
Neg logit contributions | |
late | -0.044 |
aback | -0.038 |
Start | -0.037 |
sm | -0.037 |
O | -0.037 |
Token | so |
Token ID | 523 |
Feature activation | -2.06e-02 |
Pos logit contributions | |
sizes | +0.037 |
neck | +0.031 |
racing | +0.031 |
pretending | +0.031 |
toes | +0.030 |
Neg logit contributions | |
late | -0.043 |
O | -0.042 |
sm | -0.041 |
Start | -0.041 |
aback | -0.040 |
Token | happy |
Token ID | 3772 |
Feature activation | -1.83e-02 |
Pos logit contributions | |
late | +0.038 |
O | +0.035 |
aback | +0.035 |
sm | +0.034 |
Start | +0.034 |
Neg logit contributions | |
sizes | -0.030 |
toes | -0.024 |
bows | -0.024 |
ABC | -0.024 |
planets | -0.023 |
Token | His |
Token ID | 2399 |
Feature activation | +3.64e-02 |
Pos logit contributions | |
sm | +0.007 |
late | +0.007 |
poisonous | +0.007 |
poisoned | +0.007 |
izz | +0.007 |
Neg logit contributions | |
sizes | -0.005 |
ABC | -0.005 |
planets | -0.005 |
toes | -0.004 |
cheeks | -0.004 |
Token | birthday |
Token ID | 10955 |
Feature activation | +9.46e-03 |
Pos logit contributions | |
sizes | +0.069 |
bows | +0.060 |
hips | +0.058 |
cultures | +0.057 |
planets | +0.057 |
Neg logit contributions | |
late | -0.060 |
severe | -0.050 |
poisoned | -0.049 |
poisonous | -0.049 |
O | -0.048 |
Token | had |
Token ID | 550 |
Feature activation | -1.03e-02 |
Pos logit contributions | |
sizes | +0.016 |
planets | +0.014 |
bows | +0.013 |
ABC | +0.013 |
cultures | +0.013 |
Neg logit contributions | |
late | -0.017 |
aback | -0.015 |
sm | -0.015 |
Start | -0.014 |
O | -0.014 |
Token | ended |
Token ID | 4444 |
Feature activation | +4.96e-04 |
Pos logit contributions | |
late | +0.016 |
aback | +0.015 |
sm | +0.014 |
izz | +0.014 |
O | +0.014 |
Neg logit contributions | |
sizes | -0.018 |
planets | -0.016 |
bows | -0.016 |
clubs | -0.016 |
ABC | -0.016 |
Token | in |
Token ID | 287 |
Feature activation | -1.72e-02 |
Pos logit contributions | |
sizes | +0.001 |
planets | +0.001 |
cultures | +0.001 |
bows | +0.001 |
ABC | +0.001 |
Neg logit contributions | |
late | -0.001 |
aback | -0.001 |
sm | -0.001 |
Start | -0.001 |
severe | -0.001 |
Token | disaster |
Token ID | 9336 |
Feature activation | -1.71e-01 |
Pos logit contributions | |
late | +0.022 |
aback | +0.020 |
O | +0.020 |
Start | +0.020 |
sm | +0.019 |
Neg logit contributions | |
sizes | -0.035 |
planets | -0.032 |
ABC | -0.031 |
clubs | -0.030 |
bows | -0.030 |
Token | . |
Token ID | 13 |
Feature activation | -1.00e-02 |
Pos logit contributions | |
late | +0.320 |
aback | +0.286 |
O | +0.282 |
Start | +0.279 |
sm | +0.275 |
Neg logit contributions | |
sizes | -0.269 |
bows | -0.229 |
planets | -0.228 |
ABC | -0.219 |
clubs | -0.215 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -4.56e-02 |
Pos logit contributions | |
late | +0.017 |
poisonous | +0.017 |
sm | +0.016 |
poisoned | +0.016 |
O | +0.016 |
Neg logit contributions | |
sizes | -0.015 |
ABC | -0.014 |
planets | -0.013 |
languages | -0.012 |
bows | -0.012 |
Token | Jimmy |
Token ID | 40335 |
Feature activation | -1.40e-02 |
Pos logit contributions | |
late | +0.053 |
aback | +0.043 |
Start | +0.041 |
sm | +0.041 |
O | +0.040 |
Neg logit contributions | |
sizes | -0.105 |
planets | -0.095 |
bows | -0.094 |
ABC | -0.094 |
clubs | -0.092 |
Token | was |
Token ID | 373 |
Feature activation | -1.87e-02 |
Pos logit contributions | |
late | +0.027 |
aback | +0.024 |
Start | +0.024 |
O | +0.024 |
sm | +0.023 |
Neg logit contributions | |
sizes | -0.021 |
planets | -0.018 |
bows | -0.018 |
ABC | -0.018 |
toes | -0.017 |
Token | new |
Token ID | 649 |
Feature activation | -1.77e-02 |
Pos logit contributions | |
late | +0.038 |
O | +0.037 |
aback | +0.037 |
Start | +0.036 |
sm | +0.036 |
Neg logit contributions | |
sizes | -0.022 |
planets | -0.020 |
ABC | -0.020 |
toes | -0.020 |
pretending | -0.019 |
Token | Mom |
Token ID | 29252 |
Feature activation | -4.38e-02 |
Pos logit contributions | |
late | +0.044 |
aback | +0.040 |
sm | +0.037 |
poisoned | +0.035 |
poisonous | +0.035 |
Neg logit contributions | |
sizes | -0.059 |
ABC | -0.055 |
planets | -0.054 |
clubs | -0.053 |
toes | -0.053 |
Token | came |
Token ID | 1625 |
Feature activation | -4.47e-02 |
Pos logit contributions | |
late | +0.069 |
aback | +0.060 |
Start | +0.059 |
O | +0.058 |
sm | +0.058 |
Neg logit contributions | |
sizes | -0.085 |
planets | -0.075 |
bows | -0.074 |
cultures | -0.073 |
ABC | -0.073 |
Token | and |
Token ID | 290 |
Feature activation | -2.94e-02 |
Pos logit contributions | |
late | +0.061 |
aback | +0.050 |
Start | +0.048 |
sm | +0.048 |
O | +0.047 |
Neg logit contributions | |
sizes | -0.098 |
bows | -0.088 |
planets | -0.087 |
ABC | -0.085 |
cultures | -0.085 |
Token | saw |
Token ID | 2497 |
Feature activation | -6.18e-02 |
Pos logit contributions | |
late | +0.056 |
vious | +0.051 |
aback | +0.050 |
ores | +0.050 |
severe | +0.049 |
Neg logit contributions | |
pretending | -0.030 |
waving | -0.028 |
sizes | -0.028 |
laughing | -0.027 |
neck | -0.027 |
Token | the |
Token ID | 262 |
Feature activation | +5.04e-03 |
Pos logit contributions | |
late | +0.083 |
aback | +0.070 |
severe | +0.069 |
Start | +0.068 |
O | +0.068 |
Neg logit contributions | |
sizes | -0.122 |
planets | -0.114 |
ABC | -0.110 |
patterns | -0.109 |
clubs | -0.109 |
Token | disaster |
Token ID | 9336 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
sizes | +0.009 |
ABC | +0.008 |
planets | +0.008 |
bows | +0.008 |
toes | +0.007 |
Neg logit contributions | |
late | -0.009 |
aback | -0.008 |
Start | -0.008 |
O | -0.008 |
sm | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | -1.41e-02 |
Pos logit contributions | |
late | +0.338 |
aback | +0.302 |
Start | +0.294 |
O | +0.293 |
sm | +0.291 |
Neg logit contributions | |
sizes | -0.243 |
planets | -0.205 |
bows | -0.205 |
ABC | -0.199 |
clubs | -0.193 |
Token | She |
Token ID | 1375 |
Feature activation | -2.75e-02 |
Pos logit contributions | |
late | +0.023 |
sm | +0.021 |
aback | +0.021 |
O | +0.021 |
izz | +0.020 |
Neg logit contributions | |
sizes | -0.023 |
ABC | -0.020 |
bows | -0.020 |
planets | -0.020 |
cheeks | -0.019 |
Token | was |
Token ID | 373 |
Feature activation | +5.61e-03 |
Pos logit contributions | |
late | +0.058 |
aback | +0.051 |
heaven | +0.048 |
Start | +0.047 |
Aid | +0.046 |
Neg logit contributions | |
sizes | -0.034 |
planets | -0.029 |
ABC | -0.029 |
neck | -0.029 |
clubs | -0.028 |
Token | not |
Token ID | 407 |
Feature activation | -3.49e-02 |
Pos logit contributions | |
sizes | +0.007 |
pretending | +0.006 |
racing | +0.006 |
neck | +0.006 |
toes | +0.006 |
Neg logit contributions | |
late | -0.011 |
aback | -0.010 |
O | -0.010 |
sm | -0.010 |
Start | -0.010 |
Token | angry |
Token ID | 7954 |
Feature activation | -2.08e-02 |
Pos logit contributions | |
late | +0.062 |
O | +0.060 |
aback | +0.059 |
Start | +0.057 |
sm | +0.056 |
Neg logit contributions | |
sizes | -0.051 |
toes | -0.044 |
pretending | -0.044 |
neck | -0.044 |
ABC | -0.044 |
Token | again |
Token ID | 757 |
Feature activation | -7.16e-02 |
Pos logit contributions | |
sizes | +0.002 |
planets | +0.002 |
bows | +0.002 |
ABC | +0.002 |
toes | +0.002 |
Neg logit contributions | |
late | -0.002 |
O | -0.002 |
Start | -0.002 |
aback | -0.002 |
izz | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | +7.85e-03 |
Pos logit contributions | |
late | +0.144 |
aback | +0.129 |
Start | +0.127 |
O | +0.126 |
sm | +0.125 |
Neg logit contributions | |
sizes | -0.105 |
planets | -0.089 |
bows | -0.087 |
ABC | -0.085 |
cultures | -0.084 |
Token | But |
Token ID | 887 |
Feature activation | +2.73e-02 |
Pos logit contributions | |
sizes | +0.013 |
planets | +0.012 |
ABC | +0.012 |
bows | +0.011 |
toes | +0.011 |
Neg logit contributions | |
late | -0.014 |
sm | -0.012 |
aback | -0.012 |
O | -0.012 |
Start | -0.012 |
Token | unb |
Token ID | 22619 |
Feature activation | -4.91e-02 |
Pos logit contributions | |
sizes | +0.049 |
planets | +0.043 |
bows | +0.042 |
ABC | +0.042 |
cultures | +0.041 |
Neg logit contributions | |
late | -0.046 |
aback | -0.040 |
Start | -0.039 |
sm | -0.039 |
O | -0.039 |
Token | ek |
Token ID | 988 |
Feature activation | -1.38e-02 |
Pos logit contributions | |
late | +0.072 |
aback | +0.060 |
Start | +0.059 |
sm | +0.058 |
O | +0.058 |
Neg logit contributions | |
sizes | -0.100 |
planets | -0.089 |
bows | -0.088 |
ABC | -0.087 |
clubs | -0.086 |
Token | nown |
Token ID | 3408 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
late | +0.025 |
aback | +0.021 |
Start | +0.020 |
sm | +0.020 |
O | +0.020 |
Neg logit contributions | |
sizes | -0.023 |
bows | -0.020 |
planets | -0.020 |
ABC | -0.020 |
necks | -0.019 |
Token | to |
Token ID | 284 |
Feature activation | -7.48e-02 |
Pos logit contributions | |
late | +0.266 |
severe | +0.223 |
aback | +0.220 |
Start | +0.219 |
O | +0.216 |
Neg logit contributions | |
sizes | -0.293 |
planets | -0.270 |
clubs | -0.266 |
bows | -0.259 |
ABC | -0.259 |
Token | him |
Token ID | 683 |
Feature activation | -1.78e-02 |
Pos logit contributions | |
late | +0.109 |
aback | +0.092 |
Start | +0.091 |
sm | +0.089 |
O | +0.087 |
Neg logit contributions | |
sizes | -0.149 |
planets | -0.136 |
ABC | -0.133 |
toes | -0.130 |
clubs | -0.130 |
Token | , |
Token ID | 11 |
Feature activation | +1.12e-02 |
Pos logit contributions | |
late | +0.035 |
aback | +0.030 |
sm | +0.029 |
Start | +0.029 |
O | +0.029 |
Neg logit contributions | |
sizes | -0.028 |
bows | -0.024 |
planets | -0.024 |
ABC | -0.023 |
clubs | -0.023 |
Token | the |
Token ID | 262 |
Feature activation | +5.12e-03 |
Pos logit contributions | |
sizes | +0.017 |
planets | +0.015 |
neck | +0.015 |
cultures | +0.015 |
toes | +0.015 |
Neg logit contributions | |
izz | -0.018 |
late | -0.018 |
O | -0.018 |
poisonous | -0.017 |
sm | -0.017 |
Token | king |
Token ID | 5822 |
Feature activation | -3.14e-02 |
Pos logit contributions | |
sizes | +0.008 |
bows | +0.007 |
clubs | +0.006 |
ABC | +0.006 |
cultures | +0.006 |
Neg logit contributions | |
late | -0.010 |
Start | -0.009 |
aback | -0.009 |
sm | -0.009 |
O | -0.008 |
Token | |
Token ID | 220 |
Feature activation | +1.15e-02 |
Pos logit contributions | |
sizes | +0.007 |
bows | +0.006 |
planets | +0.006 |
ABC | +0.006 |
clubs | +0.006 |
Neg logit contributions | |
late | -0.006 |
aback | -0.005 |
sm | -0.005 |
O | -0.005 |
Start | -0.005 |
Token |
|
Token ID | 198 |
Feature activation | -1.89e-02 |
Pos logit contributions | |
sizes | +0.019 |
bows | +0.018 |
ABC | +0.017 |
hips | +0.017 |
planets | +0.017 |
Neg logit contributions | |
late | -0.019 |
aback | -0.017 |
poisonous | -0.017 |
sm | -0.017 |
poisoned | -0.017 |
Token |
|
Token ID | 198 |
Feature activation | -2.25e-02 |
Pos logit contributions | |
late | +0.032 |
aback | +0.029 |
poisonous | +0.029 |
poisoned | +0.029 |
sm | +0.028 |
Neg logit contributions | |
sizes | -0.029 |
ABC | -0.026 |
clubs | -0.026 |
bows | -0.025 |
planets | -0.025 |
Token | But |
Token ID | 1537 |
Feature activation | +2.40e-02 |
Pos logit contributions | |
late | +0.035 |
aback | +0.034 |
poisonous | +0.033 |
poisoned | +0.033 |
heaven | +0.030 |
Neg logit contributions | |
sizes | -0.036 |
clubs | -0.033 |
racing | -0.032 |
utes | -0.032 |
ABC | -0.032 |
Token | then |
Token ID | 788 |
Feature activation | -4.63e-02 |
Pos logit contributions | |
sizes | +0.040 |
planets | +0.035 |
bows | +0.034 |
toes | +0.034 |
ABC | +0.034 |
Neg logit contributions | |
late | -0.042 |
aback | -0.037 |
sm | -0.037 |
Start | -0.037 |
O | -0.036 |
Token | disaster |
Token ID | 9336 |
Feature activation | -1.66e-01 |
Pos logit contributions | |
late | +0.109 |
aback | +0.099 |
sm | +0.098 |
O | +0.097 |
Start | +0.097 |
Neg logit contributions | |
sizes | -0.049 |
planets | -0.040 |
bows | -0.040 |
ABC | -0.038 |
clubs | -0.038 |
Token | struck |
Token ID | 7425 |
Feature activation | -5.64e-02 |
Pos logit contributions | |
late | +0.227 |
aback | +0.193 |
O | +0.185 |
Start | +0.182 |
severe | +0.181 |
Neg logit contributions | |
sizes | -0.342 |
bows | -0.308 |
planets | -0.300 |
ABC | -0.294 |
clubs | -0.289 |
Token | ! |
Token ID | 0 |
Feature activation | -2.16e-02 |
Pos logit contributions | |
late | +0.094 |
aback | +0.080 |
Start | +0.078 |
sm | +0.078 |
O | +0.078 |
Neg logit contributions | |
sizes | -0.103 |
planets | -0.090 |
bows | -0.090 |
ABC | -0.088 |
clubs | -0.087 |
Token | Suddenly |
Token ID | 24975 |
Feature activation | -2.17e-02 |
Pos logit contributions | |
late | +0.034 |
sm | +0.034 |
poisonous | +0.033 |
poisoned | +0.032 |
O | +0.032 |
Neg logit contributions | |
sizes | -0.033 |
ABC | -0.032 |
bows | -0.031 |
cheeks | -0.030 |
planets | -0.029 |
Token | , |
Token ID | 11 |
Feature activation | +5.71e-03 |
Pos logit contributions | |
late | +0.056 |
sm | +0.051 |
aback | +0.050 |
O | +0.050 |
Start | +0.050 |
Neg logit contributions | |
sizes | -0.016 |
bows | -0.013 |
planets | -0.013 |
clubs | -0.013 |
ABC | -0.012 |
Token | the |
Token ID | 262 |
Feature activation | -2.88e-03 |
Pos logit contributions | |
sizes | +0.009 |
planets | +0.009 |
bows | +0.009 |
ABC | +0.008 |
clubs | +0.008 |
Neg logit contributions | |
sm | -0.008 |
aback | -0.008 |
late | -0.008 |
poisonous | -0.008 |
Aid | -0.007 |
Token | done |
Token ID | 1760 |
Feature activation | +1.36e-03 |
Pos logit contributions | |
late | +0.067 |
aback | +0.060 |
Start | +0.058 |
O | +0.057 |
sm | +0.057 |
Neg logit contributions | |
sizes | -0.057 |
bows | -0.049 |
planets | -0.048 |
ABC | -0.048 |
clubs | -0.048 |
Token | ? |
Token ID | 30 |
Feature activation | -1.16e-02 |
Pos logit contributions | |
sizes | +0.003 |
planets | +0.003 |
bows | +0.002 |
ABC | +0.002 |
clubs | +0.002 |
Neg logit contributions | |
late | -0.002 |
aback | -0.002 |
Start | -0.002 |
sm | -0.002 |
O | -0.002 |
Token | This |
Token ID | 770 |
Feature activation | -2.88e-02 |
Pos logit contributions | |
late | +0.020 |
aback | +0.019 |
severe | +0.018 |
poisonous | +0.018 |
sm | +0.018 |
Neg logit contributions | |
sizes | -0.018 |
ABC | -0.016 |
bows | -0.016 |
planets | -0.016 |
clubs | -0.015 |
Token | is |
Token ID | 318 |
Feature activation | +2.63e-02 |
Pos logit contributions | |
late | +0.054 |
aback | +0.047 |
Start | +0.046 |
sm | +0.046 |
O | +0.046 |
Neg logit contributions | |
sizes | -0.047 |
planets | -0.041 |
bows | -0.040 |
ABC | -0.039 |
cultures | -0.039 |
Token | a |
Token ID | 257 |
Feature activation | +1.21e-02 |
Pos logit contributions | |
sizes | +0.046 |
ABC | +0.040 |
planets | +0.039 |
winning | +0.039 |
pretending | +0.039 |
Neg logit contributions | |
aback | -0.043 |
Start | -0.040 |
late | -0.038 |
handed | -0.038 |
izz | -0.037 |
Token | disaster |
Token ID | 9336 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
sizes | +0.024 |
planets | +0.021 |
bows | +0.021 |
ABC | +0.020 |
clubs | +0.020 |
Neg logit contributions | |
late | -0.019 |
aback | -0.016 |
Start | -0.015 |
sm | -0.015 |
O | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | -6.95e-03 |
Pos logit contributions | |
late | +0.305 |
aback | +0.289 |
O | +0.284 |
severe | +0.278 |
Start | +0.276 |
Neg logit contributions | |
sizes | -0.250 |
bows | -0.216 |
planets | -0.211 |
ABC | -0.201 |
pretending | -0.195 |
Token | You |
Token ID | 921 |
Feature activation | -2.14e-02 |
Pos logit contributions | |
late | +0.013 |
aback | +0.012 |
poisonous | +0.011 |
severe | +0.011 |
sm | +0.011 |
Neg logit contributions | |
sizes | -0.011 |
ABC | -0.010 |
planets | -0.009 |
bows | -0.009 |
clubs | -0.009 |
Token | did |
Token ID | 750 |
Feature activation | +8.49e-02 |
Pos logit contributions | |
late | +0.046 |
aback | +0.045 |
Start | +0.042 |
O | +0.041 |
Aid | +0.039 |
Neg logit contributions | |
sizes | -0.026 |
planets | -0.023 |
