Token | have |
Token ID | 423 |
Feature activation | -4.27e+00 |
Pos logit contributions | |
Su | +0.034 |
Suz | +0.034 |
Sus | +0.034 |
Mill | +0.033 |
Alf | +0.033 |
Neg logit contributions | |
wy | -0.020 |
istered | -0.019 |
ggy | -0.019 |
ruined | -0.019 |
sharp | -0.018 |
Token | stopped |
Token ID | 5025 |
Feature activation | -9.02e-02 |
Pos logit contributions | |
wy | +0.074 |
istered | +0.070 |
uch | +0.068 |
ruined | +0.068 |
ggy | +0.067 |
Neg logit contributions | |
Su | -0.109 |
Suz | -0.107 |
Sus | -0.106 |
Mill | -0.106 |
Alf | -0.105 |
Token | the |
Token ID | 262 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
ruined | +0.002 |
wy | +0.002 |
sharp | +0.002 |
burns | +0.002 |
ggy | +0.002 |
Neg logit contributions | |
Suz | -0.002 |
Su | -0.002 |
Mill | -0.002 |
Sus | -0.002 |
Alf | -0.002 |
Token | rh |
Token ID | 9529 |
Feature activation | +1.98e+00 |
Pos logit contributions | |
Suz | +0.029 |
Su | +0.029 |
Mill | +0.028 |
Sus | +0.028 |
Jan | +0.027 |
Neg logit contributions | |
ruined | -0.031 |
sharp | -0.029 |
wy | -0.029 |
ggy | -0.029 |
pain | -0.028 |
Token | in |
Token ID | 259 |
Feature activation | +2.53e+00 |
Pos logit contributions | |
Alf | +0.045 |
Su | +0.045 |
Suz | +0.045 |
Sus | +0.044 |
Mill | +0.044 |
Neg logit contributions | |
ruined | -0.034 |
wy | -0.034 |
sharp | -0.034 |
istered | -0.033 |
sting | -0.033 |
Token | oc |
Token ID | 420 |
Feature activation | +1.05e+01 |
Pos logit contributions | |
Suz | +0.047 |
Su | +0.046 |
Sus | +0.045 |
Mill | +0.045 |
Jan | +0.041 |
Neg logit contributions | |
ruined | -0.064 |
ggy | -0.062 |
wy | -0.062 |
burns | -0.061 |
sharp | -0.061 |
Token | eros |
Token ID | 27498 |
Feature activation | +2.09e+00 |
Pos logit contributions | |
Suz | +0.246 |
Su | +0.238 |
Mill | +0.238 |
Sus | +0.234 |
Ally | +0.231 |
Neg logit contributions | |
wy | -0.219 |
ps | -0.215 |
ruined | -0.213 |
burns | -0.212 |
ggy | -0.211 |
Token | . |
Token ID | 13 |
Feature activation | +2.46e+00 |
Pos logit contributions | |
Suz | +0.060 |
Su | +0.059 |
Mill | +0.058 |
Sus | +0.058 |
Alf | +0.056 |
Neg logit contributions | |
ruined | -0.032 |
wy | -0.030 |
ggy | -0.029 |
sharp | -0.029 |
burns | -0.028 |
Token | He |
Token ID | 679 |
Feature activation | -5.60e-01 |
Pos logit contributions | |
Suz | +0.051 |
Mill | +0.050 |
Su | +0.048 |
Sus | +0.047 |
Ally | +0.046 |
Neg logit contributions | |
burns | -0.049 |
ruined | -0.048 |
pain | -0.046 |
sharp | -0.046 |
istered | -0.046 |
Token | is |
Token ID | 318 |
Feature activation | -5.57e+00 |
Pos logit contributions | |
wy | +0.010 |
istered | +0.009 |
kin | +0.009 |
ggie | +0.009 |
ggy | +0.009 |
Neg logit contributions | |
Alf | -0.014 |
Suz | -0.013 |
Sus | -0.013 |
Su | -0.013 |
Mill | -0.013 |
Token | sleeping |
Token ID | 11029 |
Feature activation | +8.39e-01 |
Pos logit contributions | |
wy | +0.104 |
uch | +0.100 |
istered | +0.097 |
arest | +0.094 |
ggy | +0.092 |
Neg logit contributions | |
Su | -0.135 |
Sus | -0.133 |
Suz | -0.132 |
Alf | -0.132 |
Mill | -0.130 |
Token | try |
Token ID | 1949 |
Feature activation | -4.37e-01 |
Pos logit contributions | |
Suz | +0.131 |
Su | +0.128 |
Alf | +0.127 |
Mill | +0.127 |
Sus | +0.124 |
Neg logit contributions | |
wy | -0.100 |
ruined | -0.099 |
ggy | -0.096 |
ggie | -0.095 |
uch | -0.093 |
Token | to |
Token ID | 284 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
ruined | +0.010 |
sharp | +0.010 |
ggy | +0.010 |
wy | +0.010 |
sting | +0.009 |
Neg logit contributions | |
Suz | -0.009 |
Su | -0.009 |
Mill | -0.009 |
Sus | -0.008 |
Alf | -0.008 |
Token | grab |
Token ID | 5552 |
Feature activation | +1.74e+00 |
Pos logit contributions | |
Suz | +0.023 |
Mill | +0.022 |
Su | +0.022 |
Twe | +0.021 |
line | +0.021 |
Neg logit contributions | |
istered | -0.032 |
ruined | -0.030 |
wy | -0.030 |
burns | -0.028 |
horrible | -0.028 |
Token | the |
Token ID | 262 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
Suz | +0.033 |
Su | +0.033 |
Sus | +0.032 |
Mill | +0.032 |
Alf | +0.031 |
Neg logit contributions | |
ruined | -0.042 |
wy | -0.042 |
ggy | -0.041 |
istered | -0.040 |
uch | -0.040 |
Token | av |
Token ID | 1196 |
Feature activation | +2.12e-01 |
Pos logit contributions | |
Suz | +0.031 |
Mill | +0.030 |
Sus | +0.030 |
Su | +0.030 |
Alf | +0.029 |
Neg logit contributions | |
ggy | -0.035 |
ggie | -0.034 |
wy | -0.033 |
istered | -0.033 |
ruined | -0.032 |
Token | oc |
Token ID | 420 |
Feature activation | +1.05e+01 |
Pos logit contributions | |
Suz | +0.003 |
Su | +0.003 |
Mill | +0.003 |
Sus | +0.003 |
Alf | +0.003 |
Neg logit contributions | |
ruined | -0.006 |
wy | -0.006 |
ggy | -0.006 |
sharp | -0.006 |
istered | -0.006 |
Token | ados |
Token ID | 22484 |
Feature activation | +7.48e-02 |
Pos logit contributions | |
Suz | +0.154 |
Su | +0.151 |
Sus | +0.147 |
Mill | +0.143 |
Alf | +0.136 |
Neg logit contributions | |
wy | -0.306 |
ruined | -0.295 |
sharp | -0.291 |
burns | -0.290 |
ggy | -0.290 |
Token | . |
Token ID | 13 |
Feature activation | +1.98e+00 |
Pos logit contributions | |
Suz | +0.002 |
Su | +0.002 |
Mill | +0.002 |
Sus | +0.002 |
Alf | +0.002 |
Neg logit contributions | |
wy | -0.002 |
ruined | -0.002 |
ggy | -0.001 |
ggie | -0.001 |
istered | -0.001 |
Token | But |
Token ID | 887 |
Feature activation | +4.42e+00 |
Pos logit contributions | |
Suz | +0.043 |
Mill | +0.043 |
Alf | +0.041 |
Sus | +0.041 |
Jan | +0.040 |
Neg logit contributions | |
sharp | -0.038 |
ruined | -0.037 |
sting | -0.037 |
ggy | -0.037 |
burns | -0.037 |
Token | the |
Token ID | 262 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
Suz | +0.093 |
Mill | +0.092 |
Su | +0.092 |
Sus | +0.090 |
Alf | +0.090 |
Neg logit contributions | |
ruined | -0.098 |
sharp | -0.092 |
hurt | -0.091 |
wy | -0.090 |
bad | -0.090 |
Token | rock |
Token ID | 3881 |
Feature activation | -5.91e-01 |
Pos logit contributions | |
ggy | +0.004 |
wy | +0.004 |
ggie | +0.004 |
ruined | +0.004 |
istered | +0.004 |
Neg logit contributions | |
Mill | -0.004 |
Suz | -0.004 |
Su | -0.004 |
Sus | -0.004 |
Alf | -0.004 |
Token | They |
Token ID | 1119 |
Feature activation | -8.77e-01 |
Pos logit contributions | |
Suz | +0.045 |
Mill | +0.044 |
Alf | +0.043 |
Su | +0.043 |
Sus | +0.042 |
Neg logit contributions | |
ruined | -0.056 |
burns | -0.054 |
sharp | -0.054 |
ggy | -0.053 |
sting | -0.053 |
Token | forget |
Token ID | 6044 |
Feature activation | +5.98e-01 |
Pos logit contributions | |
wy | +0.018 |
ggy | +0.017 |
ggie | +0.017 |
istered | +0.017 |
ruined | +0.017 |
Neg logit contributions | |
Su | -0.020 |
Suz | -0.020 |
Sus | -0.019 |
Alf | -0.019 |
Mill | -0.018 |
Token | about |
Token ID | 546 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
Suz | +0.016 |
Mill | +0.016 |
Su | +0.016 |
Alf | +0.016 |
Sus | +0.016 |
Neg logit contributions | |
ruined | -0.009 |
bad | -0.009 |
sharp | -0.009 |
ggy | -0.009 |
burns | -0.008 |
Token | the |
Token ID | 262 |
Feature activation | +7.30e-01 |
Pos logit contributions | |
Suz | +0.038 |
Mill | +0.037 |
Su | +0.037 |
Alf | +0.037 |
Sus | +0.036 |
Neg logit contributions | |
ruined | -0.040 |
sharp | -0.038 |
wy | -0.037 |
ggy | -0.037 |
pain | -0.036 |
Token | av |
Token ID | 1196 |
Feature activation | +2.24e-01 |
Pos logit contributions | |
Suz | +0.017 |
Su | +0.017 |
Mill | +0.017 |
Sus | +0.017 |
Alf | +0.016 |
Neg logit contributions | |
wy | -0.014 |
ggy | -0.014 |
ggie | -0.013 |
ruined | -0.013 |
istered | -0.013 |
Token | oc |
Token ID | 420 |
Feature activation | +1.04e+01 |
Pos logit contributions | |
Suz | +0.003 |
Su | +0.003 |
Mill | +0.003 |
Sus | +0.003 |
Alf | +0.003 |
Neg logit contributions | |
ruined | -0.007 |
wy | -0.007 |
ggy | -0.006 |
sharp | -0.006 |
ggie | -0.006 |
Token | ados |
Token ID | 22484 |
Feature activation | -2.61e-01 |
Pos logit contributions | |
Suz | +0.163 |
Su | +0.163 |
Sus | +0.155 |
Mill | +0.149 |
Alf | +0.145 |
Neg logit contributions | |
wy | -0.298 |
ruined | -0.288 |
ps | -0.284 |
burns | -0.283 |
uch | -0.281 |
Token | . |
Token ID | 13 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
wy | +0.005 |
ruined | +0.005 |
istered | +0.005 |
ggy | +0.005 |
ggie | +0.005 |
Neg logit contributions | |
Suz | -0.006 |
Su | -0.006 |
Mill | -0.006 |
Sus | -0.006 |
Alf | -0.006 |
Token | They |
Token ID | 1119 |
Feature activation | -9.93e-01 |
Pos logit contributions | |
Suz | +0.030 |
Mill | +0.029 |
Su | +0.029 |
Sus | +0.029 |
Alf | +0.028 |
Neg logit contributions | |
ruined | -0.042 |
ggy | -0.040 |
sharp | -0.040 |
burns | -0.040 |
wy | -0.040 |
Token | just |
Token ID | 655 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
wy | +0.020 |
ggy | +0.020 |
ggie | +0.020 |
istered | +0.020 |
uch | +0.019 |
Neg logit contributions | |
Suz | -0.022 |
Su | -0.022 |
Sus | -0.021 |
Alf | -0.021 |
Mill | -0.020 |
Token | want |
Token ID | 765 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
Suz | +0.038 |
Su | +0.037 |
Sus | +0.037 |
Mill | +0.036 |
Alf | +0.036 |
Neg logit contributions | |
ggy | -0.034 |
ggie | -0.033 |
wy | -0.033 |
istered | -0.032 |
uch | -0.031 |
Token | back |
Token ID | 736 |
Feature activation | +2.83e+00 |
Pos logit contributions | |
Suz | +0.015 |
Alf | +0.015 |
Mill | +0.014 |
Su | +0.014 |
Sus | +0.014 |
Neg logit contributions | |
sharp | -0.012 |
big | -0.011 |
ruined | -0.011 |
wy | -0.011 |
ps | -0.011 |
Token | to |
Token ID | 284 |
Feature activation | +3.50e+00 |
Pos logit contributions | |
Cr | +0.062 |
Alf | +0.061 |
Suz | +0.061 |
Su | +0.060 |
Mill | +0.059 |
Neg logit contributions | |
sharp | -0.053 |
big | -0.051 |
ruined | -0.051 |
hurt | -0.050 |
ggy | -0.049 |
Token | the |
Token ID | 262 |
Feature activation | +2.34e+00 |
Pos logit contributions | |
Suz | +0.078 |
Mill | +0.077 |
Alf | +0.076 |
cities | +0.074 |
Jan | +0.073 |
Neg logit contributions | |
sharp | -0.064 |
ruined | -0.064 |
hurt | -0.062 |
pain | -0.062 |
ggy | -0.061 |
Token | rh |
Token ID | 9529 |
Feature activation | +1.74e+00 |
Pos logit contributions | |
Suz | +0.048 |
Su | +0.047 |
Mill | +0.046 |
Sus | +0.046 |
Alf | +0.045 |
Neg logit contributions | |
ruined | -0.053 |
wy | -0.053 |
ggy | -0.051 |
sharp | -0.050 |
istered | -0.050 |
Token | in |
Token ID | 259 |
Feature activation | +2.88e+00 |
Pos logit contributions | |
Alf | +0.041 |
Su | +0.041 |
Suz | +0.041 |
Sus | +0.040 |
ress | +0.039 |
Neg logit contributions | |
ruined | -0.031 |
wy | -0.030 |
istered | -0.029 |
burns | -0.029 |
sting | -0.029 |
Token | oc |
Token ID | 420 |
Feature activation | +1.04e+01 |
Pos logit contributions | |
Su | +0.062 |
Sus | +0.061 |
Suz | +0.061 |
Mill | +0.059 |
Ally | +0.057 |
Neg logit contributions | |
ggy | -0.063 |
sharp | -0.061 |
hurt | -0.060 |
ruined | -0.059 |
ggie | -0.059 |
Token | eros |
Token ID | 27498 |
Feature activation | +2.73e+00 |
Pos logit contributions | |
Suz | +0.274 |
Mill | +0.267 |
Su | +0.266 |
Sus | +0.264 |
Ally | +0.261 |
Neg logit contributions | |
ps | -0.196 |
wy | -0.188 |
ggy | -0.187 |
burns | -0.181 |
ggie | -0.181 |
Token | and |
Token ID | 290 |
Feature activation | +7.05e+00 |
Pos logit contributions | |
Suz | +0.080 |
Su | +0.079 |
Mill | +0.077 |
Sus | +0.077 |
Alf | +0.076 |
Neg logit contributions | |
ruined | -0.036 |
ggy | -0.036 |
sharp | -0.034 |
ggie | -0.034 |
hurt | -0.033 |
Token | showed |
Token ID | 3751 |
Feature activation | +3.62e+00 |
Pos logit contributions | |
Suz | +0.185 |
Su | +0.182 |
Mill | +0.182 |
Alf | +0.179 |
Sus | +0.178 |
Neg logit contributions | |
ruined | -0.113 |
sharp | -0.108 |
hurt | -0.105 |
ggy | -0.105 |
wy | -0.100 |
Token | it |
Token ID | 340 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
Suz | +0.072 |
Mill | +0.068 |
Su | +0.068 |
Alf | +0.066 |
Sus | +0.065 |
Neg logit contributions | |
sharp | -0.078 |
ggy | -0.077 |
ruined | -0.076 |
ggie | -0.076 |
wy | -0.074 |
Token | what |
Token ID | 644 |
Feature activation | -5.39e-01 |
Pos logit contributions | |
ruined | +0.032 |
sharp | +0.032 |
ggy | +0.031 |
wy | +0.030 |
ggie | +0.030 |
Neg logit contributions | |
Su | -0.029 |
Suz | -0.028 |
Mill | -0.028 |
Sus | -0.027 |
Alf | -0.027 |
Token | to |
Token ID | 284 |
Feature activation | -6.38e-01 |
Pos logit contributions | |
ruined | +0.064 |
wy | +0.063 |
ggy | +0.061 |
sharp | +0.061 |
ggie | +0.060 |
Neg logit contributions | |
Suz | -0.054 |
Su | -0.053 |
Mill | -0.052 |
Sus | -0.052 |
Alf | -0.051 |
Token | pet |
Token ID | 4273 |
Feature activation | +4.64e+00 |
Pos logit contributions | |
wy | +0.015 |
istered | +0.014 |
ery | +0.013 |
kin | +0.013 |
arest | +0.013 |
Neg logit contributions | |
Suz | -0.014 |
Su | -0.014 |
Mill | -0.014 |
Sus | -0.014 |
Twe | -0.013 |
Token | the |
Token ID | 262 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
Suz | +0.105 |
Su | +0.100 |
Mill | +0.100 |
Sus | +0.099 |
Alf | +0.097 |
Neg logit contributions | |
ruined | -0.094 |
sharp | -0.092 |
wy | -0.091 |
hurt | -0.089 |
ggy | -0.088 |
Token | rh |
Token ID | 9529 |
Feature activation | +1.73e+00 |
Pos logit contributions | |
Alf | +0.032 |
Suz | +0.032 |
Su | +0.032 |
Mill | +0.032 |
Sus | +0.031 |
Neg logit contributions | |
wy | -0.038 |
ruined | -0.037 |
ggy | -0.037 |
ggie | -0.036 |
istered | -0.036 |
Token | in |
Token ID | 259 |
Feature activation | +2.65e+00 |
Pos logit contributions | |
Alf | +0.038 |
Suz | +0.037 |
Sus | +0.036 |
Su | +0.036 |
Mill | +0.036 |
Neg logit contributions | |
ruined | -0.032 |
pain | -0.031 |
istered | -0.031 |
sharp | -0.031 |
wy | -0.031 |
Token | oc |
Token ID | 420 |
Feature activation | +1.03e+01 |
Pos logit contributions | |
Suz | +0.049 |
Su | +0.048 |
Sus | +0.047 |
Mill | +0.047 |
Jan | +0.043 |
Neg logit contributions | |
ruined | -0.066 |
ggy | -0.066 |
wy | -0.065 |
sharp | -0.064 |
ggie | -0.064 |
Token | eros |
Token ID | 27498 |
Feature activation | +2.18e+00 |
Pos logit contributions | |
Suz | +0.248 |
Su | +0.243 |
Mill | +0.237 |
Sus | +0.236 |
Ally | +0.230 |
Neg logit contributions | |
wy | -0.211 |
ps | -0.203 |
ggy | -0.201 |
burns | -0.200 |
ruined | -0.199 |
Token | . |
Token ID | 13 |
Feature activation | +2.09e+00 |
Pos logit contributions | |
Suz | +0.059 |
Su | +0.059 |
Mill | +0.058 |
Sus | +0.058 |
Alf | +0.057 |
Neg logit contributions | |
ruined | -0.035 |
wy | -0.034 |
ggy | -0.033 |
sharp | -0.032 |
ggie | -0.031 |
Token | It |
Token ID | 632 |
Feature activation | -2.47e+00 |
Pos logit contributions | |
Suz | +0.044 |
Su | +0.043 |
Mill | +0.042 |
Sus | +0.042 |
Alf | +0.041 |
Neg logit contributions | |
ruined | -0.044 |
ggy | -0.043 |
sharp | -0.043 |
wy | -0.043 |
burns | -0.042 |
Token | looked |
Token ID | 3114 |
Feature activation | -3.56e+00 |
Pos logit contributions | |
wy | +0.049 |
arest | +0.046 |
istered | +0.045 |
kin | +0.045 |
itch | +0.043 |
Neg logit contributions | |
Suz | -0.058 |
Mill | -0.057 |
Su | -0.055 |
Sus | -0.054 |
Alf | -0.054 |
Token | so |
Token ID | 523 |
Feature activation | -9.30e-01 |
Pos logit contributions | |
wy | +0.055 |
ggy | +0.054 |
ggie | +0.052 |
uch | +0.051 |
kin | +0.049 |
Neg logit contributions | |
Suz | -0.098 |
Sus | -0.098 |
Su | -0.098 |
Mill | -0.097 |
Alf | -0.094 |
Token | unicorn |
Token ID | 44986 |
Feature activation | +4.61e-01 |
Pos logit contributions | |
Alf | +0.043 |
Suz | +0.043 |
Mill | +0.043 |
Su | +0.043 |
Sus | +0.042 |
Neg logit contributions | |
wy | -0.049 |
ruined | -0.048 |
istered | -0.047 |
ggy | -0.047 |
ggie | -0.046 |
Token | took |
Token ID | 1718 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
Su | +0.012 |
Suz | +0.012 |
Sus | +0.012 |
Mill | +0.012 |
Alf | +0.011 |
Neg logit contributions | |
ruined | -0.008 |
sharp | -0.007 |
ggy | -0.007 |
wy | -0.007 |
ggie | -0.007 |
Token | the |
Token ID | 262 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
Suz | +0.038 |
Su | +0.038 |
Sus | +0.037 |
Mill | +0.037 |
Alf | +0.036 |
Neg logit contributions | |
ruined | -0.018 |
sharp | -0.018 |
wy | -0.017 |
pain | -0.017 |
ggy | -0.017 |
Token | rh |
Token ID | 9529 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
Alf | +0.035 |
Mill | +0.035 |
Suz | +0.034 |
Su | +0.034 |
Sus | +0.033 |
Neg logit contributions | |
wy | -0.034 |
ggy | -0.034 |
ruined | -0.034 |
ggie | -0.033 |
istered | -0.033 |
Token | in |
Token ID | 259 |
Feature activation | +2.29e+00 |
Pos logit contributions | |
Alf | +0.038 |
Suz | +0.037 |
Su | +0.037 |
Sus | +0.037 |
Mill | +0.037 |
Neg logit contributions | |
ruined | -0.027 |
wy | -0.025 |
istered | -0.025 |
sting | -0.025 |
burns | -0.025 |
Token | oc |
Token ID | 420 |
Feature activation | +1.03e+01 |
Pos logit contributions | |
Su | +0.044 |
Suz | +0.043 |
Sus | +0.043 |
Mill | +0.041 |
Jos | +0.038 |
Neg logit contributions | |
sharp | -0.056 |
wy | -0.056 |
ruined | -0.054 |
ggy | -0.054 |
burns | -0.053 |
Token | eros |
Token ID | 27498 |
Feature activation | +1.94e+00 |
Pos logit contributions | |
Suz | +0.244 |
Su | +0.240 |
Mill | +0.234 |
Sus | +0.233 |
Ally | +0.225 |
Neg logit contributions | |
wy | -0.216 |
ps | -0.208 |
ggy | -0.206 |
ggie | -0.202 |
ruined | -0.201 |
Token | to |
Token ID | 284 |
Feature activation | +1.70e+00 |
Pos logit contributions | |
Su | +0.042 |
Suz | +0.041 |
Sus | +0.040 |