bows | -0.022 |
clubs | -0.022 |
nations | -0.021 |
Token | not |
Token ID | 407 |
Feature activation | -2.39e-02 |
Pos logit contributions | |
sizes | +0.095 |
ABC | +0.083 |
planets | +0.080 |
bows | +0.079 |
clubs | +0.078 |
Neg logit contributions | |
late | -0.186 |
aback | -0.182 |
sm | -0.172 |
O | -0.170 |
izz | -0.169 |
Token | listen |
Token ID | 6004 |
Feature activation | +3.72e-02 |
Pos logit contributions | |
late | +0.041 |
aback | +0.041 |
O | +0.038 |
Start | +0.037 |
severe | +0.037 |
Neg logit contributions | |
sizes | -0.038 |
bows | -0.033 |
nations | -0.032 |
planets | -0.031 |
cultures | -0.031 |
Token | before |
Token ID | 878 |
Feature activation | +5.24e-03 |
Pos logit contributions | |
sizes | +0.004 |
planets | +0.003 |
bows | +0.003 |
ABC | +0.003 |
cultures | +0.003 |
Neg logit contributions | |
late | -0.004 |
aback | -0.003 |
sm | -0.003 |
Start | -0.003 |
O | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | +6.65e-03 |
Pos logit contributions | |
sizes | +0.009 |
bows | +0.007 |
planets | +0.007 |
cultures | +0.007 |
ABC | +0.007 |
Neg logit contributions | |
late | -0.010 |
aback | -0.008 |
Start | -0.008 |
sm | -0.008 |
O | -0.008 |
Token | But |
Token ID | 887 |
Feature activation | +2.90e-02 |
Pos logit contributions | |
sizes | +0.010 |
toes | +0.009 |
ABC | +0.009 |
planets | +0.009 |
cheeks | +0.008 |
Neg logit contributions | |
late | -0.012 |
sm | -0.012 |
poisonous | -0.011 |
severe | -0.011 |
aback | -0.011 |
Token | then |
Token ID | 788 |
Feature activation | -4.08e-02 |
Pos logit contributions | |
sizes | +0.044 |
toes | +0.041 |
planets | +0.039 |
cheeks | +0.037 |
ABC | +0.037 |
Neg logit contributions | |
late | -0.052 |
aback | -0.051 |
sm | -0.051 |
Start | -0.050 |
severe | -0.048 |
Token | , |
Token ID | 11 |
Feature activation | +2.40e-02 |
Pos logit contributions | |
late | +0.071 |
aback | +0.062 |
Start | +0.060 |
sm | +0.060 |
O | +0.060 |
Neg logit contributions | |
sizes | -0.071 |
planets | -0.063 |
bows | -0.062 |
ABC | -0.061 |
clubs | -0.060 |
Token | disaster |
Token ID | 9336 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
sizes | +0.041 |
toes | +0.039 |
planets | +0.038 |
ABC | +0.036 |
racing | +0.034 |
Neg logit contributions | |
aback | -0.038 |
late | -0.037 |
sm | -0.037 |
Start | -0.036 |
O | -0.034 |
Token | struck |
Token ID | 7425 |
Feature activation | -5.70e-02 |
Pos logit contributions | |
late | +0.297 |
aback | +0.280 |
severe | +0.266 |
O | +0.266 |
Start | +0.263 |
Neg logit contributions | |
sizes | -0.246 |
bows | -0.218 |
planets | -0.208 |
ABC | -0.201 |
toes | -0.192 |
Token | ! |
Token ID | 0 |
Feature activation | -1.97e-02 |
Pos logit contributions | |
late | +0.103 |
aback | +0.090 |
Start | +0.088 |
sm | +0.087 |
O | +0.087 |
Neg logit contributions | |
sizes | -0.096 |
planets | -0.083 |
bows | -0.082 |
ABC | -0.081 |
clubs | -0.080 |
Token | On |
Token ID | 1550 |
Feature activation | -3.64e-02 |
Pos logit contributions | |
sm | +0.036 |
poisonous | +0.035 |
aback | +0.035 |
severe | +0.034 |
poisoned | +0.034 |
Neg logit contributions | |
ABC | -0.027 |
sizes | -0.026 |
toes | -0.025 |
cheeks | -0.024 |
planets | -0.022 |
Token | the |
Token ID | 262 |
Feature activation | +6.43e-03 |
Pos logit contributions | |
late | +0.046 |
aback | +0.042 |
sm | +0.041 |
Start | +0.040 |
O | +0.038 |
Neg logit contributions | |
sizes | -0.078 |
planets | -0.074 |
ABC | -0.071 |
toes | -0.070 |
clubs | -0.070 |
Token | day |
Token ID | 1110 |
Feature activation | -5.54e-03 |
Pos logit contributions | |
sizes | +0.009 |
bows | +0.008 |
planets | +0.008 |
ABC | +0.007 |
cultures | +0.007 |
Neg logit contributions | |
late | -0.013 |
Start | -0.011 |
sm | -0.011 |
aback | -0.011 |
O | -0.011 |
Token | came |
Token ID | 1625 |
Feature activation | -4.05e-02 |
Pos logit contributions | |
late | +0.049 |
aback | +0.041 |
Start | +0.040 |
O | +0.040 |
sm | +0.040 |
Neg logit contributions | |
sizes | -0.056 |
planets | -0.049 |
bows | -0.049 |
ABC | -0.048 |
clubs | -0.047 |
Token | running |
Token ID | 2491 |
Feature activation | -4.93e-03 |
Pos logit contributions | |
late | +0.069 |
aback | +0.059 |
Start | +0.058 |
O | +0.057 |
sm | +0.057 |
Neg logit contributions | |
sizes | -0.073 |
planets | -0.064 |
bows | -0.063 |
ABC | -0.062 |
clubs | -0.061 |
Token | and |
Token ID | 290 |
Feature activation | -3.19e-02 |
Pos logit contributions | |
late | +0.010 |
O | +0.009 |
Start | +0.009 |
izz | +0.009 |
aback | +0.009 |
Neg logit contributions | |
sizes | -0.006 |
planets | -0.006 |
bows | -0.005 |
ABC | -0.005 |
toes | -0.005 |
Token | saw |
Token ID | 2497 |
Feature activation | -5.95e-02 |
Pos logit contributions | |
late | +0.057 |
O | +0.053 |
aback | +0.050 |
severe | +0.050 |
Aid | +0.049 |
Neg logit contributions | |
sizes | -0.047 |
pretending | -0.045 |
necks | -0.041 |
waving | -0.041 |
neck | -0.040 |
Token | the |
Token ID | 262 |
Feature activation | +1.10e-02 |
Pos logit contributions | |
late | +0.091 |
aback | +0.086 |
Start | +0.082 |
severe | +0.080 |
Aid | +0.079 |
Neg logit contributions | |
sizes | -0.100 |
planets | -0.091 |
patterns | -0.091 |
pretending | -0.089 |
ABC | -0.089 |
Token | disaster |
Token ID | 9336 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
sizes | +0.020 |
bows | +0.018 |
ABC | +0.018 |
planets | +0.017 |
patterns | +0.017 |
Neg logit contributions | |
late | -0.018 |
aback | -0.017 |
Start | -0.016 |
O | -0.016 |
izz | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | -9.51e-03 |
Pos logit contributions | |
late | +0.325 |
aback | +0.293 |
Start | +0.284 |
O | +0.283 |
sm | +0.280 |
Neg logit contributions | |
sizes | -0.235 |
planets | -0.198 |
bows | -0.198 |
ABC | -0.191 |
clubs | -0.185 |
Token | She |
Token ID | 1375 |
Feature activation | -2.78e-02 |
Pos logit contributions | |
aback | +0.017 |
sm | +0.017 |
Aid | +0.017 |
ited | +0.017 |
late | +0.016 |
Neg logit contributions | |
sizes | -0.012 |
ABC | -0.011 |
bows | -0.010 |
cheeks | -0.010 |
azes | -0.010 |
Token | turned |
Token ID | 2900 |
Feature activation | -1.70e-02 |
Pos logit contributions | |
late | +0.058 |
aback | +0.054 |
heaven | +0.049 |
Aid | +0.049 |
handed | +0.049 |
Neg logit contributions | |
sizes | -0.033 |
planets | -0.029 |
neck | -0.028 |
necks | -0.028 |
ABC | -0.027 |
Token | off |
Token ID | 572 |
Feature activation | -3.56e-02 |
Pos logit contributions | |
handed | +0.038 |
heaven | +0.034 |
Gu | +0.034 |
Start | +0.034 |
Aid | +0.034 |
Neg logit contributions | |
sizes | -0.014 |
lines | -0.013 |
toes | -0.013 |
, | -0.012 |
cheeks | -0.012 |
Token | the |
Token ID | 262 |
Feature activation | +1.48e-02 |
Pos logit contributions | |
handed | +0.069 |
Aid | +0.067 |
aback | +0.067 |
vous | +0.063 |
izz | +0.063 |
Neg logit contributions | |
, | -0.039 |
ABC | -0.037 |
stories | -0.035 |
sizes | -0.034 |
bows | -0.033 |
Token | laughing |
Token ID | 14376 |
Feature activation | +3.40e-02 |
Pos logit contributions | |
sizes | +0.060 |
planets | +0.050 |
bows | +0.050 |
ABC | +0.049 |
toes | +0.048 |
Neg logit contributions | |
late | -0.088 |
aback | -0.078 |
sm | -0.076 |
O | -0.076 |
Start | -0.076 |
Token | . |
Token ID | 13 |
Feature activation | +1.17e-02 |
Pos logit contributions | |
sizes | +0.041 |
planets | +0.034 |
bows | +0.034 |
toes | +0.033 |
ABC | +0.031 |
Neg logit contributions | |
late | -0.072 |
aback | -0.068 |
izz | -0.067 |
Start | -0.067 |
O | -0.067 |
Token | " |
Token ID | 366 |
Feature activation | -1.93e-02 |
Pos logit contributions | |
sizes | +0.017 |
ABC | +0.014 |
bows | +0.014 |
planets | +0.014 |
toes | +0.013 |
Neg logit contributions | |
late | -0.023 |
aback | -0.021 |
sm | -0.020 |
Start | -0.020 |
O | -0.020 |
Token | What |
Token ID | 2061 |
Feature activation | -2.99e-02 |
Pos logit contributions | |
aback | +0.028 |
late | +0.027 |
poisonous | +0.025 |
poisoned | +0.025 |
severe | +0.024 |
Neg logit contributions | |
sizes | -0.037 |
planets | -0.032 |
bows | -0.032 |
necks | -0.031 |
ABC | -0.031 |
Token | a |
Token ID | 257 |
Feature activation | -3.83e-03 |
Pos logit contributions | |
late | +0.056 |
aback | +0.048 |
sm | +0.048 |
Start | +0.048 |
O | +0.047 |
Neg logit contributions | |
sizes | -0.049 |
planets | -0.042 |
bows | -0.042 |
ABC | -0.041 |
cultures | -0.041 |
Token | disaster |
Token ID | 9336 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
late | +0.006 |
aback | +0.005 |
Start | +0.005 |
sm | +0.005 |
O | +0.005 |
Neg logit contributions | |
sizes | -0.008 |
planets | -0.007 |
bows | -0.007 |
ABC | -0.007 |
clubs | -0.007 |
Token | ! |
Token ID | 0 |
Feature activation | -1.77e-02 |
Pos logit contributions | |
late | +0.294 |
severe | +0.274 |
aback | +0.274 |
O | +0.264 |
Aid | +0.264 |
Neg logit contributions | |
sizes | -0.242 |
bows | -0.212 |
planets | -0.203 |
ABC | -0.193 |
pretending | -0.192 |
Token | You |
Token ID | 921 |
Feature activation | -1.61e-02 |
Pos logit contributions | |
late | +0.030 |
aback | +0.028 |
poisonous | +0.027 |
severe | +0.027 |
sm | +0.027 |
Neg logit contributions | |
sizes | -0.029 |
ABC | -0.026 |
toes | -0.024 |
planets | -0.024 |
bows | -0.024 |
Token | two |
Token ID | 734 |
Feature activation | +3.28e-02 |
Pos logit contributions | |
late | +0.036 |
aback | +0.033 |
O | +0.032 |
Start | +0.032 |
sm | +0.031 |
Neg logit contributions | |
sizes | -0.019 |
planets | -0.017 |
clubs | -0.015 |
bows | -0.015 |
nations | -0.015 |
Token | and |
Token ID | 290 |
Feature activation | -2.78e-02 |
Pos logit contributions | |
sizes | +0.057 |
planets | +0.048 |
toes | +0.048 |
bows | +0.048 |
clubs | +0.047 |
Neg logit contributions | |
late | -0.058 |
aback | -0.053 |
O | -0.051 |
Start | -0.051 |
sm | -0.048 |
Token | Rex |
Token ID | 17853 |
Feature activation | +5.93e-02 |
Pos logit contributions | |
late | +0.055 |
aback | +0.052 |
Start | +0.050 |
sm | +0.049 |
izz | +0.048 |
Neg logit contributions | |
sizes | -0.042 |
toes | -0.039 |
planets | -0.036 |
neck | -0.035 |
cheeks | -0.035 |
Token | to |
Token ID | 284 |
Feature activation | -1.93e-02 |
Pos logit contributions | |
late | +0.029 |
aback | +0.025 |
Start | +0.024 |
O | +0.024 |
sm | +0.024 |
Neg logit contributions | |
sizes | -0.039 |
planets | -0.034 |
bows | -0.034 |
ABC | -0.034 |
toes | -0.033 |
Token | start |
Token ID | 923 |
Feature activation | +4.94e-03 |
Pos logit contributions | |
late | +0.038 |
aback | +0.034 |
sm | +0.033 |
Start | +0.032 |
O | +0.032 |
Neg logit contributions | |
sizes | -0.029 |
planets | -0.026 |
ABC | -0.025 |
clubs | -0.025 |
bows | -0.025 |
Token | his |
Token ID | 465 |
Feature activation | +5.19e-03 |
Pos logit contributions | |
sizes | +0.010 |
bows | +0.009 |
planets | +0.009 |
cultures | +0.009 |
ABC | +0.009 |
Neg logit contributions | |
late | -0.007 |
aback | -0.006 |
Start | -0.006 |
sm | -0.006 |
O | -0.006 |
Token | journey |
Token ID | 7002 |
Feature activation | +1.05e-02 |
Pos logit contributions | |
sizes | +0.009 |
bows | +0.008 |
planets | +0.008 |
cultures | +0.007 |
ABC | +0.007 |
Neg logit contributions | |
late | -0.009 |
aback | -0.008 |
O | -0.008 |
Start | -0.008 |
sm | -0.008 |
Token | when |
Token ID | 618 |
Feature activation | +3.63e-02 |
Pos logit contributions | |
sizes | +0.018 |
planets | +0.016 |
ABC | +0.015 |
bows | +0.015 |
cultures | +0.015 |
Neg logit contributions | |
late | -0.019 |
aback | -0.017 |
Start | -0.016 |
sm | -0.016 |
O | -0.015 |
Token | disaster |
Token ID | 9336 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
sizes | +0.078 |
bows | +0.070 |
planets | +0.067 |
cultures | +0.066 |
necks | +0.066 |
Neg logit contributions | |
late | -0.054 |
O | -0.041 |
Start | -0.041 |
aback | -0.040 |
sm | -0.040 |
Token | struck |
Token ID | 7425 |
Feature activation | -5.08e-02 |
Pos logit contributions | |
late | +0.281 |
aback | +0.251 |
O | +0.243 |
Start | +0.241 |
sm | +0.239 |
Neg logit contributions | |
sizes | -0.269 |
bows | -0.233 |
planets | -0.231 |
ABC | -0.224 |
clubs | -0.217 |
Token | . |
Token ID | 13 |
Feature activation | -6.49e-03 |
Pos logit contributions | |
late | +0.096 |
aback | +0.082 |
Start | +0.079 |
sm | +0.078 |
O | +0.078 |
Neg logit contributions | |
sizes | -0.085 |
bows | -0.073 |
planets | -0.073 |
ABC | -0.073 |
cultures | -0.072 |
Token | All |
Token ID | 1439 |
Feature activation | -1.80e-02 |
Pos logit contributions | |
late | +0.012 |
sm | +0.011 |
severe | +0.011 |
poisonous | +0.011 |
izz | +0.011 |
Neg logit contributions | |
sizes | -0.010 |
ABC | -0.009 |
planets | -0.008 |
toes | -0.008 |
bows | -0.008 |
Token | the |
Token ID | 262 |
Feature activation | -1.63e-02 |
Pos logit contributions | |
late | +0.025 |
O | +0.025 |
Start | +0.025 |
aback | +0.023 |
severe | +0.023 |
Neg logit contributions | |
sizes | -0.035 |
planets | -0.032 |
toes | -0.029 |
nations | -0.029 |
languages | -0.029 |
Token | things |
Token ID | 1243 |
Feature activation | +3.70e-02 |
Pos logit contributions | |
late | +0.031 |
aback | +0.026 |
Start | +0.025 |
severe | +0.025 |
O | +0.025 |
Neg logit contributions | |
sizes | -0.025 |
bows | -0.023 |
hips | -0.022 |
planets | -0.022 |
ABC | -0.021 |
Token | was |
Token ID | 373 |
Feature activation | +2.54e-02 |
Pos logit contributions | |
sizes | +0.052 |
planets | +0.045 |
neck | +0.043 |
ABC | +0.043 |
necks | +0.043 |
Neg logit contributions | |
late | -0.056 |
aback | -0.047 |
sm | -0.046 |
Start | -0.046 |
O | -0.045 |
Token | delighted |
Token ID | 20707 |
Feature activation | -1.26e-02 |
Pos logit contributions | |
sizes | +0.038 |
ABC | +0.032 |
pretending | +0.032 |
toes | +0.032 |
neck | +0.032 |
Neg logit contributions | |
late | -0.047 |
O | -0.044 |
sm | -0.044 |
aback | -0.043 |
Start | -0.043 |
Token | . |
Token ID | 13 |
Feature activation | +1.31e-02 |
Pos logit contributions | |
late | +0.020 |
aback | +0.017 |
sm | +0.016 |
Start | +0.016 |
O | +0.015 |
Neg logit contributions | |
sizes | -0.026 |
planets | -0.023 |
ABC | -0.023 |
hips | -0.022 |
bows | -0.022 |
Token | But |
Token ID | 887 |
Feature activation | +3.41e-02 |
Pos logit contributions | |
sizes | +0.023 |
planets | +0.020 |
bows | +0.020 |
ABC | +0.019 |
clubs | +0.019 |
Neg logit contributions | |
late | -0.023 |
aback | -0.020 |
sm | -0.019 |
Start | -0.019 |
O | -0.019 |
Token | then |
Token ID | 788 |
Feature activation | -4.08e-02 |
Pos logit contributions | |
sizes | +0.057 |
planets | +0.049 |
toes | +0.049 |
clubs | +0.048 |
necks | +0.047 |
Neg logit contributions | |
late | -0.060 |
sm | -0.054 |
aback | -0.054 |
Start | -0.053 |
O | -0.052 |
Token | disaster |
Token ID | 9336 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
late | +0.069 |
aback | +0.059 |
Start | +0.058 |
O | +0.057 |
sm | +0.057 |
Neg logit contributions | |
sizes | -0.075 |
planets | -0.065 |
bows | -0.065 |
ABC | -0.064 |
cultures | -0.063 |
Token | struck |
Token ID | 7425 |
Feature activation | -5.36e-02 |
Pos logit contributions | |
late | +0.215 |
aback | +0.191 |
severe | +0.183 |
O | +0.180 |
Start | +0.178 |
Neg logit contributions | |
sizes | -0.314 |
bows | -0.285 |
planets | -0.269 |
ABC | -0.263 |
pretending | -0.257 |
Token | , |
Token ID | 11 |
Feature activation | +3.22e-03 |
Pos logit contributions | |
late | +0.082 |
aback | +0.068 |
Start | +0.066 |
O | +0.065 |
sm | +0.065 |
Neg logit contributions | |
sizes | -0.108 |
planets | -0.096 |
bows | -0.095 |
ABC | -0.094 |
cultures | -0.093 |
Token | he |
Token ID | 339 |
Feature activation | -4.30e-02 |
Pos logit contributions | |
sizes | +0.005 |
planets | +0.004 |
clubs | +0.004 |
bows | +0.004 |
ABC | +0.004 |
Neg logit contributions | |
late | -0.006 |
sm | -0.005 |
aback | -0.005 |
O | -0.005 |
Start | -0.005 |
Token | put |
Token ID | 1234 |