Mill | +0.038 |
Alf | +0.038 |
Neg logit contributions | |
sharp | -0.042 |
ruined | -0.042 |
burns | -0.040 |
ggy | -0.039 |
hurt | -0.039 |
Token | a |
Token ID | 257 |
Feature activation | -2.58e+00 |
Pos logit contributions | |
Suz | +0.044 |
Su | +0.043 |
Mill | +0.043 |
Sus | +0.043 |
Alf | +0.042 |
Neg logit contributions | |
ruined | -0.029 |
wy | -0.028 |
sharp | -0.028 |
ggy | -0.028 |
sting | -0.027 |
Token | nearby |
Token ID | 6716 |
Feature activation | +1.94e+00 |
Pos logit contributions | |
ruined | +0.037 |
sharp | +0.036 |
ggy | +0.034 |
wy | +0.034 |
bad | +0.033 |
Neg logit contributions | |
Suz | -0.076 |
Su | -0.075 |
Sus | -0.073 |
Mill | -0.073 |
Alf | -0.072 |
Token | pond |
Token ID | 16723 |
Feature activation | +9.05e-01 |
Pos logit contributions | |
Suz | +0.046 |
Su | +0.045 |
Sus | +0.045 |
Mill | +0.044 |
Hil | +0.042 |
Neg logit contributions | |
sharp | -0.039 |
big | -0.037 |
ruined | -0.036 |
bad | -0.035 |
pain | -0.035 |
Token | food |
Token ID | 2057 |
Feature activation | +8.61e-01 |
Pos logit contributions | |
Suz | +0.015 |
Su | +0.015 |
Sus | +0.014 |
Mill | +0.014 |
Alf | +0.014 |
Neg logit contributions | |
wy | -0.012 |
ruined | -0.012 |
sharp | -0.011 |
ggy | -0.011 |
burns | -0.011 |
Token | for |
Token ID | 329 |
Feature activation | +9.72e-01 |
Pos logit contributions | |
Suz | +0.018 |
Su | +0.018 |
Sus | +0.017 |
Mill | +0.017 |
Alf | +0.017 |
Neg logit contributions | |
ruined | -0.019 |
wy | -0.019 |
sharp | -0.018 |
ggy | -0.018 |
burns | -0.018 |
Token | the |
Token ID | 262 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
Suz | +0.022 |
Su | +0.021 |
Sus | +0.021 |
Mill | +0.020 |
Alf | +0.020 |
Neg logit contributions | |
ruined | -0.020 |
sharp | -0.020 |
ggy | -0.019 |
wy | -0.019 |
bad | -0.019 |
Token | rh |
Token ID | 9529 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
Suz | +0.041 |
Su | +0.040 |
Mill | +0.039 |
Sus | +0.039 |
Alf | +0.038 |
Neg logit contributions | |
ruined | -0.034 |
wy | -0.033 |
sharp | -0.033 |
ggy | -0.032 |
pain | -0.032 |
Token | in |
Token ID | 259 |
Feature activation | +2.75e+00 |
Pos logit contributions | |
Alf | +0.043 |
Suz | +0.042 |
Su | +0.042 |
Mill | +0.041 |
Sus | +0.041 |
Neg logit contributions | |
ruined | -0.031 |
wy | -0.030 |
pain | -0.030 |
burns | -0.030 |
sting | -0.030 |
Token | oc |
Token ID | 420 |
Feature activation | +1.03e+01 |
Pos logit contributions | |
Sus | +0.058 |
Su | +0.057 |
Suz | +0.057 |
Mill | +0.055 |
Jos | +0.053 |
Neg logit contributions | |
ggy | -0.062 |
wy | -0.062 |
ruined | -0.060 |
sharp | -0.060 |
hurt | -0.059 |
Token | eros |
Token ID | 27498 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
Suz | +0.228 |
Su | +0.223 |
Sus | +0.219 |
Mill | +0.218 |
Ally | +0.209 |
Neg logit contributions | |
wy | -0.229 |
ggy | -0.221 |
ruined | -0.219 |
ggie | -0.215 |
burns | -0.215 |
Token | and |
Token ID | 290 |
Feature activation | +7.01e+00 |
Pos logit contributions | |
Suz | +0.047 |
Su | +0.047 |
Sus | +0.046 |
Mill | +0.046 |
Alf | +0.045 |
Neg logit contributions | |
ruined | -0.026 |
wy | -0.025 |
ggy | -0.024 |
sharp | -0.024 |
burns | -0.023 |
Token | his |
Token ID | 465 |
Feature activation | +8.10e-01 |
Pos logit contributions | |
Suz | +0.170 |
Su | +0.169 |
Sus | +0.167 |
Mill | +0.162 |
Alf | +0.160 |
Neg logit contributions | |
ruined | -0.135 |
sharp | -0.129 |
wy | -0.125 |
burns | -0.124 |
hurt | -0.124 |
Token | friends |
Token ID | 2460 |
Feature activation | -4.68e-01 |
Pos logit contributions | |
Suz | +0.022 |
Su | +0.022 |
Sus | +0.022 |
Mill | +0.022 |
Alf | +0.021 |
Neg logit contributions | |
ruined | -0.013 |
wy | -0.012 |
sharp | -0.012 |
ggy | -0.012 |
burns | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | +2.58e+00 |
Pos logit contributions | |
ruined | +0.007 |
wy | +0.007 |
ggy | +0.007 |
sharp | +0.007 |
ggie | +0.007 |
Neg logit contributions | |
Suz | -0.013 |
Su | -0.013 |
Mill | -0.012 |
Sus | -0.012 |
Alf | -0.012 |
Token | to |
Token ID | 284 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
ruined | +0.072 |
sharp | +0.070 |
burns | +0.068 |
wy | +0.068 |
ggy | +0.068 |
Neg logit contributions | |
Suz | -0.061 |
Su | -0.060 |
Mill | -0.058 |
Sus | -0.058 |
Alf | -0.057 |
Token | see |
Token ID | 766 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
wy | +0.037 |
istered | +0.035 |
ruined | +0.034 |
ery | +0.033 |
sharp | +0.033 |
Neg logit contributions | |
Su | -0.041 |
Suz | -0.040 |
Sus | -0.039 |
Mill | -0.039 |
Alf | -0.039 |
Token | the |
Token ID | 262 |
Feature activation | +5.55e-01 |
Pos logit contributions | |
Suz | +0.037 |
Su | +0.036 |
Mill | +0.036 |
Sus | +0.035 |
Alf | +0.034 |
Neg logit contributions | |
ruined | -0.032 |
sharp | -0.031 |
bad | -0.030 |
wy | -0.030 |
hurt | -0.029 |
Token | rh |
Token ID | 9529 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
Suz | +0.011 |
Su | +0.011 |
Mill | +0.011 |
Sus | +0.011 |
Alf | +0.011 |
Neg logit contributions | |
wy | -0.012 |
ruined | -0.012 |
ggy | -0.012 |
istered | -0.012 |
ggie | -0.012 |
Token | in |
Token ID | 259 |
Feature activation | +2.14e+00 |
Pos logit contributions | |
Alf | +0.032 |
Suz | +0.032 |
Su | +0.031 |
Sus | +0.031 |
Mill | +0.031 |
Neg logit contributions | |
ruined | -0.024 |
wy | -0.024 |
sharp | -0.024 |
istered | -0.023 |
pain | -0.023 |
Token | oc |
Token ID | 420 |
Feature activation | +1.03e+01 |
Pos logit contributions | |
Suz | +0.039 |
Su | +0.038 |
Mill | +0.038 |
Sus | +0.038 |
Jan | +0.034 |
Neg logit contributions | |
ruined | -0.055 |
ggy | -0.054 |
wy | -0.053 |
sharp | -0.052 |
burns | -0.052 |
Token | eros |
Token ID | 27498 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
Suz | +0.242 |
Su | +0.236 |
Mill | +0.232 |
Sus | +0.230 |
Ally | +0.227 |
Neg logit contributions | |
wy | -0.212 |
ruined | -0.208 |
ps | -0.206 |
burns | -0.205 |
ggy | -0.205 |
Token | anymore |
Token ID | 7471 |
Feature activation | +8.53e-01 |
Pos logit contributions | |
Suz | +0.043 |
Su | +0.042 |
Mill | +0.042 |
Sus | +0.041 |
Alf | +0.041 |
Neg logit contributions | |
ruined | -0.029 |
wy | -0.029 |
ggy | -0.028 |
sharp | -0.027 |
ggie | -0.027 |
Token | . |
Token ID | 13 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
Suz | +0.019 |
Su | +0.018 |
Sus | +0.018 |
Mill | +0.018 |
Alf | +0.018 |
Neg logit contributions | |
wy | -0.017 |
ruined | -0.017 |
istered | -0.016 |
uch | -0.016 |
sharp | -0.016 |
Token | He |
Token ID | 679 |
Feature activation | -8.06e-01 |
Pos logit contributions | |
Suz | +0.033 |
Su | +0.033 |
Mill | +0.032 |
Sus | +0.032 |
Alf | +0.030 |
Neg logit contributions | |
ruined | -0.038 |
burns | -0.037 |
sharp | -0.037 |
istered | -0.036 |
wy | -0.036 |
Token | is |
Token ID | 318 |
Feature activation | -5.85e+00 |
Pos logit contributions | |
wy | +0.014 |
istered | +0.014 |
kin | +0.014 |
arest | +0.013 |
ggie | +0.013 |
Neg logit contributions | |
Alf | -0.018 |
Suz | -0.017 |
Mill | -0.017 |
Su | -0.017 |
K | -0.017 |
Token | happened |
Token ID | 3022 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
wy | +0.019 |
ruined | +0.019 |
istered | +0.018 |
ggy | +0.018 |
sharp | +0.018 |
Neg logit contributions | |
Suz | -0.018 |
Su | -0.018 |
Mill | -0.017 |
Sus | -0.017 |
Alf | -0.017 |
Token | to |
Token ID | 284 |
Feature activation | +7.49e-01 |
Pos logit contributions | |
ruined | +0.021 |
wy | +0.021 |
ggy | +0.020 |
sharp | +0.019 |
istered | +0.019 |
Neg logit contributions | |
Suz | -0.024 |
Su | -0.023 |
Mill | -0.023 |
Sus | -0.023 |
Alf | -0.023 |
Token | the |
Token ID | 262 |
Feature activation | +2.02e+00 |
Pos logit contributions | |
Suz | +0.015 |
Su | +0.014 |
Mill | +0.014 |
Sus | +0.014 |
Alf | +0.014 |
Neg logit contributions | |
ruined | -0.017 |
wy | -0.017 |
ggy | -0.017 |
sharp | -0.017 |
ggie | -0.016 |
Token | rh |
Token ID | 9529 |
Feature activation | +1.94e+00 |
Pos logit contributions | |
Mill | +0.042 |
Alf | +0.042 |
Suz | +0.042 |
Sus | +0.042 |
Su | +0.041 |
Neg logit contributions | |
wy | -0.044 |
ruined | -0.042 |
istered | -0.041 |
ggy | -0.041 |
ggie | -0.040 |
Token | in |
Token ID | 259 |
Feature activation | +3.02e+00 |
Pos logit contributions | |
Alf | +0.043 |
Suz | +0.041 |
ress | +0.040 |
Su | +0.040 |
Mill | +0.040 |
Neg logit contributions | |
istered | -0.036 |
ruined | -0.036 |
wy | -0.035 |
burns | -0.035 |
sting | -0.034 |
Token | oc |
Token ID | 420 |
Feature activation | +1.02e+01 |
Pos logit contributions | |
Suz | +0.056 |
Su | +0.055 |
Sus | +0.054 |
Mill | +0.052 |
Jos | +0.049 |
Neg logit contributions | |
ggy | -0.076 |
ruined | -0.076 |
sharp | -0.073 |
wy | -0.073 |
ggie | -0.073 |
Token | eros |
Token ID | 27498 |
Feature activation | +2.39e+00 |
Pos logit contributions | |
Suz | +0.239 |
Su | +0.234 |
Mill | +0.228 |
Sus | +0.228 |
Ally | +0.220 |
Neg logit contributions | |
wy | -0.211 |
ggy | -0.206 |
ruined | -0.205 |
ps | -0.204 |
ggie | -0.202 |
Token | , |
Token ID | 11 |
Feature activation | +4.09e+00 |
Pos logit contributions | |
Suz | +0.062 |
Su | +0.061 |
Mill | +0.060 |
Sus | +0.060 |
Alf | +0.059 |
Neg logit contributions | |
ruined | -0.042 |
wy | -0.040 |
ggy | -0.039 |
sharp | -0.038 |
ggie | -0.038 |
Token | but |
Token ID | 475 |
Feature activation | +5.13e+00 |
Pos logit contributions | |
Suz | +0.100 |
Mill | +0.096 |
Su | +0.096 |
Alf | +0.095 |
Sus | +0.094 |
Neg logit contributions | |
ruined | -0.077 |
sharp | -0.074 |
hurt | -0.071 |
bad | -0.070 |
pain | -0.070 |
Token | it |
Token ID | 340 |
Feature activation | -2.49e+00 |
Pos logit contributions | |
Suz | +0.108 |
Su | +0.108 |
Mill | +0.104 |
Sus | +0.102 |
Alf | +0.101 |
Neg logit contributions | |
ruined | -0.113 |
sharp | -0.107 |
ggy | -0.106 |
hurt | -0.106 |
bad | -0.105 |
Token | was |
Token ID | 373 |
Feature activation | -5.61e+00 |
Pos logit contributions | |
wy | +0.049 |
istered | +0.047 |
arest | +0.044 |
ruined | +0.044 |
uch | +0.043 |
Neg logit contributions | |
Suz | -0.058 |
Mill | -0.058 |
Sus | -0.056 |
Su | -0.056 |
Alf | -0.056 |
Token | and |
Token ID | 290 |
Feature activation | +5.95e+00 |
Pos logit contributions | |
Suz | +0.069 |
Su | +0.068 |
Mill | +0.067 |
Sus | +0.067 |
Alf | +0.066 |
Neg logit contributions | |
ruined | -0.050 |
wy | -0.048 |
ggy | -0.047 |
sharp | -0.047 |
ggie | -0.045 |
Token | took |
Token ID | 1718 |
Feature activation | +9.77e-01 |
Pos logit contributions | |
Suz | +0.157 |
Su | +0.155 |
Mill | +0.153 |
Alf | +0.153 |
Sus | +0.150 |
Neg logit contributions | |
ruined | -0.104 |
hurt | -0.093 |
sharp | -0.091 |
burns | -0.089 |
sting | -0.089 |
Token | the |
Token ID | 262 |
Feature activation | +7.50e-01 |
Pos logit contributions | |
Suz | +0.023 |
Su | +0.023 |
Mill | +0.022 |
Sus | +0.022 |
Alf | +0.022 |
Neg logit contributions | |
ruined | -0.019 |
wy | -0.018 |
sharp | -0.018 |
ggy | -0.018 |
pain | -0.018 |
Token | rh |
Token ID | 9529 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
Suz | +0.016 |
Su | +0.016 |
Mill | +0.016 |
Sus | +0.016 |
Alf | +0.016 |
Neg logit contributions | |
wy | -0.016 |
ruined | -0.016 |
ggy | -0.015 |
istered | -0.015 |
ggie | -0.015 |
Token | in |
Token ID | 259 |
Feature activation | +2.06e+00 |
Pos logit contributions | |
Alf | +0.031 |
Suz | +0.031 |
Su | +0.031 |
Sus | +0.031 |
Mill | +0.031 |
Neg logit contributions | |
ruined | -0.022 |
wy | -0.022 |
pain | -0.021 |
sharp | -0.021 |
sting | -0.021 |
Token | oc |
Token ID | 420 |
Feature activation | +1.02e+01 |
Pos logit contributions | |
Suz | +0.045 |
Sus | +0.044 |
Su | +0.044 |
Mill | +0.043 |
Jan | +0.041 |
Neg logit contributions | |
ggy | -0.045 |
sharp | -0.045 |
wy | -0.044 |
hurt | -0.044 |
ruined | -0.044 |
Token | eros |
Token ID | 27498 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
Suz | +0.238 |
Su | +0.230 |
Mill | +0.227 |
Sus | +0.226 |
Ally | +0.218 |
Neg logit contributions | |
wy | -0.216 |
ggy | -0.209 |
ruined | -0.208 |
ps | -0.207 |
burns | -0.205 |
Token | home |
Token ID | 1363 |
Feature activation | +9.59e-01 |
Pos logit contributions | |
Suz | +0.027 |
Su | +0.027 |
Sus | +0.026 |
Mill | +0.026 |
Alf | +0.025 |
Neg logit contributions | |
ruined | -0.037 |
sharp | -0.036 |
hurt | -0.035 |
ggy | -0.035 |
burns | -0.035 |
Token | with |
Token ID | 351 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
Suz | +0.026 |
Su | +0.026 |
Mill | +0.026 |
Sus | +0.026 |
Alf | +0.025 |
Neg logit contributions | |
ruined | -0.015 |
wy | -0.014 |
ggy | -0.014 |
sharp | -0.014 |
istered | -0.013 |
Token | her |
Token ID | 607 |
Feature activation | -8.59e-02 |
Pos logit contributions | |
Suz | +0.029 |
Mill | +0.029 |
Su | +0.028 |
Sus | +0.028 |
Alf | +0.027 |
Neg logit contributions | |
wy | -0.031 |
uch | -0.029 |
ggy | -0.029 |
ruined | -0.029 |
ggie | -0.029 |
Token | . |
Token ID | 13 |
Feature activation | +2.01e+00 |
Pos logit contributions | |
wy | +0.002 |
ggie | +0.002 |
istered | +0.002 |
uch | +0.002 |
ggy | +0.002 |
Neg logit contributions | |
Mill | -0.002 |
Suz | -0.002 |
Su | -0.002 |
Sus | -0.002 |
Alf | -0.002 |
Token | wait |
Token ID | 4043 |
Feature activation | +4.79e-01 |
Pos logit contributions | |
wy | +0.018 |
istered | +0.018 |
ching | +0.016 |
arest | +0.016 |
uch | +0.016 |
Neg logit contributions | |
Su | -0.017 |
Suz | -0.017 |
Sus | -0.017 |
Mill | -0.016 |
Alf | -0.015 |
Token | until |
Token ID | 1566 |
Feature activation | +4.52e+00 |
Pos logit contributions | |
Suz | +0.009 |
Su | +0.009 |
Mill | +0.009 |
Sus | +0.009 |
Alf | +0.009 |
Neg logit contributions | |
ruined | -0.011 |
wy | -0.011 |
ggy | -0.011 |
sharp | -0.011 |
istered | -0.011 |
Token | the |
Token ID | 262 |
Feature activation | +8.12e-01 |
Pos logit contributions | |
Suz | +0.091 |
Su | +0.090 |
Mill | +0.089 |
Sus | +0.088 |
Alf | +0.086 |
Neg logit contributions | |
wy | -0.103 |
ruined | -0.102 |
ggy | -0.099 |
istered | -0.097 |
sharp | -0.097 |
Token | rh |
Token ID | 9529 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
Suz | +0.018 |
Su | +0.017 |
Mill | +0.017 |
Sus | +0.017 |
Alf | +0.016 |
Neg logit contributions | |
ruined | -0.018 |
wy | -0.017 |
sharp | -0.017 |
ggy | -0.017 |
pain | -0.016 |
Token | in |
Token ID | 259 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
Suz | +0.024 |
Su | +0.023 |
Alf | +0.023 |
Sus | +0.023 |
Mill | +0.023 |
Neg logit contributions | |
ruined | -0.017 |
istered | -0.017 |
wy | -0.017 |
sharp | -0.017 |
pain | -0.017 |
Token | oc |
Token ID | 420 |
Feature activation | +1.02e+01 |
Pos logit contributions | |
Suz | +0.034 |
Sus | +0.034 |
Su | +0.034 |
Mill | +0.034 |
Ally | +0.031 |
Neg logit contributions | |
ruined | -0.043 |
ggy | -0.043 |
wy | -0.042 |
burns | -0.041 |
ggie | -0.041 |
Token | eros |
Token ID | 27498 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
Suz | +0.240 |
Su | +0.236 |
Mill | +0.234 |
Sus | +0.232 |
Ally | +0.229 |
Neg logit contributions | |
ps | -0.210 |
wy | -0.205 |
ggy | -0.202 |
burns | -0.201 |
ruined | -0.197 |
Token | is |
Token ID | 318 |
Feature activation | -4.18e+00 |
Pos logit contributions | |
Suz | +0.030 |
Su | +0.030 |
Mill | +0.030 |
Sus | +0.029 |
Alf | +0.029 |
Neg logit contributions | |
wy | -0.017 |
ruined | -0.017 |
ggy | -0.016 |
istered | -0.016 |
sharp | -0.016 |
Token | gone |
Token ID | 3750 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
arest | +0.070 |
ggy | +0.069 |
istered | +0.068 |
ggie | +0.067 |
wy | +0.066 |
Neg logit contributions | |
Su | -0.101 |
Suz | -0.099 |
Sus | -0.099 |
Mill | -0.098 |
Alf | -0.096 |
Token | ." |
Token ID | 526 |
Feature activation | +9.26e-01 |
Pos logit contributions | |
wy | +0.026 |
ruined | +0.025 |
ggy | +0.025 |
ggie | +0.025 |
istered | +0.024 |
Neg logit contributions | |
Suz | -0.035 |
Su | -0.034 |
Mill | -0.034 |
Sus | -0.034 |
Alf | -0.033 |
Token |
|
Token ID | 198 |
Feature activation | -5.18e+00 |
Pos logit contributions | |
Suz | +0.024 |
Alf | +0.024 |
Mill | +0.024 |
Su | +0.024 |
Sus | +0.023 |
Neg logit contributions | |
ruined | -0.014 |
pain | -0.013 |
bad | -0.013 |
sting | -0.013 |
sharp | -0.013 |
Token | care |
Token ID | 1337 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
Suz | +0.004 |
Su | +0.004 |
Mill | +0.004 |
Sus | +0.004 |
Alf | +0.004 |
Neg logit contributions | |
wy | -0.003 |
ruined | -0.003 |
ggy | -0.003 |
istered | -0.003 |
ggie | -0.003 |
Token | of |
Token ID | 286 |
Feature activation | +3.78e+00 |
Pos logit contributions | |
wy | +0.032 |
ruined | +0.031 |
ggy | +0.030 |
ggie | +0.030 |
sharp | +0.029 |
Neg logit contributions | |
Suz | -0.045 |
Su | -0.044 |
Sus | -0.043 |
Mill | -0.043 |
Alf | -0.042 |
Token | the |
Token ID | 262 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
Suz | +0.074 |
Su | +0.073 |
Mill | +0.072 |
Sus | +0.071 |
Alf | +0.070 |
Neg logit contributions | |
ruined | -0.088 |
wy | -0.087 |
ggy | -0.085 |
sharp | -0.084 |
ggie | -0.082 |
Token | rh |
Token ID | 9529 |
Feature activation | +1.70e+00 |
Pos logit contributions | |
Suz | +0.034 |
Su | +0.034 |
Mill | +0.034 |
Sus | +0.034 |
Alf | +0.033 |
Neg logit contributions | |
wy | -0.029 |
ruined | -0.028 |
ggy | -0.028 |
ggie | -0.027 |
istered | -0.027 |
Token | in |
Token ID | 259 |
Feature activation | +2.99e+00 |