Feature activation | -7.47e-02 |
Pos logit contributions | |
late | +0.074 |
aback | +0.064 |
Start | +0.062 |
sm | +0.062 |
O | +0.061 |
Neg logit contributions | |
sizes | -0.077 |
planets | -0.067 |
bows | -0.066 |
ABC | -0.066 |
clubs | -0.065 |
Token | the |
Token ID | 262 |
Feature activation | +1.50e-02 |
Pos logit contributions | |
late | +0.117 |
Start | +0.107 |
severe | +0.104 |
sm | +0.102 |
O | +0.102 |
Neg logit contributions | |
sizes | -0.139 |
planets | -0.124 |
clubs | -0.123 |
toes | -0.122 |
neck | -0.119 |
Token | . |
Token ID | 13 |
Feature activation | +5.41e-03 |
Pos logit contributions | |
late | +0.011 |
aback | +0.010 |
Start | +0.009 |
O | +0.009 |
sm | +0.009 |
Neg logit contributions | |
sizes | -0.009 |
planets | -0.008 |
bows | -0.007 |
ABC | -0.007 |
clubs | -0.007 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -4.18e-02 |
Pos logit contributions | |
sizes | +0.009 |
ABC | +0.007 |
planets | +0.007 |
cultures | +0.007 |
bows | +0.007 |
Neg logit contributions | |
late | -0.009 |
poisonous | -0.009 |
poisoned | -0.008 |
severe | -0.008 |
sm | -0.008 |
Token | Jimmy |
Token ID | 40335 |
Feature activation | -1.39e-02 |
Pos logit contributions | |
late | +0.050 |
aback | +0.041 |
Start | +0.039 |
sm | +0.039 |
O | +0.038 |
Neg logit contributions | |
sizes | -0.095 |
planets | -0.086 |
bows | -0.085 |
ABC | -0.085 |
clubs | -0.083 |
Token | was |
Token ID | 373 |
Feature activation | -1.09e-02 |
Pos logit contributions | |
late | +0.027 |
aback | +0.023 |
Start | +0.023 |
O | +0.023 |
sm | +0.023 |
Neg logit contributions | |
sizes | -0.021 |
planets | -0.019 |
bows | -0.018 |
ABC | -0.018 |
cultures | -0.017 |
Token | 3 |
Token ID | 513 |
Feature activation | -8.02e-02 |
Pos logit contributions | |
late | +0.021 |
aback | +0.021 |
Start | +0.020 |
O | +0.020 |
sm | +0.020 |
Neg logit contributions | |
sizes | -0.014 |
planets | -0.012 |
toes | -0.012 |
pretending | -0.012 |
ABC | -0.012 |
Token | - |
Token ID | 12 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
late | +0.167 |
aback | +0.148 |
sm | +0.146 |
Start | +0.145 |
O | +0.144 |
Neg logit contributions | |
sizes | -0.113 |
planets | -0.095 |
bows | -0.095 |
ABC | -0.092 |
clubs | -0.090 |
Token | years |
Token ID | 19002 |
Feature activation | -8.81e-02 |
Pos logit contributions | |
late | +0.268 |
aback | +0.239 |
Start | +0.236 |
O | +0.235 |
severe | +0.221 |
Neg logit contributions | |
sizes | -0.241 |
clubs | -0.219 |
ABC | -0.216 |
planets | -0.216 |
toes | -0.215 |
Token | - |
Token ID | 12 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
late | +0.112 |
aback | +0.092 |
Start | +0.089 |
O | +0.088 |
sm | +0.084 |
Neg logit contributions | |
sizes | -0.196 |
planets | -0.176 |
bows | -0.174 |
ABC | -0.174 |
clubs | -0.171 |
Token | old |
Token ID | 727 |
Feature activation | -4.46e-02 |
Pos logit contributions | |
late | +0.179 |
aback | +0.150 |
O | +0.147 |
Start | +0.146 |
severe | +0.135 |
Neg logit contributions | |
sizes | -0.275 |
ABC | -0.249 |
planets | -0.248 |
clubs | -0.246 |
cultures | -0.246 |
Token | and |
Token ID | 290 |
Feature activation | -3.64e-02 |
Pos logit contributions | |
late | +0.081 |
aback | +0.069 |
sm | +0.068 |
Start | +0.064 |
O | +0.062 |
Neg logit contributions | |
sizes | -0.077 |
bows | -0.069 |
planets | -0.067 |
hips | -0.067 |
ABC | -0.066 |
Token | he |
Token ID | 339 |
Feature activation | -2.42e-02 |
Pos logit contributions | |
late | +0.062 |
aback | +0.052 |
Start | +0.051 |
sm | +0.051 |
O | +0.050 |
Neg logit contributions | |
sizes | -0.066 |
bows | -0.058 |
planets | -0.058 |
ABC | -0.057 |
clubs | -0.056 |
Token |
|
Token ID | 198 |
Feature activation | -5.17e-03 |
Pos logit contributions | |
sizes | +0.038 |
planets | +0.034 |
bows | +0.034 |
ABC | +0.033 |
cultures | +0.033 |
Neg logit contributions | |
late | -0.033 |
aback | -0.028 |
Start | -0.027 |
O | -0.027 |
sm | -0.026 |
Token |
|
Token ID | 198 |
Feature activation | -9.57e-03 |
Pos logit contributions | |
late | +0.008 |
aback | +0.008 |
sm | +0.007 |
poisoned | +0.007 |
poisonous | +0.007 |
Neg logit contributions | |
sizes | -0.009 |
planets | -0.008 |
ABC | -0.008 |
clubs | -0.008 |
hips | -0.007 |
Token | But |
Token ID | 1537 |
Feature activation | +2.69e-02 |
Pos logit contributions | |
late | +0.016 |
aback | +0.015 |
sm | +0.014 |
poisonous | +0.014 |
poisoned | +0.014 |
Neg logit contributions | |
sizes | -0.016 |
clubs | -0.014 |
planets | -0.014 |
ABC | -0.014 |
grid | -0.014 |
Token | then |
Token ID | 788 |
Feature activation | -4.06e-02 |
Pos logit contributions | |
sizes | +0.052 |
bows | +0.046 |
planets | +0.046 |
ABC | +0.046 |
cultures | +0.045 |
Neg logit contributions | |
late | -0.043 |
aback | -0.036 |
O | -0.035 |
Start | -0.035 |
sm | -0.034 |
Token | , |
Token ID | 11 |
Feature activation | +2.44e-02 |
Pos logit contributions | |
late | +0.076 |
aback | +0.066 |
Start | +0.065 |
O | +0.064 |
sm | +0.063 |
Neg logit contributions | |
sizes | -0.069 |
bows | -0.059 |
ABC | -0.058 |
planets | -0.058 |
cultures | -0.057 |
Token | disaster |
Token ID | 9336 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
sizes | +0.047 |
planets | +0.042 |
bows | +0.041 |
ABC | +0.041 |
clubs | +0.040 |
Neg logit contributions | |
late | -0.038 |
aback | -0.032 |
Start | -0.032 |
sm | -0.031 |
O | -0.031 |
Token | ! |
Token ID | 0 |
Feature activation | -1.56e-02 |
Pos logit contributions | |
late | +0.220 |
aback | +0.187 |
severe | +0.183 |
O | +0.177 |
Aid | +0.175 |
Neg logit contributions | |
sizes | -0.313 |
bows | -0.284 |
planets | -0.278 |
ABC | -0.261 |
toes | -0.260 |
Token | The |
Token ID | 383 |
Feature activation | +2.46e-02 |
Pos logit contributions | |
late | +0.027 |
sm | +0.024 |
aback | +0.024 |
Start | +0.023 |
O | +0.023 |
Neg logit contributions | |
sizes | -0.026 |
clubs | -0.023 |
planets | -0.023 |
ABC | -0.022 |
bows | -0.022 |
Token | top |
Token ID | 1353 |
Feature activation | -5.11e-02 |
Pos logit contributions | |
sizes | +0.041 |
bows | +0.035 |
planets | +0.035 |
cultures | +0.034 |
clubs | +0.033 |
Neg logit contributions | |
late | -0.045 |
aback | -0.039 |
Start | -0.038 |
O | -0.038 |
sm | -0.038 |
Token | suddenly |
Token ID | 6451 |
Feature activation | -2.83e-02 |
Pos logit contributions | |
late | +0.079 |
aback | +0.066 |
Start | +0.064 |
O | +0.064 |
sm | +0.064 |
Neg logit contributions | |
sizes | -0.100 |
planets | -0.089 |
bows | -0.088 |
ABC | -0.087 |
clubs | -0.086 |
Token | stopped |
Token ID | 5025 |
Feature activation | -3.76e-02 |
Pos logit contributions | |
late | +0.049 |
aback | +0.043 |
Start | +0.042 |
sm | +0.041 |
O | +0.041 |
Neg logit contributions | |
sizes | -0.049 |
planets | -0.043 |
bows | -0.043 |
ABC | -0.042 |
clubs | -0.041 |
Token | One |
Token ID | 3198 |
Feature activation | -3.84e-02 |
Pos logit contributions | |
late | +0.061 |
aback | +0.052 |
severe | +0.050 |
Start | +0.049 |
poisonous | +0.049 |
Neg logit contributions | |
sizes | -0.103 |
planets | -0.094 |
bows | -0.094 |
ABC | -0.093 |
clubs | -0.090 |
Token | day |
Token ID | 1110 |
Feature activation | -3.60e-02 |
Pos logit contributions | |
aback | +0.089 |
late | +0.089 |
Start | +0.085 |
plug | +0.083 |
O | +0.083 |
Neg logit contributions | |
sizes | -0.038 |
ABC | -0.031 |
toes | -0.031 |
planets | -0.030 |
bows | -0.028 |
Token | , |
Token ID | 11 |
Feature activation | +1.27e-03 |
Pos logit contributions | |
late | +0.093 |
aback | +0.086 |
Start | +0.084 |
sm | +0.083 |
severe | +0.083 |
Neg logit contributions | |
sizes | -0.028 |
toes | -0.023 |
planets | -0.022 |
ABC | -0.021 |
bows | -0.021 |
Token | a |
Token ID | 257 |
Feature activation | -2.93e-02 |
Pos logit contributions | |
sizes | +0.003 |
planets | +0.002 |
toes | +0.002 |
bows | +0.002 |
clubs | +0.002 |
Neg logit contributions | |
late | -0.002 |
aback | -0.001 |
severe | -0.001 |
Start | -0.001 |
sm | -0.001 |
Token | 3 |
Token ID | 513 |
Feature activation | -7.79e-02 |
Pos logit contributions | |
late | +0.039 |
O | +0.031 |
sm | +0.030 |
Start | +0.030 |
aback | +0.030 |
Neg logit contributions | |
sizes | -0.065 |
planets | -0.058 |
bows | -0.058 |
cultures | -0.057 |
clubs | -0.056 |
Token | - |
Token ID | 12 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
late | +0.129 |
aback | +0.115 |
Start | +0.106 |
O | +0.103 |
severe | +0.101 |
Neg logit contributions | |
sizes | -0.141 |
ABC | -0.126 |
planets | -0.125 |
toes | -0.123 |
bows | -0.121 |
Token | year |
Token ID | 1941 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
late | +0.172 |
aback | +0.147 |
Start | +0.136 |
O | +0.133 |
severe | +0.127 |
Neg logit contributions | |
sizes | -0.341 |
planets | -0.313 |
ABC | -0.308 |
hips | -0.307 |
nations | -0.307 |
Token | - |
Token ID | 12 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
late | +0.154 |
aback | +0.133 |
Start | +0.128 |
O | +0.127 |
sm | +0.117 |
Neg logit contributions | |
sizes | -0.239 |
planets | -0.215 |
ABC | -0.214 |
bows | -0.212 |
toes | -0.211 |
Token | old |
Token ID | 727 |
Feature activation | -5.29e-02 |
Pos logit contributions | |
late | +0.186 |
aback | +0.159 |
Start | +0.150 |
O | +0.150 |
severe | +0.140 |
Neg logit contributions | |
sizes | -0.303 |
planets | -0.275 |
ABC | -0.272 |
bows | -0.271 |
clubs | -0.270 |
Token | girl |
Token ID | 2576 |
Feature activation | -4.38e-02 |
Pos logit contributions | |
late | +0.094 |
aback | +0.085 |
Start | +0.083 |
O | +0.082 |
severe | +0.082 |
Neg logit contributions | |
sizes | -0.082 |
planets | -0.075 |
ABC | -0.071 |
clubs | -0.070 |
neck | -0.070 |
Token | named |
Token ID | 3706 |
Feature activation | -1.00e-02 |
Pos logit contributions | |
late | +0.080 |
aback | +0.070 |
Start | +0.068 |
O | +0.067 |
sm | +0.066 |
Neg logit contributions | |
sizes | -0.072 |
planets | -0.063 |
bows | -0.062 |
ABC | -0.061 |
clubs | -0.061 |
Token | One |
Token ID | 3198 |
Feature activation | -4.03e-02 |
Pos logit contributions | |
late | +0.064 |
aback | +0.052 |
Start | +0.050 |
sm | +0.050 |
O | +0.049 |
Neg logit contributions | |
sizes | -0.113 |
planets | -0.103 |
bows | -0.102 |
ABC | -0.101 |
clubs | -0.099 |
Token | day |
Token ID | 1110 |
Feature activation | -3.63e-02 |
Pos logit contributions | |
late | +0.093 |
aback | +0.091 |
Start | +0.088 |
O | +0.086 |
plug | +0.085 |
Neg logit contributions | |
sizes | -0.042 |
planets | -0.034 |
ABC | -0.034 |
toes | -0.033 |
bows | -0.031 |
Token | , |
Token ID | 11 |
Feature activation | -2.64e-05 |
Pos logit contributions | |
late | +0.087 |
aback | +0.079 |
Start | +0.077 |
sm | +0.077 |
O | +0.077 |
Neg logit contributions | |
sizes | -0.040 |
planets | -0.032 |
bows | -0.031 |
ABC | -0.030 |
clubs | -0.029 |
Token | a |
Token ID | 257 |
Feature activation | -3.28e-02 |
Pos logit contributions | |
late | +0.000 |
aback | +0.000 |
Start | +0.000 |
sm | +0.000 |
O | +0.000 |
Neg logit contributions | |
sizes | -0.000 |
planets | -0.000 |
bows | -0.000 |
ABC | -0.000 |
clubs | -0.000 |
Token | three |
Token ID | 1115 |
Feature activation | -6.93e-02 |
Pos logit contributions | |
late | +0.043 |
O | +0.034 |
sm | +0.033 |
Start | +0.033 |
aback | +0.032 |
Neg logit contributions | |
sizes | -0.074 |
planets | -0.066 |
bows | -0.066 |
cultures | -0.065 |
clubs | -0.064 |
Token | - |
Token ID | 12 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
late | +0.101 |
aback | +0.087 |
Start | +0.081 |
O | +0.079 |
sm | +0.077 |
Neg logit contributions | |
sizes | -0.142 |
planets | -0.127 |
ABC | -0.125 |
bows | -0.124 |
clubs | -0.123 |
Token | year |
Token ID | 1941 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
late | +0.158 |
aback | +0.130 |
Start | +0.122 |
O | +0.122 |
severe | +0.117 |
Neg logit contributions | |
sizes | -0.354 |
planets | -0.327 |
clubs | -0.320 |
bows | -0.319 |
cultures | -0.319 |
Token | - |
Token ID | 12 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
late | +0.140 |
aback | +0.116 |
Start | +0.111 |
O | +0.111 |
sm | +0.107 |
Neg logit contributions | |
sizes | -0.247 |
planets | -0.223 |
bows | -0.220 |
ABC | -0.219 |
clubs | -0.217 |
Token | old |
Token ID | 727 |
Feature activation | -5.36e-02 |
Pos logit contributions | |
late | +0.171 |
aback | +0.142 |
O | +0.136 |
Start | +0.135 |
severe | +0.126 |
Neg logit contributions | |
sizes | -0.313 |
planets | -0.285 |
bows | -0.282 |
ABC | -0.279 |
clubs | -0.279 |
Token | boy |
Token ID | 2933 |
Feature activation | -3.12e-02 |
Pos logit contributions | |
late | +0.090 |
aback | +0.078 |
Start | +0.077 |
O | +0.075 |
severe | +0.074 |
Neg logit contributions | |
sizes | -0.094 |
planets | -0.085 |
bows | -0.082 |
clubs | -0.082 |
ABC | -0.081 |
Token | was |
Token ID | 373 |
Feature activation | -1.01e-02 |
Pos logit contributions | |
late | +0.053 |
aback | +0.045 |
sm | +0.045 |
O | +0.044 |
Start | +0.044 |
Neg logit contributions | |
sizes | -0.057 |
planets | -0.050 |
bows | -0.050 |
ABC | -0.049 |
cultures | -0.048 |
Token | day |
Token ID | 1110 |
Feature activation | -2.88e-02 |
Pos logit contributions | |
aback | +0.062 |
Start | +0.058 |
late | +0.056 |
plug | +0.056 |
O | +0.055 |
Neg logit contributions | |
sizes | -0.017 |
ABC | -0.015 |
toes | -0.013 |
planets | -0.013 |
hobbies | -0.011 |
Token | , |
Token ID | 11 |
Feature activation | +8.83e-03 |
Pos logit contributions | |
late | +0.071 |
aback | +0.065 |
Start | +0.064 |
sm | +0.063 |
O | +0.063 |
Neg logit contributions | |
sizes | -0.028 |
planets | -0.023 |
bows | -0.022 |
ABC | -0.022 |
toes | -0.021 |
Token | a |
Token ID | 257 |
Feature activation | -1.78e-02 |
Pos logit contributions | |
sizes | +0.018 |
planets | +0.017 |
toes | +0.016 |
ABC | +0.016 |
bows | +0.016 |
Neg logit contributions | |
late | -0.012 |
aback | -0.011 |
Start | -0.010 |
izz | -0.010 |
severe | -0.010 |
Token | little |
Token ID | 1310 |
Feature activation | -3.69e-02 |
Pos logit contributions | |
late | +0.028 |
aback | +0.026 |
sm | +0.023 |
Start | +0.023 |
izz | +0.023 |
Neg logit contributions | |
sizes | -0.032 |
ABC | -0.030 |
planets | -0.028 |
bows | -0.028 |
toes | -0.027 |
Token | 3 |
Token ID | 513 |
Feature activation | -7.50e-02 |
Pos logit contributions | |
late | +0.064 |
O | +0.058 |
izz | +0.058 |
sm | +0.057 |
aback | +0.057 |
Neg logit contributions | |
sizes | -0.061 |
planets | -0.053 |
bows | -0.052 |
ABC | -0.051 |
clubs | -0.050 |
Token | - |
Token ID | 12 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
late | +0.133 |
aback | +0.117 |
O | +0.109 |
Start | +0.108 |
severe | +0.105 |
Neg logit contributions | |
sizes | -0.130 |
ABC | -0.115 |
planets | -0.112 |
toes | -0.111 |
languages | -0.110 |
Token | year |
Token ID | 1941 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
late | +0.192 |
aback | +0.161 |
O | +0.153 |
Start | +0.151 |
severe | +0.151 |
Neg logit contributions | |
sizes | -0.312 |
nations | -0.288 |
ABC | -0.286 |
planets | -0.285 |
hips | -0.285 |
Token | - |
Token ID | 12 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
late | +0.150 |
aback | +0.129 |
O | +0.126 |
Start | +0.125 |
sm | +0.116 |
Neg logit contributions | |
sizes | -0.228 |
ABC | -0.204 |
planets | -0.204 |
bows | -0.200 |
clubs | -0.200 |
Token | old |
Token ID | 727 |
Feature activation | -5.44e-02 |
Pos logit contributions | |
late | +0.197 |
aback | +0.169 |
O | +0.165 |
Start | +0.159 |
severe | +0.155 |
Neg logit contributions | |
sizes | -0.273 |
ABC | -0.247 |
planets | -0.246 |
bows | -0.246 |
cultures | -0.246 |
Token | boy |
Token ID | 2933 |
Feature activation | -2.80e-02 |
Pos logit contributions | |
late | +0.091 |
aback | +0.077 |
O | +0.077 |
Start | +0.076 |
sm | +0.074 |
Neg logit contributions | |
sizes | -0.098 |
planets | -0.087 |
bows | -0.085 |
ABC | -0.085 |
cultures | -0.083 |
Token | named |
Token ID | 3706 |
Feature activation | -8.57e-03 |
Pos logit contributions | |
late | +0.047 |
aback | +0.040 |
Start | +0.039 |
O | +0.039 |
sm | +0.038 |
Neg logit contributions | |
sizes | -0.050 |
planets | -0.044 |
bows | -0.044 |
ABC | -0.043 |
clubs | -0.043 |
Token | day |
Token ID | 1110 |
Feature activation | -2.85e-02 |
Pos logit contributions | |
aback | +0.069 |
late | +0.065 |
Start | +0.064 |
plug | +0.062 |
O | +0.061 |
Neg logit contributions | |
sizes | -0.029 |
planets | -0.024 |
ABC | -0.024 |
toes | -0.024 |
bows | -0.021 |
Token | , |
Token ID | 11 |
Feature activation | +6.66e-03 |
Pos logit contributions | |
late | +0.063 |
aback | +0.056 |
O | +0.056 |
Start | +0.055 |
sm | +0.055 |
Neg logit contributions | |
sizes | -0.038 |
planets | -0.031 |
bows | -0.031 |
cultures | -0.030 |
ABC | -0.030 |
Token | a |
Token ID | 257 |
Feature activation | -2.08e-02 |
Pos logit contributions | |
sizes | +0.013 |
planets | +0.012 |
toes | +0.012 |
ABC | +0.012 |
clubs | +0.012 |
Neg logit contributions | |
late | -0.009 |
aback | -0.009 |
severe | -0.008 |
izz | -0.008 |
sm | -0.008 |
Token | little |
Token ID | 1310 |
Feature activation | -3.85e-02 |
Pos logit contributions | |
late | +0.030 |
aback | +0.025 |
Start | +0.024 |
sm | +0.024 |
O | +0.024 |
Neg logit contributions | |
sizes | -0.042 |
planets | -0.038 |
bows | -0.037 |
ABC | -0.037 |
clubs | -0.037 |
Token | 3 |
Token ID | 513 |
Feature activation | -7.67e-02 |
Pos logit contributions | |
late | +0.064 |
aback | +0.057 |
Start | +0.056 |
O | +0.055 |
sm | +0.055 |
Neg logit contributions | |
sizes | -0.067 |
planets | -0.060 |
bows | -0.059 |
clubs | -0.057 |
ABC | -0.057 |
Token | - |
Token ID | 12 |
Feature activation | -1.53e-01 |
Pos logit contributions | |
late | +0.125 |
aback | +0.110 |
Start | +0.102 |
O | +0.100 |
severe | +0.098 |
Neg logit contributions | |
sizes | -0.143 |
ABC | -0.125 |
planets | -0.125 |
toes | -0.122 |
bows | -0.122 |
Token | year |
Token ID | 1941 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
late | +0.184 |
aback | +0.152 |
severe | +0.142 |
Start | +0.141 |
O | +0.140 |
Neg logit contributions | |
sizes | -0.319 |
planets | -0.300 |
nations | -0.297 |
hips | -0.295 |
languages | -0.293 |
Token | - |
Token ID | 12 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
late | +0.149 |
aback | +0.128 |
Start | +0.123 |
O | +0.123 |
sm | +0.114 |
Neg logit contributions | |
sizes | -0.237 |
planets | -0.214 |
ABC | -0.211 |
bows | -0.210 |
clubs | -0.208 |
Token | old |
Token ID | 727 |
Feature activation | -5.31e-02 |
Pos logit contributions | |
late | +0.190 |
aback | +0.162 |
O | +0.154 |
Start | +0.152 |
severe | +0.148 |
Neg logit contributions | |
sizes | -0.285 |
planets | -0.263 |
bows | -0.258 |
nations | -0.257 |
ABC | -0.257 |
Token | girl |
Token ID | 2576 |
Feature activation | -4.45e-02 |
Pos logit contributions | |
late | +0.093 |
aback | +0.080 |
Start | +0.080 |
O | +0.079 |
severe | +0.078 |
Neg logit contributions | |
sizes | -0.089 |
planets | -0.081 |
bows | -0.078 |
ABC | -0.077 |
clubs | -0.076 |
Token | found |
Token ID | 1043 |
Feature activation | -9.22e-02 |
Pos logit contributions | |
late | +0.078 |
aback | +0.067 |
Start | +0.066 |
O | +0.065 |
sm | +0.064 |
Neg logit contributions | |
sizes | -0.077 |
planets | -0.068 |
bows | -0.067 |
ABC | -0.066 |
clubs | -0.066 |
Token | |
Token ID | 220 |
Feature activation | +7.58e-03 |
Pos logit contributions | |
late | +0.005 |
sm | +0.005 |
severe | +0.005 |
aback | +0.004 |
poisonous | +0.004 |
Neg logit contributions | |
sizes | -0.004 |
ABC | -0.003 |
planets | -0.003 |
toes | -0.003 |
bows | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | -2.76e-02 |
Pos logit contributions | |
sizes | +0.012 |
ABC | +0.011 |
planets | +0.011 |
hips | +0.011 |
bows | +0.011 |
Neg logit contributions | |
late | -0.013 |
aback | -0.012 |
sm | -0.011 |
O | -0.011 |
poisoned | -0.011 |
Token |
|
Token ID | 198 |
Feature activation | -3.06e-02 |
Pos logit contributions | |
late | +0.048 |
aback | +0.044 |
poisoned | +0.042 |
poisonous | +0.042 |
sm | +0.042 |
Neg logit contributions | |
sizes | -0.043 |
ABC | -0.039 |
planets | -0.037 |
languages | -0.035 |
clubs | -0.035 |
Token | A |
Token ID | 32 |
Feature activation | -1.48e-02 |
Pos logit contributions | |
aback | +0.049 |
late | +0.046 |
poisoned | +0.042 |
Aid | +0.042 |
sm | +0.041 |
Neg logit contributions | |
sizes | -0.050 |
ABC | -0.045 |
planets | -0.044 |
necks | -0.044 |
cultures | -0.043 |
Token | 3 |
Token ID | 513 |
Feature activation | -7.01e-02 |
Pos logit contributions | |
late | +0.023 |
aback | +0.021 |
sm | +0.019 |
Start | +0.019 |
O | +0.019 |
Neg logit contributions | |
sizes | -0.027 |
ABC | -0.025 |
planets | -0.024 |
bows | -0.023 |
clubs | -0.023 |
Token | - |
Token ID | 12 |
Feature activation | -1.52e-01 |
Pos logit contributions | |
late | +0.121 |
aback | +0.106 |
O | +0.100 |
Start | +0.099 |
severe | +0.096 |
Neg logit contributions | |
sizes | -0.123 |
planets | -0.108 |
ABC | -0.107 |
languages | -0.105 |
nations | -0.105 |
Token | year |
Token ID | 1941 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
late | +0.187 |
aback | +0.159 |
O | +0.152 |
Start | +0.147 |
severe | +0.145 |
Neg logit contributions | |
sizes | -0.309 |
nations | -0.291 |
languages | -0.289 |
hips | -0.287 |
planets | -0.285 |
Token | - |
Token ID | 12 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
late | +0.145 |
aback | +0.125 |
Start | +0.120 |
O | +0.120 |
sm | +0.113 |
Neg logit contributions | |
sizes | -0.219 |
planets | -0.198 |
ABC | -0.197 |
clubs | -0.193 |
bows | -0.193 |
Token | old |
Token ID | 727 |
Feature activation | -4.78e-02 |
Pos logit contributions | |
late | +0.198 |
aback | +0.172 |
O | +0.168 |
Start | +0.161 |
severe | +0.156 |
Neg logit contributions | |
sizes | -0.271 |
nations | -0.249 |
planets | -0.248 |
languages | -0.247 |
cultures | -0.245 |
Token | child |
Token ID | 1200 |
Feature activation | -5.89e-02 |
Pos logit contributions | |
late | +0.082 |
O | +0.071 |
aback | +0.070 |
Start | +0.069 |
severe | +0.068 |
Neg logit contributions | |
sizes | -0.082 |
planets | -0.074 |
ABC | -0.071 |
nations | -0.070 |
bows | -0.070 |
Token | noticed |
Token ID | 6810 |
Feature activation | -6.73e-02 |
Pos logit contributions | |
late | +0.095 |
aback | +0.081 |
Start | +0.079 |
sm | +0.079 |
O | +0.078 |
Neg logit contributions | |
sizes | -0.112 |
planets | -0.098 |
bows | -0.098 |
ABC | -0.096 |
cultures | -0.095 |
Token | day |
Token ID | 1110 |
Feature activation | -2.64e-02 |
Pos logit contributions | |
aback | +0.060 |
late | +0.059 |
Start | +0.057 |
plug | +0.056 |
severe | +0.054 |
Neg logit contributions | |
sizes | -0.026 |
toes | -0.021 |
ABC | -0.021 |
planets | -0.021 |
bows | -0.019 |
Token | , |
Token ID | 11 |
Feature activation | +9.51e-03 |
Pos logit contributions | |
late | +0.058 |
aback | +0.051 |
O | +0.051 |
sm | +0.050 |
Start | +0.050 |
Neg logit contributions | |
sizes | -0.037 |
bows | -0.030 |
planets | -0.030 |
cultures | -0.029 |
ABC | -0.028 |
Token | a |
Token ID | 257 |
Feature activation | -1.97e-02 |
Pos logit contributions | |
sizes | +0.020 |
planets | +0.019 |
ABC | +0.018 |
toes | +0.018 |
bows | +0.018 |
Neg logit contributions | |
late | -0.012 |
aback | -0.011 |
Start | -0.010 |
sm | -0.010 |
izz | -0.010 |
Token | little |
Token ID | 1310 |
Feature activation | -3.74e-02 |
Pos logit contributions | |
late | +0.029 |
aback | +0.024 |
Start | +0.023 |
sm | +0.023 |
O | +0.023 |
Neg logit contributions | |
sizes | -0.039 |
planets | -0.035 |
ABC | -0.035 |
bows | -0.035 |
clubs | -0.034 |
Token | 3 |
Token ID | 513 |
Feature activation | -7.64e-02 |
Pos logit contributions | |
late | +0.063 |
aback | +0.056 |
Start | +0.055 |
sm | +0.054 |
severe | +0.054 |
Neg logit contributions | |
sizes | -0.065 |
planets | -0.057 |
bows | -0.056 |
clubs | -0.056 |
toes | -0.054 |
Token | - |
Token ID | 12 |
Feature activation | -1.52e-01 |
Pos logit contributions | |
late | +0.114 |
aback | +0.098 |
Start | +0.092 |
O | +0.090 |
severe | +0.088 |
Neg logit contributions | |
sizes | -0.152 |
planets | -0.135 |
ABC | -0.133 |
bows | -0.132 |
clubs | -0.131 |
Token | year |
Token ID | 1941 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
late | +0.170 |
aback | +0.135 |
Start | +0.127 |
severe | +0.126 |
O | +0.125 |
Neg logit contributions | |
sizes | -0.341 |
planets | -0.313 |
bows | -0.309 |
nations | -0.308 |
clubs | -0.307 |
Token | - |
Token ID | 12 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
late | +0.133 |
aback | +0.110 |
Start | +0.106 |
O | +0.105 |
sm | +0.102 |
Neg logit contributions | |
sizes | -0.238 |
planets | -0.215 |
bows | -0.212 |
ABC | -0.211 |
clubs | -0.209 |
Token | old |
Token ID | 727 |
Feature activation | -5.05e-02 |
Pos logit contributions | |
late | +0.172 |
aback | +0.142 |
O | +0.134 |
Start | +0.134 |
severe | +0.128 |
Neg logit contributions | |
sizes | -0.306 |
planets | -0.278 |
bows | -0.275 |
ABC | -0.272 |
cultures | -0.271 |
Token | girl |
Token ID | 2576 |
Feature activation | -4.47e-02 |
Pos logit contributions | |
late | +0.083 |
aback | +0.070 |
Start | +0.069 |
O | +0.069 |
sm | +0.067 |
Neg logit contributions | |
sizes | -0.092 |
planets | -0.083 |
bows | -0.081 |
ABC | -0.080 |
clubs | -0.079 |
Token | was |
Token ID | 373 |
Feature activation | -3.22e-03 |
Pos logit contributions | |
late | +0.072 |
aback | +0.061 |
Start | +0.060 |
O | +0.059 |
sm | +0.059 |
Neg logit contributions | |
sizes | -0.084 |
planets | -0.075 |
bows | -0.074 |
ABC | -0.073 |
clubs | -0.072 |
Token | One |
Token ID | 3198 |
Feature activation | -3.92e-02 |
Pos logit contributions | |
late | +0.066 |
aback | +0.055 |
Start | +0.053 |
sm | +0.052 |
severe | +0.052 |
Neg logit contributions | |
sizes | -0.109 |
planets | -0.099 |
bows | -0.099 |
ABC | -0.097 |
clubs | -0.095 |
Token | day |
Token ID | 1110 |
Feature activation | -3.54e-02 |
Pos logit contributions | |
late | +0.091 |
aback | +0.090 |
Start | +0.086 |
plug | +0.084 |
O | +0.084 |
Neg logit contributions | |
sizes | -0.039 |
planets | -0.032 |
ABC | -0.032 |
toes | -0.031 |
bows | -0.029 |
Token | , |
Token ID | 11 |
Feature activation | +1.79e-03 |
Pos logit contributions | |
late | +0.084 |
aback | +0.076 |
Start | +0.074 |
O | +0.074 |
sm | +0.074 |
Neg logit contributions | |
sizes | -0.040 |
planets | -0.032 |
bows | -0.032 |
ABC | -0.031 |
cultures | -0.030 |
Token | a |
Token ID | 257 |
Feature activation | -3.04e-02 |
Pos logit contributions | |
sizes | +0.004 |
planets | +0.004 |
bows | +0.004 |
toes | +0.004 |
ABC | +0.004 |
Neg logit contributions | |
late | -0.002 |
aback | -0.002 |
Start | -0.002 |
sm | -0.002 |
severe | -0.002 |
Token | three |
Token ID | 1115 |
Feature activation | -6.48e-02 |
Pos logit contributions | |
late | +0.039 |
O | +0.031 |
sm | +0.030 |
Start | +0.029 |
aback | +0.028 |
Neg logit contributions | |
sizes | -0.070 |
bows | -0.063 |
planets | -0.062 |
cultures | -0.061 |
clubs | -0.061 |
Token | - |
Token ID | 12 |
Feature activation | -1.51e-01 |
Pos logit contributions | |
late | +0.103 |
aback | +0.091 |
Start | +0.085 |
O | +0.082 |
severe | +0.080 |
Neg logit contributions | |
sizes | -0.125 |
planets | -0.111 |
ABC | -0.110 |
toes | -0.108 |
clubs | -0.107 |
Token | year |
Token ID | 1941 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
late | +0.154 |
aback | +0.127 |
Start | +0.117 |
O | +0.117 |
severe | +0.111 |
Neg logit contributions | |
sizes | -0.357 |
planets | -0.329 |
bows | -0.321 |
ABC | -0.321 |
cultures | -0.321 |
Token | - |
Token ID | 12 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
late | +0.146 |
aback | +0.123 |
Start | +0.118 |
O | +0.118 |
sm | +0.111 |
Neg logit contributions | |
sizes | -0.240 |
planets | -0.217 |
ABC | -0.214 |
bows | -0.213 |
clubs | -0.211 |
Token | old |
Token ID | 727 |
Feature activation | -5.37e-02 |
Pos logit contributions | |
late | +0.171 |
aback | +0.141 |
O | +0.134 |
Start | +0.134 |
severe | +0.125 |
Neg logit contributions | |
sizes | -0.314 |
planets | -0.286 |
bows | -0.282 |
ABC | -0.281 |
cultures | -0.279 |
Token | boy |
Token ID | 2933 |
Feature activation | -2.90e-02 |
Pos logit contributions | |
late | +0.091 |
aback | +0.080 |
Start | +0.079 |
O | +0.078 |
severe | +0.076 |
Neg logit contributions | |
sizes | -0.093 |
planets | -0.084 |
bows | -0.081 |
ABC | -0.080 |
clubs | -0.080 |
Token | was |
Token ID | 373 |
Feature activation | -9.93e-03 |
Pos logit contributions | |
late | +0.052 |
aback | +0.045 |
Start | +0.044 |
O | +0.044 |
sm | +0.043 |
Neg logit contributions | |
sizes | -0.050 |
planets | -0.043 |
bows | -0.043 |
ABC | -0.042 |
clubs | -0.042 |
Token | classroom |
Token ID | 15806 |
Feature activation | -1.41e-02 |
Pos logit contributions | |
late | +0.039 |
O | +0.031 |
sm | +0.030 |
Start | +0.029 |
aback | +0.027 |
Neg logit contributions | |
sizes | -0.070 |
bows | -0.062 |
planets | -0.062 |
cultures | -0.061 |
clubs | -0.061 |
Token | . |
Token ID | 13 |
Feature activation | +6.88e-03 |
Pos logit contributions | |
late | +0.022 |
sm | +0.019 |
Start | +0.018 |
O | +0.016 |
aback | +0.016 |
Neg logit contributions | |
sizes | -0.027 |
planets | -0.025 |
cultures | -0.025 |
hips | -0.024 |
necks | -0.023 |
Token | Jake |
Token ID | 14757 |
Feature activation | +2.29e-02 |
Pos logit contributions | |
sizes | +0.013 |
bows | +0.012 |
ABC | +0.012 |
planets | +0.012 |
toes | +0.011 |
Neg logit contributions | |
late | -0.010 |
severe | -0.009 |
aback | -0.009 |
poisonous | -0.009 |
poisoned | -0.009 |
Token | was |
Token ID | 373 |
Feature activation | +1.64e-02 |
Pos logit contributions | |
sizes | +0.037 |
planets | +0.032 |
bows | +0.031 |
ABC | +0.031 |
clubs | +0.030 |
Neg logit contributions | |
late | -0.043 |
aback | -0.038 |
Start | -0.037 |
O | -0.037 |
sm | -0.037 |
Token | 3 |
Token ID | 513 |
Feature activation | -6.77e-02 |
Pos logit contributions | |
sizes | +0.031 |
planets | +0.027 |
bows | +0.027 |
cultures | +0.026 |
clubs | +0.026 |
Neg logit contributions | |
late | -0.028 |
aback | -0.023 |
Start | -0.022 |
sm | -0.022 |
O | -0.022 |
Token | - |
Token ID | 12 |
Feature activation | -1.51e-01 |
Pos logit contributions | |
late | +0.117 |
sm | +0.103 |
Start | +0.098 |
aback | +0.098 |
O | +0.095 |
Neg logit contributions | |
sizes | -0.118 |
bows | -0.106 |
planets | -0.104 |
hips | -0.103 |
cultures | -0.101 |
Token | years |
Token ID | 19002 |
Feature activation | -7.57e-02 |
Pos logit contributions | |
late | +0.211 |
aback | +0.178 |
Start | +0.171 |
O | +0.169 |
sm | +0.163 |
Neg logit contributions | |
sizes | -0.312 |
planets | -0.280 |
bows | -0.276 |
ABC | -0.275 |
clubs | -0.273 |
Token | - |
Token ID | 12 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
late | +0.087 |
aback | +0.068 |
sm | +0.066 |
Start | +0.065 |
O | +0.064 |
Neg logit contributions | |
sizes | -0.177 |
planets | -0.161 |
bows | -0.160 |
ABC | -0.157 |
cultures | -0.156 |
Token | old |
Token ID | 727 |
Feature activation | -3.79e-02 |
Pos logit contributions | |
late | +0.140 |
aback | +0.109 |
sm | +0.107 |
Start | +0.105 |
O | +0.103 |
Neg logit contributions | |
sizes | -0.303 |
planets | -0.275 |
bows | -0.272 |
ABC | -0.269 |
clubs | -0.266 |
Token | and |
Token ID | 290 |
Feature activation | -2.83e-02 |
Pos logit contributions | |
late | +0.060 |
sm | +0.052 |
aback | +0.051 |
Start | +0.046 |
my | +0.045 |
Neg logit contributions | |
sizes | -0.071 |
hips | -0.068 |
bows | -0.065 |
planets | -0.064 |
ABC | -0.064 |
Token | the |
Token ID | 262 |
Feature activation | +3.45e-03 |
Pos logit contributions | |
late | +0.049 |
O | +0.040 |