Pos logit contributions | |
Alf | +0.038 |
Suz | +0.037 |
Sus | +0.037 |
Su | +0.036 |
Mill | +0.036 |
Neg logit contributions | |
ruined | -0.031 |
sting | -0.030 |
pain | -0.030 |
wy | -0.030 |
sharp | -0.030 |
Token | oc |
Token ID | 420 |
Feature activation | +1.01e+01 |
Pos logit contributions | |
Suz | +0.055 |
Su | +0.055 |
Sus | +0.053 |
Mill | +0.053 |
Ally | +0.050 |
Neg logit contributions | |
ruined | -0.075 |
ggy | -0.074 |
wy | -0.073 |
sharp | -0.073 |
ggie | -0.071 |
Token | eros |
Token ID | 27498 |
Feature activation | +2.07e+00 |
Pos logit contributions | |
Suz | +0.231 |
Su | +0.227 |
Mill | +0.221 |
Sus | +0.221 |
Ally | +0.217 |
Neg logit contributions | |
wy | -0.217 |
ruined | -0.208 |
ggy | -0.207 |
burns | -0.206 |
ps | -0.206 |
Token | and |
Token ID | 290 |
Feature activation | +5.75e+00 |
Pos logit contributions | |
Suz | +0.055 |
Su | +0.054 |
Mill | +0.053 |
Sus | +0.053 |
Alf | +0.052 |
Neg logit contributions | |
ruined | -0.036 |
wy | -0.034 |
ggy | -0.033 |
sharp | -0.033 |
ggie | -0.032 |
Token | it |
Token ID | 340 |
Feature activation | -1.90e+00 |
Pos logit contributions | |
Suz | +0.134 |
Su | +0.133 |
Mill | +0.131 |
Sus | +0.130 |
Alf | +0.128 |
Neg logit contributions | |
ruined | -0.113 |
wy | -0.111 |
ggy | -0.107 |
sharp | -0.106 |
istered | -0.103 |
Token | needed |
Token ID | 2622 |
Feature activation | -3.25e+00 |
Pos logit contributions | |
wy | +0.038 |
ggie | +0.036 |
ggy | +0.036 |
arest | +0.035 |
istered | +0.034 |
Neg logit contributions | |
Suz | -0.044 |
Mill | -0.043 |
Sus | -0.043 |
Su | -0.042 |
Alf | -0.041 |
Token | to |
Token ID | 284 |
Feature activation | -3.79e-01 |
Pos logit contributions | |
ruined | +0.073 |
wy | +0.072 |
ggy | +0.070 |
sharp | +0.069 |
istered | +0.068 |
Neg logit contributions | |
Suz | -0.067 |
Su | -0.066 |
Mill | -0.065 |
Sus | -0.065 |
Alf | -0.063 |
Token | store |
Token ID | 3650 |
Feature activation | +3.67e+00 |
Pos logit contributions | |
Suz | +0.044 |
Su | +0.043 |
Mill | +0.042 |
Sus | +0.042 |
Alf | +0.041 |
Neg logit contributions | |
ruined | -0.051 |
wy | -0.050 |
ggy | -0.048 |
sharp | -0.048 |
ggie | -0.047 |
Token | to |
Token ID | 284 |
Feature activation | +2.65e+00 |
Pos logit contributions | |
Suz | +0.108 |
Su | +0.104 |
Mill | +0.103 |
Ally | +0.102 |
Alf | +0.102 |
Neg logit contributions | |
ruined | -0.048 |
big | -0.046 |
broken | -0.044 |
not | -0.042 |
sharp | -0.042 |
Token | get |
Token ID | 651 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
Suz | +0.053 |
Su | +0.053 |
Mill | +0.052 |
Sus | +0.052 |
Alf | +0.050 |
Neg logit contributions | |
wy | -0.061 |
ruined | -0.061 |
ggy | -0.059 |
istered | -0.058 |
sharp | -0.058 |
Token | more |
Token ID | 517 |
Feature activation | +2.70e-01 |
Pos logit contributions | |
ruined | +0.028 |
wy | +0.027 |
sharp | +0.026 |
bad | +0.025 |
hurt | +0.025 |
Neg logit contributions | |
Suz | -0.042 |
Su | -0.041 |
Mill | -0.041 |
Alf | -0.040 |
Sus | -0.040 |
Token | av |
Token ID | 1196 |
Feature activation | +5.01e-02 |
Pos logit contributions | |
Suz | +0.007 |
Sus | +0.007 |
Mill | +0.007 |
Su | +0.006 |
Alf | +0.006 |
Neg logit contributions | |
ggy | -0.005 |
ggie | -0.005 |
wy | -0.005 |
ruined | -0.005 |
istered | -0.005 |
Token | oc |
Token ID | 420 |
Feature activation | +1.01e+01 |
Pos logit contributions | |
Suz | +0.001 |
Su | +0.001 |
Mill | +0.001 |
Sus | +0.001 |
Alf | +0.001 |
Neg logit contributions | |
ruined | -0.001 |
wy | -0.001 |
ggy | -0.001 |
sharp | -0.001 |
istered | -0.001 |
Token | ados |
Token ID | 22484 |
Feature activation | -4.02e-01 |
Pos logit contributions | |
Suz | +0.143 |
Su | +0.140 |
Sus | +0.135 |
Mill | +0.133 |
Alf | +0.127 |
Neg logit contributions | |
wy | -0.300 |
ruined | -0.291 |
ggy | -0.289 |
sharp | -0.285 |
ps | -0.284 |
Token | . |
Token ID | 13 |
Feature activation | +2.71e+00 |
Pos logit contributions | |
ruined | +0.008 |
wy | +0.008 |
ggy | +0.007 |
sharp | +0.007 |
istered | +0.007 |
Neg logit contributions | |
Suz | -0.009 |
Su | -0.009 |
Mill | -0.009 |
Sus | -0.009 |
Alf | -0.009 |
Token | Gary |
Token ID | 10936 |
Feature activation | +6.86e-01 |
Pos logit contributions | |
Su | +0.051 |
Suz | +0.051 |
Sus | +0.049 |
Mill | +0.048 |
Alf | +0.047 |
Neg logit contributions | |
ruined | -0.065 |
wy | -0.064 |
sharp | -0.063 |
ggy | -0.062 |
burns | -0.062 |
Token | looked |
Token ID | 3114 |
Feature activation | -2.81e+00 |
Pos logit contributions | |
Suz | +0.018 |
Su | +0.018 |
Mill | +0.018 |
Sus | +0.017 |
Alf | +0.017 |
Neg logit contributions | |
ruined | -0.011 |
wy | -0.011 |
ggy | -0.011 |
sharp | -0.011 |
ggie | -0.010 |
Token | at |
Token ID | 379 |
Feature activation | +2.78e+00 |
Pos logit contributions | |
ruined | +0.059 |
wy | +0.057 |
sharp | +0.056 |
bad | +0.053 |
istered | +0.053 |
Neg logit contributions | |
Suz | -0.063 |
Su | -0.062 |
Mill | -0.061 |
Sus | -0.060 |
Alf | -0.060 |
Token | had |
Token ID | 550 |
Feature activation | -3.07e+00 |
Pos logit contributions | |
inkle | +0.031 |
wy | +0.031 |
itching | +0.030 |
arest | +0.030 |
sting | +0.030 |
Neg logit contributions | |
Su | -0.033 |
Sus | -0.033 |
Suz | -0.032 |
Mill | -0.032 |
Alf | -0.032 |
Token | never |
Token ID | 1239 |
Feature activation | +3.40e-01 |
Pos logit contributions | |
wy | +0.047 |
istered | +0.047 |
inkle | +0.044 |
ching | +0.043 |
arest | +0.043 |
Neg logit contributions | |
Su | -0.083 |
Sus | -0.081 |
Mill | -0.081 |
Suz | -0.081 |
Alf | -0.078 |
Token | seen |
Token ID | 1775 |
Feature activation | +2.46e-01 |
Pos logit contributions | |
Su | +0.008 |
Suz | +0.008 |
Sus | +0.008 |
Mill | +0.008 |
Alf | +0.007 |
Neg logit contributions | |
istered | -0.006 |
wy | -0.006 |
itch | -0.006 |
inkle | -0.006 |
ggy | -0.006 |
Token | the |
Token ID | 262 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
Suz | +0.005 |
Su | +0.005 |
Mill | +0.005 |
Sus | +0.005 |
Alf | +0.005 |
Neg logit contributions | |
wy | -0.005 |
ruined | -0.005 |
ggy | -0.005 |
istered | -0.005 |
uch | -0.005 |
Token | av |
Token ID | 1196 |
Feature activation | -2.17e-01 |
Pos logit contributions | |
Mill | +0.023 |
Su | +0.023 |
Sus | +0.023 |
Suz | +0.023 |
Alf | +0.023 |
Neg logit contributions | |
wy | -0.022 |
ggy | -0.021 |
ruined | -0.021 |
istered | -0.021 |
ggie | -0.021 |
Token | oc |
Token ID | 420 |
Feature activation | +1.00e+01 |
Pos logit contributions | |
ruined | +0.007 |
wy | +0.006 |
ggy | +0.006 |
ggie | +0.006 |
burns | +0.006 |
Neg logit contributions | |
Suz | -0.003 |
Mill | -0.003 |
Su | -0.003 |
Alf | -0.002 |
Sus | -0.002 |
Token | ados |
Token ID | 22484 |
Feature activation | -5.71e-01 |
Pos logit contributions | |
Suz | +0.160 |
Su | +0.156 |
Sus | +0.149 |
Mill | +0.146 |
Alf | +0.140 |
Neg logit contributions | |
wy | -0.282 |
ruined | -0.276 |
ggy | -0.267 |
ps | -0.266 |
sharp | -0.266 |
Token | . |
Token ID | 13 |
Feature activation | +2.39e+00 |
Pos logit contributions | |
wy | +0.013 |
ruined | +0.013 |
ggy | +0.013 |
istered | +0.012 |
ggie | +0.012 |
Neg logit contributions | |
Su | -0.011 |
Suz | -0.011 |
Sus | -0.011 |
Mill | -0.011 |
Alf | -0.010 |
Token | They |
Token ID | 1119 |
Feature activation | -3.68e-01 |
Pos logit contributions | |
Suz | +0.048 |
Mill | +0.046 |
Su | +0.046 |
Sus | +0.045 |
ress | +0.043 |
Neg logit contributions | |
ruined | -0.054 |
sharp | -0.051 |
pain | -0.051 |
bad | -0.050 |
burns | -0.050 |
Token | wished |
Token ID | 16555 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
wy | +0.009 |
uch | +0.008 |
arest | +0.008 |
ggy | +0.008 |
ggie | +0.008 |
Neg logit contributions | |
Alf | -0.007 |
Su | -0.007 |
Suz | -0.007 |
Sus | -0.007 |
Mill | -0.007 |
Token | they |
Token ID | 484 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
Suz | +0.033 |
Mill | +0.032 |
Su | +0.032 |
ress | +0.032 |
Ally | +0.031 |
Neg logit contributions | |
ruined | -0.040 |
bad | -0.039 |
not | -0.038 |
sharp | -0.038 |
ggy | -0.038 |
Token | to |
Token ID | 284 |
Feature activation | -6.89e-01 |
Pos logit contributions | |
wy | +0.074 |
ruined | +0.073 |
ggy | +0.069 |
sharp | +0.069 |
istered | +0.069 |
Neg logit contributions | |
Suz | -0.076 |
Su | -0.075 |
Sus | -0.075 |
Mill | -0.074 |
Alf | -0.072 |
Token | help |
Token ID | 1037 |
Feature activation | +2.79e+00 |
Pos logit contributions | |
wy | +0.016 |
istered | +0.016 |
ruined | +0.014 |
uch | +0.014 |
ifying | +0.014 |
Neg logit contributions | |
Suz | -0.015 |
Sus | -0.014 |
Mill | -0.014 |
Su | -0.014 |
Alf | -0.013 |
Token | the |
Token ID | 262 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
Suz | +0.072 |
Su | +0.072 |
Mill | +0.070 |
Sus | +0.069 |
Alf | +0.069 |
Neg logit contributions | |
ruined | -0.046 |
sharp | -0.045 |
hurt | -0.044 |
ggy | -0.044 |
sting | -0.042 |
Token | rh |
Token ID | 9529 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
Suz | +0.044 |
Su | +0.044 |
Mill | +0.043 |
Sus | +0.043 |
Alf | +0.042 |
Neg logit contributions | |
ruined | -0.034 |
wy | -0.033 |
ggy | -0.032 |
sharp | -0.031 |
istered | -0.031 |
Token | in |
Token ID | 259 |
Feature activation | +2.86e+00 |
Pos logit contributions | |
Alf | +0.039 |
Suz | +0.039 |
Su | +0.038 |
Sus | +0.038 |
Mill | +0.037 |
Neg logit contributions | |
wy | -0.028 |
ruined | -0.028 |
istered | -0.026 |
pain | -0.026 |
sharp | -0.026 |
Token | oc |
Token ID | 420 |
Feature activation | +1.00e+01 |
Pos logit contributions | |
Suz | +0.057 |
Su | +0.057 |
Sus | +0.057 |
Mill | +0.056 |
Ally | +0.050 |
Neg logit contributions | |
ggy | -0.067 |
ruined | -0.066 |
hurt | -0.065 |
sharp | -0.064 |
ggie | -0.064 |
Token | eros |
Token ID | 27498 |
Feature activation | +2.26e+00 |
Pos logit contributions | |
Suz | +0.237 |
Mill | +0.232 |
Su | +0.231 |
Sus | +0.228 |
Ally | +0.223 |
Neg logit contributions | |
ggy | -0.206 |
wy | -0.205 |
ps | -0.203 |
ggie | -0.200 |
ruined | -0.200 |
Token | . |
Token ID | 13 |
Feature activation | +2.38e+00 |
Pos logit contributions | |
Su | +0.063 |
Suz | +0.063 |
Mill | +0.062 |
Sus | +0.062 |
Alf | +0.061 |
Neg logit contributions | |
ruined | -0.034 |
ggy | -0.032 |
wy | -0.031 |
sharp | -0.031 |
hurt | -0.031 |
Token | The |
Token ID | 383 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
cities | +0.070 |
forth | +0.063 |
oceans | +0.063 |
line | +0.063 |
discovering | +0.062 |
Neg logit contributions | |
ruined | -0.025 |
big | -0.025 |
two | -0.023 |
ggy | -0.023 |
not | -0.023 |
Token | zo |
Token ID | 40565 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
Suz | +0.037 |
Su | +0.037 |
Mill | +0.036 |
Sus | +0.036 |
Alf | +0.036 |
Neg logit contributions | |
ruined | -0.027 |
wy | -0.027 |
ggy | -0.026 |
sharp | -0.025 |
istered | -0.025 |
Token | oke |
Token ID | 2088 |
Feature activation | +2.40e+00 |
Pos logit contributions | |
Suz | +0.033 |
Su | +0.033 |
Mill | +0.033 |
Sus | +0.032 |
Alf | +0.031 |
Neg logit contributions | |
ruined | -0.031 |
wy | -0.030 |
ggy | -0.030 |
sharp | -0.029 |
ggie | -0.029 |
Token | thanked |
Token ID | 26280 |
Feature activation | +4.45e+00 |
Pos logit contributions | |
Suz | +0.038 |
Su | +0.037 |
Mill | +0.037 |
Alf | +0.037 |
Sus | +0.037 |
Neg logit contributions | |
ruined | -0.029 |
wy | -0.028 |
ggy | -0.027 |
sharp | -0.026 |
hurt | -0.026 |
Token | the |
Token ID | 262 |
Feature activation | +2.44e+00 |
Pos logit contributions | |
Suz | +0.093 |
Su | +0.090 |
ress | +0.088 |
line | +0.087 |
Sus | +0.086 |
Neg logit contributions | |
sharp | -0.089 |
ggie | -0.089 |
ggy | -0.087 |
ruined | -0.086 |
bad | -0.086 |
Token | elderly |
Token ID | 13830 |
Feature activation | +5.02e+00 |
Pos logit contributions | |
Suz | +0.057 |
Su | +0.056 |
Sus | +0.054 |
Mill | +0.054 |
Jan | +0.052 |
Neg logit contributions | |
ruined | -0.049 |
sharp | -0.048 |
wy | -0.048 |
ggy | -0.047 |
bad | -0.046 |
Token | rh |
Token ID | 9529 |
Feature activation | +1.94e+00 |
Pos logit contributions | |
Suz | +0.116 |
Su | +0.115 |
Sus | +0.109 |
Jos | +0.106 |
Mill | +0.105 |
Neg logit contributions | |
ggy | -0.103 |
sharp | -0.099 |
ggie | -0.097 |
ruined | -0.096 |
hurt | -0.096 |
Token | in |
Token ID | 259 |
Feature activation | +3.02e+00 |
Pos logit contributions | |
Suz | +0.053 |
Su | +0.052 |
Mill | +0.052 |
Sus | +0.051 |
Alf | +0.051 |
Neg logit contributions | |
ruined | -0.030 |
wy | -0.029 |
sharp | -0.028 |
istered | -0.028 |
burns | -0.027 |
Token | oc |
Token ID | 420 |
Feature activation | +1.00e+01 |
Pos logit contributions | |
Su | +0.067 |
Sus | +0.065 |
Suz | +0.064 |
Jos | +0.060 |
Mill | +0.059 |
Neg logit contributions | |
ggy | -0.064 |
ggie | -0.061 |
wy | -0.061 |
sharp | -0.060 |
ery | -0.060 |
Token | eros |
Token ID | 27498 |
Feature activation | +2.75e+00 |
Pos logit contributions | |
Suz | +0.243 |
Su | +0.241 |
Sus | +0.233 |
Mill | +0.230 |
Jos | +0.224 |
Neg logit contributions | |
wy | -0.196 |
ps | -0.196 |
ggy | -0.195 |
ggie | -0.191 |
ruined | -0.180 |
Token | for |
Token ID | 329 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
Su | +0.067 |
Suz | +0.066 |
Sus | +0.064 |
Mill | +0.062 |
Hil | +0.061 |
Neg logit contributions | |
ggy | -0.048 |
ggie | -0.048 |
sharp | -0.047 |
ruined | -0.046 |
bad | -0.045 |
Token | his |
Token ID | 465 |
Feature activation | +9.64e-01 |
Pos logit contributions | |
Suz | +0.034 |
Su | +0.033 |
Mill | +0.032 |
Sus | +0.032 |
Alf | +0.032 |
Neg logit contributions | |
ruined | -0.033 |
ggy | -0.031 |
sharp | -0.031 |
wy | -0.031 |
ggie | -0.031 |
Token | wonderful |
Token ID | 7932 |
Feature activation | +2.41e+00 |
Pos logit contributions | |
Suz | +0.025 |
Mill | +0.024 |
Su | +0.024 |
Sus | +0.024 |
Alf | +0.024 |
Neg logit contributions | |
wy | -0.017 |
ruined | -0.016 |
istered | -0.015 |
ggy | -0.015 |
uch | -0.015 |
Token | surprise |
Token ID | 5975 |
Feature activation | +2.18e+00 |
Pos logit contributions | |
Suz | +0.046 |
Su | +0.045 |
Mill | +0.045 |
Sus | +0.045 |
Alf | +0.043 |
Neg logit contributions | |
wy | -0.058 |
ruined | -0.057 |
istered | -0.055 |
ggy | -0.054 |
sharp | -0.054 |
Token | net |
Token ID | 2010 |
Feature activation | -9.44e-01 |
Pos logit contributions | |
wy | +0.002 |
istered | +0.002 |
ggy | +0.002 |
ruined | +0.002 |
ggie | +0.002 |
Neg logit contributions | |
Alf | -0.002 |
Suz | -0.002 |
Su | -0.002 |
Mill | -0.002 |
Sus | -0.002 |
Token | on |
Token ID | 319 |
Feature activation | +2.14e+00 |
Pos logit contributions | |
ruined | +0.018 |
wy | +0.018 |
ggy | +0.017 |
sharp | +0.017 |
ggie | +0.017 |
Neg logit contributions | |
Suz | -0.022 |
Su | -0.022 |
Mill | -0.022 |
Sus | -0.022 |
Alf | -0.021 |
Token | the |
Token ID | 262 |
Feature activation | +2.40e+00 |
Pos logit contributions | |
Suz | +0.050 |
Su | +0.048 |
Mill | +0.048 |
Sus | +0.048 |
Alf | +0.046 |
Neg logit contributions | |
ruined | -0.042 |
sharp | -0.042 |
wy | -0.041 |
ggy | -0.041 |
ggie | -0.040 |
Token | rh |
Token ID | 9529 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
Suz | +0.049 |
Su | +0.048 |
Mill | +0.048 |
Alf | +0.048 |
Sus | +0.047 |
Neg logit contributions | |
wy | -0.052 |
ruined | -0.051 |
istered | -0.050 |
ggy | -0.050 |
uch | -0.049 |
Token | in |
Token ID | 259 |
Feature activation | +2.97e+00 |
Pos logit contributions | |
Alf | +0.038 |
Suz | +0.037 |
Su | +0.036 |
Sus | +0.036 |
ress | +0.036 |
Neg logit contributions | |
ruined | -0.030 |
sting | -0.029 |
pain | -0.029 |
wy | -0.029 |
istered | -0.029 |
Token | oc |
Token ID | 420 |
Feature activation | +9.99e+00 |
Pos logit contributions | |
Suz | +0.054 |
Su | +0.054 |
Sus | +0.054 |
Mill | +0.052 |
Alf | +0.048 |
Neg logit contributions | |
ggy | -0.074 |
wy | -0.074 |
ruined | -0.074 |
sharp | -0.073 |
ggie | -0.072 |
Token | eros |
Token ID | 27498 |
Feature activation | +2.53e+00 |
Pos logit contributions | |
Suz | +0.229 |
Su | +0.226 |
Mill | +0.221 |
Sus | +0.221 |
Ally | +0.210 |
Neg logit contributions | |
wy | -0.212 |
ggy | -0.204 |
ruined | -0.204 |
burns | -0.202 |
ps | -0.202 |
Token | . |
Token ID | 13 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
Suz | +0.077 |
Su | +0.076 |
Sus | +0.075 |
Mill | +0.075 |
Alf | +0.072 |
Neg logit contributions | |
ruined | -0.034 |
ggy | -0.032 |
wy | -0.032 |
sharp | -0.032 |
burns | -0.031 |
Token | They |
Token ID | 1119 |
Feature activation | -9.66e-01 |
Pos logit contributions | |
Suz | +0.034 |
Mill | +0.034 |
Sus | +0.033 |
ress | +0.033 |
ie | +0.033 |
Neg logit contributions | |
A | -0.023 |
burns | -0.023 |
big | -0.023 |
sharp | -0.022 |
ggy | -0.022 |
Token | put |
Token ID | 1234 |
Feature activation | +1.95e+00 |
Pos logit contributions | |
wy | +0.019 |
ggy | +0.019 |
ggie | +0.019 |
uch | +0.018 |
istered | +0.018 |
Neg logit contributions | |
Alf | -0.021 |
Suz | -0.021 |
Su | -0.021 |
Mill | -0.021 |
Sus | -0.020 |
Token | the |
Token ID | 262 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
Suz | +0.045 |
Mill | +0.044 |
Su | +0.044 |
Sus | +0.043 |
Alf | +0.042 |
Neg logit contributions | |
ruined | -0.040 |
wy | -0.039 |
sharp | -0.039 |
ps | -0.037 |
burns | -0.037 |
Token | and |
Token ID | 290 |
Feature activation | +5.31e+00 |
Pos logit contributions | |
ruined | +0.031 |
sharp | +0.031 |
wy | +0.029 |
istered | +0.029 |