Start | +0.040 |
sm | +0.040 |
aback | +0.039 |
Neg logit contributions | |
sizes | -0.050 |
bows | -0.046 |
planets | -0.045 |
clubs | -0.044 |
necks | -0.044 |
Token | dogs |
Token ID | 6844 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
sizes | +0.121 |
planets | +0.110 |
ABC | +0.107 |
clubs | +0.105 |
bows | +0.104 |
Neg logit contributions | |
late | -0.075 |
aback | -0.066 |
Start | -0.062 |
O | -0.061 |
izz | -0.060 |
Token | . |
Token ID | 13 |
Feature activation | +1.77e-02 |
Pos logit contributions | |
sizes | +0.212 |
planets | +0.183 |
bows | +0.180 |
ABC | +0.178 |
clubs | +0.174 |
Neg logit contributions | |
late | -0.255 |
aback | -0.221 |
Start | -0.217 |
sm | -0.216 |
O | -0.215 |
Token | Do |
Token ID | 2141 |
Feature activation | +4.19e-02 |
Pos logit contributions | |
sizes | +0.034 |
planets | +0.030 |
bows | +0.030 |
ABC | +0.029 |
clubs | +0.029 |
Neg logit contributions | |
late | -0.028 |
aback | -0.024 |
Start | -0.023 |
sm | -0.023 |
O | -0.023 |
Token | you |
Token ID | 345 |
Feature activation | -2.00e-02 |
Pos logit contributions | |
sizes | +0.118 |
bows | +0.110 |
pit | +0.106 |
mast | +0.106 |
planets | +0.105 |
Neg logit contributions | |
late | -0.022 |
O | -0.021 |
my | -0.021 |
Start | -0.016 |
another | -0.015 |
Token | like |
Token ID | 588 |
Feature activation | +6.01e-02 |
Pos logit contributions | |
late | +0.029 |
aback | +0.024 |
Start | +0.023 |
sm | +0.023 |
O | +0.023 |
Neg logit contributions | |
sizes | -0.041 |
planets | -0.037 |
bows | -0.037 |
clubs | -0.037 |
ABC | -0.036 |
Token | dogs |
Token ID | 6844 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
sizes | +0.129 |
planets | +0.117 |
ABC | +0.114 |
bows | +0.113 |
clubs | +0.113 |
Neg logit contributions | |
late | -0.082 |
aback | -0.070 |
Start | -0.066 |
sm | -0.065 |
O | -0.065 |
Token | ?" |
Token ID | 1701 |
Feature activation | -8.22e-02 |
Pos logit contributions | |
sizes | +0.245 |
bows | +0.220 |
planets | +0.217 |
ABC | +0.215 |
clubs | +0.212 |
Neg logit contributions | |
late | -0.225 |
aback | -0.209 |
Start | -0.200 |
O | -0.197 |
sm | -0.196 |
Token | Tom |
Token ID | 4186 |
Feature activation | +1.20e-02 |
Pos logit contributions | |
late | +0.149 |
aback | +0.142 |
sm | +0.139 |
Start | +0.133 |
severe | +0.133 |
Neg logit contributions | |
sizes | -0.130 |
planets | -0.114 |
ABC | -0.110 |
clubs | -0.108 |
nations | -0.106 |
Token | asks |
Token ID | 7893 |
Feature activation | -3.19e-02 |
Pos logit contributions | |
sizes | +0.026 |
bows | +0.023 |
clubs | +0.023 |
planets | +0.023 |
hips | +0.023 |
Neg logit contributions | |
late | -0.016 |
aback | -0.014 |
Start | -0.013 |
O | -0.012 |
sm | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | +8.38e-03 |
Pos logit contributions | |
late | +0.057 |
aback | +0.048 |
sm | +0.047 |
O | +0.046 |
Start | +0.046 |
Neg logit contributions | |
sizes | -0.057 |
bows | -0.050 |
planets | -0.049 |
cultures | -0.048 |
ABC | -0.047 |
Token |
|
Token ID | 198 |
Feature activation | -1.70e-02 |
Pos logit contributions | |
sizes | +0.011 |
ABC | +0.010 |
planets | +0.010 |
clubs | +0.010 |
neck | +0.009 |
Neg logit contributions | |
late | -0.015 |
poisonous | -0.015 |
aback | -0.015 |
sm | -0.014 |
severe | -0.014 |
Token | together |
Token ID | 1978 |
Feature activation | +5.33e-02 |
Pos logit contributions | |
sizes | +0.064 |
cultures | +0.055 |
ABC | +0.055 |
planets | +0.053 |
clubs | +0.053 |
Neg logit contributions | |
late | -0.058 |
sm | -0.047 |
aback | -0.047 |
Start | -0.044 |
another | -0.043 |
Token | . |
Token ID | 13 |
Feature activation | +1.68e-02 |
Pos logit contributions | |
sizes | +0.090 |
planets | +0.076 |
bows | +0.076 |
clubs | +0.075 |
cultures | +0.075 |
Neg logit contributions | |
late | -0.097 |
aback | -0.082 |
sm | -0.081 |
Start | -0.080 |
O | -0.079 |
Token | Lily |
Token ID | 20037 |
Feature activation | -1.17e-02 |
Pos logit contributions | |
sizes | +0.032 |
planets | +0.028 |
bows | +0.027 |
ABC | +0.027 |
cultures | +0.027 |
Neg logit contributions | |
late | -0.028 |
aback | -0.023 |
Start | -0.023 |
O | -0.023 |
sm | -0.022 |
Token | played |
Token ID | 2826 |
Feature activation | +7.07e-02 |
Pos logit contributions | |
late | +0.018 |
aback | +0.015 |
Start | +0.015 |
O | +0.015 |
sm | +0.015 |
Neg logit contributions | |
sizes | -0.022 |
hips | -0.020 |
cultures | -0.019 |
bows | -0.019 |
clubs | -0.019 |
Token | her |
Token ID | 607 |
Feature activation | +2.05e-02 |
Pos logit contributions | |
sizes | +0.135 |
planets | +0.118 |
bows | +0.117 |
ABC | +0.115 |
cultures | +0.114 |
Neg logit contributions | |
late | -0.114 |
aback | -0.096 |
Start | -0.094 |
O | -0.093 |
sm | -0.092 |
Token | songs |
Token ID | 7259 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
sizes | +0.036 |
hips | +0.029 |
cultures | +0.028 |
clubs | +0.028 |
nations | +0.028 |
Neg logit contributions | |
late | -0.033 |
my | -0.029 |
another | -0.029 |
sm | -0.028 |
Start | -0.027 |
Token | as |
Token ID | 355 |
Feature activation | +1.84e-02 |
Pos logit contributions | |
sizes | +0.241 |
cultures | +0.208 |
planets | +0.205 |
ABC | +0.203 |
clubs | +0.202 |
Neg logit contributions | |
late | -0.249 |
aback | -0.210 |
sm | -0.207 |
Start | -0.201 |
O | -0.198 |
Token | best |
Token ID | 1266 |
Feature activation | +4.22e-02 |
Pos logit contributions | |
sizes | +0.040 |
clubs | +0.036 |
necks | +0.035 |
cultures | +0.035 |
cheeks | +0.035 |
Neg logit contributions | |
late | -0.026 |
sm | -0.020 |
O | -0.019 |
Start | -0.018 |
severe | -0.017 |
Token | as |
Token ID | 355 |
Feature activation | +1.22e-02 |
Pos logit contributions | |
sizes | +0.078 |
bows | +0.068 |
planets | +0.068 |
ABC | +0.067 |
cultures | +0.066 |
Neg logit contributions | |
late | -0.070 |
aback | -0.059 |
sm | -0.058 |
Start | -0.058 |
O | -0.058 |
Token | she |
Token ID | 673 |
Feature activation | -3.89e-02 |
Pos logit contributions | |
sizes | +0.027 |
necks | +0.025 |
clubs | +0.025 |
cultures | +0.024 |
languages | +0.024 |
Neg logit contributions | |
late | -0.016 |
sm | -0.012 |
O | -0.011 |
another | -0.011 |
my | -0.010 |
Token | could |
Token ID | 714 |
Feature activation | +8.55e-02 |
Pos logit contributions | |
late | +0.071 |
aback | +0.062 |
Start | +0.061 |
sm | +0.061 |
O | +0.061 |
Neg logit contributions | |
sizes | -0.065 |
planets | -0.055 |
bows | -0.055 |
ABC | -0.054 |
cultures | -0.053 |
Token | of |
Token ID | 286 |
Feature activation | -2.65e-02 |
Pos logit contributions | |
sizes | +0.005 |
ABC | +0.005 |
planets | +0.005 |
bows | +0.005 |
cultures | +0.005 |
Neg logit contributions | |
late | -0.001 |
sm | -0.001 |
aback | -0.001 |
Start | -0.001 |
poisonous | -0.001 |
Token | colors |
Token ID | 7577 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
late | +0.046 |
aback | +0.040 |
sm | +0.040 |
Start | +0.040 |
O | +0.039 |
Neg logit contributions | |
sizes | -0.045 |
bows | -0.040 |
planets | -0.039 |
ABC | -0.039 |
clubs | -0.038 |
Token | , |
Token ID | 11 |
Feature activation | +5.26e-02 |
Pos logit contributions | |
sizes | +0.181 |
ABC | +0.180 |
cultures | +0.180 |
hobbies | +0.179 |
habitats | +0.179 |
Neg logit contributions | |
late | -0.156 |
sm | -0.132 |
aback | -0.129 |
another | -0.119 |
Start | -0.118 |
Token | shapes |
Token ID | 15268 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
sizes | +0.072 |
hips | +0.070 |
ABC | +0.068 |
utes | +0.067 |
bows | +0.066 |
Neg logit contributions | |
late | -0.096 |
aback | -0.084 |
sm | -0.081 |
Start | -0.080 |
poisonous | -0.077 |
Token | and |
Token ID | 290 |
Feature activation | -5.53e-04 |
Pos logit contributions | |
ABC | +0.182 |
sizes | +0.182 |
cultures | +0.180 |
habitats | +0.179 |
hobbies | +0.177 |
Neg logit contributions | |
late | -0.142 |
sm | -0.129 |
aback | -0.120 |
another | -0.115 |
here | -0.112 |
Token | sizes |
Token ID | 10620 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
late | +0.001 |
aback | +0.001 |
sm | +0.001 |
Start | +0.001 |
another | +0.001 |
Neg logit contributions | |
hips | -0.001 |
utes | -0.001 |
bles | -0.001 |
azes | -0.001 |
ABC | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | +1.36e-02 |
Pos logit contributions | |
ABC | +0.264 |
sizes | +0.258 |
cultures | +0.255 |
planets | +0.253 |
hobbies | +0.252 |
Neg logit contributions | |
late | -0.203 |
sm | -0.183 |
aback | -0.176 |
Start | -0.160 |
another | -0.156 |
Token | She |
Token ID | 1375 |
Feature activation | +2.62e-03 |
Pos logit contributions | |
sizes | +0.026 |
planets | +0.023 |
bows | +0.023 |
ABC | +0.023 |
cultures | +0.022 |
Neg logit contributions | |
late | -0.021 |
aback | -0.018 |
sm | -0.018 |
O | -0.018 |
Start | -0.018 |
Token | couldn |
Token ID | 3521 |
Feature activation | +1.08e-02 |
Pos logit contributions | |
sizes | +0.004 |
bows | +0.004 |
planets | +0.004 |
ABC | +0.004 |
cultures | +0.004 |
Neg logit contributions | |
late | -0.005 |
aback | -0.004 |
O | -0.004 |
Start | -0.004 |
sm | -0.004 |
Token | 't |
Token ID | 470 |
Feature activation | -2.69e-02 |
Pos logit contributions | |
ABC | +0.012 |
bows | +0.011 |
sizes | +0.011 |
racing | +0.010 |
hips | +0.010 |
Neg logit contributions | |
late | -0.023 |
aback | -0.022 |
sm | -0.021 |
poisonous | -0.021 |
poisoned | -0.020 |
Token | believe |
Token ID | 1975 |
Feature activation | +3.41e-02 |
Pos logit contributions | |
late | +0.049 |
aback | +0.043 |
Start | +0.041 |
sm | +0.041 |
O | +0.041 |
Neg logit contributions | |
sizes | -0.045 |
planets | -0.039 |
bows | -0.039 |
ABC | -0.038 |
toes | -0.037 |
Token | She |
Token ID | 1375 |
Feature activation | -4.82e-03 |
Pos logit contributions | |
sizes | +0.023 |
planets | +0.021 |
bows | +0.020 |
ABC | +0.020 |
clubs | +0.020 |
Neg logit contributions | |
late | -0.016 |
aback | -0.013 |
Start | -0.013 |
O | -0.013 |
sm | -0.013 |
Token | tells |
Token ID | 4952 |
Feature activation | +1.26e-02 |
Pos logit contributions | |
late | +0.008 |
aback | +0.007 |
Start | +0.007 |
sm | +0.007 |
O | +0.007 |
Neg logit contributions | |
sizes | -0.008 |
bows | -0.007 |
planets | -0.007 |
ABC | -0.007 |
clubs | -0.007 |
Token | her |
Token ID | 607 |
Feature activation | -8.95e-03 |
Pos logit contributions | |
sizes | +0.027 |
planets | +0.024 |
bows | +0.024 |
ABC | +0.024 |
clubs | +0.023 |
Neg logit contributions | |
late | -0.017 |
aback | -0.014 |
Start | -0.014 |
sm | -0.014 |
O | -0.014 |
Token | friends |
Token ID | 2460 |
Feature activation | +8.94e-02 |
Pos logit contributions | |
late | +0.017 |
aback | +0.015 |
Start | +0.015 |
sm | +0.015 |
O | +0.015 |
Neg logit contributions | |
sizes | -0.014 |
planets | -0.012 |
bows | -0.012 |
ABC | -0.012 |
clubs | -0.011 |
Token | the |
Token ID | 262 |
Feature activation | +2.91e-02 |
Pos logit contributions | |
sizes | +0.181 |
planets | +0.160 |
bows | +0.159 |
ABC | +0.157 |
clubs | +0.155 |
Neg logit contributions | |
late | -0.129 |
aback | -0.108 |
sm | -0.106 |
Start | -0.105 |
O | -0.102 |
Token | names |
Token ID | 3891 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
sizes | +0.046 |
planets | +0.039 |
bows | +0.037 |
toes | +0.037 |
ABC | +0.037 |
Neg logit contributions | |
late | -0.054 |
Start | -0.046 |
aback | -0.046 |
sm | -0.046 |
O | -0.045 |
Token | of |
Token ID | 286 |
Feature activation | -1.85e-03 |
Pos logit contributions | |
sizes | +0.256 |
planets | +0.227 |
bows | +0.225 |
ABC | +0.222 |
clubs | +0.219 |
Neg logit contributions | |
late | -0.209 |
aback | -0.179 |
Start | -0.174 |
O | -0.172 |
sm | -0.169 |
Token | the |
Token ID | 262 |
Feature activation | +3.49e-02 |
Pos logit contributions | |
late | +0.002 |
aback | +0.002 |
Start | +0.002 |
O | +0.002 |
sm | +0.002 |
Neg logit contributions | |
sizes | -0.004 |
planets | -0.004 |
bows | -0.004 |
ABC | -0.004 |
clubs | -0.004 |
Token | flowers |
Token ID | 12734 |
Feature activation | +6.72e-02 |
Pos logit contributions | |
sizes | +0.053 |
planets | +0.044 |
ABC | +0.044 |
hips | +0.044 |
toes | +0.043 |
Neg logit contributions | |
late | -0.064 |
sm | -0.056 |
Start | -0.054 |
aback | -0.053 |
O | -0.053 |
Token | and |
Token ID | 290 |
Feature activation | -1.02e-02 |
Pos logit contributions | |
sizes | +0.108 |
planets | +0.093 |
ABC | +0.092 |
bows | +0.091 |
clubs | +0.090 |
Neg logit contributions | |
late | -0.123 |
sm | -0.106 |
aback | -0.105 |
Start | -0.103 |
O | -0.101 |
Token | what |
Token ID | 644 |
Feature activation | +2.48e-03 |
Pos logit contributions | |
late | +0.015 |
aback | +0.013 |
Start | +0.012 |
sm | +0.012 |
O | +0.012 |
Neg logit contributions | |
sizes | -0.021 |
planets | -0.018 |
bows | -0.018 |
ABC | -0.018 |
clubs | -0.018 |
Token | dolls |
Token ID | 36062 |
Feature activation | +4.37e-02 |
Pos logit contributions | |
late | +0.095 |
sm | +0.086 |
aback | +0.085 |
Start | +0.084 |
O | +0.084 |
Neg logit contributions | |
sizes | -0.046 |
bows | -0.040 |
planets | -0.038 |
ABC | -0.037 |
hips | -0.037 |
Token | of |
Token ID | 286 |
Feature activation | -2.42e-02 |
Pos logit contributions | |
sizes | +0.076 |
planets | +0.069 |
ABC | +0.068 |
cultures | +0.067 |
mast | +0.066 |
Neg logit contributions | |
late | -0.074 |
sm | -0.063 |
aback | -0.061 |
Start | -0.056 |
izz | -0.056 |
Token | different |
Token ID | 1180 |
Feature activation | +1.47e-02 |
Pos logit contributions | |
late | +0.038 |
aback | +0.032 |
Start | +0.031 |
O | +0.031 |
sm | +0.031 |
Neg logit contributions | |
sizes | -0.046 |
planets | -0.041 |
bows | -0.041 |
ABC | -0.040 |
clubs | -0.040 |
Token | colors |
Token ID | 7577 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
sizes | +0.012 |
mast | +0.011 |
hips | +0.011 |
planets | +0.011 |
clubs | +0.010 |
Neg logit contributions | |
late | -0.034 |
aback | -0.032 |
sm | -0.032 |
Start | -0.031 |
O | -0.030 |
Token | and |
Token ID | 290 |
Feature activation | +4.48e-03 |
Pos logit contributions | |
sizes | +0.206 |
cultures | +0.203 |
mast | +0.197 |
ABC | +0.195 |
planets | +0.194 |
Neg logit contributions | |
late | -0.173 |
sm | -0.142 |
aback | -0.136 |
another | -0.130 |
O | -0.128 |
Token | sizes |
Token ID | 10620 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
hips | +0.003 |
utes | +0.003 |
mast | +0.003 |
castle | +0.003 |
pit | +0.003 |
Neg logit contributions | |
late | -0.010 |
my | -0.009 |
sm | -0.009 |
medicine | -0.009 |
O | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | +1.55e-02 |
Pos logit contributions | |
sizes | +0.284 |
ABC | +0.276 |
planets | +0.275 |
cultures | +0.274 |
mast | +0.268 |
Neg logit contributions | |
late | -0.211 |
sm | -0.185 |
aback | -0.170 |
Start | -0.158 |
another | -0.157 |
Token | She |
Token ID | 1375 |
Feature activation | +1.45e-03 |
Pos logit contributions | |
sizes | +0.028 |
ABC | +0.025 |
planets | +0.025 |
bows | +0.024 |
toes | +0.024 |
Neg logit contributions | |
late | -0.026 |
aback | -0.023 |
severe | -0.023 |
sm | -0.023 |
Start | -0.022 |
Token | was |
Token ID | 373 |
Feature activation | +3.33e-02 |
Pos logit contributions | |
sizes | +0.002 |
bows | +0.002 |
planets | +0.002 |
cultures | +0.002 |
ABC | +0.002 |
Neg logit contributions | |
late | -0.003 |
O | -0.002 |
aback | -0.002 |
sm | -0.002 |
Start | -0.002 |
Token | very |
Token ID | 845 |
Feature activation | -4.61e-02 |
Pos logit contributions | |
sizes | +0.061 |
planets | +0.053 |
bows | +0.052 |
ABC | +0.052 |
toes | +0.050 |
Neg logit contributions | |
late | -0.055 |
aback | -0.049 |
Start | -0.048 |
O | -0.047 |
sm | -0.047 |
Token | organized |
Token ID | 8389 |
Feature activation | -1.14e-02 |
Pos logit contributions | |
late | +0.077 |
aback | +0.075 |
Start | +0.070 |
O | +0.069 |
severe | +0.067 |
Neg logit contributions | |
sizes | -0.080 |
toes | -0.069 |
ABC | -0.069 |