ggy | +0.029 |
Neg logit contributions | |
Su | -0.044 |
Suz | -0.044 |
Mill | -0.042 |
Sus | -0.042 |
Alf | -0.041 |
Token | hugged |
Token ID | 41130 |
Feature activation | +3.36e+00 |
Pos logit contributions | |
Suz | +0.133 |
Su | +0.131 |
Mill | +0.129 |
Sus | +0.128 |
Alf | +0.128 |
Neg logit contributions | |
ruined | -0.095 |
wy | -0.090 |
sharp | -0.090 |
ggy | -0.089 |
sting | -0.086 |
Token | the |
Token ID | 262 |
Feature activation | +2.57e+00 |
Pos logit contributions | |
Suz | +0.086 |
Hil | +0.084 |
Su | +0.081 |
Mill | +0.081 |
Alf | +0.081 |
Neg logit contributions | |
sharp | -0.054 |
bad | -0.050 |
pain | -0.050 |
big | -0.049 |
hurt | -0.047 |
Token | rh |
Token ID | 9529 |
Feature activation | +1.96e+00 |
Pos logit contributions | |
Suz | +0.056 |
Su | +0.055 |
Mill | +0.054 |
Sus | +0.054 |
Alf | +0.053 |
Neg logit contributions | |
ruined | -0.055 |
wy | -0.054 |
sharp | -0.053 |
ggy | -0.052 |
sting | -0.051 |
Token | in |
Token ID | 259 |
Feature activation | +2.92e+00 |
Pos logit contributions | |
Suz | +0.046 |
Alf | +0.045 |
Sus | +0.045 |
Su | +0.045 |
Mill | +0.044 |
Neg logit contributions | |
ruined | -0.036 |
pain | -0.034 |
wy | -0.034 |
istered | -0.033 |
sting | -0.033 |
Token | oc |
Token ID | 420 |
Feature activation | +9.96e+00 |
Pos logit contributions | |
Su | +0.059 |
Suz | +0.058 |
Sus | +0.057 |
Mill | +0.056 |
Hil | +0.053 |
Neg logit contributions | |
sharp | -0.068 |
ggy | -0.067 |
wy | -0.066 |
ggie | -0.064 |
ruined | -0.063 |
Token | eros |
Token ID | 27498 |
Feature activation | +2.31e+00 |
Pos logit contributions | |
Suz | +0.243 |
Su | +0.241 |
Mill | +0.233 |
Sus | +0.232 |
Ally | +0.230 |
Neg logit contributions | |
wy | -0.196 |
ps | -0.193 |
ggy | -0.183 |
burns | -0.182 |
ggie | -0.178 |
Token | . |
Token ID | 13 |
Feature activation | +2.69e+00 |
Pos logit contributions | |
Su | +0.065 |
Suz | +0.065 |
Sus | +0.063 |
Mill | +0.063 |
Alf | +0.061 |
Neg logit contributions | |
sharp | -0.033 |
ggy | -0.033 |
ruined | -0.033 |
ggie | -0.032 |
wy | -0.032 |
Token | He |
Token ID | 679 |
Feature activation | +1.67e-01 |
Pos logit contributions | |
Suz | +0.060 |
Su | +0.058 |
Mill | +0.057 |
Hil | +0.056 |
Sus | +0.055 |
Neg logit contributions | |
two | -0.046 |
sharp | -0.044 |
Deal | -0.043 |
big | -0.042 |
A | -0.041 |
Token | finally |
Token ID | 3443 |
Feature activation | -9.64e-01 |
Pos logit contributions | |
Suz | +0.004 |
Su | +0.004 |
Mill | +0.004 |
Sus | +0.004 |
Alf | +0.004 |
Neg logit contributions | |
wy | -0.003 |
istered | -0.003 |
ruined | -0.003 |
uch | -0.003 |
ggy | -0.003 |
Token | understood |
Token ID | 7247 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
istered | +0.022 |
wy | +0.021 |
burns | +0.020 |
uch | +0.020 |
ggy | +0.020 |
Neg logit contributions | |
Su | -0.020 |
Suz | -0.020 |
Mill | -0.020 |
Sus | -0.020 |
Alf | -0.019 |
Token | trapped |
Token ID | 13640 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
wy | +0.098 |
uch | +0.097 |
arest | +0.090 |
ggy | +0.086 |
ggie | +0.085 |
Neg logit contributions | |
Suz | -0.123 |
Alf | -0.121 |
Mill | -0.120 |
Su | -0.120 |
Sus | -0.118 |
Token | with |
Token ID | 351 |
Feature activation | +6.75e-01 |
Pos logit contributions | |
wy | +0.024 |
ruined | +0.024 |
ggy | +0.023 |
sharp | +0.022 |
ggie | +0.022 |
Neg logit contributions | |
Suz | -0.031 |
Su | -0.030 |
Mill | -0.030 |
Sus | -0.030 |
Alf | -0.029 |
Token | the |
Token ID | 262 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
Suz | +0.013 |
Su | +0.013 |
Mill | +0.013 |
Sus | +0.013 |
Alf | +0.013 |
Neg logit contributions | |
wy | -0.016 |
ruined | -0.016 |
ggy | -0.015 |
uch | -0.015 |
istered | -0.015 |
Token | rh |
Token ID | 9529 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
Alf | +0.022 |
Su | +0.022 |
Suz | +0.022 |
Mill | +0.022 |
Sus | +0.021 |
Neg logit contributions | |
wy | -0.022 |
ruined | -0.021 |
ggy | -0.021 |
istered | -0.021 |
ggie | -0.021 |
Token | in |
Token ID | 259 |
Feature activation | +2.37e+00 |
Pos logit contributions | |
Alf | +0.029 |
Suz | +0.028 |
Su | +0.028 |
Sus | +0.028 |
Mill | +0.027 |
Neg logit contributions | |
ruined | -0.022 |
wy | -0.022 |
istered | -0.022 |
pain | -0.021 |
sting | -0.021 |
Token | oc |
Token ID | 420 |
Feature activation | +9.95e+00 |
Pos logit contributions | |
Suz | +0.038 |
Su | +0.037 |
Sus | +0.036 |
Mill | +0.036 |
Alf | +0.034 |
Neg logit contributions | |
ruined | -0.065 |
wy | -0.064 |
ggy | -0.064 |
sharp | -0.063 |
ggie | -0.062 |
Token | eros |
Token ID | 27498 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
Suz | +0.223 |
Su | +0.218 |
Sus | +0.215 |
Mill | +0.214 |
Ally | +0.205 |
Neg logit contributions | |
wy | -0.210 |
ps | -0.208 |
ruined | -0.207 |
ggy | -0.206 |
burns | -0.203 |
Token | . |
Token ID | 13 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
Suz | +0.041 |
Su | +0.040 |
Sus | +0.040 |
Mill | +0.040 |
Alf | +0.039 |
Neg logit contributions | |
ruined | -0.028 |
wy | -0.027 |
ggy | -0.026 |
sharp | -0.026 |
ggie | -0.025 |
Token | They |
Token ID | 1119 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
Suz | +0.019 |
Su | +0.019 |
Mill | +0.018 |
Sus | +0.018 |
Alf | +0.018 |
Neg logit contributions | |
ruined | -0.031 |
wy | -0.031 |
ggy | -0.030 |
sharp | -0.030 |
istered | -0.029 |
Token | looked |
Token ID | 3114 |
Feature activation | -3.45e+00 |
Pos logit contributions | |
wy | +0.028 |
uch | +0.027 |
arest | +0.026 |
ggie | +0.026 |
istered | +0.026 |
Neg logit contributions | |
Suz | -0.028 |
Alf | -0.028 |
Su | -0.028 |
Sus | -0.027 |
Mill | -0.027 |
Token | for |
Token ID | 329 |
Feature activation | -7.42e-01 |
Pos logit contributions | |
wy | +0.081 |
ruined | +0.081 |
ggy | +0.078 |
ggie | +0.076 |
sharp | +0.076 |
Neg logit contributions | |
Suz | -0.067 |
Su | -0.066 |
Mill | -0.066 |
Sus | -0.065 |
Alf | -0.064 |
Token | will |
Token ID | 481 |
Feature activation | -2.59e+00 |
Pos logit contributions | |
ggy | +0.037 |
wy | +0.036 |
ggie | +0.036 |
kin | +0.035 |
uch | +0.035 |
Neg logit contributions | |
Su | -0.053 |
Alf | -0.052 |
Suz | -0.052 |
Sus | -0.051 |
Mill | -0.051 |
Token | visit |
Token ID | 3187 |
Feature activation | +2.60e+00 |
Pos logit contributions | |
wy | +0.049 |
ruined | +0.046 |
istered | +0.046 |
ggy | +0.043 |
uch | +0.043 |
Neg logit contributions | |
Suz | -0.063 |
Su | -0.063 |
Mill | -0.063 |
Alf | -0.062 |
Sus | -0.062 |
Token | the |
Token ID | 262 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
Suz | +0.065 |
Su | +0.062 |
Mill | +0.060 |
Hil | +0.059 |
Sus | +0.059 |
Neg logit contributions | |
ruined | -0.048 |
sharp | -0.047 |
bad | -0.046 |
hurt | -0.046 |
ggy | -0.045 |
Token | rh |
Token ID | 9529 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
Suz | +0.028 |
Su | +0.028 |
Mill | +0.027 |
Sus | +0.027 |
Alf | +0.025 |
Neg logit contributions | |
ruined | -0.029 |
sharp | -0.028 |
wy | -0.028 |
ggy | -0.027 |
bad | -0.027 |
Token | in |
Token ID | 259 |
Feature activation | +2.42e+00 |
Pos logit contributions | |
Alf | +0.041 |
Suz | +0.040 |
Su | +0.040 |
Sus | +0.039 |
Mill | +0.039 |
Neg logit contributions | |
ruined | -0.029 |
wy | -0.028 |
pain | -0.028 |
istered | -0.028 |
sting | -0.028 |
Token | oc |
Token ID | 420 |
Feature activation | +9.92e+00 |
Pos logit contributions | |
Suz | +0.059 |
Su | +0.058 |
Sus | +0.058 |
Mill | +0.056 |
Jan | +0.052 |
Neg logit contributions | |
ggy | -0.049 |
ruined | -0.048 |
ggie | -0.047 |
wy | -0.046 |
hurt | -0.046 |
Token | eros |
Token ID | 27498 |
Feature activation | +2.03e+00 |
Pos logit contributions | |
Suz | +0.245 |
Su | +0.242 |
Sus | +0.235 |
Mill | +0.235 |
Ally | +0.227 |
Neg logit contributions | |
wy | -0.195 |
ggy | -0.190 |
ps | -0.189 |
ruined | -0.186 |
ggie | -0.185 |
Token | at |
Token ID | 379 |
Feature activation | +2.92e+00 |
Pos logit contributions | |
Suz | +0.055 |
Su | +0.055 |
Sus | +0.053 |
Mill | +0.053 |
Jan | +0.050 |
Neg logit contributions | |
ruined | -0.034 |
ggy | -0.033 |
wy | -0.033 |
ggie | -0.033 |
sharp | -0.032 |
Token | the |
Token ID | 262 |
Feature activation | +8.46e-01 |
Pos logit contributions | |
Suz | +0.069 |
Su | +0.067 |
Sus | +0.065 |
Mill | +0.064 |
iked | +0.062 |
Neg logit contributions | |
ruined | -0.057 |
sharp | -0.055 |
bad | -0.054 |
big | -0.054 |
hurt | -0.054 |
Token | zoo |
Token ID | 26626 |
Feature activation | +3.04e+00 |
Pos logit contributions | |
Suz | +0.014 |
Su | +0.014 |
Mill | +0.014 |
Sus | +0.014 |
Alf | +0.013 |
Neg logit contributions | |
ruined | -0.022 |
wy | -0.022 |
ggy | -0.021 |
sharp | -0.021 |
ggie | -0.021 |
Token | . |
Token ID | 13 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
Suz | +0.098 |
Su | +0.095 |
Mill | +0.095 |
Sus | +0.094 |
Jan | +0.089 |
Neg logit contributions | |
ruined | -0.037 |
ggy | -0.037 |
ggie | -0.035 |
sharp | -0.033 |
bad | -0.033 |
Token | . |
Token ID | 13 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
Suz | +0.010 |
Su | +0.010 |
Sus | +0.010 |
Mill | +0.010 |
Alf | +0.010 |
Neg logit contributions | |
ruined | -0.009 |
ggy | -0.009 |
sharp | -0.009 |
wy | -0.009 |
hurt | -0.009 |
Token | He |
Token ID | 679 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
Suz | +0.003 |
Alf | +0.003 |
line | +0.003 |
Su | +0.003 |
cities | +0.003 |
Neg logit contributions | |
pain | -0.004 |
ggy | -0.003 |
ruined | -0.003 |
ggie | -0.003 |
sharp | -0.003 |
Token | was |
Token ID | 373 |
Feature activation | -7.12e+00 |
Pos logit contributions | |
istered | +0.040 |
wy | +0.039 |
Deal | +0.038 |
arest | +0.038 |
ruined | +0.037 |
Neg logit contributions | |
Suz | -0.033 |
Su | -0.032 |
Sus | -0.032 |
Mill | -0.032 |
Alf | -0.031 |
Token | a |
Token ID | 257 |
Feature activation | -6.20e+00 |
Pos logit contributions | |
ruined | +0.086 |
wy | +0.086 |
ggy | +0.079 |
sharp | +0.077 |
istered | +0.076 |
Neg logit contributions | |
Suz | -0.220 |
Su | -0.218 |
Mill | -0.216 |
Sus | -0.215 |
Alf | -0.212 |
Token | mis |
Token ID | 2984 |
Feature activation | -3.93e+00 |
Pos logit contributions | |
wy | +0.075 |
ruined | +0.072 |
ggy | +0.067 |
ps | +0.065 |
istered | +0.065 |
Neg logit contributions | |
Suz | -0.191 |
Su | -0.190 |
Mill | -0.188 |
Sus | -0.188 |
Alf | -0.184 |
Token | chie |
Token ID | 3043 |
Feature activation | -8.90e+00 |
Pos logit contributions | |
wy | +0.066 |
ruined | +0.065 |
ggy | +0.062 |
sharp | +0.062 |
istered | +0.062 |
Neg logit contributions | |
Suz | -0.100 |
Su | -0.100 |
Mill | -0.099 |
Sus | -0.098 |
Alf | -0.098 |
Token | vous |
Token ID | 31222 |
Feature activation | -2.89e+00 |
Pos logit contributions | |
ggy | +0.112 |
wy | +0.111 |
ruined | +0.110 |
ggie | +0.105 |
sharp | +0.104 |
Neg logit contributions | |
Suz | -0.264 |
Mill | -0.262 |
Su | -0.261 |
Sus | -0.259 |
Alf | -0.259 |
Token | little |
Token ID | 1310 |
Feature activation | +7.00e-01 |
Pos logit contributions | |
ruined | +0.054 |
sharp | +0.053 |
wy | +0.051 |
ggy | +0.051 |
pain | +0.051 |
Neg logit contributions | |
Suz | -0.069 |
Su | -0.067 |
Mill | -0.067 |
Alf | -0.066 |
Sus | -0.066 |
Token | baby |
Token ID | 5156 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
Suz | +0.015 |
Su | +0.015 |
Mill | +0.015 |
Sus | +0.014 |
Alf | +0.014 |
Neg logit contributions | |
ruined | -0.015 |
sharp | -0.015 |
wy | -0.014 |
hurt | -0.014 |
bad | -0.014 |
Token | and |
Token ID | 290 |
Feature activation | +4.00e+00 |
Pos logit contributions | |
Suz | +0.006 |
Su | +0.006 |
Mill | +0.006 |
Alf | +0.006 |
Sus | +0.006 |
Neg logit contributions | |
ruined | -0.003 |
ggy | -0.003 |
sharp | -0.003 |
hurt | -0.003 |
wy | -0.003 |
Token | always |
Token ID | 1464 |
Feature activation | -6.96e-02 |
Pos logit contributions | |
Suz | +0.099 |
Su | +0.099 |
Mill | +0.097 |
Sus | +0.097 |
Alf | +0.095 |
Neg logit contributions | |
wy | -0.072 |
ruined | -0.072 |
ggy | -0.068 |
istered | -0.068 |
sharp | -0.066 |
Token | , |
Token ID | 11 |
Feature activation | +4.67e+00 |
Pos logit contributions | |
wy | +0.023 |
ruined | +0.023 |
ggy | +0.022 |
istered | +0.021 |
uch | +0.021 |
Neg logit contributions | |
Suz | -0.021 |
Su | -0.021 |
Sus | -0.020 |
Mill | -0.020 |
Alf | -0.020 |
Token | but |
Token ID | 475 |
Feature activation | +5.73e+00 |
Pos logit contributions | |
Suz | +0.084 |
Su | +0.083 |
Mill | +0.082 |
Sus | +0.081 |
Alf | +0.079 |
Neg logit contributions | |
ruined | -0.117 |
wy | -0.116 |
ggy | -0.113 |
sharp | -0.111 |
istered | -0.110 |
Token | it |
Token ID | 340 |
Feature activation | -2.49e+00 |
Pos logit contributions | |
Suz | +0.109 |
Su | +0.108 |
Mill | +0.106 |
Sus | +0.104 |
Alf | +0.102 |
Neg logit contributions | |
ruined | -0.139 |
wy | -0.135 |
sharp | -0.134 |
ggy | -0.131 |
burns | -0.129 |
Token | didn |
Token ID | 1422 |
Feature activation | -6.58e+00 |
Pos logit contributions | |
wy | +0.053 |
istered | +0.051 |
arest | +0.050 |
Deal | +0.050 |
ggie | +0.047 |
Neg logit contributions | |
Suz | -0.056 |
Su | -0.052 |
Sus | -0.052 |
Mill | -0.051 |
Jan | -0.051 |
Token | 't |
Token ID | 470 |
Feature activation | -4.45e+00 |
Pos logit contributions | |
wy | +0.145 |
istered | +0.132 |
ruined | +0.129 |
tricked | +0.120 |
aky | +0.119 |
Neg logit contributions | |
Suz | -0.145 |
Su | -0.143 |
Sus | -0.142 |
Alf | -0.141 |
Mill | -0.141 |
Token | seem |
Token ID | 1283 |
Feature activation | -8.65e+00 |
Pos logit contributions | |
wy | +0.092 |
ggy | +0.089 |
ggie | +0.087 |
istered | +0.087 |
ruined | +0.085 |
Neg logit contributions | |
Suz | -0.103 |
Sus | -0.100 |
Su | -0.099 |
Mill | -0.099 |
Alf | -0.098 |
Token | to |
Token ID | 284 |
Feature activation | -2.34e+00 |
Pos logit contributions | |
wy | +0.192 |
ggy | +0.186 |
uch | +0.183 |
ggie | +0.180 |
ruined | +0.175 |
Neg logit contributions | |
Su | -0.184 |
Suz | -0.183 |
Sus | -0.183 |
Mill | -0.181 |
Alf | -0.172 |
Token | work |
Token ID | 670 |
Feature activation | -3.47e+00 |
Pos logit contributions | |
wy | +0.049 |
istered | +0.048 |
ggy | +0.045 |
ggie | +0.044 |
ruined | +0.043 |
Neg logit contributions | |
Suz | -0.053 |
Sus | -0.052 |
Mill | -0.050 |
Su | -0.050 |
Alf | -0.048 |
Token | . |
Token ID | 13 |
Feature activation | +1.73e+00 |
Pos logit contributions | |
wy | +0.069 |
uch | +0.068 |
sting | +0.068 |
ggy | +0.068 |
istered | +0.068 |
Neg logit contributions | |
Sus | -0.077 |
Su | -0.076 |
Suz | -0.073 |
Mill | -0.073 |
Alf | -0.072 |
Token | He |
Token ID | 679 |
Feature activation | -8.98e-01 |
Pos logit contributions | |
Suz | +0.037 |
Jos | +0.037 |
Su | +0.036 |
Hil | +0.036 |
Sus | +0.036 |
Neg logit contributions | |
sharp | -0.034 |
ggy | -0.034 |
ggie | -0.033 |
burns | -0.032 |
big | -0.031 |
Token | got |
Token ID | 1392 |
Feature activation | -3.51e+00 |
Pos logit contributions | |
istered | +0.019 |
wy | +0.018 |
arest | +0.018 |
Deal | +0.017 |
vern | +0.017 |
Neg logit contributions | |
Suz | -0.020 |
Su | -0.019 |
Sus | -0.019 |
Alf | -0.018 |
Mill | -0.018 |
Token | , |
Token ID | 11 |
Feature activation | +4.26e+00 |
Pos logit contributions | |
Suz | +0.050 |
Su | +0.050 |
Mill | +0.048 |
Sus | +0.048 |
Alf | +0.048 |
Neg logit contributions | |
ruined | -0.032 |
sharp | -0.032 |
wy | -0.031 |
ggy | -0.030 |
sting | -0.030 |
Token | but |
Token ID | 475 |
Feature activation | +5.31e+00 |
Pos logit contributions | |
Su | +0.105 |
Suz | +0.105 |
Alf | +0.105 |
Mill | +0.103 |
Sus | +0.100 |
Neg logit contributions | |
ruined | -0.078 |
sharp | -0.078 |
hurt | -0.073 |
broken | -0.072 |
pain | -0.071 |
Token | it |
Token ID | 340 |
Feature activation | -2.56e+00 |
Pos logit contributions | |
Suz | +0.125 |
Su | +0.122 |
Alf | +0.122 |
Mill | +0.121 |
bank | +0.118 |
Neg logit contributions | |
ruined | -0.110 |
hurt | -0.104 |
bad | -0.102 |
sharp | -0.100 |
broken | -0.097 |
Token | didn |
Token ID | 1422 |
Feature activation | -6.86e+00 |
Pos logit contributions | |
wy | +0.052 |
istered | +0.048 |
arest | +0.047 |
ggy | +0.046 |
ruined | +0.046 |
Neg logit contributions | |
Suz | -0.060 |
Su | -0.057 |
Mill | -0.057 |
Sus | -0.057 |
Alf | -0.055 |
Token | 't |
Token ID | 470 |
Feature activation | -4.35e+00 |
Pos logit contributions | |
wy | +0.154 |
istered | +0.138 |
ruined | +0.131 |
tricked | +0.125 |
ery | +0.125 |
Neg logit contributions | |
Suz | -0.153 |
Su | -0.153 |
Sus | -0.152 |
Mill | -0.151 |
Alf | -0.146 |
Token | seem |
Token ID | 1283 |
Feature activation | -8.63e+00 |
Pos logit contributions | |
wy | +0.077 |
ggy | +0.073 |
ruined | +0.073 |
ggie | +0.071 |
istered | +0.071 |
Neg logit contributions | |
Suz | -0.113 |
Mill | -0.111 |
Sus | -0.111 |
Su | -0.111 |
Alf | -0.108 |
Token | to |
Token ID | 284 |
Feature activation | -2.30e+00 |
Pos logit contributions | |
wy | +0.157 |
ggy | +0.150 |
ruined | +0.145 |
ggie | +0.145 |
uch | +0.145 |
Neg logit contributions | |
Suz | -0.218 |
Su | -0.217 |
Mill | -0.216 |
Sus | -0.216 |
Alf | -0.207 |
Token | work |
Token ID | 670 |
Feature activation | -3.99e+00 |
Pos logit contributions | |
wy | +0.045 |
istered | +0.044 |
ggy | +0.043 |
ggie | +0.042 |
ruined | +0.040 |
Neg logit contributions | |
Suz | -0.056 |
Mill | -0.056 |
Sus | -0.055 |
Su | -0.054 |
Alf | -0.053 |
Token | . |
Token ID | 13 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
wy | +0.077 |
ggy | +0.073 |
ruined | +0.073 |
istered | +0.072 |
uch | +0.072 |
Neg logit contributions | |
Sus | -0.094 |
Su | -0.094 |
Suz | -0.093 |
Mill | -0.093 |
Alf | -0.089 |
Token | The |
Token ID | 383 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
Alf | +0.047 |
Suz | +0.046 |
Su | +0.045 |
cities | +0.045 |
aro | +0.044 |
Neg logit contributions | |
ruined | -0.029 |
sharp | -0.028 |
A | -0.028 |
two | -0.028 |
ripped | -0.028 |
Token | star |
Token ID | 3491 |
Feature activation | -6.33e-01 |
Pos logit contributions | |
Sus | +0.036 |
Alf | +0.036 |
Suz | +0.035 |
Mill | +0.035 |
Su | +0.034 |
Neg logit contributions | |
wy | -0.031 |
istered | -0.030 |
ruined | -0.027 |
ggy | -0.027 |
uch | -0.026 |
Token | didn |
Token ID | 1422 |
Feature activation | -6.49e+00 |
Pos logit contributions | |
Suz | +0.029 |
Su | +0.029 |
Mill | +0.028 |
Sus | +0.028 |
Alf | +0.028 |
Neg logit contributions | |
ruined | -0.026 |
wy | -0.026 |
sharp | -0.025 |
ggy | -0.025 |
burns | -0.024 |
Token | â |
Token ID | 22940 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
wy | +0.140 |
istered | +0.126 |
ruined | +0.122 |
aky | +0.114 |
sting | +0.113 |
Neg logit contributions | |
Sus | -0.149 |
Su | -0.148 |
Suz | -0.147 |
Mill | -0.146 |
Alf | -0.144 |
Token | € |
Token ID | 26391 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
Su | +0.030 |
Suz | +0.030 |
Mill | +0.029 |
Sus | +0.029 |
Alf | +0.028 |
Neg logit contributions | |
ruined | -0.028 |
wy | -0.027 |
sharp | -0.027 |
istered | -0.027 |
ggy | -0.026 |
Token | ™ |
Token ID | 8151 |
Feature activation | -2.55e+00 |
Pos logit contributions | |
ruined | +0.024 |
wy | +0.023 |
ggy | +0.022 |
sharp | +0.022 |
ggie | +0.022 |
Neg logit contributions | |
Suz | -0.035 |
Su | -0.035 |
Mill | -0.034 |
Sus | -0.034 |
Alf | -0.033 |
Token | t |
Token ID | 83 |
Feature activation | -4.08e+00 |
Pos logit contributions | |
ruined | +0.032 |
wy | +0.032 |
ggy | +0.030 |
sharp | +0.029 |
istered | +0.028 |
Neg logit contributions | |
Suz | -0.077 |
Su | -0.076 |
Mill | -0.075 |
Sus | -0.075 |
Alf | -0.074 |
Token | seem |
Token ID | 1283 |
Feature activation | -8.61e+00 |
Pos logit contributions | |
ruined | +0.069 |
wy | +0.069 |
ggy | +0.065 |
sharp | +0.064 |
istered | +0.063 |
Neg logit contributions | |
Suz | -0.107 |
Su | -0.105 |
Mill | -0.104 |
Sus | -0.104 |
Alf | -0.102 |
Token | to |
Token ID | 284 |
Feature activation | -2.30e+00 |
Pos logit contributions | |
wy | +0.162 |
ggy | +0.155 |
uch | +0.152 |
ggie | +0.149 |
ruined | +0.148 |
Neg logit contributions | |
Su | -0.212 |
Sus | -0.211 |
Suz | -0.210 |
Mill | -0.209 |
Alf | -0.201 |
Token | work |
Token ID | 670 |
Feature activation | -3.58e+00 |
Pos logit contributions | |
wy | +0.047 |
istered | +0.045 |
ggy | +0.043 |
ruined | +0.041 |
ggie | +0.041 |
Neg logit contributions | |
Sus | -0.054 |
Suz | -0.054 |
Mill | -0.054 |
Su | -0.053 |
Alf | -0.051 |
Token | . |
Token ID | 13 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
wy | +0.067 |
ruined | +0.064 |
ggy | +0.064 |
sting | +0.064 |
uch | +0.063 |
Neg logit contributions | |
Sus | -0.085 |
Su | -0.085 |
Suz | -0.084 |
Mill | -0.083 |
Alf | -0.081 |
Token |
|
Token ID | 198 |
Feature activation | -5.63e+00 |
Pos logit contributions | |
Suz | +0.030 |
Ally | +0.029 |
Mill | +0.029 |
Su | +0.029 |
ho | +0.028 |
Neg logit contributions | |
two | -0.017 |
A | -0.016 |
sharp | -0.015 |
Deal | -0.015 |
big | -0.015 |
Token |
|
Token ID | 198 |
Feature activation | -4.69e+00 |
Pos logit contributions | |
ggy | +0.105 |
ruined | +0.103 |
wy | +0.101 |
ggie | +0.100 |
sharp | +0.099 |
Neg logit contributions | |
Suz | -0.133 |
Su | -0.130 |
Mill | -0.130 |
Sus | -0.129 |
Alf | -0.126 |
Token | , |
Token ID | 11 |
Feature activation | +4.27e+00 |
Pos logit contributions | |
Suz | +0.011 |
Su | +0.011 |
Mill | +0.011 |
Sus | +0.011 |
Alf | +0.011 |
Neg logit contributions | |
ruined | -0.009 |
wy | -0.009 |
ggy | -0.008 |
sharp | -0.008 |
istered | -0.008 |
Token | but |
Token ID | 475 |
Feature activation | +5.34e+00 |
Pos logit contributions | |
Suz | +0.090 |
Su | +0.089 |
Mill | +0.088 |
Alf | +0.087 |
Sus | +0.087 |
Neg logit contributions | |
ruined | -0.094 |
sharp | -0.090 |
wy | -0.090 |
ggy | -0.086 |
sting | -0.086 |
Token | it |
Token ID | 340 |
Feature activation | -2.44e+00 |
Pos logit contributions | |
Suz | +0.093 |
Su | +0.092 |
Alf | +0.092 |
Mill | +0.090 |
Sus | +0.086 |
Neg logit contributions | |
ruined | -0.137 |
sharp | -0.128 |
wy | -0.127 |
hurt | -0.126 |
ggy | -0.125 |
Token | didn |
Token ID | 1422 |
Feature activation | -6.65e+00 |
Pos logit contributions | |
arest | +0.053 |
wy | +0.051 |
istered | +0.051 |
Deal | +0.050 |
ps | +0.050 |
Neg logit contributions | |
Suz | -0.052 |
Mill | -0.050 |
Su | -0.050 |
Sus | -0.050 |
Twe | -0.047 |
Token | 't |
Token ID | 470 |
Feature activation | -4.69e+00 |
Pos logit contributions | |
wy | +0.153 |
istered | +0.141 |
ruined | +0.131 |
aky | +0.129 |
ery | +0.129 |
Neg logit contributions | |
Su | -0.138 |
Suz | -0.137 |
Sus | -0.137 |
Twe | -0.137 |
Mill | -0.136 |
Token | seem |
Token ID | 1283 |
Feature activation | -8.61e+00 |
Pos logit contributions | |
wy | +0.083 |
ggy | +0.081 |
istered | +0.080 |
ggie | +0.079 |
ruined | +0.077 |
Neg logit contributions | |
Suz | -0.119 |
Sus | -0.117 |
Mill | -0.117 |
Su | -0.116 |
Alf | -0.111 |
Token | tasty |
Token ID | 25103 |
Feature activation | -1.71e+00 |
Pos logit contributions | |
wy | +0.154 |
ggy | +0.151 |
uch | +0.148 |
ggie | +0.145 |
istered | +0.140 |
Neg logit contributions | |
Su | -0.215 |
Sus | -0.214 |
Mill | -0.212 |
Suz | -0.211 |
Alf | -0.198 |
Token | to |
Token ID | 284 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
ruined | +0.032 |
wy | +0.032 |
ggy | +0.031 |
istered | +0.030 |
sharp | +0.030 |
Neg logit contributions | |
Su | -0.041 |
Suz | -0.041 |
Sus | -0.040 |
Mill | -0.040 |
Alf | -0.039 |
Token | her |
Token ID | 607 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
istered | +0.024 |
wy | +0.023 |
ruined | +0.022 |
ps | +0.022 |
ggy | +0.022 |
Neg logit contributions | |
Suz | -0.025 |
Su | -0.024 |
Mill | -0.024 |
Sus | -0.024 |
Twe | -0.022 |
Token | . |
Token ID | 13 |
Feature activation | +1.98e+00 |
Pos logit contributions | |
Suz | +0.036 |
Su | +0.036 |
Mill | +0.035 |
Sus | +0.035 |
Alf | +0.034 |
Neg logit contributions | |
wy | -0.027 |
ruined | -0.026 |
ggy | -0.024 |
istered | -0.024 |
sharp | -0.024 |
Token | She |
Token ID | 1375 |
Feature activation | -5.10e-01 |
Pos logit contributions | |
Alf | +0.045 |
Suz | +0.044 |
cities | +0.043 |
Su | +0.043 |
Mill | +0.043 |
Neg logit contributions | |
big | -0.033 |
ruined | -0.033 |
two | -0.031 |
bad | -0.031 |
sharp | -0.031 |
Token | didn |
Token ID | 1422 |
Feature activation | -5.36e+00 |
Pos logit contributions | |
wy | +0.036 |
istered | +0.034 |
ggy | +0.034 |
ruined | +0.034 |
ggie | +0.033 |
Neg logit contributions | |
Suz | -0.047 |
Mill | -0.046 |
Sus | -0.046 |
Su | -0.045 |
Alf | -0.045 |
Token | â |
Token ID | 22940 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
wy | +0.090 |
ruined | +0.079 |
istered | +0.077 |
ggy | +0.073 |
ggie | +0.072 |
Neg logit contributions | |
Suz | -0.152 |
Sus | -0.151 |
Mill | -0.150 |
Su | -0.150 |
Alf | -0.146 |
Token | € |
Token ID | 26391 |
Feature activation | -2.52e+00 |
Pos logit contributions | |
Suz | +0.032 |
Su | +0.032 |
Mill | +0.031 |
Sus | +0.031 |
Alf | +0.031 |
Neg logit contributions | |
ruined | -0.028 |
wy | -0.027 |
ggy | -0.026 |
sharp | -0.026 |
ggie | -0.026 |
Token | ™ |
Token ID | 8151 |
Feature activation | -3.63e+00 |
Pos logit contributions | |
ruined | +0.053 |
wy | +0.052 |
ggy | +0.051 |
sharp | +0.049 |
ggie | +0.049 |
Neg logit contributions | |
Suz | -0.056 |
Su | -0.055 |
Mill | -0.054 |
Sus | -0.054 |
Alf | -0.053 |
Token | t |
Token ID | 83 |
Feature activation | -5.05e+00 |
Pos logit contributions | |
ruined | +0.042 |
wy | +0.041 |
ggy | +0.039 |
uch | +0.037 |
ggie | +0.037 |
Neg logit contributions | |
Suz | -0.112 |
Mill | -0.111 |
Su | -0.110 |
Alf | -0.109 |
Sus | -0.109 |
Token | seem |
Token ID | 1283 |
Feature activation | -8.58e+00 |
Pos logit contributions | |
ruined | +0.081 |
wy | +0.078 |
sharp | +0.075 |
ggy | +0.074 |
pain | +0.073 |
Neg logit contributions | |
Suz | -0.136 |
Su | -0.134 |
Mill | -0.133 |
Sus | -0.132 |
Alf | -0.131 |
Token | to |
Token ID | 284 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
wy | +0.147 |
ruined | +0.140 |
ggy | +0.138 |
istered | +0.133 |
ggie | +0.133 |
Neg logit contributions | |
Suz | -0.224 |
Su | -0.223 |
Sus | -0.221 |
Mill | -0.220 |
Alf | -0.212 |
Token | be |
Token ID | 307 |
Feature activation | -4.41e+00 |
Pos logit contributions | |
wy | +0.026 |
istered | +0.025 |
ruined | +0.025 |
ggy | +0.024 |
sharp | +0.023 |
Neg logit contributions | |
Suz | -0.038 |
Su | -0.038 |
Sus | -0.038 |
Mill | -0.037 |
Alf | -0.036 |
Token | ending |
Token ID | 7464 |
Feature activation | -3.87e-01 |
Pos logit contributions | |
wy | +0.072 |
uch | +0.066 |
istered | +0.066 |
ggy | +0.065 |
ruined | +0.065 |
Neg logit contributions | |
Su | -0.120 |
Suz | -0.119 |
Sus | -0.118 |
Mill | -0.116 |
Alf | -0.110 |
Token | . |
Token ID | 13 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
wy | +0.007 |
ruined | +0.007 |
ggy | +0.007 |
sharp | +0.006 |
istered | +0.006 |
Neg logit contributions | |
Suz | -0.010 |
Su | -0.010 |
Mill | -0.009 |
Sus | -0.009 |
Alf | -0.009 |
Token | Diana |
Token ID | 25752 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
Suz | +0.026 |
cities | +0.026 |
Alf | +0.025 |
Mill | +0.025 |
Ally | +0.024 |
Neg logit contributions | |
ggy | -0.020 |
ruined | -0.019 |
ggie | -0.019 |
A | -0.018 |
Deal | -0.018 |
Token | answer |
Token ID | 3280 |
Feature activation | +3.56e-01 |
Pos logit contributions | |
wy | +0.078 |
istered | +0.077 |
ruined | +0.076 |
uch | +0.073 |
ggy | +0.072 |
Neg logit contributions | |
Suz | -0.105 |
Su | -0.101 |
Sus | -0.101 |
Mill | -0.100 |
Alf | -0.097 |
Token | , |
Token ID | 11 |
Feature activation | +2.91e+00 |
Pos logit contributions | |
Suz | +0.009 |
Mill | +0.009 |
Su | +0.009 |
Sus | +0.008 |
Alf | +0.008 |
Neg logit contributions | |
ruined | -0.006 |
sharp | -0.006 |
ggy | -0.006 |
ggie | -0.006 |
wy | -0.006 |
Token | but |
Token ID | 475 |
Feature activation | +4.05e+00 |
Pos logit contributions | |
Suz | +0.069 |
Sus | +0.067 |
Mill | +0.066 |
Su | +0.066 |
Alf | +0.065 |
Neg logit contributions | |
sharp | -0.054 |
ruined | -0.052 |
bad | -0.050 |
pain | -0.050 |
ggy | -0.050 |
Token | it |
Token ID | 340 |
Feature activation | -2.23e+00 |
Pos logit contributions | |
Suz | +0.062 |
Su | +0.061 |
Sus | +0.060 |
Mill | +0.059 |
Alf | +0.058 |
Neg logit contributions | |
ruined | -0.110 |
ggy | -0.108 |
wy | -0.108 |
sharp | -0.107 |
ggie | -0.106 |
Token | did |
Token ID | 750 |
Feature activation | -4.90e+00 |
Pos logit contributions | |
wy | +0.045 |
istered | +0.042 |
ruined | +0.041 |
arest | +0.040 |
uch | +0.040 |
Neg logit contributions | |
Suz | -0.053 |
Su | -0.050 |
Mill | -0.050 |
Sus | -0.050 |
Alf | -0.049 |
Token | seem |
Token ID | 1283 |
Feature activation | -8.56e+00 |
Pos logit contributions | |
wy | +0.070 |
istered | +0.057 |
uch | +0.054 |
ruined | +0.052 |
arest | +0.052 |
Neg logit contributions | |
Suz | -0.149 |
Mill | -0.146 |
Sus | -0.146 |
Su | -0.146 |
Alf | -0.145 |
Token | to |
Token ID | 284 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
wy | +0.137 |
ruined | +0.128 |
ggy | +0.127 |
uch | +0.126 |
istered | +0.123 |
Neg logit contributions | |
Suz | -0.236 |
Su | -0.235 |
Mill | -0.231 |
Sus | -0.231 |
Alf | -0.224 |
Token | move |
Token ID | 1445 |
Feature activation | +4.82e-01 |
Pos logit contributions | |
istered | +0.037 |
wy | +0.036 |
ruined | +0.033 |
uch | +0.033 |
arest | +0.033 |
Neg logit contributions | |
Suz | -0.040 |
Mill | -0.039 |
Su | -0.038 |
Sus | -0.038 |
Ally | -0.037 |
Token | away |
Token ID | 1497 |
Feature activation | +1.86e+00 |
Pos logit contributions | |
Suz | +0.012 |
Su | +0.012 |
Mill | +0.012 |
Sus | +0.012 |
Alf | +0.012 |
Neg logit contributions | |
ruined | -0.009 |
wy | -0.008 |
sharp | -0.008 |
ggy | -0.008 |
hurt | -0.008 |
Token | from |
Token ID | 422 |
Feature activation | +3.40e+00 |
Pos logit contributions | |
Suz | +0.044 |
Su | +0.044 |
Mill | +0.043 |
Sus | +0.043 |
Alf | +0.042 |
Neg logit contributions | |
ruined | -0.036 |
wy | -0.035 |
sharp | -0.034 |
ggy | -0.034 |
ggie | -0.033 |
Token | Bob |
Token ID | 5811 |
Feature activation | +2.55e+00 |
Pos logit contributions | |
Suz | +0.073 |
Su | +0.072 |
Mill | +0.071 |
Sus | +0.070 |
Alf | +0.069 |
Neg logit contributions | |
ruined | -0.073 |
wy | -0.072 |
sharp | -0.071 |
ggy | -0.070 |
pain | -0.068 |
Token | , |
Token ID | 11 |
Feature activation | +3.75e+00 |
Pos logit contributions | |
Su | +0.050 |
Suz | +0.048 |
Sus | +0.048 |
Alf | +0.047 |
Mill | +0.046 |
Neg logit contributions | |
ruined | -0.030 |
sharp | -0.030 |
wy | -0.028 |
ggy | -0.028 |
burns | -0.028 |
Token | but |
Token ID | 475 |
Feature activation | +5.13e+00 |
Pos logit contributions | |
Suz | +0.095 |
Su | +0.095 |
Alf | +0.093 |
Sus | +0.092 |
Mill | +0.092 |
Neg logit contributions | |
ruined | -0.068 |
sharp | -0.066 |
wy | -0.062 |
hurt | -0.061 |
sting | -0.060 |
Token | it |
Token ID | 340 |
Feature activation | -2.15e+00 |
Pos logit contributions | |
Su | +0.111 |
Suz | +0.110 |
Mill | +0.107 |
Sus | +0.105 |
Alf | +0.104 |
Neg logit contributions | |
ruined | -0.113 |
sharp | -0.108 |
hurt | -0.105 |
wy | -0.103 |
bad | -0.102 |
Token | didn |
Token ID | 1422 |
Feature activation | -6.53e+00 |
Pos logit contributions | |
wy | +0.040 |
ruined | +0.038 |
istered | +0.038 |
ggy | +0.037 |
ggie | +0.037 |
Neg logit contributions | |
Suz | -0.053 |
Su | -0.051 |
Mill | -0.051 |
Sus | -0.051 |
Alf | -0.050 |
Token | 't |
Token ID | 470 |
Feature activation | -4.24e+00 |
Pos logit contributions | |
wy | +0.146 |
istered | +0.132 |
ruined | +0.126 |
aky | +0.119 |
pain | +0.118 |
Neg logit contributions | |
Suz | -0.147 |
Su | -0.146 |
Sus | -0.146 |
Mill | -0.146 |
Alf | -0.142 |
Token | seem |
Token ID | 1283 |
Feature activation | -8.52e+00 |
Pos logit contributions | |
wy | +0.077 |
ggy | +0.073 |
ruined | +0.072 |
ggie | +0.071 |
istered | +0.071 |
Neg logit contributions | |
Suz | -0.109 |
Mill | -0.107 |
Sus | -0.106 |
Su | -0.106 |
Alf | -0.103 |
Token | to |
Token ID | 284 |
Feature activation | -2.20e+00 |
Pos logit contributions | |
wy | +0.191 |
ggy | +0.185 |
ggie | +0.180 |
uch | +0.179 |
ruined | +0.178 |
Neg logit contributions | |
Suz | -0.178 |
Su | -0.178 |
Mill | -0.178 |
Sus | -0.177 |
Alf | -0.166 |
Token | change |
Token ID | 1487 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
wy | +0.043 |
istered | +0.041 |
ggy | +0.039 |
ggie | +0.039 |
burns | +0.037 |
Neg logit contributions | |
Suz | -0.055 |
Mill | -0.055 |
Sus | -0.054 |
Su | -0.053 |
Alf | -0.050 |
Token | much |
Token ID | 881 |
Feature activation | -7.21e-01 |
Pos logit contributions | |
Suz | +0.004 |
Su | +0.004 |
Mill | +0.004 |
Sus | +0.004 |
Alf | +0.004 |
Neg logit contributions | |
wy | -0.003 |
ruined | -0.003 |
ggy | -0.003 |
ggie | -0.003 |
sharp | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
wy | +0.014 |
ggy | +0.014 |
ggie | +0.014 |
uch | +0.014 |
istered | +0.013 |
Neg logit contributions | |
Mill | -0.017 |
Suz | -0.017 |
Sus | -0.017 |
Su | -0.017 |
Alf | -0.016 |
Token |
|
Token ID | 198 |
Feature activation | -5.46e+00 |
Pos logit contributions | |
Suz | +0.036 |
Su | +0.035 |
Mill | +0.035 |
Ally | +0.034 |
Hil | +0.033 |
Neg logit contributions | |
two | -0.022 |
A | -0.021 |
sharp | -0.021 |
Luckily | -0.020 |
big | -0.020 |
Token | . |
Token ID | 13 |
Feature activation | +2.54e+00 |
Pos logit contributions | |
Su | +0.055 |
Suz | +0.055 |
Sus | +0.053 |
Mill | +0.052 |
Cr | +0.051 |
Neg logit contributions | |
ruined | -0.027 |
sharp | -0.027 |
ggy | -0.026 |
big | -0.025 |
hurt | -0.025 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -4.93e+00 |
Pos logit contributions | |
Suz | +0.061 |
Su | +0.061 |
Sus | +0.060 |
cities | +0.060 |
Jos | +0.058 |
Neg logit contributions | |
ggy | -0.035 |
ching | -0.035 |
two | -0.033 |
ggie | -0.033 |
pain | -0.033 |
Token | Joe |
Token ID | 19585 |
Feature activation | -6.59e-01 |
Pos logit contributions | |
ruined | +0.093 |
wy | +0.091 |
ggy | +0.089 |
sharp | +0.086 |
ggie | +0.085 |
Neg logit contributions | |
Suz | -0.115 |
Su | -0.113 |
Mill | -0.112 |
Sus | -0.111 |
Alf | -0.109 |
Token | y |
Token ID | 88 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
ruined | +0.013 |
wy | +0.012 |
sharp | +0.012 |
ggy | +0.012 |
burns | +0.011 |
Neg logit contributions | |
Suz | -0.016 |
Su | -0.015 |
Mill | -0.015 |
Sus | -0.015 |
Alf | -0.015 |
Token | had |
Token ID | 550 |
Feature activation | -5.45e+00 |
Pos logit contributions | |
ruined | +0.023 |
wy | +0.021 |
ggy | +0.021 |
sharp | +0.021 |
ggie | +0.020 |
Neg logit contributions | |
Suz | -0.032 |
Su | -0.032 |
Mill | -0.031 |
Sus | -0.031 |
Alf | -0.031 |
Token | been |