bows | -0.068 |
planets | -0.067 |
Token | . |
Token ID | 13 |
Feature activation | +9.36e-03 |
Pos logit contributions | |
sizes | +0.031 |
planets | +0.029 |
cultures | +0.029 |
nations | +0.028 |
ABC | +0.028 |
Neg logit contributions | |
late | -0.028 |
aback | -0.023 |
sm | -0.021 |
Start | -0.020 |
severe | -0.020 |
Token | " |
Token ID | 366 |
Feature activation | -1.51e-02 |
Pos logit contributions | |
sizes | +0.017 |
bows | +0.015 |
planets | +0.015 |
ABC | +0.014 |
clubs | +0.014 |
Neg logit contributions | |
late | -0.015 |
aback | -0.013 |
sm | -0.013 |
Start | -0.013 |
severe | -0.013 |
Token | You |
Token ID | 1639 |
Feature activation | +2.23e-02 |
Pos logit contributions | |
aback | +0.022 |
poisonous | +0.020 |
late | +0.019 |
poisoned | +0.019 |
severe | +0.018 |
Neg logit contributions | |
sizes | -0.027 |
necks | -0.024 |
ABC | -0.023 |
clubs | -0.023 |
neck | -0.023 |
Token | have |
Token ID | 423 |
Feature activation | -1.30e-02 |
Pos logit contributions | |
sizes | +0.032 |
clubs | +0.027 |
planets | +0.027 |
hips | +0.026 |
bows | +0.026 |
Neg logit contributions | |
late | -0.047 |
sm | -0.041 |
aback | -0.040 |
O | -0.040 |
Start | -0.039 |
Token | the |
Token ID | 262 |
Feature activation | +2.46e-02 |
Pos logit contributions | |
late | +0.020 |
izz | +0.018 |
sm | +0.018 |
aback | +0.018 |
O | +0.017 |
Neg logit contributions | |
sizes | -0.025 |
clubs | -0.022 |
planets | -0.022 |
necks | -0.021 |
ABC | -0.021 |
Token | blue |
Token ID | 4171 |
Feature activation | +6.38e-02 |
Pos logit contributions | |
sizes | +0.037 |
bows | +0.034 |
cultures | +0.032 |
ABC | +0.032 |
planets | +0.032 |
Neg logit contributions | |
late | -0.048 |
aback | -0.041 |
Start | -0.039 |
O | -0.039 |
poisoned | -0.038 |
Token | boat |
Token ID | 8848 |
Feature activation | -2.13e-02 |
Pos logit contributions | |
sizes | +0.105 |
bows | +0.094 |
cultures | +0.089 |
ABC | +0.088 |
planets | +0.086 |
Neg logit contributions | |
late | -0.113 |
aback | -0.098 |
O | -0.096 |
sm | -0.095 |
Start | -0.094 |
Token | !" |
Token ID | 2474 |
Feature activation | -4.03e-02 |
Pos logit contributions | |
late | +0.039 |
O | +0.036 |
Start | +0.035 |
izz | +0.035 |
aback | +0.035 |
Neg logit contributions | |
sizes | -0.035 |
bows | -0.030 |
clubs | -0.028 |
planets | -0.028 |
hips | -0.028 |
Token |
|
Token ID | 198 |
Feature activation | -1.54e-02 |
Pos logit contributions | |
late | +0.063 |
aback | +0.055 |
sm | +0.054 |
Start | +0.053 |
severe | +0.052 |
Neg logit contributions | |
sizes | -0.075 |
planets | -0.066 |
ABC | -0.065 |
bows | -0.065 |
clubs | -0.064 |
Token |
|
Token ID | 198 |
Feature activation | -1.85e-02 |
Pos logit contributions | |
late | +0.026 |
aback | +0.024 |
poisoned | +0.023 |
severe | +0.023 |
sm | +0.023 |
Neg logit contributions | |
sizes | -0.024 |
ABC | -0.022 |
planets | -0.021 |
clubs | -0.021 |
hips | -0.021 |
Token | " |
Token ID | 1 |
Feature activation | -4.76e-02 |
Pos logit contributions | |
late | +0.029 |
aback | +0.026 |
sm | +0.025 |
Start | +0.024 |
poisoned | +0.024 |
Neg logit contributions | |
sizes | -0.034 |
clubs | -0.030 |
planets | -0.029 |
necks | -0.029 |
bows | -0.028 |
Token | and |
Token ID | 290 |
Feature activation | -1.54e-02 |
Pos logit contributions | |
sizes | +0.084 |
planets | +0.073 |
ABC | +0.073 |
bows | +0.072 |
necks | +0.071 |
Neg logit contributions | |
late | -0.075 |
sm | -0.065 |
aback | -0.062 |
Start | -0.060 |
izz | -0.057 |
Token | the |
Token ID | 262 |
Feature activation | +1.99e-02 |
Pos logit contributions | |
late | +0.024 |
aback | +0.020 |
sm | +0.020 |
Start | +0.019 |
O | +0.019 |
Neg logit contributions | |
sizes | -0.029 |
bows | -0.026 |
ABC | -0.026 |
planets | -0.026 |
hips | -0.025 |
Token | cars |
Token ID | 5006 |
Feature activation | +4.22e-02 |
Pos logit contributions | |
sizes | +0.036 |
bows | +0.032 |
planets | +0.031 |
cultures | +0.031 |
hips | +0.030 |
Neg logit contributions | |
late | -0.034 |
aback | -0.027 |
Start | -0.027 |
O | -0.027 |
sm | -0.027 |
Token | and |
Token ID | 290 |
Feature activation | -1.20e-02 |
Pos logit contributions | |
sizes | +0.072 |
ABC | +0.064 |
planets | +0.063 |
cultures | +0.063 |
languages | +0.061 |
Neg logit contributions | |
late | -0.072 |
sm | -0.062 |
aback | -0.060 |
Start | -0.059 |
poisoned | -0.058 |
Token | the |
Token ID | 262 |
Feature activation | +2.31e-02 |
Pos logit contributions | |
late | +0.014 |
aback | +0.011 |
Start | +0.011 |
sm | +0.011 |
O | +0.011 |
Neg logit contributions | |
sizes | -0.028 |
planets | -0.025 |
bows | -0.025 |
ABC | -0.025 |
clubs | -0.024 |
Token | trees |
Token ID | 7150 |
Feature activation | +8.13e-02 |
Pos logit contributions | |
sizes | +0.040 |
bows | +0.036 |
cultures | +0.035 |
planets | +0.034 |
hips | +0.034 |
Neg logit contributions | |
late | -0.040 |
aback | -0.032 |
Start | -0.032 |
O | -0.032 |
sm | -0.032 |
Token | . |
Token ID | 13 |
Feature activation | +1.21e-02 |
Pos logit contributions | |
sizes | +0.147 |
ABC | +0.137 |
planets | +0.134 |
cultures | +0.133 |
hobbies | +0.131 |
Neg logit contributions | |
late | -0.131 |
sm | -0.111 |
aback | -0.103 |
poisonous | -0.100 |
Start | -0.100 |
Token | The |
Token ID | 383 |
Feature activation | +2.71e-02 |
Pos logit contributions | |
sizes | +0.024 |
bows | +0.021 |
planets | +0.021 |
clubs | +0.020 |
ABC | +0.020 |
Neg logit contributions | |
late | -0.018 |
sm | -0.016 |
aback | -0.016 |
severe | -0.016 |
O | -0.015 |
Token | hot |
Token ID | 3024 |
Feature activation | -2.99e-02 |
Pos logit contributions | |
sizes | +0.048 |
bows | +0.042 |
planets | +0.041 |
cultures | +0.040 |
clubs | +0.040 |
Neg logit contributions | |
late | -0.047 |
aback | -0.039 |
Start | -0.039 |
sm | -0.039 |
O | -0.039 |
Token | red |
Token ID | 2266 |
Feature activation | +1.49e-02 |
Pos logit contributions | |
late | +0.057 |
aback | +0.049 |
O | +0.048 |
sm | +0.048 |
Start | +0.048 |
Neg logit contributions | |
sizes | -0.047 |
planets | -0.040 |
bows | -0.040 |
ABC | -0.039 |
cultures | -0.039 |
Token | balloon |
Token ID | 21190 |
Feature activation | -2.04e-02 |
Pos logit contributions | |
sizes | +0.024 |
planets | +0.021 |
bows | +0.021 |
ABC | +0.021 |
clubs | +0.020 |
Neg logit contributions | |
late | -0.028 |
aback | -0.025 |
Start | -0.024 |
sm | -0.024 |
O | -0.024 |
Token | holes |
Token ID | 10421 |
Feature activation | +2.03e-02 |
Pos logit contributions | |
late | +0.022 |
aback | +0.020 |
izz | +0.019 |
sm | +0.019 |
Start | +0.018 |
Neg logit contributions | |
sizes | -0.025 |
planets | -0.022 |
clubs | -0.022 |
neck | -0.022 |
toes | -0.021 |
Token | and |
Token ID | 290 |
Feature activation | -1.52e-02 |
Pos logit contributions | |
sizes | +0.033 |
planets | +0.028 |
bows | +0.028 |
toes | +0.027 |
clubs | +0.027 |
Neg logit contributions | |
late | -0.038 |
aback | -0.034 |
Start | -0.034 |
O | -0.034 |
sm | -0.033 |
Token | rust |
Token ID | 17000 |
Feature activation | +2.69e-02 |
Pos logit contributions | |
late | +0.031 |
aback | +0.028 |
sm | +0.027 |
Start | +0.027 |
izz | +0.027 |
Neg logit contributions | |
sizes | -0.023 |
planets | -0.020 |
toes | -0.019 |
necks | -0.019 |
clubs | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | +4.81e-03 |
Pos logit contributions | |
sizes | +0.047 |
planets | +0.039 |
bows | +0.038 |
toes | +0.037 |
clubs | +0.036 |
Neg logit contributions | |
late | -0.050 |
aback | -0.046 |
Start | -0.045 |
O | -0.043 |
severe | -0.042 |
Token | It |
Token ID | 632 |
Feature activation | -1.11e-02 |
Pos logit contributions | |
sizes | +0.009 |
planets | +0.008 |
ABC | +0.008 |
bows | +0.008 |
clubs | +0.007 |
Neg logit contributions | |
late | -0.008 |
aback | -0.007 |
sm | -0.007 |
Start | -0.007 |
severe | -0.006 |
Token | can |
Token ID | 460 |
Feature activation | +6.71e-02 |
Pos logit contributions | |
late | +0.025 |
aback | +0.023 |
O | +0.023 |
severe | +0.023 |
sm | +0.022 |
Neg logit contributions | |
sizes | -0.014 |
planets | -0.012 |
bows | -0.011 |
necks | -0.011 |
ABC | -0.010 |
Token | hurt |
Token ID | 5938 |
Feature activation | +1.91e-02 |
Pos logit contributions | |
sizes | +0.081 |
hips | +0.078 |
neck | +0.073 |
planets | +0.073 |
toes | +0.072 |
Neg logit contributions | |
aback | -0.145 |
late | -0.141 |
sm | -0.137 |
Start | -0.130 |
handed | -0.121 |
Token | you |
Token ID | 345 |
Feature activation | -2.53e-02 |
Pos logit contributions | |
sizes | +0.039 |
planets | +0.035 |
necks | +0.034 |
clubs | +0.033 |
toes | +0.033 |
Neg logit contributions | |
late | -0.029 |
aback | -0.025 |
Start | -0.024 |
severe | -0.023 |
sm | -0.023 |
Token | ," |
Token ID | 553 |
Feature activation | -6.21e-02 |
Pos logit contributions | |
late | +0.044 |
aback | +0.040 |
Start | +0.040 |
O | +0.039 |
sm | +0.039 |
Neg logit contributions | |
sizes | -0.043 |
bows | -0.037 |
planets | -0.036 |
ABC | -0.036 |
toes | -0.036 |
Token | Tom |
Token ID | 4186 |
Feature activation | +1.52e-02 |
Pos logit contributions | |
late | +0.107 |
aback | +0.095 |
sm | +0.091 |
Start | +0.091 |
O | +0.088 |
Neg logit contributions | |
sizes | -0.109 |
planets | -0.096 |
ABC | -0.095 |
bows | -0.094 |
toes | -0.093 |
Token | says |
Token ID | 1139 |
Feature activation | +1.67e-02 |
Pos logit contributions | |
sizes | +0.027 |
planets | +0.023 |
bows | +0.023 |
ABC | +0.023 |
clubs | +0.023 |
Neg logit contributions | |
late | -0.026 |
aback | -0.023 |
Start | -0.022 |
sm | -0.022 |
O | -0.022 |
Token | to |
Token ID | 284 |
Feature activation | +7.96e-03 |
Pos logit contributions | |
sizes | +0.124 |
bows | +0.115 |
planets | +0.112 |
ABC | +0.111 |
cultures | +0.110 |
Neg logit contributions | |
late | -0.065 |
sm | -0.048 |
aback | -0.048 |
O | -0.047 |
Start | -0.046 |
Token | make |
Token ID | 787 |
Feature activation | +3.27e-02 |
Pos logit contributions | |
sizes | +0.012 |
planets | +0.010 |
bows | +0.010 |
ABC | +0.009 |
clubs | +0.009 |
Neg logit contributions | |
late | -0.016 |
aback | -0.014 |
Start | -0.014 |
O | -0.014 |
sm | -0.014 |
Token | up |
Token ID | 510 |
Feature activation | -3.36e-02 |
Pos logit contributions | |
sizes | +0.061 |
bows | +0.054 |
planets | +0.053 |
cultures | +0.053 |
ABC | +0.053 |
Neg logit contributions | |
late | -0.052 |
aback | -0.044 |
Start | -0.044 |
sm | -0.042 |
O | -0.042 |
Token | stories |
Token ID | 3923 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
late | +0.072 |
sm | +0.062 |
Start | +0.061 |
aback | +0.060 |
severe | +0.059 |
Neg logit contributions | |
sizes | -0.044 |
planets | -0.036 |
bows | -0.036 |
ABC | -0.036 |
necks | -0.035 |
Token | with |
Token ID | 351 |
Feature activation | +3.40e-03 |
Pos logit contributions | |
sizes | +0.212 |
cultures | +0.193 |
necks | +0.191 |
planets | +0.189 |
toes | +0.187 |
Neg logit contributions | |
late | -0.196 |
aback | -0.156 |
sm | -0.149 |
Start | -0.147 |
another | -0.143 |
Token | their |
Token ID | 511 |
Feature activation | +5.29e-02 |
Pos logit contributions | |
sizes | +0.007 |
bows | +0.007 |
ABC | +0.007 |
cultures | +0.007 |
planets | +0.007 |
Neg logit contributions | |
late | -0.004 |
sm | -0.003 |
O | -0.003 |
aback | -0.003 |
Start | -0.003 |
Token | dolls |
Token ID | 36062 |
Feature activation | +7.10e-02 |
Pos logit contributions | |
sizes | +0.080 |
bows | +0.076 |
cultures | +0.072 |
hips | +0.070 |
iece | +0.070 |
Neg logit contributions | |
late | -0.087 |
sm | -0.076 |
my | -0.075 |
poisonous | -0.075 |
medicine | -0.073 |
Token | and |
Token ID | 290 |
Feature activation | +4.61e-03 |
Pos logit contributions | |
sizes | +0.117 |
planets | +0.103 |
ABC | +0.102 |
cultures | +0.101 |
bows | +0.099 |
Neg logit contributions | |
late | -0.129 |
aback | -0.107 |
sm | -0.107 |
severe | -0.103 |
Start | -0.103 |
Token | cars |
Token ID | 5006 |
Feature activation | +6.32e-02 |
Pos logit contributions | |
bows | +0.007 |
sizes | +0.007 |
hips | +0.007 |
ABC | +0.007 |
igo | +0.006 |
Neg logit contributions | |
late | -0.007 |
my | -0.007 |
heaven | -0.006 |
another | -0.006 |
severe | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | +1.51e-02 |
Pos logit contributions | |
sizes | +0.105 |
planets | +0.092 |
ABC | +0.091 |
cultures | +0.090 |
bows | +0.088 |
Neg logit contributions | |
late | -0.115 |
aback | -0.097 |
sm | -0.096 |
Start | -0.094 |
O | -0.093 |
Token | Lily |
Token ID | 20037 |
Feature activation | -1.22e-02 |
Pos logit contributions | |
sizes | +0.030 |
planets | +0.027 |
bows | +0.026 |
ABC | +0.026 |
clubs | +0.026 |
Neg logit contributions | |
late | -0.023 |
aback | -0.020 |
Start | -0.019 |
sm | -0.019 |
O | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | +1.98e-02 |
Pos logit contributions | |
sizes | +0.100 |
planets | +0.091 |
ABC | +0.091 |
cultures | +0.090 |
bows | +0.089 |
Neg logit contributions | |
late | -0.087 |
sm | -0.068 |
aback | -0.068 |
another | -0.064 |
severe | -0.063 |
Token | They |
Token ID | 1119 |
Feature activation | +6.03e-02 |
Pos logit contributions | |
sizes | +0.032 |
planets | +0.028 |
bows | +0.027 |
ABC | +0.027 |
cultures | +0.027 |
Neg logit contributions | |
late | -0.038 |
aback | -0.032 |
Start | -0.031 |
O | -0.031 |
sm | -0.031 |
Token | wait |
Token ID | 4043 |
Feature activation | -3.08e-03 |
Pos logit contributions | |
sizes | +0.100 |
planets | +0.086 |
bows | +0.085 |
ABC | +0.084 |
cultures | +0.083 |
Neg logit contributions | |
late | -0.109 |
aback | -0.095 |
Start | -0.093 |
sm | -0.092 |
O | -0.092 |
Token | for |
Token ID | 329 |
Feature activation | -8.83e-02 |
Pos logit contributions | |
late | +0.005 |
sm | +0.004 |
aback | +0.004 |
Start | +0.003 |
O | +0.003 |
Neg logit contributions | |
sizes | -0.006 |
planets | -0.006 |
bows | -0.006 |
cultures | -0.006 |
clubs | -0.006 |
Token | the |
Token ID | 262 |
Feature activation | +2.21e-02 |
Pos logit contributions | |
late | +0.113 |
aback | +0.090 |
Start | +0.088 |
O | +0.088 |
sm | +0.087 |
Neg logit contributions | |
sizes | -0.197 |
bows | -0.177 |
planets | -0.177 |
ABC | -0.174 |
cultures | -0.172 |
Token | music |
Token ID | 2647 |
Feature activation | +7.75e-02 |
Pos logit contributions | |
sizes | +0.034 |
bows | +0.030 |
planets | +0.030 |
clubs | +0.029 |
cultures | +0.029 |
Neg logit contributions | |
late | -0.042 |
O | -0.036 |
aback | -0.035 |
sm | -0.035 |
Start | -0.035 |
Token | to |
Token ID | 284 |
Feature activation | -8.47e-03 |
Pos logit contributions | |
sizes | +0.132 |
planets | +0.116 |
ABC | +0.113 |
bows | +0.113 |
cultures | +0.111 |
Neg logit contributions | |
late | -0.138 |
aback | -0.118 |
sm | -0.116 |
Start | -0.115 |
O | -0.113 |
Token | start |
Token ID | 923 |
Feature activation | +1.27e-02 |
Pos logit contributions | |
late | +0.016 |
aback | +0.014 |
sm | +0.014 |
Start | +0.014 |
O | +0.013 |
Neg logit contributions | |
sizes | -0.014 |
planets | -0.012 |
ABC | -0.012 |
bows | -0.012 |
clubs | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | +1.42e-02 |
Pos logit contributions | |
sizes | +0.024 |
planets | +0.021 |
bows | +0.021 |
cultures | +0.020 |
hips | +0.020 |
Neg logit contributions | |
late | -0.021 |
sm | -0.017 |
aback | -0.016 |
another | -0.015 |
Start | -0.015 |
Token | They |
Token ID | 1119 |
Feature activation | +5.75e-02 |
Pos logit contributions | |
sizes | +0.023 |
planets | +0.020 |
bows | +0.020 |
ABC | +0.019 |
cultures | +0.019 |
Neg logit contributions | |
late | -0.027 |
aback | -0.023 |
Start | -0.023 |
O | -0.023 |
sm | -0.022 |
Token | are |
Token ID | 389 |
Feature activation | +3.49e-02 |
Pos logit contributions | |
sizes | +0.094 |
planets | +0.082 |
bows | +0.081 |
ABC | +0.080 |
clubs | +0.078 |
Neg logit contributions | |
late | -0.107 |
aback | -0.093 |
Start | -0.091 |
sm | -0.090 |
O | -0.090 |