Token ID | 587 |
Feature activation | -8.49e+00 |
Pos logit contributions | |
wy | +0.071 |
istered | +0.067 |
sting | +0.066 |
ggy | +0.065 |
ruined | +0.064 |
Neg logit contributions | |
Su | -0.169 |
Sus | -0.167 |
Suz | -0.165 |
Mill | -0.164 |
Alf | -0.158 |
Token | a |
Token ID | 257 |
Feature activation | -6.88e+00 |
Pos logit contributions | |
ruined | +0.172 |
wy | +0.169 |
ggy | +0.163 |
sharp | +0.161 |
istered | +0.158 |
Neg logit contributions | |
Suz | -0.193 |
Su | -0.191 |
Mill | -0.188 |
Sus | -0.187 |
Alf | -0.184 |
Token | very |
Token ID | 845 |
Feature activation | -5.82e+00 |
Pos logit contributions | |
ruined | +0.107 |
wy | +0.107 |
ggy | +0.101 |
sharp | +0.098 |
istered | +0.097 |
Neg logit contributions | |
Suz | -0.187 |
Su | -0.186 |
Mill | -0.184 |
Sus | -0.183 |
Alf | -0.180 |
Token | obedient |
Token ID | 41652 |
Feature activation | +2.53e-01 |
Pos logit contributions | |
wy | +0.093 |
ruined | +0.090 |
ps | +0.085 |
ggy | +0.084 |
istered | +0.083 |
Neg logit contributions | |
Suz | -0.157 |
Su | -0.156 |
Sus | -0.156 |
Mill | -0.154 |
Alf | -0.147 |
Token | boy |
Token ID | 2933 |
Feature activation | -2.79e+00 |
Pos logit contributions | |
Suz | +0.007 |
Su | +0.007 |
Mill | +0.006 |
Alf | +0.006 |
Sus | +0.006 |
Neg logit contributions | |
ruined | -0.004 |
sharp | -0.004 |
pain | -0.004 |
ggy | -0.004 |
wy | -0.004 |
Token | yesterday |
Token ID | 7415 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
ggie | +0.035 |
ggy | +0.035 |
ruined | +0.034 |
sharp | +0.032 |
wy | +0.031 |
Neg logit contributions | |
Suz | -0.084 |
Su | -0.081 |
Mill | -0.081 |
Alf | -0.079 |
Sus | -0.079 |
Token | , |
Token ID | 11 |
Feature activation | +4.67e+00 |
Pos logit contributions | |
wy | +0.015 |
ruined | +0.014 |
ggy | +0.014 |
istered | +0.014 |
ggie | +0.014 |
Neg logit contributions | |
Suz | -0.018 |
Mill | -0.018 |
Sus | -0.017 |
Su | -0.017 |
Alf | -0.017 |
Token | but |
Token ID | 475 |
Feature activation | +5.63e+00 |
Pos logit contributions | |
Suz | +0.109 |
Su | +0.108 |
Mill | +0.106 |
Sus | +0.105 |
Alf | +0.104 |
Neg logit contributions | |
ruined | -0.092 |
sharp | -0.088 |
wy | -0.086 |
ggy | -0.084 |
hurt | -0.084 |
Token | it |
Token ID | 340 |
Feature activation | -2.12e+00 |
Pos logit contributions | |
Alf | +0.113 |
Mill | +0.110 |
Su | +0.106 |
Suz | +0.104 |
Ally | +0.104 |
Neg logit contributions | |
sharp | -0.121 |
ruined | -0.120 |
bad | -0.114 |
hurt | -0.113 |
naughty | -0.113 |
Token | didn |
Token ID | 1422 |
Feature activation | -6.52e+00 |
Pos logit contributions | |
wy | +0.045 |
istered | +0.043 |
arest | +0.041 |
Deal | +0.041 |
ps | +0.040 |
Neg logit contributions | |
Suz | -0.049 |
Mill | -0.046 |
Sus | -0.046 |
Su | -0.046 |
Alf | -0.045 |
Token | 't |
Token ID | 470 |
Feature activation | -4.13e+00 |
Pos logit contributions | |
wy | +0.160 |
istered | +0.142 |
ruined | +0.137 |
aky | +0.134 |
kin | +0.129 |
Neg logit contributions | |
Suz | -0.135 |
Mill | -0.135 |
Su | -0.133 |
Sus | -0.133 |
Alf | -0.127 |
Token | seem |
Token ID | 1283 |
Feature activation | -8.48e+00 |
Pos logit contributions | |
wy | +0.078 |
uch | +0.072 |
istered | +0.071 |
ggy | +0.071 |
ruined | +0.070 |
Neg logit contributions | |
Suz | -0.108 |
Mill | -0.106 |
Sus | -0.105 |
Su | -0.104 |
Alf | -0.102 |
Token | to |
Token ID | 284 |
Feature activation | -2.24e+00 |
Pos logit contributions | |
wy | +0.190 |
ggy | +0.180 |
uch | +0.179 |
ruined | +0.176 |
ggie | +0.175 |
Neg logit contributions | |
Su | -0.180 |
Suz | -0.179 |
Mill | -0.178 |
Sus | -0.177 |
Alf | -0.169 |
Token | notice |
Token ID | 4003 |
Feature activation | +2.54e+00 |
Pos logit contributions | |
wy | +0.046 |
istered | +0.045 |
uch | +0.041 |
ggy | +0.041 |
ruined | +0.041 |
Neg logit contributions | |
Suz | -0.053 |
Mill | -0.052 |
Sus | -0.052 |
Su | -0.052 |
Alf | -0.050 |
Token | anything |
Token ID | 1997 |
Feature activation | -3.04e+00 |
Pos logit contributions | |
Suz | +0.063 |
Mill | +0.062 |
Su | +0.062 |
Alf | +0.062 |
Sus | +0.061 |
Neg logit contributions | |
ruined | -0.045 |
sharp | -0.043 |
wy | -0.041 |
ggy | -0.040 |
pain | -0.040 |
Token | . |
Token ID | 13 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
wy | +0.060 |
uch | +0.055 |
ruined | +0.052 |
ggy | +0.052 |
istered | +0.052 |
Neg logit contributions | |
Suz | -0.073 |
Sus | -0.073 |
Su | -0.073 |
Mill | -0.073 |
Alf | -0.069 |
Token | Sandy |
Token ID | 17581 |
Feature activation | -5.89e-01 |
Pos logit contributions | |
cities | +0.027 |
Alf | +0.027 |
Mill | +0.026 |
Ally | +0.025 |
stack | +0.025 |
Neg logit contributions | |
big | -0.023 |
A | -0.023 |
two | -0.023 |
sharp | -0.023 |
Luckily | -0.022 |
Token | " |
Token ID | 366 |
Feature activation | -5.13e-01 |
Pos logit contributions | |
cities | +0.073 |
iked | +0.068 |
Suz | +0.068 |
Su | +0.068 |
ress | +0.068 |
Neg logit contributions | |
not | -0.075 |
sharp | -0.075 |
ruined | -0.073 |
hurt | -0.073 |
big | -0.072 |
Token | Yes |
Token ID | 5297 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
ruined | +0.007 |
wy | +0.007 |
ggy | +0.007 |
ggie | +0.007 |
uch | +0.007 |
Neg logit contributions | |
Alf | -0.014 |
Su | -0.014 |
Suz | -0.014 |
Mill | -0.014 |
Sus | -0.014 |
Token | , |
Token ID | 11 |
Feature activation | +2.09e+00 |
Pos logit contributions | |
ruined | +0.003 |
wy | +0.003 |
ggy | +0.003 |
sharp | +0.003 |
ggie | +0.003 |
Neg logit contributions | |
Suz | -0.003 |
Su | -0.003 |
Mill | -0.003 |
Sus | -0.003 |
Alf | -0.003 |
Token | it |
Token ID | 340 |
Feature activation | -2.79e+00 |
Pos logit contributions | |
Suz | +0.045 |
Alf | +0.045 |
Su | +0.045 |
Mill | +0.044 |
bank | +0.044 |
Neg logit contributions | |
ruined | -0.042 |
sharp | -0.040 |
ggy | -0.038 |
bad | -0.037 |
ggie | -0.037 |
Token | does |
Token ID | 857 |
Feature activation | -4.36e+00 |
Pos logit contributions | |
wy | +0.052 |
istered | +0.048 |
ruined | +0.047 |
sharp | +0.046 |
ggy | +0.046 |
Neg logit contributions | |
Suz | -0.069 |
Mill | -0.067 |
Sus | -0.066 |
Su | -0.066 |
Alf | -0.064 |
Token | seem |
Token ID | 1283 |
Feature activation | -8.47e+00 |
Pos logit contributions | |
wy | +0.086 |
ruined | +0.080 |
istered | +0.077 |
uch | +0.073 |
burns | +0.072 |
Neg logit contributions | |
Suz | -0.108 |
Su | -0.106 |
Mill | -0.106 |
Sus | -0.106 |
Alf | -0.103 |
Token | friendly |
Token ID | 8030 |
Feature activation | -1.80e-01 |
Pos logit contributions | |
wy | +0.140 |
ggy | +0.129 |
istered | +0.128 |
uch | +0.126 |
ruined | +0.126 |
Neg logit contributions | |
Suz | -0.230 |
Su | -0.229 |
Mill | -0.229 |
Sus | -0.228 |
Alf | -0.218 |
Token | . |
Token ID | 13 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
ruined | +0.003 |
wy | +0.003 |
ggy | +0.003 |
sharp | +0.003 |
ggie | +0.003 |
Neg logit contributions | |
Suz | -0.005 |
Su | -0.005 |
Mill | -0.005 |
Sus | -0.005 |
Alf | -0.005 |
Token | But |
Token ID | 887 |
Feature activation | +3.67e+00 |
Pos logit contributions | |
Su | +0.035 |
Suz | +0.034 |
Mill | +0.033 |
Sus | +0.033 |
Alf | +0.033 |
Neg logit contributions | |
ggy | -0.027 |
ggie | -0.027 |
Deal | -0.026 |
A | -0.026 |
sharp | -0.026 |
Token | we |
Token ID | 356 |
Feature activation | -2.28e+00 |
Pos logit contributions | |
Su | +0.094 |
Suz | +0.093 |
Mill | +0.091 |
Alf | +0.091 |
Sus | +0.090 |
Neg logit contributions | |
ruined | -0.063 |
sharp | -0.059 |
wy | -0.058 |
ggy | -0.057 |
sting | -0.057 |
Token | have |
Token ID | 423 |
Feature activation | -5.22e+00 |
Pos logit contributions | |
istered | +0.042 |
ggy | +0.041 |
wy | +0.041 |
ggie | +0.040 |
burns | +0.037 |
Neg logit contributions | |
Suz | -0.056 |
Mill | -0.056 |
Su | -0.055 |
Sus | -0.054 |
Alf | -0.053 |
Token | , |
Token ID | 11 |
Feature activation | +2.51e+00 |
Pos logit contributions | |
ruined | +0.032 |
sharp | +0.032 |
ggy | +0.031 |
wy | +0.031 |
ggie | +0.030 |
Neg logit contributions | |
Suz | -0.038 |
Su | -0.037 |
Mill | -0.036 |
Sus | -0.036 |
Alf | -0.035 |
Token | but |
Token ID | 475 |
Feature activation | +4.55e+00 |
Pos logit contributions | |
Suz | +0.063 |
Mill | +0.063 |
Su | +0.061 |
Sus | +0.060 |
Ally | +0.058 |
Neg logit contributions | |
sharp | -0.048 |
ruined | -0.045 |
hurt | -0.045 |
bad | -0.045 |
pain | -0.045 |
Token | he |
Token ID | 339 |
Feature activation | -2.12e+00 |
Pos logit contributions | |
Suz | +0.098 |
Mill | +0.098 |
Su | +0.097 |
Sus | +0.093 |
Ally | +0.090 |
Neg logit contributions | |
ruined | -0.103 |
sharp | -0.099 |
hurt | -0.098 |
bad | -0.096 |
pain | -0.094 |
Token | didn |
Token ID | 1422 |
Feature activation | -7.51e+00 |
Pos logit contributions | |
wy | +0.042 |
istered | +0.041 |
ps | +0.039 |
ruined | +0.039 |
burns | +0.039 |
Neg logit contributions | |
Suz | -0.049 |
Su | -0.049 |
Sus | -0.047 |
Mill | -0.046 |
Alf | -0.046 |
Token | 't |
Token ID | 470 |
Feature activation | -4.44e+00 |
Pos logit contributions | |
wy | +0.174 |
istered | +0.160 |
ruined | +0.152 |
sting | +0.144 |
ery | +0.143 |
Neg logit contributions | |
Su | -0.165 |
Sus | -0.159 |
Suz | -0.157 |
Alf | -0.154 |
Jan | -0.151 |
Token | seem |
Token ID | 1283 |
Feature activation | -8.46e+00 |
Pos logit contributions | |
wy | +0.076 |
ruined | +0.074 |
istered | +0.073 |
ggy | +0.071 |
burns | +0.070 |
Neg logit contributions | |
Su | -0.114 |
Suz | -0.113 |
Sus | -0.111 |
Mill | -0.110 |
Alf | -0.108 |
Token | to |
Token ID | 284 |
Feature activation | -2.72e+00 |
Pos logit contributions | |
wy | +0.192 |
ggy | +0.183 |
uch | +0.182 |
ruined | +0.182 |
istered | +0.179 |
Neg logit contributions | |
Su | -0.173 |
Suz | -0.168 |
Sus | -0.168 |
Mill | -0.165 |
Alf | -0.159 |
Token | win |
Token ID | 1592 |
Feature activation | -4.44e+00 |
Pos logit contributions | |
istered | +0.052 |
wy | +0.052 |
burns | +0.049 |
ruined | +0.047 |
ery | +0.046 |
Neg logit contributions | |
Su | -0.062 |
Sus | -0.062 |
Suz | -0.060 |
J | -0.060 |
Alf | -0.059 |
Token | very |
Token ID | 845 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
wy | +0.097 |
istered | +0.093 |
ruined | +0.090 |
uch | +0.090 |
burns | +0.089 |
Neg logit contributions | |
Su | -0.096 |
Sus | -0.094 |
Suz | -0.094 |
Alf | -0.091 |
Mill | -0.090 |
Token | often |
Token ID | 1690 |
Feature activation | +8.81e-01 |
Pos logit contributions | |
wy | +0.026 |
ruined | +0.024 |
istered | +0.023 |
burns | +0.023 |
uch | +0.023 |
Neg logit contributions | |
Su | -0.039 |
Sus | -0.039 |
J | -0.038 |
Suz | -0.038 |
Alf | -0.037 |
Token | . |
Token ID | 13 |
Feature activation | +5.57e-01 |
Pos logit contributions | |
Suz | +0.024 |
Su | +0.024 |
Mill | +0.024 |
Sus | +0.023 |
Alf | +0.023 |
Neg logit contributions | |
ruined | -0.014 |
wy | -0.014 |
ggy | -0.013 |
sharp | -0.013 |
ggie | -0.012 |
Token | , |
Token ID | 11 |
Feature activation | +4.43e+00 |
Pos logit contributions | |
wy | +0.005 |
ruined | +0.005 |
ggy | +0.005 |
burns | +0.005 |
istered | +0.005 |
Neg logit contributions | |
Suz | -0.005 |
Su | -0.005 |
Mill | -0.005 |
Sus | -0.005 |
Alf | -0.005 |
Token | but |
Token ID | 475 |
Feature activation | +6.11e+00 |
Pos logit contributions | |
Suz | +0.120 |
Su | +0.120 |
Sus | +0.119 |
Mill | +0.118 |
Alf | +0.117 |
Neg logit contributions | |
sharp | -0.075 |
hurt | -0.072 |
not | -0.068 |
sting | -0.068 |
ruined | -0.068 |
Token | it |
Token ID | 340 |
Feature activation | -2.11e+00 |
Pos logit contributions | |
Alf | +0.140 |
Suz | +0.138 |
Mill | +0.138 |
Su | +0.134 |
Hil | +0.131 |
Neg logit contributions | |
ruined | -0.127 |
hurt | -0.120 |
bad | -0.118 |
sharp | -0.115 |
pain | -0.112 |
Token | didn |
Token ID | 1422 |
Feature activation | -6.52e+00 |
Pos logit contributions | |
wy | +0.043 |
istered | +0.041 |
arest | +0.039 |
Deal | +0.038 |
ruined | +0.038 |
Neg logit contributions | |
Suz | -0.049 |
Su | -0.047 |
Mill | -0.046 |
Sus | -0.046 |
Alf | -0.045 |
Token | 't |
Token ID | 470 |
Feature activation | -3.99e+00 |
Pos logit contributions | |
wy | +0.149 |
istered | +0.130 |
ruined | +0.125 |
ery | +0.123 |
aky | +0.120 |
Neg logit contributions | |
Su | -0.152 |
Suz | -0.151 |
Sus | -0.148 |
Mill | -0.147 |
Twe | -0.142 |
Token | seem |
Token ID | 1283 |
Feature activation | -8.40e+00 |
Pos logit contributions | |
wy | +0.067 |
ruined | +0.065 |
ggy | +0.062 |
istered | +0.061 |
ggie | +0.060 |
Neg logit contributions | |
Suz | -0.107 |
Su | -0.106 |
Mill | -0.105 |
Sus | -0.105 |
Alf | -0.102 |
Token | to |
Token ID | 284 |
Feature activation | -2.21e+00 |
Pos logit contributions | |
wy | +0.184 |
ruined | +0.179 |
ggy | +0.176 |
istered | +0.171 |
ggie | +0.171 |
Neg logit contributions | |
Suz | -0.178 |
Su | -0.178 |
Mill | -0.174 |
Sus | -0.174 |
Alf | -0.167 |
Token | work |
Token ID | 670 |
Feature activation | -3.69e+00 |
Pos logit contributions | |
wy | +0.043 |
istered | +0.042 |
ruined | +0.040 |
burns | +0.039 |
ggy | +0.039 |
Neg logit contributions | |
Suz | -0.053 |
Su | -0.052 |
Mill | -0.052 |
Sus | -0.052 |
Alf | -0.050 |
Token | . |
Token ID | 13 |
Feature activation | +2.05e+00 |
Pos logit contributions | |
wy | +0.074 |
ruined | +0.071 |
istered | +0.070 |
burns | +0.070 |
uch | +0.069 |
Neg logit contributions | |
Su | -0.084 |
Sus | -0.084 |
Suz | -0.083 |
Mill | -0.082 |
Alf | -0.078 |
Token | Lily |
Token ID | 20037 |
Feature activation | -5.82e-01 |
Pos logit contributions | |
Alf | +0.049 |
cities | +0.049 |
ships | +0.046 |
Suz | +0.046 |
Mill | +0.045 |
Neg logit contributions | |
ruined | -0.032 |
A | -0.031 |
big | -0.031 |
bad | -0.030 |
Luckily | -0.030 |
Token | laughed |
Token ID | 13818 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
wy | +0.010 |
ruined | +0.010 |
istered | +0.009 |
ggy | +0.009 |
sharp | +0.009 |
Neg logit contributions | |
Suz | -0.015 |
Su | -0.015 |
Mill | -0.014 |
Sus | -0.014 |
Alf | -0.014 |
Token | , |
Token ID | 11 |
Feature activation | +3.82e+00 |
Pos logit contributions | |
Suz | +0.058 |
Mill | +0.056 |
Su | +0.056 |
Sus | +0.055 |
Alf | +0.052 |
Neg logit contributions | |
ggy | -0.025 |
ggie | -0.024 |
ruined | -0.022 |
big | -0.021 |
hurt | -0.021 |
Token | but |
Token ID | 475 |
Feature activation | +4.66e+00 |
Pos logit contributions | |
Suz | +0.082 |
Mill | +0.082 |
Alf | +0.081 |
bank | +0.079 |
Su | +0.079 |
Neg logit contributions | |
sharp | -0.077 |
ruined | -0.077 |
hurt | -0.072 |
bad | -0.071 |
big | -0.071 |
Token | she |
Token ID | 673 |
Feature activation | -2.08e+00 |
Pos logit contributions | |
cities | +0.106 |
Suz | +0.102 |
Su | +0.101 |
Mill | +0.101 |
Alf | +0.101 |
Neg logit contributions | |
ruined | -0.094 |
hurt | -0.089 |
not | -0.087 |
bad | -0.086 |
sharp | -0.084 |
Token | said |
Token ID | 531 |
Feature activation | +1.97e-01 |
Pos logit contributions | |
ps | +0.044 |
wy | +0.043 |
istered | +0.043 |
burns | +0.041 |
ching | +0.041 |
Neg logit contributions | |
Suz | -0.046 |
Su | -0.045 |
Sus | -0.044 |
Mill | -0.044 |
Alf | -0.042 |
Token | they |
Token ID | 484 |
Feature activation | -2.95e+00 |
Pos logit contributions | |
Suz | +0.006 |
Mill | +0.006 |
Su | +0.006 |
Alf | +0.006 |
Sus | +0.006 |
Neg logit contributions | |
ruined | -0.002 |
ggy | -0.002 |
sharp | -0.002 |
ggie | -0.002 |
wy | -0.002 |
Token | didn |
Token ID | 1422 |
Feature activation | -8.38e+00 |
Pos logit contributions | |
wy | +0.066 |
ps | +0.064 |
ggy | +0.062 |
ggie | +0.061 |
sting | +0.060 |
Neg logit contributions | |
Sus | -0.061 |
Su | -0.061 |
Suz | -0.061 |
Mill | -0.060 |
Alf | -0.059 |
Token | 't |
Token ID | 470 |
Feature activation | -4.73e+00 |
Pos logit contributions | |
wy | +0.171 |
istered | +0.156 |
ruined | +0.153 |
ery | +0.144 |
pain | +0.143 |
Neg logit contributions | |
Su | -0.205 |
Alf | -0.199 |
Suz | -0.199 |
Sus | -0.199 |
Mill | -0.196 |
Token | have |
Token ID | 423 |
Feature activation | -4.96e+00 |
Pos logit contributions | |
ruined | +0.073 |
wy | +0.071 |
ggy | +0.068 |
sharp | +0.068 |
ggie | +0.066 |
Neg logit contributions | |
Suz | -0.131 |
Su | -0.129 |
Mill | -0.128 |
Sus | -0.127 |
Alf | -0.125 |
Token | a |
Token ID | 257 |
Feature activation | -5.82e+00 |
Pos logit contributions | |
ruined | +0.083 |
wy | +0.082 |
ggy | +0.078 |
sharp | +0.077 |
istered | +0.076 |
Neg logit contributions | |
Suz | -0.130 |
Su | -0.129 |
Mill | -0.127 |
Sus | -0.126 |
Alf | -0.124 |
Token | plan |
Token ID | 1410 |
Feature activation | -4.54e+00 |
Pos logit contributions | |
ruined | +0.106 |
sharp | +0.101 |
bad | +0.098 |
ggy | +0.095 |
sting | +0.093 |
Neg logit contributions | |
Suz | -0.151 |
Mill | -0.146 |
Su | -0.146 |
Sus | -0.145 |
Alf | -0.140 |
Token | yet |
Token ID | 1865 |
Feature activation | -7.77e-01 |
Pos logit contributions | |
ruined | +0.071 |
ggy | +0.067 |
wy | +0.067 |
ggie | +0.064 |
sharp | +0.064 |
Neg logit contributions | |
Suz | -0.126 |
Mill | -0.123 |
Su | -0.123 |
Sus | -0.121 |
Alf | -0.120 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -5.18e+00 |
Pos logit contributions | |
line | +0.044 |
Suz | +0.044 |
Su | +0.044 |
ships | +0.044 |
cities | +0.044 |
Neg logit contributions | |
A | -0.018 |
two | -0.018 |
ggy | -0.017 |
Deal | -0.017 |
big | -0.017 |
Token | Peter |
Token ID | 19727 |
Feature activation | +1.73e-01 |
Pos logit contributions | |
ruined | +0.107 |
wy | +0.105 |
ggy | +0.102 |
sharp | +0.100 |
ggie | +0.099 |
Neg logit contributions | |
Suz | -0.114 |
Su | -0.112 |
Mill | -0.111 |
Sus | -0.110 |
Alf | -0.108 |
Token | was |
Token ID | 373 |
Feature activation | -6.41e+00 |
Pos logit contributions | |
Suz | +0.004 |
Su | +0.004 |
Mill | +0.004 |
Sus | +0.004 |
Alf | +0.004 |
Neg logit contributions | |
ruined | -0.003 |
wy | -0.003 |
ggy | -0.003 |
sharp | -0.003 |
istered | -0.003 |
Token | a |
Token ID | 257 |
Feature activation | -5.86e+00 |
Pos logit contributions | |
wy | +0.131 |
ruined | +0.131 |
ggy | +0.125 |
sharp | +0.123 |
istered | +0.123 |
Neg logit contributions | |
Suz | -0.145 |
Su | -0.143 |
Mill | -0.141 |
Sus | -0.141 |
Alf | -0.137 |
Token | mis |
Token ID | 2984 |
Feature activation | -3.41e+00 |
Pos logit contributions | |
ruined | +0.072 |
wy | +0.069 |
sharp | +0.067 |
ggy | +0.066 |
ggie | +0.063 |
Neg logit contributions | |
Suz | -0.180 |
Su | -0.178 |
Mill | -0.176 |
Sus | -0.175 |
Alf | -0.173 |
Token | chie |
Token ID | 3043 |
Feature activation | -8.38e+00 |
Pos logit contributions | |
wy | +0.052 |
ruined | +0.051 |
ggy | +0.049 |
istered | +0.049 |
sharp | +0.049 |
Neg logit contributions | |
Suz | -0.091 |
Su | -0.091 |
Mill | -0.090 |
Alf | -0.089 |
Sus | -0.088 |
Token | vous |
Token ID | 31222 |
Feature activation | -2.78e+00 |
Pos logit contributions | |
ggy | +0.102 |
wy | +0.101 |
ruined | +0.101 |
ggie | +0.097 |
sharp | +0.095 |
Neg logit contributions | |
Suz | -0.250 |
Mill | -0.248 |
Su | -0.246 |
Alf | -0.245 |
Sus | -0.244 |
Token | 3 |
Token ID | 513 |
Feature activation | -3.20e+00 |
Pos logit contributions | |
sharp | +0.050 |
ruined | +0.049 |
naughty | +0.048 |
bad | +0.048 |
pain | +0.048 |
Neg logit contributions | |
Suz | -0.066 |
Su | -0.064 |
Mill | -0.064 |
Alf | -0.064 |
Jan | -0.062 |
Token | year |
Token ID | 614 |
Feature activation | -2.74e-01 |
Pos logit contributions | |
ruined | +0.053 |
wy | +0.052 |
ggy | +0.052 |
sharp | +0.050 |
ggie | +0.050 |
Neg logit contributions | |
Suz | -0.084 |
Su | -0.082 |
Mill | -0.082 |
Sus | -0.081 |
Alf | -0.080 |
Token | old |
Token ID | 1468 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
sharp | +0.003 |
ruined | +0.003 |
bad | +0.003 |
naughty | +0.003 |
big | +0.003 |
Neg logit contributions | |
Suz | -0.009 |
Su | -0.009 |
Mill | -0.009 |
Alf | -0.008 |
Sus | -0.008 |
Token | who |
Token ID | 508 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
ruined | +0.021 |
ggy | +0.021 |
sharp | +0.021 |
ggie | +0.020 |
hurt | +0.020 |
Neg logit contributions | |
Suz | -0.032 |
Su | -0.031 |
Mill | -0.031 |
Alf | -0.030 |
Jan | -0.030 |
Token | her |
Token ID | 607 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
Suz | +0.091 |
Su | +0.090 |
Mill | +0.088 |
Sus | +0.088 |
Alf | +0.085 |
Neg logit contributions | |
ruined | -0.106 |
wy | -0.105 |
ggy | -0.101 |
sharp | -0.100 |
istered | -0.099 |
Token | come |
Token ID | 1282 |
Feature activation | -7.34e-01 |
Pos logit contributions | |
Suz | +0.030 |
Su | +0.030 |
Sus | +0.029 |
Mill | +0.029 |
Alf | +0.029 |
Neg logit contributions | |
wy | -0.026 |
ruined | -0.025 |
istered | -0.024 |
ggy | -0.024 |
sharp | -0.024 |
Token | back |
Token ID | 736 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
ruined | +0.014 |
wy | +0.013 |
sharp | +0.013 |
ggy | +0.013 |
hurt | +0.013 |
Neg logit contributions | |
Suz | -0.018 |
Su | -0.017 |
Mill | -0.017 |
Sus | -0.017 |
Alf | -0.017 |
Token | . |
Token ID | 13 |
Feature activation | +2.52e+00 |
Pos logit contributions | |
Suz | +0.040 |
Su | +0.039 |
Mill | +0.039 |
Sus | +0.038 |
Alf | +0.038 |
Neg logit contributions | |
ruined | -0.026 |
sharp | -0.025 |
wy | -0.025 |
ggy | -0.024 |
burns | -0.024 |
Token | You |
Token ID | 921 |
Feature activation | -3.72e+00 |
Pos logit contributions | |
Suz | +0.054 |
Su | +0.053 |
Sus | +0.052 |
Mill | +0.051 |
Alf | +0.051 |
Neg logit contributions | |
Deal | -0.047 |
sharp | -0.044 |
burns | -0.044 |
ggy | -0.044 |
pain | -0.044 |
Token | seem |
Token ID | 1283 |
Feature activation | -8.36e+00 |
Pos logit contributions | |
ggy | +0.076 |
ggie | +0.075 |
istered | +0.075 |
wy | +0.074 |
itching | +0.070 |
Neg logit contributions | |
Alf | -0.085 |
Mill | -0.083 |
Suz | -0.081 |
Sus | -0.080 |
Ally | -0.078 |
Token | like |
Token ID | 588 |
Feature activation | -6.14e-01 |
Pos logit contributions | |
wy | +0.164 |
uch | +0.154 |
ggy | +0.149 |
istered | +0.146 |
kin | +0.144 |
Neg logit contributions | |
Mill | -0.203 |
Sus | -0.202 |
Su | -0.200 |
Suz | -0.196 |
Ally | -0.190 |
Token | a |
Token ID | 257 |
Feature activation | -4.40e+00 |
Pos logit contributions | |
ruined | +0.013 |
wy | +0.012 |
sharp | +0.012 |
ggy | +0.012 |
burns | +0.012 |
Neg logit contributions | |
Suz | -0.014 |
Su | -0.014 |
Mill | -0.013 |
Sus | -0.013 |
Alf | -0.013 |
Token | good |
Token ID | 922 |
Feature activation | -2.97e-01 |
Pos logit contributions | |
ruined | +0.060 |
wy | +0.060 |
ggy | +0.056 |
sharp | +0.054 |
istered | +0.053 |
Neg logit contributions | |
Suz | -0.129 |
Su | -0.128 |
Mill | -0.126 |
Sus | -0.126 |
Alf | -0.124 |
Token | boy |
Token ID | 2933 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
ruined | +0.005 |
pain | +0.005 |
ggy | +0.005 |
sharp | +0.005 |
wy | +0.005 |
Neg logit contributions | |
Suz | -0.007 |
Su | -0.007 |
Mill | -0.007 |
Alf | -0.007 |
Sus | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | +1.73e+00 |
Pos logit contributions | |
ruined | +0.018 |
wy | +0.018 |
ggy | +0.017 |
sharp | +0.017 |
ggie | +0.016 |
Neg logit contributions | |
Suz | -0.027 |
Su | -0.027 |
Mill | -0.027 |
Sus | -0.026 |
Alf | -0.026 |
Token | . |
Token ID | 13 |
Feature activation | +2.10e+00 |
Pos logit contributions | |
ruined | +0.000 |
ggy | +0.000 |
wy | +0.000 |
ggie | +0.000 |
sharp | +0.000 |
Neg logit contributions | |
Suz | -0.001 |
Mill | -0.001 |
Su | -0.001 |
Sus | -0.001 |
Alf | -0.001 |
Token | But |
Token ID | 887 |
Feature activation | +4.16e+00 |
Pos logit contributions | |
Suz | +0.052 |
Mill | +0.049 |
Su | +0.049 |
Sus | +0.048 |
Alf | +0.046 |
Neg logit contributions | |
ruined | -0.038 |
sharp | -0.037 |
bad | -0.036 |
big | -0.035 |
sting | -0.035 |
Token | Coco |
Token ID | 48222 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
Suz | +0.094 |
Su | +0.091 |
Mill | +0.090 |
Sus | +0.089 |
Alf | +0.087 |
Neg logit contributions | |
ruined | -0.088 |
wy | -0.084 |
ggy | -0.083 |
sharp | -0.083 |
hurt | -0.081 |
Token | did |
Token ID | 750 |
Feature activation | -6.22e+00 |
Pos logit contributions | |
arest | +0.029 |
wy | +0.029 |
istered | +0.029 |
Deal | +0.028 |
ps | +0.027 |
Neg logit contributions | |
Su | -0.034 |
Suz | -0.034 |
Mill | -0.033 |
Sus | -0.033 |
Ally | -0.032 |
Token | not |
Token ID | 407 |
Feature activation | -4.06e+00 |
Pos logit contributions | |
wy | +0.081 |
istered | +0.067 |
arest | +0.063 |
ery | +0.063 |
ruined | +0.063 |
Neg logit contributions | |
Suz | -0.193 |
Su | -0.192 |
Sus | -0.190 |
Mill | -0.188 |
Alf | -0.187 |
Token | seem |
Token ID | 1283 |
Feature activation | -8.35e+00 |
Pos logit contributions | |
wy | +0.078 |
istered | +0.075 |
ruined | +0.074 |
uch | +0.072 |
ggy | +0.071 |
Neg logit contributions | |
Suz | -0.098 |
Su | -0.096 |
Mill | -0.096 |
Sus | -0.096 |
Alf | -0.093 |
Token | to |
Token ID | 284 |
Feature activation | -2.33e+00 |
Pos logit contributions | |
wy | +0.177 |
ruined | +0.167 |
uch | +0.167 |
istered | +0.166 |
ggy | +0.165 |
Neg logit contributions | |
Su | -0.185 |
Suz | -0.182 |
Mill | -0.180 |
Sus | -0.180 |
Alf | -0.171 |
Token | understand |
Token ID | 1833 |
Feature activation | +6.59e-01 |
Pos logit contributions | |
wy | +0.048 |
istered | +0.048 |
ery | +0.044 |
uch | +0.043 |
ruined | +0.043 |
Neg logit contributions | |
Suz | -0.053 |
Su | -0.053 |
Mill | -0.052 |
Sus | -0.052 |
Alf | -0.050 |
Token | . |
Token ID | 13 |
Feature activation | +2.10e+00 |
Pos logit contributions | |
Suz | +0.014 |
Su | +0.014 |
Mill | +0.013 |
Sus | +0.013 |
Alf | +0.013 |
Neg logit contributions | |
ruined | -0.015 |
wy | -0.014 |
ggy | -0.014 |
sharp | -0.014 |
istered | -0.014 |
Token | He |
Token ID | 679 |
Feature activation | -6.52e-01 |
Pos logit contributions | |
Suz | +0.043 |
Su | +0.042 |
Mill | +0.042 |
Sus | +0.041 |
Alf | +0.039 |
Neg logit contributions | |
ruined | -0.047 |
sharp | -0.045 |
bad | -0.045 |
ggy | -0.044 |
pain | -0.044 |
Token | would |
Token ID | 561 |
Feature activation | -2.72e+00 |
Pos logit contributions | |
arest | +0.015 |
wy | +0.014 |
istered | +0.014 |
vern | +0.014 |
Deal | +0.013 |
Neg logit contributions | |
Su | -0.013 |
Suz | -0.013 |
K | -0.013 |
Alf | -0.012 |
Sus | -0.012 |
Token | it |
Token ID | 340 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
Suz | +0.024 |
Su | +0.024 |
Mill | +0.023 |
Sus | +0.023 |
Alf | +0.023 |
Neg logit contributions | |
ruined | -0.020 |
wy | -0.020 |
ggy | -0.019 |
sharp | -0.019 |
istered | -0.018 |
Token | . |
Token ID | 13 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
wy | +0.036 |
ruined | +0.035 |
ggy | +0.034 |
istered | +0.034 |
sting | +0.033 |
Neg logit contributions | |
Suz | -0.047 |
Su | -0.047 |
Mill | -0.047 |
Sus | -0.047 |
Alf | -0.045 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -5.41e+00 |
Pos logit contributions | |
cities | +0.040 |
line | +0.039 |
bank | +0.039 |
ho | +0.038 |
vans | +0.037 |
Neg logit contributions | |
ruined | -0.017 |
big | -0.017 |
A | -0.016 |
ching | -0.016 |
sense | -0.016 |
Token | Sam |
Token ID | 16305 |
Feature activation | +5.37e-04 |
Pos logit contributions | |
ruined | +0.102 |
wy | +0.099 |
ggy | +0.098 |
sharp | +0.095 |
ggie | +0.095 |
Neg logit contributions | |
Suz | -0.126 |
Su | -0.124 |
Mill | -0.122 |
Sus | -0.121 |
Alf | -0.119 |
Token | had |
Token ID | 550 |
Feature activation | -5.13e+00 |
Pos logit contributions | |
Suz | +0.000 |
Su | +0.000 |
Mill | +0.000 |
Alf | +0.000 |
Sus | +0.000 |
Neg logit contributions | |
ruined | -0.000 |
wy | -0.000 |
sharp | -0.000 |
burns | -0.000 |
ggy | -0.000 |
Token | been |
Token ID | 587 |
Feature activation | -8.35e+00 |
Pos logit contributions | |
wy | +0.070 |
istered | +0.066 |
ggy | +0.065 |
sting | +0.065 |
ruined | +0.064 |
Neg logit contributions | |
Su | -0.156 |
Sus | -0.154 |
Suz | -0.152 |
Mill | -0.151 |
Alf | -0.145 |
Token | playing |
Token ID | 2712 |
Feature activation | -2.13e+00 |
Pos logit contributions | |
wy | +0.160 |
ruined | +0.160 |
ggy | +0.153 |
sharp | +0.150 |
istered | +0.149 |
Neg logit contributions | |
Suz | -0.198 |
Su | -0.196 |
Mill | -0.193 |
Sus | -0.193 |
Alf | -0.188 |
Token | with |
Token ID | 351 |
Feature activation | +2.34e-01 |
Pos logit contributions | |
ruined | +0.040 |
wy | +0.039 |
ggy | +0.038 |
sharp | +0.038 |
ggie | +0.037 |
Neg logit contributions | |
Suz | -0.051 |
Su | -0.051 |
Mill | -0.050 |
Sus | -0.050 |
Alf | -0.049 |
Token | his |
Token ID | 465 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
Suz | +0.005 |
Su | +0.004 |
Sus | +0.004 |
Mill | +0.004 |
Alf | +0.004 |
Neg logit contributions | |
wy | -0.006 |
ruined | -0.006 |
istered | -0.005 |
ggy | -0.005 |
uch | -0.005 |
Token | friends |
Token ID | 2460 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
wy | +0.022 |
ruined | +0.021 |
istered | +0.020 |
uch | +0.020 |
sting | +0.020 |
Neg logit contributions | |
Suz | -0.025 |
Sus | -0.025 |
Su | -0.025 |
Mill | -0.025 |
Alf | -0.024 |
Token | all |
Token ID | 477 |
Feature activation | +9.66e-01 |
Pos logit contributions | |
ruined | +0.018 |
ggie | +0.018 |
wy | +0.018 |
ggy | +0.018 |
sharp | +0.017 |
Neg logit contributions | |
Suz | -0.026 |
Su | -0.025 |
Mill | -0.025 |
Sus | -0.024 |
Alf | -0.024 |
Token | , |
Token ID | 11 |
Feature activation | +3.87e+00 |
Pos logit contributions | |
wy | +0.048 |
ruined | +0.047 |
uch | +0.045 |
istered | +0.045 |
ggy | +0.045 |
Neg logit contributions | |
Suz | -0.054 |
Su | -0.054 |
Sus | -0.053 |
Mill | -0.052 |
Alf | -0.050 |
Token | but |
Token ID | 475 |
Feature activation | +5.13e+00 |
Pos logit contributions | |
Suz | +0.079 |
Mill | +0.078 |
Su | +0.078 |
Alf | +0.075 |
Sus | +0.075 |
Neg logit contributions | |
ruined | -0.087 |
sharp | -0.086 |
hurt | -0.082 |
pain | -0.082 |
ggy | -0.081 |
Token | he |
Token ID | 339 |
Feature activation | -1.87e+00 |
Pos logit contributions | |
Suz | +0.103 |
Su | +0.101 |
Mill | +0.099 |
Alf | +0.098 |
Sus | +0.097 |
Neg logit contributions | |
ruined | -0.120 |
sharp | -0.114 |
wy | -0.113 |
hurt | -0.111 |
bad | -0.111 |
Token | didn |
Token ID | 1422 |
Feature activation | -7.27e+00 |
Pos logit contributions | |
wy | +0.040 |
istered | +0.040 |
arest | +0.040 |
ps | +0.039 |
ruined | +0.038 |
Neg logit contributions | |
Suz | -0.039 |
Su | -0.038 |
Sus | -0.037 |
Alf | -0.036 |
Mill | -0.036 |
Token | 't |
Token ID | 470 |
Feature activation | -4.43e+00 |
Pos logit contributions | |
wy | +0.171 |
istered | +0.156 |
ruined | +0.151 |
aky | +0.145 |
kin | +0.145 |
Neg logit contributions | |
Su | -0.153 |
Suz | -0.149 |
Sus | -0.145 |
Twe | -0.145 |
Cr | -0.143 |
Token | seem |
Token ID | 1283 |
Feature activation | -8.34e+00 |
Pos logit contributions | |
wy | +0.088 |
ruined | +0.085 |
istered | +0.083 |
uch | +0.082 |
ggy | +0.081 |
Neg logit contributions | |
Suz | -0.104 |
Su | -0.103 |
Sus | -0.101 |
Mill | -0.100 |
Alf | -0.098 |
Token | to |
Token ID | 284 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
wy | +0.216 |
ggy | +0.207 |
uch | +0.206 |
ggie | +0.203 |
ruined | +0.202 |
Neg logit contributions | |
Su | -0.145 |
Suz | -0.141 |
Sus | -0.140 |
Mill | -0.140 |
Alf | -0.131 |
Token | be |
Token ID | 307 |
Feature activation | -4.45e+00 |
Pos logit contributions | |
wy | +0.046 |
istered | +0.046 |
arest | +0.044 |
ruined | +0.044 |
ery | +0.043 |
Neg logit contributions | |
Suz | -0.047 |
Su | -0.046 |
Mill | -0.046 |
Sus | -0.046 |
Cr | -0.045 |
Token | getting |
Token ID | 1972 |
Feature activation | -2.73e+00 |
Pos logit contributions | |
arest | +0.081 |
wy | +0.077 |
uch | +0.076 |
istered | +0.076 |
Deal | +0.073 |
Neg logit contributions | |
Su | -0.110 |
Suz | -0.108 |
Sus | -0.105 |
Cr | -0.102 |
Mill | -0.102 |
Token | bigger |
Token ID | 5749 |
Feature activation | +9.05e-01 |
Pos logit contributions | |
wy | +0.043 |
ggy | +0.043 |
ggie | +0.042 |
ruined | +0.041 |
uch | +0.040 |
Neg logit contributions | |
Suz | -0.073 |
Su | -0.073 |
Sus | -0.072 |
Mill | -0.071 |
Alf | -0.070 |
Token | or |
Token ID | 393 |
Feature activation | +4.76e+00 |
Pos logit contributions | |
Suz | +0.022 |
Su | +0.022 |
Sus | +0.022 |
Mill | +0.022 |
Alf | +0.022 |
Neg logit contributions | |
wy | -0.016 |
ruined | -0.016 |
ggy | -0.015 |
ggie | -0.015 |
uch | -0.015 |
Token | little |
Token ID | 1310 |
Feature activation | +4.89e-01 |
Pos logit contributions | |
ruined | +0.060 |
wy | +0.059 |
burns | +0.053 |
ggy | +0.053 |
istered | +0.052 |
Neg logit contributions | |
Suz | -0.166 |
Su | -0.165 |
Mill | -0.163 |
Sus | -0.163 |
Alf | -0.160 |
Token | boy |
Token ID | 2933 |
Feature activation | -2.45e+00 |
Pos logit contributions | |
Suz | +0.011 |
Su | +0.011 |
Alf | +0.010 |
Mill | +0.010 |
Sus | +0.010 |
Neg logit contributions | |
sharp | -0.010 |
ruined | -0.010 |
wy | -0.010 |
bad | -0.009 |
pain | -0.009 |
Token | named |
Token ID | 3706 |
Feature activation | +4.09e+00 |
Pos logit contributions | |
ruined | +0.057 |
ggy | +0.056 |
hurt | +0.054 |
burns | +0.053 |
wy | +0.053 |
Neg logit contributions | |
Alf | -0.047 |
Mill | -0.047 |
Suz | -0.046 |
Su | -0.046 |
Sus | -0.046 |
Token | Joe |
Token ID | 5689 |
Feature activation | -7.15e-01 |
Pos logit contributions | |
Suz | +0.044 |
Mill | +0.043 |
Su | +0.041 |
Sus | +0.040 |
ress | +0.040 |
Neg logit contributions | |
ruined | -0.128 |
sharp | -0.127 |
wy | -0.127 |
big | -0.122 |
burns | -0.121 |
Token | had |
Token ID | 550 |
Feature activation | -5.61e+00 |
Pos logit contributions | |
wy | +0.014 |
ruined | +0.014 |
istered | +0.014 |
ggy | +0.014 |
ggie | +0.014 |
Neg logit contributions | |
Suz | -0.016 |
Su | -0.016 |
Sus | -0.016 |
Mill | -0.016 |
Alf | -0.015 |
Token | been |
Token ID | 587 |
Feature activation | -8.33e+00 |
Pos logit contributions | |
wy | +0.077 |
istered | +0.069 |
sting | +0.068 |
ps | +0.067 |
ggy | +0.067 |
Neg logit contributions | |
Su | -0.170 |
Sus | -0.167 |
Suz | -0.167 |
Mill | -0.164 |
Alf | -0.160 |
Token | feeling |
Token ID | 4203 |
Feature activation | -6.32e+00 |
Pos logit contributions | |
ruined | +0.183 |
wy | +0.177 |
ggy | +0.173 |
sharp | +0.173 |
ggie | +0.169 |
Neg logit contributions | |
Suz | -0.177 |
Su | -0.173 |
Mill | -0.173 |
Sus | -0.169 |
Alf | -0.168 |
Token | restless |
Token ID | 42537 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
wy | +0.116 |
ruined | +0.114 |
ggy | +0.114 |
ggie | +0.110 |
uch | +0.109 |
Neg logit contributions | |
Sus | -0.152 |
Suz | -0.152 |
Su | -0.151 |
Mill | -0.148 |
Alf | -0.145 |
Token | . |
Token ID | 13 |
Feature activation | +7.86e-01 |
Pos logit contributions | |
ruined | +0.038 |
wy | +0.038 |
ggy | +0.036 |
sharp | +0.035 |
istered | +0.035 |
Neg logit contributions | |