Token | touch |
Token ID | 3638 |
Feature activation | -1.01e-02 |
Pos logit contributions | |
late | +0.047 |
severe | +0.041 |
sm | +0.037 |
poisoned | +0.037 |
infected | +0.036 |
Neg logit contributions | |
sizes | -0.029 |
patterns | -0.027 |
clubs | -0.027 |
toes | -0.026 |
planets | -0.026 |
Token | them |
Token ID | 606 |
Feature activation | +2.51e-03 |
Pos logit contributions | |
late | +0.013 |
aback | +0.011 |
Start | +0.010 |
O | +0.010 |
sm | +0.010 |
Neg logit contributions | |
sizes | -0.022 |
planets | -0.020 |
bows | -0.020 |
ABC | -0.020 |
clubs | -0.020 |
Token | , |
Token ID | 11 |
Feature activation | +5.74e-02 |
Pos logit contributions | |
sizes | +0.005 |
cultures | +0.004 |
planets | +0.004 |
ABC | +0.004 |
habitats | +0.004 |
Neg logit contributions | |
late | -0.004 |
aback | -0.003 |
another | -0.003 |
Start | -0.003 |
sm | -0.003 |
Token | feeling |
Token ID | 4203 |
Feature activation | -6.41e-02 |
Pos logit contributions | |
sizes | +0.083 |
planets | +0.071 |
bows | +0.070 |
ABC | +0.069 |
cultures | +0.067 |
Neg logit contributions | |
late | -0.118 |
aback | -0.104 |
Start | -0.102 |
sm | -0.101 |
O | -0.100 |
Token | the |
Token ID | 262 |
Feature activation | +1.29e-02 |
Pos logit contributions | |
late | +0.099 |
O | +0.086 |
plug | +0.084 |
Start | +0.084 |
aback | +0.083 |
Neg logit contributions | |
sizes | -0.122 |
planets | -0.104 |
toes | -0.102 |
patterns | -0.102 |
neck | -0.099 |
Token | soft |
Token ID | 2705 |
Feature activation | +2.96e-02 |
Pos logit contributions | |
sizes | +0.025 |
ABC | +0.024 |
cultures | +0.024 |
planets | +0.024 |
azes | +0.023 |
Neg logit contributions | |
late | -0.018 |
aback | -0.015 |
poisonous | -0.015 |
poisoned | -0.014 |
O | -0.014 |
Token | pet |
Token ID | 4273 |
Feature activation | +1.75e-02 |
Pos logit contributions | |
hips | +0.040 |
ABC | +0.039 |
sizes | +0.039 |
azes | +0.039 |
nations | +0.039 |
Neg logit contributions | |
late | -0.052 |
aback | -0.048 |
poisonous | -0.047 |
sm | -0.046 |
O | -0.045 |
Token | als |
Token ID | 874 |
Feature activation | -4.66e-03 |
Pos logit contributions | |
sizes | +0.031 |
planets | +0.028 |
ABC | +0.027 |
cultures | +0.027 |
bows | +0.027 |
Neg logit contributions | |
late | -0.029 |
aback | -0.025 |
sm | -0.025 |
O | -0.025 |
Start | -0.024 |
Token | . |
Token ID | 13 |
Feature activation | +1.54e-02 |
Pos logit contributions | |
late | +0.008 |
aback | +0.007 |
sm | +0.007 |
Start | +0.007 |
O | +0.007 |
Neg logit contributions | |
sizes | -0.008 |
ABC | -0.007 |
planets | -0.007 |
cultures | -0.007 |
bows | -0.007 |
Token | It |
Token ID | 632 |
Feature activation | -1.39e-02 |
Pos logit contributions | |
sizes | +0.025 |
planets | +0.021 |
ABC | +0.021 |
bows | +0.021 |
clubs | +0.021 |
Neg logit contributions | |
late | -0.028 |
sm | -0.025 |
severe | -0.025 |
aback | -0.025 |
O | -0.024 |
Token | was |
Token ID | 373 |
Feature activation | +2.64e-02 |
Pos logit contributions | |
late | +0.032 |
aback | +0.027 |
severe | +0.026 |
sm | +0.026 |
Aid | +0.026 |
Neg logit contributions | |
sizes | -0.019 |
planets | -0.015 |
patterns | -0.015 |
toes | -0.014 |
bows | -0.014 |
Token | toy |
Token ID | 13373 |
Feature activation | -6.45e-03 |
Pos logit contributions | |
late | +0.015 |
aback | +0.012 |
sm | +0.012 |
Start | +0.011 |
O | +0.011 |
Neg logit contributions | |
sizes | -0.017 |
planets | -0.015 |
bows | -0.015 |
cultures | -0.015 |
hips | -0.015 |
Token | grill |
Token ID | 29901 |
Feature activation | +1.33e-02 |
Pos logit contributions | |
late | +0.010 |
sm | +0.008 |
poisoned | +0.008 |
O | +0.008 |
poisonous | +0.008 |
Neg logit contributions | |
sizes | -0.012 |
bows | -0.011 |
cultures | -0.011 |
ABC | -0.010 |
languages | -0.010 |
Token | that |
Token ID | 326 |
Feature activation | -3.29e-02 |
Pos logit contributions | |
sizes | +0.029 |
cultures | +0.027 |
bows | +0.027 |
planets | +0.027 |
ABC | +0.026 |
Neg logit contributions | |
late | -0.017 |
sm | -0.013 |
aback | -0.012 |
poisoned | -0.012 |
O | -0.012 |
Token | he |
Token ID | 339 |
Feature activation | -1.13e-02 |
Pos logit contributions | |
late | +0.064 |
aback | +0.060 |
Start | +0.059 |
severe | +0.056 |
sm | +0.056 |
Neg logit contributions | |
sizes | -0.052 |
planets | -0.045 |
ABC | -0.043 |
bows | -0.042 |
toes | -0.041 |
Token | played |
Token ID | 2826 |
Feature activation | +7.90e-02 |
Pos logit contributions | |
late | +0.025 |
aback | +0.024 |
Start | +0.023 |
severe | +0.022 |
O | +0.022 |
Neg logit contributions | |
sizes | -0.015 |
planets | -0.012 |
ABC | -0.011 |
necks | -0.011 |
neck | -0.011 |
Token | with |
Token ID | 351 |
Feature activation | +7.85e-03 |
Pos logit contributions | |
sizes | +0.140 |
planets | +0.124 |
bows | +0.122 |
ABC | +0.120 |
clubs | +0.118 |
Neg logit contributions | |
late | -0.134 |
aback | -0.118 |
Start | -0.114 |
O | -0.113 |
sm | -0.113 |
Token | every |
Token ID | 790 |
Feature activation | +2.90e-02 |
Pos logit contributions | |
sizes | +0.013 |
planets | +0.011 |
bows | +0.011 |
ABC | +0.011 |
clubs | +0.011 |
Neg logit contributions | |
late | -0.014 |
aback | -0.012 |
Start | -0.012 |
sm | -0.012 |
O | -0.012 |
Token | day |
Token ID | 1110 |
Feature activation | +2.50e-02 |
Pos logit contributions | |
sizes | +0.028 |
toes | +0.023 |
ABC | +0.022 |
planets | +0.022 |
pretending | +0.020 |
Neg logit contributions | |
aback | -0.069 |
late | -0.068 |
Start | -0.067 |
izz | -0.065 |
O | -0.065 |
Token | . |
Token ID | 13 |
Feature activation | +1.59e-02 |
Pos logit contributions | |
sizes | +0.047 |
cultures | +0.043 |
bows | +0.043 |
ABC | +0.042 |
hobbies | +0.041 |
Neg logit contributions | |
late | -0.043 |
sm | -0.032 |
aback | -0.031 |
Start | -0.030 |
another | -0.030 |
Token |
|
Token ID | 198 |
Feature activation | -1.45e-02 |
Pos logit contributions | |
sizes | +0.034 |
planets | +0.031 |
bows | +0.031 |
cultures | +0.031 |
clubs | +0.030 |
Neg logit contributions | |
late | -0.021 |
aback | -0.017 |
O | -0.017 |
Start | -0.017 |
sm | -0.016 |
Token |
|
Token ID | 198 |
Feature activation | -1.96e-02 |
Pos logit contributions | |
late | +0.023 |
aback | +0.021 |
Start | +0.020 |
sm | +0.019 |
severe | +0.019 |
Neg logit contributions | |
sizes | -0.026 |
ABC | -0.023 |
planets | -0.023 |
bows | -0.023 |
clubs | -0.022 |
Token | Mom |
Token ID | 11254 |
Feature activation | -2.71e-02 |
Pos logit contributions | |
late | +0.131 |
aback | +0.122 |
Start | +0.120 |
sm | +0.120 |
O | +0.114 |
Neg logit contributions | |
sizes | -0.184 |
planets | -0.168 |
patterns | -0.166 |
toes | -0.166 |
ABC | -0.166 |
Token | . |
Token ID | 13 |
Feature activation | +2.47e-03 |
Pos logit contributions | |
late | +0.049 |
aback | +0.043 |
Start | +0.042 |
sm | +0.041 |
O | +0.041 |
Neg logit contributions | |
sizes | -0.046 |
planets | -0.040 |
bows | -0.039 |
ABC | -0.039 |
clubs | -0.038 |
Token | He |
Token ID | 679 |
Feature activation | +1.32e-02 |
Pos logit contributions | |
sizes | +0.004 |
planets | +0.003 |
ABC | +0.003 |
toes | +0.003 |
bows | +0.003 |
Neg logit contributions | |
late | -0.004 |
sm | -0.004 |
aback | -0.004 |
izz | -0.004 |
Start | -0.004 |
Token | learned |
Token ID | 4499 |
Feature activation | +5.49e-02 |
Pos logit contributions | |
sizes | +0.019 |
planets | +0.017 |
neck | +0.017 |
necks | +0.016 |
ABC | +0.016 |
Neg logit contributions | |
late | -0.026 |
aback | -0.024 |
sm | -0.022 |
Start | -0.022 |
izz | -0.022 |
Token | his |
Token ID | 465 |
Feature activation | +1.35e-02 |
Pos logit contributions | |
sizes | +0.088 |
ABC | +0.085 |
planets | +0.081 |
clubs | +0.080 |
hobbies | +0.080 |
Neg logit contributions | |
izz | -0.078 |
aback | -0.076 |
late | -0.076 |
ited | -0.075 |
sm | -0.073 |
Token | lesson |
Token ID | 11483 |
Feature activation | -5.44e-03 |
Pos logit contributions | |
sizes | +0.028 |
bows | +0.025 |
planets | +0.025 |
clubs | +0.024 |
necks | +0.024 |
Neg logit contributions | |
late | -0.021 |
severe | -0.016 |
O | -0.016 |
Start | -0.016 |
sm | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | +4.32e-03 |
Pos logit contributions | |
late | +0.010 |
aback | +0.008 |
sm | +0.008 |
Start | +0.008 |
severe | +0.008 |
Neg logit contributions | |
sizes | -0.010 |
planets | -0.009 |
bows | -0.009 |
toes | -0.009 |
ABC | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | -2.82e-02 |
Pos logit contributions | |
sizes | +0.007 |
planets | +0.006 |
ABC | +0.006 |
bows | +0.006 |
toes | +0.006 |
Neg logit contributions | |
late | -0.007 |
sm | -0.007 |
aback | -0.007 |
izz | -0.007 |
O | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | -3.18e-02 |
Pos logit contributions | |
late | +0.045 |
aback | +0.042 |
Start | +0.040 |
sm | +0.039 |
poisoned | +0.039 |
Neg logit contributions | |
sizes | -0.047 |
planets | -0.042 |
ABC | -0.042 |
clubs | -0.040 |
hips | -0.040 |
Token | The |
Token ID | 464 |
Feature activation | +1.94e-02 |
Pos logit contributions | |
late | +0.049 |
aback | +0.048 |
sm | +0.043 |
poisoned | +0.042 |
Start | +0.042 |
Neg logit contributions | |
sizes | -0.055 |
planets | -0.049 |
ABC | -0.048 |
clubs | -0.047 |
hips | -0.047 |
Token | moral |
Token ID | 6573 |
Feature activation | -3.28e-02 |
Pos logit contributions | |
sizes | +0.033 |
bows | +0.029 |
planets | +0.028 |
cultures | +0.027 |
clubs | +0.027 |
Neg logit contributions | |
late | -0.036 |
O | -0.030 |
sm | -0.030 |
aback | -0.030 |
Start | -0.030 |
Token | them |
Token ID | 606 |
Feature activation | +3.65e-03 |
Pos logit contributions | |
sizes | +0.148 |
planets | +0.132 |
ABC | +0.130 |
bows | +0.129 |
clubs | +0.128 |
Neg logit contributions | |
late | -0.115 |
aback | -0.097 |
Start | -0.095 |
O | -0.094 |
sm | -0.093 |
Token | . |
Token ID | 13 |
Feature activation | +1.27e-02 |
Pos logit contributions | |
sizes | +0.006 |
planets | +0.005 |
bows | +0.005 |
ABC | +0.005 |
clubs | +0.005 |
Neg logit contributions | |
late | -0.007 |
aback | -0.006 |
O | -0.006 |
Start | -0.006 |
sm | -0.006 |
Token | They |
Token ID | 1119 |
Feature activation | +5.79e-02 |
Pos logit contributions | |
sizes | +0.021 |
planets | +0.018 |
bows | +0.017 |
ABC | +0.017 |
clubs | +0.017 |
Neg logit contributions | |
late | -0.023 |
aback | -0.021 |
Start | -0.020 |
sm | -0.020 |
severe | -0.020 |
Token | learned |
Token ID | 4499 |
Feature activation | +6.17e-02 |
Pos logit contributions | |
sizes | +0.090 |
planets | +0.081 |
clubs | +0.077 |
bows | +0.074 |
nations | +0.074 |
Neg logit contributions | |
late | -0.112 |
aback | -0.099 |
Start | -0.097 |
O | -0.093 |
sm | -0.092 |
Token | that |
Token ID | 326 |
Feature activation | -2.77e-02 |
Pos logit contributions | |
sizes | +0.119 |
planets | +0.109 |
clubs | +0.106 |
ABC | +0.105 |
cultures | +0.105 |
Neg logit contributions | |
late | -0.085 |
izz | -0.077 |
O | -0.076 |
aback | -0.076 |
sm | -0.074 |
Token | it |
Token ID | 340 |
Feature activation | -6.83e-02 |
Pos logit contributions | |
late | +0.043 |
aback | +0.033 |
sm | +0.032 |
Start | +0.032 |
O | +0.032 |
Neg logit contributions | |
sizes | -0.056 |
bows | -0.051 |
planets | -0.049 |
clubs | -0.048 |
ABC | -0.048 |
Token | 's |
Token ID | 338 |
Feature activation | +5.15e-02 |
Pos logit contributions | |
late | +0.129 |
aback | +0.111 |
O | +0.111 |
Start | +0.110 |
sm | +0.109 |
Neg logit contributions | |
sizes | -0.110 |
planets | -0.096 |
bows | -0.092 |
ABC | -0.092 |
cultures | -0.089 |
Token | okay |
Token ID | 8788 |
Feature activation | +4.01e-02 |
Pos logit contributions | |
sizes | +0.084 |
planets | +0.072 |
ABC | +0.068 |
cultures | +0.068 |
bows | +0.066 |
Neg logit contributions | |
late | -0.086 |
aback | -0.083 |
Start | -0.082 |
sm | -0.081 |
izz | -0.081 |
Token | to |
Token ID | 284 |
Feature activation | -3.54e-03 |
Pos logit contributions | |
sizes | +0.081 |
planets | +0.072 |
bows | +0.071 |
ABC | +0.071 |
cultures | +0.069 |
Neg logit contributions | |
late | -0.059 |
aback | -0.050 |
Start | -0.049 |
O | -0.049 |
sm | -0.048 |
Token | ask |
Token ID | 1265 |
Feature activation | +1.41e-02 |
Pos logit contributions | |
late | +0.006 |
aback | +0.005 |
Start | +0.005 |
O | +0.005 |
sm | +0.005 |
Neg logit contributions | |
sizes | -0.006 |
planets | -0.005 |
bows | -0.005 |
ABC | -0.005 |
clubs | -0.005 |
Token | for |
Token ID | 329 |
Feature activation | -7.78e-02 |
Pos logit contributions | |
sizes | +0.024 |
planets | +0.021 |
ABC | +0.021 |
cultures | +0.021 |
toes | +0.020 |
Neg logit contributions | |
late | -0.024 |
O | -0.022 |
aback | -0.021 |
Start | -0.021 |
izz | -0.021 |
Token | . |
Token ID | 13 |
Feature activation | +2.84e-02 |
Pos logit contributions | |
late | +0.072 |
Start | +0.063 |
aback | +0.063 |
O | +0.063 |
sm | +0.061 |
Neg logit contributions | |
sizes | -0.062 |
bows | -0.052 |
planets | -0.052 |
toes | -0.051 |
clubs | -0.051 |
Token | He |
Token ID | 679 |
Feature activation | +2.41e-02 |
Pos logit contributions | |
sizes | +0.049 |
planets | +0.043 |
ABC | +0.042 |
bows | +0.042 |
clubs | +0.041 |
Neg logit contributions | |
late | -0.049 |
aback | -0.043 |
sm | -0.042 |
severe | -0.042 |
Start | -0.041 |
Token | stirred |
Token ID | 33091 |
Feature activation | -1.19e-02 |
Pos logit contributions | |
sizes | +0.037 |
planets | +0.032 |
neck | +0.031 |
toes | +0.030 |
necks | +0.030 |
Neg logit contributions | |
late | -0.047 |
aback | -0.042 |
Start | -0.041 |
O | -0.040 |
sm | -0.039 |
Token | and |
Token ID | 290 |
Feature activation | -5.31e-03 |
Pos logit contributions | |
late | +0.018 |
aback | +0.015 |
Start | +0.015 |
sm | +0.015 |
O | +0.015 |
Neg logit contributions | |
sizes | -0.024 |
planets | -0.021 |
bows | -0.020 |
ABC | -0.020 |
toes | -0.020 |
Token | stirred |
Token ID | 33091 |
Feature activation | -1.26e-02 |
Pos logit contributions | |
late | +0.008 |
aback | +0.008 |
Start | +0.007 |
O | +0.007 |
severe | +0.007 |
Neg logit contributions | |
sizes | -0.010 |
planets | -0.009 |
patterns | -0.008 |
bows | -0.008 |
toes | -0.008 |
Token | until |
Token ID | 1566 |
Feature activation | +7.84e-03 |
Pos logit contributions | |
late | +0.023 |
aback | +0.020 |
O | +0.020 |
Start | +0.019 |
sm | +0.019 |
Neg logit contributions | |
sizes | -0.021 |
planets | -0.018 |
bows | -0.018 |
ABC | -0.018 |
cultures | -0.018 |
Token | everything |
Token ID | 2279 |
Feature activation | -3.26e-02 |
Pos logit contributions | |
sizes | +0.012 |
toes | +0.011 |
planets | +0.011 |
patterns | +0.010 |
cheeks | +0.010 |
Neg logit contributions | |
aback | -0.013 |
late | -0.013 |
sm | -0.013 |
Start | -0.013 |
severe | -0.012 |
Token | was |
Token ID | 373 |
Feature activation | +1.50e-02 |
Pos logit contributions | |
late | +0.070 |
aback | +0.063 |
Start | +0.063 |
O | +0.063 |
severe | +0.062 |
Neg logit contributions | |
sizes | -0.045 |
planets | -0.037 |
bows | -0.036 |
patterns | -0.035 |
toes | -0.033 |
Token | mixed |
Token ID | 7668 |
Feature activation | -4.12e-02 |
Pos logit contributions | |
sizes | +0.028 |
planets | +0.024 |
bows | +0.023 |
toes | +0.023 |
ABC | +0.023 |
Neg logit contributions | |
late | -0.024 |
aback | -0.022 |
Start | -0.021 |
sm | -0.021 |
O | -0.021 |
Token | together |
Token ID | 1978 |
Feature activation | +3.83e-02 |
Pos logit contributions | |
late | +0.072 |
aback | +0.062 |
Start | +0.061 |
O | +0.060 |
sm | +0.060 |
Neg logit contributions | |
sizes | -0.072 |
planets | -0.063 |
bows | -0.062 |
ABC | -0.061 |
clubs | -0.060 |
Token | . |
Token ID | 13 |
Feature activation | +2.57e-02 |
Pos logit contributions | |
sizes | +0.063 |
planets | +0.057 |
bows | +0.057 |
ABC | +0.057 |
cultures | +0.056 |
Neg logit contributions | |
late | -0.069 |
aback | -0.058 |
sm | -0.058 |
Start | -0.056 |
O | -0.054 |
Token | try |
Token ID | 1949 |
Feature activation | +3.85e-02 |
Pos logit contributions | |
late | +0.008 |
aback | +0.007 |
sm | +0.007 |
Start | +0.007 |
severe | +0.007 |
Neg logit contributions | |
sizes | -0.007 |
bows | -0.006 |
planets | -0.006 |
ABC | -0.006 |
clubs | -0.006 |
Token | too |
Token ID | 1165 |
Feature activation | -2.51e-03 |
Pos logit contributions | |
sizes | +0.085 |
planets | +0.077 |
ABC | +0.075 |
bows | +0.075 |
clubs | +0.074 |
Neg logit contributions | |
late | -0.050 |
aback | -0.041 |
Start | -0.039 |
sm | -0.039 |
O | -0.039 |
Token | . |
Token ID | 13 |
Feature activation | +1.01e-02 |
Pos logit contributions | |
late | +0.005 |
aback | +0.005 |
Start | +0.004 |
O | +0.004 |
sm | +0.004 |
Neg logit contributions | |
sizes | -0.004 |
planets | -0.003 |
bows | -0.003 |
ABC | -0.003 |
clubs | -0.003 |
Token | He |
Token ID | 679 |
Feature activation | +2.77e-02 |
Pos logit contributions | |
sizes | +0.016 |
toes | +0.013 |
ABC | +0.013 |
bows | +0.013 |
patterns | +0.013 |
Neg logit contributions | |
late | -0.019 |
sm | -0.017 |
severe | -0.017 |
aback | -0.017 |
poisonous | -0.017 |
Token | looked |
Token ID | 3114 |
Feature activation | -4.29e-03 |
Pos logit contributions | |
sizes | +0.046 |
planets | +0.040 |
neck | +0.039 |
necks | +0.039 |
toes | +0.039 |
Neg logit contributions | |
late | -0.052 |
aback | -0.044 |
severe | -0.043 |
sm | -0.042 |
Start | -0.042 |
Token | for |
Token ID | 329 |
Feature activation | -8.94e-02 |
Pos logit contributions | |
late | +0.008 |
O | +0.007 |
severe | +0.007 |
izz | +0.007 |
Start | +0.007 |
Neg logit contributions | |
sizes | -0.007 |
toes | -0.006 |
planets | -0.006 |
patterns | -0.006 |
clubs | -0.006 |
Token | another |
Token ID | 1194 |
Feature activation | -2.29e-02 |
Pos logit contributions | |
late | +0.136 |
severe | +0.108 |
aback | +0.105 |
Start | +0.105 |
plug | +0.104 |
Neg logit contributions | |
sizes | -0.179 |
patterns | -0.166 |
toes | -0.165 |
planets | -0.165 |
neck | -0.161 |
Token | vine |
Token ID | 17793 |
Feature activation | +4.12e-03 |
Pos logit contributions | |
late | +0.037 |
aback | +0.032 |
Start | +0.031 |
sm | +0.031 |
O | +0.030 |
Neg logit contributions | |
sizes | -0.042 |
planets | -0.038 |
ABC | -0.037 |
bows | -0.037 |
cultures | -0.037 |
Token | . |
Token ID | 13 |
Feature activation | +3.28e-03 |
Pos logit contributions | |
sizes | +0.007 |
ABC | +0.007 |
cultures | +0.007 |
planets | +0.007 |
bows | +0.007 |
Neg logit contributions | |
late | -0.007 |
aback | -0.006 |
sm | -0.006 |
Start | -0.005 |
poisoned | -0.005 |
Token | He |
Token ID | 679 |
Feature activation | +1.97e-02 |
Pos logit contributions | |
sizes | +0.005 |
toes | +0.004 |
ABC | +0.004 |
bows | +0.004 |
planets | +0.004 |
Neg logit contributions | |
late | -0.006 |
sm | -0.005 |
severe | -0.005 |
aback | -0.005 |
poisonous | -0.005 |
Token | saw |
Token ID | 2497 |
Feature activation | -4.59e-02 |
Pos logit contributions | |
sizes | +0.039 |
planets | +0.034 |
bows | +0.034 |
ABC | +0.034 |
clubs | +0.033 |
Neg logit contributions | |
late | -0.030 |
aback | -0.026 |
Start | -0.025 |
O | -0.025 |
sm | -0.025 |
Token | they |
Token ID | 484 |
Feature activation | +1.71e-02 |
Pos logit contributions | |
late | +0.052 |
aback | +0.047 |
Start | +0.046 |
O | +0.045 |
sm | +0.044 |
Neg logit contributions | |
sizes | -0.065 |
planets | -0.059 |
ABC | -0.056 |
bows | -0.055 |
cultures | -0.055 |
Token | would |
Token ID | 561 |
Feature activation | +7.50e-02 |
Pos logit contributions | |
sizes | +0.019 |
planets | +0.016 |
bows | +0.015 |
ABC | +0.015 |
cultures | +0.015 |
Neg logit contributions | |
late | -0.041 |
aback | -0.037 |
Start | -0.036 |
O | -0.036 |
sm | -0.036 |
Token | see |
Token ID | 766 |
Feature activation | -3.06e-02 |
Pos logit contributions | |
sizes | +0.145 |
bows | +0.125 |
planets | +0.125 |
ABC | +0.124 |
clubs | +0.124 |
Neg logit contributions | |
late | -0.120 |
aback | -0.098 |
Start | -0.096 |
O | -0.093 |
sm | -0.092 |
Token | Comet |
Token ID | 36238 |
Feature activation | +6.83e-02 |
Pos logit contributions | |
late | +0.042 |
aback | +0.037 |
Start | +0.037 |
O | +0.037 |
izz | +0.034 |
Neg logit contributions | |
sizes | -0.065 |
planets | -0.061 |
ABC | -0.056 |
cultures | -0.056 |
patterns | -0.056 |
Token | Hale |
Token ID | 35056 |
Feature activation | +4.32e-02 |
Pos logit contributions | |
sizes | +0.114 |
clubs | +0.098 |
planets | +0.096 |
cultures | +0.095 |
ABC | +0.095 |
Neg logit contributions | |
late | -0.122 |
aback | -0.102 |
sm | -0.102 |
Start | -0.100 |
severe | -0.096 |
Token | - |
Token ID | 12 |
Feature activation | -7.68e-02 |
Pos logit contributions | |
sizes | +0.105 |
ABC | +0.096 |
bows | +0.094 |
clubs | +0.094 |
planets | +0.093 |
Neg logit contributions | |
late | -0.041 |
aback | -0.033 |
sm | -0.032 |
Start | -0.028 |
severe | -0.027 |
Token | B |
Token ID | 33 |
Feature activation | +7.00e-02 |
Pos logit contributions | |
late | +0.131 |
aback | +0.113 |
Start | +0.109 |
O | +0.109 |
sm | +0.107 |
Neg logit contributions | |
sizes | -0.138 |
planets | -0.122 |
bows | -0.121 |
ABC | -0.119 |
cultures | -0.117 |
Token | opp |
Token ID | 10365 |
Feature activation | +1.08e-02 |
Pos logit contributions | |
sizes | +0.117 |
planets | +0.106 |
ABC | +0.097 |
clubs | +0.097 |
cultures | +0.096 |
Neg logit contributions | |
late | -0.123 |
aback | -0.111 |
sm | -0.111 |
Start | -0.106 |
O | -0.105 |
Token | again |
Token ID | 757 |
Feature activation | -5.75e-02 |
Pos logit contributions | |
sizes | +0.013 |
planets | +0.011 |
clubs | +0.011 |
ABC | +0.010 |
cultures | +0.010 |
Neg logit contributions | |
late | -0.024 |
sm | -0.021 |
aback | -0.021 |
Start | -0.020 |
severe | -0.020 |
Token | someday |
Token ID | 25580 |
Feature activation | +3.29e-02 |
Pos logit contributions | |
late | +0.113 |
aback | +0.100 |
Start | +0.098 |
O | +0.098 |
sm | +0.097 |
Neg logit contributions | |
sizes | -0.087 |
planets | -0.075 |
bows | -0.073 |
ABC | -0.072 |
cultures | -0.071 |
Token | , |
Token ID | 11 |
Feature activation | +3.61e-02 |
Pos logit contributions | |
sizes | +0.057 |
bows | +0.049 |
planets | +0.049 |
ABC | +0.049 |
clubs | +0.048 |
Neg logit contributions | |
late | -0.059 |
aback | -0.048 |
sm | -0.047 |
Start | -0.046 |
severe | -0.045 |
Token | She |
Token ID | 1375 |
Feature activation | -1.02e-02 |
Pos logit contributions | |
sizes | +0.008 |
planets | +0.007 |
bows | +0.007 |
ABC | +0.007 |
clubs | +0.007 |
Neg logit contributions | |
late | -0.006 |
aback | -0.005 |
Start | -0.005 |
O | -0.005 |
sm | -0.005 |
Token | felt |
Token ID | 2936 |
Feature activation | -2.81e-02 |
Pos logit contributions | |
late | +0.017 |
aback | +0.015 |
Start | +0.014 |
O | +0.014 |
sm | +0.014 |
Neg logit contributions | |
sizes | -0.019 |
bows | -0.016 |
planets | -0.016 |
ABC | -0.016 |
cultures | -0.016 |
Token | better |
Token ID | 1365 |
Feature activation | -6.83e-03 |
Pos logit contributions | |
late | +0.047 |
izz | +0.046 |
plug | +0.045 |
O | +0.045 |
Start | +0.043 |
Neg logit contributions | |
sizes | -0.043 |
planets | -0.037 |
patterns | -0.036 |
clubs | -0.035 |
cultures | -0.035 |
Token | and |
Token ID | 290 |
Feature activation | -2.71e-02 |
Pos logit contributions | |
late | +0.013 |
aback | +0.011 |
Start | +0.011 |
sm | +0.011 |
O | +0.011 |
Neg logit contributions | |
sizes | -0.011 |
planets | -0.009 |
bows | -0.009 |
ABC | -0.009 |
clubs | -0.009 |
Token | went |
Token ID | 1816 |
Feature activation | -5.85e-02 |
Pos logit contributions | |
late | +0.044 |
aback | +0.038 |
Start | +0.037 |
O | +0.036 |
sm | +0.036 |
Neg logit contributions | |
sizes | -0.051 |
planets | -0.045 |
bows | -0.044 |
ABC | -0.044 |
clubs | -0.043 |
Token | back |
Token ID | 736 |
Feature activation | -8.72e-02 |
Pos logit contributions | |
late | +0.073 |
aback | +0.059 |
Start | +0.056 |
O | +0.056 |
sm | +0.056 |
Neg logit contributions | |
sizes | -0.133 |
planets | -0.120 |
bows | -0.119 |
ABC | -0.117 |
clubs | -0.116 |
Token | outside |
Token ID | 2354 |
Feature activation | -1.50e-02 |
Pos logit contributions | |
O | +0.150 |
late | +0.142 |
Start | +0.140 |
izz | +0.132 |
severe | +0.132 |
Neg logit contributions | |
sizes | -0.128 |
planets | -0.126 |
pretending | -0.125 |
clubs | -0.122 |
bows | -0.120 |
Token | to |
Token ID | 284 |
Feature activation | -1.68e-02 |
Pos logit contributions | |
late | +0.023 |
aback | +0.020 |
Start | +0.020 |
O | +0.019 |
sm | +0.019 |
Neg logit contributions | |
sizes | -0.029 |
planets | -0.025 |
bows | -0.025 |
ABC | -0.025 |
clubs | -0.024 |
Token | play |
Token ID | 711 |
Feature activation | +5.07e-02 |
Pos logit contributions | |
late | +0.034 |
aback | +0.031 |
O | +0.030 |
Start | +0.030 |
sm | +0.030 |
Neg logit contributions | |
sizes | -0.024 |
planets | -0.021 |
ABC | -0.020 |
bows | -0.020 |
clubs | -0.020 |
Token | with |
Token ID | 351 |
Feature activation | -5.23e-03 |
Pos logit contributions | |
sizes | +0.069 |
planets | +0.062 |
clubs | +0.061 |
bows | +0.060 |
patterns | +0.059 |
Neg logit contributions | |
late | -0.101 |
aback | -0.092 |
severe | -0.090 |
Start | -0.089 |
izz | -0.088 |
Token | her |
Token ID | 607 |
Feature activation | +1.08e-02 |
Pos logit contributions | |
late | +0.008 |
aback | +0.007 |
Start | +0.007 |
plug | +0.006 |
O | +0.006 |
Neg logit contributions | |
sizes | -0.010 |
planets | -0.010 |
patterns | -0.009 |
clubs | -0.009 |
toes | -0.009 |
Token | Lily |
Token ID | 20037 |
Feature activation | +1.90e-03 |
Pos logit contributions | |
late | +0.104 |
severe | +0.101 |
sm | +0.096 |
eh | +0.093 |
vous | +0.092 |
Neg logit contributions | |
shirts | -0.078 |
sizes | -0.078 |
toes | -0.077 |
planets | -0.076 |
patterns | -0.074 |
Token | and |
Token ID | 290 |
Feature activation | -2.47e-02 |
Pos logit contributions | |
sizes | +0.003 |
planets | +0.003 |
bows | +0.003 |
ABC | +0.003 |
cultures | +0.003 |
Neg logit contributions | |
late | -0.003 |
aback | -0.003 |
sm | -0.003 |
Start | -0.003 |
O | -0.003 |
Token | Anna |
Token ID | 11735 |
Feature activation | +1.05e-02 |
Pos logit contributions | |
late | +0.046 |
aback | +0.041 |
sm | +0.040 |
handed | +0.040 |
O | +0.040 |
Neg logit contributions | |
sizes | -0.036 |
cheeks | -0.034 |
pretending | -0.034 |
shirts | -0.033 |
toes | -0.033 |
Token | . |
Token ID | 13 |
Feature activation | +5.99e-03 |
Pos logit contributions | |
sizes | +0.020 |
planets | +0.018 |
bows | +0.018 |
ABC | +0.018 |
cultures | +0.017 |
Neg logit contributions | |
late | -0.017 |
aback | -0.014 |
Start | -0.014 |
sm | -0.014 |
O | -0.014 |
Token | She |
Token ID | 1375 |
Feature activation | -8.32e-03 |
Pos logit contributions | |
sizes | +0.010 |
ABC | +0.009 |
planets | +0.009 |
bows | +0.008 |
toes | +0.008 |
Neg logit contributions | |
late | -0.010 |
aback | -0.009 |
sm | -0.009 |
severe | -0.009 |
poisoned | -0.009 |
Token | took |
Token ID | 1718 |
Feature activation | -7.20e-02 |
Pos logit contributions | |
late | +0.016 |
aback | +0.014 |
Start | +0.013 |
O | +0.013 |
Aid | +0.013 |
Neg logit contributions | |
sizes | -0.012 |
neck | -0.010 |
necks | -0.010 |
clubs | -0.010 |
ABC | -0.010 |
Token | them |
Token ID | 606 |
Feature activation | +3.81e-03 |
Pos logit contributions | |
late | +0.131 |
severe | +0.125 |
poisonous | +0.121 |
sm | +0.120 |
eh | +0.119 |
Neg logit contributions | |
toes | -0.094 |
shirts | -0.092 |
patterns | -0.091 |
sizes | -0.091 |
planets | -0.090 |
Token | to |
Token ID | 284 |
Feature activation | -1.48e-02 |
Pos logit contributions | |
sizes | +0.008 |
clubs | +0.007 |
bows | +0.007 |
planets | +0.007 |
toes | +0.007 |
Neg logit contributions | |
late | -0.005 |
O | -0.005 |
Start | -0.005 |
aback | -0.004 |
sm | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | +3.59e-02 |
Pos logit contributions | |
vious | +0.024 |
aback | +0.023 |
Aid | +0.023 |
late | +0.023 |
sm | +0.023 |
Neg logit contributions | |
ABC | -0.021 |
pretending | -0.020 |
neck | -0.020 |
patterns | -0.020 |
sizes | -0.020 |
Token | bedroom |
Token ID | 14043 |
Feature activation | +3.36e-02 |
Pos logit contributions | |
sizes | +0.052 |
ABC | +0.046 |
planets | +0.046 |
clubs | +0.046 |
bows | +0.045 |
Neg logit contributions | |
late | -0.069 |
aback | -0.064 |
Start | -0.061 |
sm | -0.061 |
izz | -0.060 |
Token | . |
Token ID | 13 |
Feature activation | +8.73e-03 |
Pos logit contributions | |
sizes | +0.049 |
planets | +0.041 |
bows | +0.041 |
ABC | +0.040 |
clubs | +0.039 |
Neg logit contributions | |
late | -0.068 |
aback | -0.061 |
O | -0.060 |
Start | -0.060 |
sm | -0.059 |
Token | the |
Token ID | 262 |
Feature activation | +2.05e-02 |
Pos logit contributions | |
late | +0.007 |
aback | +0.006 |
Start | +0.006 |
O | +0.006 |
sm | +0.006 |
Neg logit contributions | |
sizes | -0.006 |
planets | -0.005 |
toes | -0.005 |
clubs | -0.005 |
bows | -0.005 |
Token | boy |
Token ID | 2933 |
Feature activation | +1.16e-02 |
Pos logit contributions | |
sizes | +0.039 |
planets | +0.034 |
bows | +0.034 |
ABC | +0.033 |
cultures | +0.033 |
Neg logit contributions | |
late | -0.033 |
aback | -0.028 |
Start | -0.027 |
O | -0.027 |
sm | -0.027 |
Token | thanked |
Token ID | 26280 |
Feature activation | +5.48e-02 |
Pos logit contributions | |
sizes | +0.019 |
planets | +0.017 |
bows | +0.016 |
ABC | +0.016 |
toes | +0.016 |
Neg logit contributions | |
late | -0.021 |
aback | -0.019 |
Start | -0.018 |
O | -0.018 |
sm | -0.018 |
Token | his |
Token ID | 465 |
Feature activation | +1.15e-02 |
Pos logit contributions | |
sizes | +0.109 |
planets | +0.099 |
ABC | +0.097 |
cultures | +0.096 |
bows | +0.095 |
Neg logit contributions | |
late | -0.080 |
aback | -0.069 |
Start | -0.066 |
sm | -0.065 |
O | -0.063 |
Token | mom |
Token ID | 1995 |
Feature activation | -1.80e-02 |
Pos logit contributions | |
sizes | +0.022 |
bows | +0.019 |
planets | +0.018 |
clubs | +0.018 |
hips | +0.018 |
Neg logit contributions | |
late | -0.019 |
sm | -0.016 |
aback | -0.016 |
Start | -0.016 |
severe | -0.015 |
Token | for |
Token ID | 329 |
Feature activation | -7.72e-02 |
Pos logit contributions | |
late | +0.027 |
sm | +0.022 |
aback | +0.021 |
severe | +0.019 |
another | +0.018 |
Neg logit contributions | |
sizes | -0.036 |
planets | -0.033 |
bows | -0.033 |
clubs | -0.032 |
necks | -0.032 |
Token | helping |
Token ID | 5742 |
Feature activation | +7.63e-02 |
Pos logit contributions | |
late | +0.153 |
aback | +0.139 |
Start | +0.134 |
O | +0.133 |
sm | +0.132 |
Neg logit contributions | |
sizes | -0.111 |
planets | -0.097 |
ABC | -0.093 |
clubs | -0.093 |
cultures | -0.091 |
Token | him |
Token ID | 683 |
Feature activation | +3.36e-02 |
Pos logit contributions | |
sizes | +0.148 |
planets | +0.131 |
bows | +0.129 |
ABC | +0.129 |
clubs | +0.127 |
Neg logit contributions | |
late | -0.119 |
aback | -0.101 |
Start | -0.099 |
sm | -0.097 |
O | -0.097 |
Token | sort |
Token ID | 3297 |
Feature activation | +1.61e-02 |
Pos logit contributions | |
sizes | +0.052 |
planets | +0.044 |
bows | +0.044 |
ABC | +0.043 |
clubs | +0.042 |
Neg logit contributions | |
late | -0.065 |
aback | -0.057 |
Start | -0.056 |
O | -0.056 |
sm | -0.056 |
Token | all |
Token ID | 477 |
Feature activation | -3.56e-02 |
Pos logit contributions | |
sizes | +0.032 |
planets | +0.028 |
clubs | +0.028 |
bows | +0.027 |
toes | +0.027 |
Neg logit contributions | |
late | -0.024 |
O | -0.021 |
Start | -0.021 |
sm | -0.020 |
severe | -0.019 |
Token | his |
Token ID | 465 |
Feature activation | +3.77e-03 |
Pos logit contributions | |
late | +0.045 |
O | +0.042 |
Start | +0.040 |
severe | +0.037 |
poisoned | +0.037 |
Neg logit contributions | |
sizes | -0.079 |
planets | -0.069 |
patterns | -0.067 |
languages | -0.066 |
cultures | -0.066 |