Suz | -0.056 |
Su | -0.056 |
Mill | -0.055 |
Sus | -0.055 |
Alf | -0.054 |
Token | His |
Token ID | 2399 |
Feature activation | -1.73e-01 |
Pos logit contributions | |
Ally | +0.019 |
ress | +0.018 |
Mill | +0.018 |
Hil | +0.018 |
Suz | +0.018 |
Neg logit contributions | |
big | -0.013 |
sharp | -0.012 |
burns | -0.011 |
not | -0.011 |
funny | -0.011 |
Token | mom |
Token ID | 1995 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
wy | +0.004 |
ruined | +0.004 |
istered | +0.004 |
arest | +0.004 |
ching | +0.004 |
Neg logit contributions | |
Suz | -0.003 |
Su | -0.003 |
Sus | -0.003 |
Alf | -0.003 |
Mill | -0.003 |
Token | Things |
Token ID | 11597 |
Feature activation | -2.01e+00 |
Pos logit contributions | |
Su | +0.052 |
Suz | +0.051 |
Mill | +0.051 |
line | +0.051 |
Sus | +0.050 |
Neg logit contributions | |
ruined | -0.048 |
burns | -0.048 |
sharp | -0.046 |
ggy | -0.045 |
pain | -0.045 |
Token | had |
Token ID | 550 |
Feature activation | -3.19e+00 |
Pos logit contributions | |
wy | +0.039 |
ruined | +0.038 |
ggy | +0.037 |
istered | +0.037 |
ggie | +0.036 |
Neg logit contributions | |
Suz | -0.047 |
Su | -0.047 |
Mill | -0.047 |
Sus | -0.046 |
Alf | -0.045 |
Token | been |
Token ID | 587 |
Feature activation | -5.41e+00 |
Pos logit contributions | |
wy | +0.054 |
istered | +0.052 |
uch | +0.049 |
ggy | +0.048 |
Deal | +0.048 |
Neg logit contributions | |
Su | -0.086 |
Suz | -0.086 |
Sus | -0.085 |
Mill | -0.084 |
Alf | -0.081 |
Token | moved |
Token ID | 3888 |
Feature activation | +2.42e-01 |
Pos logit contributions | |
wy | +0.107 |
istered | +0.102 |
uch | +0.100 |
ggy | +0.100 |
sting | +0.098 |
Neg logit contributions | |
Su | -0.130 |
Sus | -0.129 |
Suz | -0.128 |
Mill | -0.125 |
Alf | -0.118 |
Token | around |
Token ID | 1088 |
Feature activation | +2.39e+00 |
Pos logit contributions | |
Suz | +0.005 |
Su | +0.005 |
Mill | +0.005 |
Sus | +0.005 |
Alf | +0.005 |
Neg logit contributions | |
ruined | -0.005 |
wy | -0.005 |
sharp | -0.005 |
ggy | -0.005 |
istered | -0.005 |
Token | and |
Token ID | 290 |
Feature activation | +6.33e+00 |
Pos logit contributions | |
Suz | +0.058 |
Su | +0.058 |
Alf | +0.057 |
Mill | +0.056 |
Sus | +0.055 |
Neg logit contributions | |
ruined | -0.044 |
sharp | -0.041 |
pain | -0.039 |
bad | -0.039 |
wy | -0.038 |
Token | the |
Token ID | 262 |
Feature activation | +1.93e+00 |
Pos logit contributions | |
Su | +0.140 |
Suz | +0.140 |
Alf | +0.138 |
Mill | +0.137 |
Sus | +0.133 |
Neg logit contributions | |
ruined | -0.131 |
sharp | -0.121 |
hurt | -0.118 |
bad | -0.114 |
pain | -0.113 |
Token | sand |
Token ID | 6450 |
Feature activation | +4.36e-01 |
Pos logit contributions | |
Sus | +0.038 |
Suz | +0.038 |
Mill | +0.038 |
Su | +0.038 |
Alf | +0.035 |
Neg logit contributions | |
wy | -0.046 |
ggy | -0.044 |
istered | -0.044 |
ruined | -0.043 |
ggie | -0.043 |
Token | was |
Token ID | 373 |
Feature activation | -4.09e+00 |
Pos logit contributions | |
Suz | +0.011 |
Su | +0.011 |
Mill | +0.011 |
Sus | +0.011 |
Alf | +0.010 |
Neg logit contributions | |
ruined | -0.008 |
wy | -0.008 |
ggy | -0.007 |
sharp | -0.007 |
istered | -0.007 |
Token | in |
Token ID | 287 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
wy | +0.082 |
ggy | +0.077 |
uch | +0.077 |
istered | +0.076 |
ggie | +0.075 |
Neg logit contributions | |
Suz | -0.097 |
Su | -0.097 |
Sus | -0.096 |
Mill | -0.095 |
Alf | -0.091 |
Token | different |
Token ID | 1180 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
Suz | +0.026 |
Sus | +0.026 |
Su | +0.026 |
Mill | +0.026 |
Alf | +0.024 |
Neg logit contributions | |
wy | -0.030 |
uch | -0.029 |
ggy | -0.028 |
istered | -0.027 |
ggie | -0.027 |
Token | kids |
Token ID | 3988 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
Suz | +0.083 |
Su | +0.082 |
Mill | +0.081 |
Sus | +0.080 |
Alf | +0.079 |
Neg logit contributions | |
ruined | -0.068 |
wy | -0.067 |
ggy | -0.064 |
sharp | -0.064 |
ggie | -0.062 |
Token | learned |
Token ID | 4499 |
Feature activation | -2.32e+00 |
Pos logit contributions | |
ruined | +0.030 |
hurt | +0.027 |
wy | +0.026 |
sharp | +0.026 |
ggy | +0.025 |
Neg logit contributions | |
Suz | -0.039 |
Su | -0.038 |
Mill | -0.037 |
Alf | -0.037 |
Sus | -0.037 |
Token | about |
Token ID | 546 |
Feature activation | +3.67e-02 |
Pos logit contributions | |
ruined | +0.040 |
wy | +0.039 |
ggy | +0.038 |
sharp | +0.038 |
ggie | +0.037 |
Neg logit contributions | |
Suz | -0.060 |
Su | -0.059 |
Mill | -0.058 |
Sus | -0.058 |
Alf | -0.057 |
Token | the |
Token ID | 262 |
Feature activation | +8.83e-01 |
Pos logit contributions | |
Suz | +0.001 |
Su | +0.001 |
Sus | +0.001 |
Mill | +0.001 |
Alf | +0.001 |
Neg logit contributions | |
sharp | -0.001 |
ruined | -0.001 |
ggy | -0.001 |
bad | -0.001 |
hurt | -0.001 |
Token | jewel |
Token ID | 16927 |
Feature activation | -8.75e-01 |
Pos logit contributions | |
Mill | +0.022 |
Sus | +0.021 |
Alf | +0.021 |
Suz | +0.021 |
Su | +0.020 |
Neg logit contributions | |
wy | -0.016 |
istered | -0.015 |
ggy | -0.015 |
ruined | -0.015 |
burns | -0.014 |
Token | and |
Token ID | 290 |
Feature activation | +5.58e+00 |
Pos logit contributions | |
ruined | +0.015 |
wy | +0.014 |
ggy | +0.014 |
sharp | +0.014 |
ggie | +0.013 |
Neg logit contributions | |
Suz | -0.023 |
Su | -0.023 |
Mill | -0.023 |
Sus | -0.023 |
Alf | -0.022 |
Token | asked |
Token ID | 1965 |
Feature activation | +3.66e+00 |
Pos logit contributions | |
Suz | +0.130 |
Su | +0.127 |
Mill | +0.125 |
Sus | +0.123 |
Alf | +0.120 |
Neg logit contributions | |
ruined | -0.114 |
sharp | -0.106 |
hurt | -0.105 |
bad | -0.102 |
ggy | -0.099 |
Token | to |
Token ID | 284 |
Feature activation | +8.81e-01 |
Pos logit contributions | |
Suz | +0.090 |
Su | +0.087 |
Mill | +0.084 |
Hil | +0.084 |
ress | +0.083 |
Neg logit contributions | |
bad | -0.066 |
sharp | -0.062 |
big | -0.060 |
naughty | -0.059 |
funny | -0.059 |
Token | come |
Token ID | 1282 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
Suz | +0.021 |
Su | +0.021 |
Mill | +0.021 |
Sus | +0.021 |
Alf | +0.020 |
Neg logit contributions | |
wy | -0.017 |
ruined | -0.016 |
istered | -0.016 |
ggy | -0.016 |
sharp | -0.015 |
Token | and |
Token ID | 290 |
Feature activation | +4.45e+00 |
Pos logit contributions | |
ruined | +0.026 |
ggy | +0.026 |
sharp | +0.026 |
hurt | +0.025 |
wy | +0.025 |
Neg logit contributions | |
Su | -0.040 |
Suz | -0.039 |
Mill | -0.038 |
Sus | -0.038 |
Alf | -0.037 |
Token | see |
Token ID | 766 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
Suz | +0.108 |
Su | +0.106 |
Mill | +0.106 |
Sus | +0.105 |
Alf | +0.103 |
Neg logit contributions | |
wy | -0.084 |
ruined | -0.083 |
ggy | -0.079 |
istered | -0.078 |
sharp | -0.077 |
Token | She |
Token ID | 1375 |
Feature activation | -3.43e-01 |
Pos logit contributions | |
Alf | +0.049 |
Suz | +0.046 |
reating | +0.046 |
cities | +0.046 |
Cr | +0.046 |
Neg logit contributions | |
big | -0.026 |
A | -0.025 |
sharp | -0.023 |
two | -0.023 |
a | -0.022 |
Token | walked |
Token ID | 6807 |
Feature activation | +3.59e-01 |
Pos logit contributions | |
ruined | +0.007 |
wy | +0.007 |
ggy | +0.006 |
sharp | +0.006 |
istered | +0.006 |
Neg logit contributions | |
Suz | -0.008 |
Su | -0.008 |
Mill | -0.008 |
Sus | -0.008 |
Alf | -0.008 |
Token | up |
Token ID | 510 |
Feature activation | +2.09e+00 |
Pos logit contributions | |
Su | +0.009 |
Suz | +0.009 |
Alf | +0.009 |
Mill | +0.008 |
Sus | +0.008 |
Neg logit contributions | |
sharp | -0.006 |
big | -0.006 |
ruined | -0.006 |
hurt | -0.006 |
naughty | -0.006 |
Token | to |
Token ID | 284 |
Feature activation | +4.23e+00 |
Pos logit contributions | |
Alf | +0.050 |
Su | +0.050 |
Suz | +0.049 |
Cr | +0.049 |
Hil | +0.048 |
Neg logit contributions | |
sharp | -0.037 |
big | -0.036 |
ruined | -0.035 |
hurt | -0.035 |
broken | -0.033 |
Token | it |
Token ID | 340 |
Feature activation | -3.75e-01 |
Pos logit contributions | |
Suz | +0.098 |
Su | +0.096 |
Alf | +0.094 |
Mill | +0.093 |
Sus | +0.092 |
Neg logit contributions | |
sharp | -0.079 |
ruined | -0.078 |
hurt | -0.075 |
pain | -0.074 |
bad | -0.074 |
Token | and |
Token ID | 290 |
Feature activation | +6.93e+00 |
Pos logit contributions | |
sharp | +0.005 |
ruined | +0.005 |
hurt | +0.005 |
ggy | +0.005 |
big | +0.005 |
Neg logit contributions | |
Su | -0.011 |
Suz | -0.011 |
Alf | -0.010 |
Sus | -0.010 |
Mill | -0.010 |
Token | knocked |
Token ID | 13642 |
Feature activation | +4.15e+00 |
Pos logit contributions | |
Suz | +0.190 |
Su | +0.189 |
Alf | +0.185 |
Mill | +0.182 |
Sus | +0.180 |
Neg logit contributions | |
ruined | -0.105 |
sharp | -0.101 |
hurt | -0.098 |
naughty | -0.090 |
broken | -0.088 |
Token | on |
Token ID | 319 |
Feature activation | +2.86e+00 |
Pos logit contributions | |
Alf | +0.116 |
bank | +0.113 |
Suz | +0.113 |
Cr | +0.112 |
Mill | +0.112 |
Neg logit contributions | |
ruined | -0.057 |
sharp | -0.056 |
hurt | -0.054 |
pain | -0.054 |
wy | -0.053 |
Token | the |
Token ID | 262 |
Feature activation | +2.62e+00 |
Pos logit contributions | |
Suz | +0.070 |
Cr | +0.069 |
Alf | +0.068 |
Su | +0.068 |
bank | +0.067 |
Neg logit contributions | |
sharp | -0.051 |
ruined | -0.049 |
big | -0.047 |
hurt | -0.046 |
bad | -0.046 |
Token | door |
Token ID | 3420 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
Suz | +0.059 |
Su | +0.058 |
Mill | +0.057 |
Sus | +0.057 |
Alf | +0.056 |
Neg logit contributions | |
ruined | -0.055 |
sharp | -0.052 |
wy | -0.052 |
ggy | -0.051 |
burns | -0.051 |
Token | . |
Token ID | 13 |
Feature activation | +2.30e+00 |
Pos logit contributions | |
Cr | +0.048 |
Suz | +0.047 |
Mill | +0.047 |
Alf | +0.047 |
Su | +0.047 |
Neg logit contributions | |
ruined | -0.018 |
sharp | -0.017 |
hurt | -0.016 |
burns | -0.016 |
ggy | -0.016 |
Token | flower |
Token ID | 15061 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
Mill | +0.016 |
Sus | +0.015 |
Suz | +0.015 |
Ally | +0.015 |
cities | +0.014 |
Neg logit contributions | |
wy | -0.017 |
istered | -0.017 |
ggy | -0.016 |
ggie | -0.016 |
uch | -0.016 |
Token | was |
Token ID | 373 |
Feature activation | -5.02e+00 |
Pos logit contributions | |
Suz | +0.029 |
Mill | +0.028 |
Su | +0.028 |
Sus | +0.028 |
Alf | +0.027 |
Neg logit contributions | |
wy | -0.020 |
ruined | -0.019 |
istered | -0.019 |
ggy | -0.018 |
ggie | -0.018 |
Token | growing |
Token ID | 3957 |
Feature activation | -2.58e+00 |
Pos logit contributions | |
wy | +0.088 |
arest | +0.080 |
istered | +0.079 |
uch | +0.079 |
itch | +0.079 |
Neg logit contributions | |
Sus | -0.132 |
Suz | -0.132 |
Mill | -0.132 |
Su | -0.130 |
Jan | -0.120 |
Token | even |
Token ID | 772 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
ggy | +0.051 |
wy | +0.050 |
ggie | +0.049 |
istered | +0.047 |
ruined | +0.047 |
Neg logit contributions | |
Suz | -0.061 |
Mill | -0.060 |
Sus | -0.060 |
Su | -0.060 |
Jan | -0.054 |
Token | bigger |
Token ID | 5749 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
Suz | +0.030 |
Sus | +0.030 |
Su | +0.030 |
Mill | +0.030 |
Alf | +0.028 |
Neg logit contributions | |
ggy | -0.022 |
ggie | -0.021 |
wy | -0.021 |
istered | -0.021 |
uch | -0.020 |
Token | and |
Token ID | 290 |
Feature activation | +5.97e+00 |
Pos logit contributions | |
Suz | +0.028 |
Su | +0.027 |
Mill | +0.027 |
Sus | +0.027 |
Alf | +0.026 |
Neg logit contributions | |
ruined | -0.020 |
wy | -0.020 |
ggy | -0.019 |
sharp | -0.019 |
istered | -0.019 |
Token | brighter |
Token ID | 26083 |
Feature activation | +3.18e-01 |
Pos logit contributions | |
Suz | +0.166 |
Su | +0.164 |
Mill | +0.162 |
Sus | +0.161 |
Alf | +0.159 |
Neg logit contributions | |
ruined | -0.091 |
wy | -0.089 |
ggy | -0.084 |
sharp | -0.083 |
istered | -0.081 |
Token | . |
Token ID | 13 |
Feature activation | +2.05e+00 |
Pos logit contributions | |
Suz | +0.008 |
Su | +0.008 |
Mill | +0.008 |
Sus | +0.008 |
Alf | +0.008 |
Neg logit contributions | |
ruined | -0.006 |
wy | -0.006 |
ggy | -0.005 |
sharp | -0.005 |
istered | -0.005 |
Token | The |
Token ID | 383 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
forth | +0.043 |
iked | +0.042 |
ships | +0.041 |
Su | +0.041 |
line | +0.041 |
Neg logit contributions | |
two | -0.034 |
A | -0.032 |
Deal | -0.031 |
sharp | -0.031 |
big | -0.030 |
Token | comet |
Token ID | 31733 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
Mill | +0.033 |
cities | +0.033 |
Sus | +0.032 |
Suz | +0.032 |
Ally | +0.031 |
Neg logit contributions | |
istered | -0.033 |
ggy | -0.032 |
wy | -0.032 |
uch | -0.031 |
ggie | -0.030 |
Token | was |
Token ID | 373 |
Feature activation | -5.02e+00 |
Pos logit contributions | |
ruined | +0.003 |
wy | +0.003 |
ggy | +0.003 |
sharp | +0.003 |
istered | +0.003 |
Neg logit contributions | |
Suz | -0.005 |
Su | -0.005 |
Mill | -0.005 |
Sus | -0.004 |
Alf | -0.004 |
Token | ! |
Token ID | 0 |
Feature activation | +2.70e+00 |
Pos logit contributions | |
Su | +0.006 |
Suz | +0.006 |
Alf | +0.006 |
Mill | +0.006 |
Ally | +0.005 |
Neg logit contributions | |
ggy | -0.003 |
ruined | -0.003 |
sharp | -0.003 |
ggie | -0.003 |
hurt | -0.003 |
Token | She |
Token ID | 1375 |
Feature activation | +8.22e-01 |
Pos logit contributions | |
Suz | +0.062 |
Mill | +0.060 |
Alf | +0.060 |
Su | +0.059 |
cities | +0.059 |
Neg logit contributions | |
sharp | -0.042 |
ruined | -0.041 |
big | -0.040 |
pain | -0.039 |
ggy | -0.039 |
Token | thanked |
Token ID | 26280 |
Feature activation | +4.78e+00 |
Pos logit contributions | |
Suz | +0.020 |
Su | +0.019 |
Mill | +0.019 |
Sus | +0.019 |
Alf | +0.019 |
Neg logit contributions | |
wy | -0.016 |
ruined | -0.015 |
istered | -0.015 |
ggy | -0.015 |
ggie | -0.015 |
Token | the |
Token ID | 262 |
Feature activation | +2.74e+00 |
Pos logit contributions | |
bank | +0.121 |
iked | +0.117 |
line | +0.114 |
Suz | +0.113 |
ress | +0.113 |
Neg logit contributions | |
sharp | -0.068 |
big | -0.066 |
bad | -0.066 |
hurt | -0.062 |
two | -0.062 |
Token | man |
Token ID | 582 |
Feature activation | +2.25e+00 |
Pos logit contributions | |
Suz | +0.064 |
Su | +0.063 |
Mill | +0.062 |
Sus | +0.062 |
Alf | +0.060 |
Neg logit contributions | |
ruined | -0.055 |
sharp | -0.054 |
wy | -0.052 |
pain | -0.052 |
hurt | -0.052 |
Token | and |
Token ID | 290 |
Feature activation | +6.56e+00 |
Pos logit contributions | |
Suz | +0.067 |
Su | +0.066 |
Sus | +0.064 |
Mill | +0.063 |
Hil | +0.063 |
Neg logit contributions | |
sharp | -0.028 |
a | -0.027 |
ggy | -0.027 |
ggie | -0.027 |
ching | -0.025 |
Token | sailed |
Token ID | 33835 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
Suz | +0.155 |
Su | +0.154 |
Mill | +0.151 |
Alf | +0.151 |
Sus | +0.149 |
Neg logit contributions | |
ruined | -0.117 |
hurt | -0.109 |
sharp | -0.108 |
ggy | -0.103 |
bad | -0.100 |
Token | away |
Token ID | 1497 |
Feature activation | +2.16e+00 |
Pos logit contributions | |
Suz | +0.046 |
Su | +0.045 |
Mill | +0.044 |
Alf | +0.044 |
Sus | +0.043 |
Neg logit contributions | |
sharp | -0.028 |
ruined | -0.027 |
big | -0.027 |
bad | -0.026 |
hurt | -0.026 |
Token | . |
Token ID | 13 |
Feature activation | +2.48e+00 |
Pos logit contributions | |
Suz | +0.054 |
Su | +0.053 |
Mill | +0.052 |
Alf | +0.051 |
Sus | +0.051 |
Neg logit contributions | |
ruined | -0.039 |
sharp | -0.037 |
hurt | -0.036 |
ggy | -0.036 |
sting | -0.035 |
Token | It |
Token ID | 632 |
Feature activation | -2.05e+00 |
Pos logit contributions | |
cities | +0.049 |
Suz | +0.049 |
Alf | +0.048 |
Su | +0.048 |
ho | +0.047 |
Neg logit contributions | |
two | -0.043 |
sharp | -0.041 |
pain | -0.041 |
ching | -0.041 |
ruined | -0.040 |
Token | was |
Token ID | 373 |
Feature activation | -5.10e+00 |
Pos logit contributions | |
wy | +0.038 |
istered | +0.037 |
ruined | +0.035 |
ggy | +0.035 |
ggie | +0.035 |
Neg logit contributions | |
Suz | -0.051 |
Mill | -0.050 |
Su | -0.050 |
Sus | -0.049 |
Alf | -0.049 |
Token | Peter |
Token ID | 19727 |
Feature activation | -3.01e-01 |
Pos logit contributions | |
wy | +0.091 |
ruined | +0.088 |
istered | +0.085 |
sting | +0.084 |
ggy | +0.084 |
Neg logit contributions | |
Mill | -0.095 |
Suz | -0.095 |
Alf | -0.092 |
Sus | -0.092 |
Su | -0.092 |
Token | was |
Token ID | 373 |
Feature activation | -5.63e+00 |
Pos logit contributions | |
wy | +0.006 |
istered | +0.006 |
ruined | +0.006 |
uch | +0.006 |
ggy | +0.006 |
Neg logit contributions | |
Suz | -0.007 |
Su | -0.007 |
Sus | -0.007 |
Mill | -0.007 |
Alf | -0.006 |
Token | sad |
Token ID | 6507 |
Feature activation | -5.96e-01 |
Pos logit contributions | |
wy | +0.125 |
istered | +0.112 |
ruined | +0.111 |
uch | +0.110 |
ggy | +0.110 |
Neg logit contributions | |
Suz | -0.127 |
Su | -0.127 |
Sus | -0.125 |
Mill | -0.123 |
Alf | -0.118 |
Token | that |
Token ID | 326 |
Feature activation | +2.50e+00 |
Pos logit contributions | |
ruined | +0.013 |
wy | +0.013 |
sharp | +0.012 |
ggy | +0.012 |
istered | +0.012 |
Neg logit contributions | |
Suz | -0.013 |
Su | -0.013 |
Mill | -0.012 |
Sus | -0.012 |
Alf | -0.012 |
Token | the |
Token ID | 262 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
Suz | +0.058 |
ress | +0.058 |
iked | +0.058 |
Ally | +0.058 |
Hil | +0.058 |
Neg logit contributions | |
bad | -0.046 |
hurt | -0.046 |
pain | -0.045 |
ruined | -0.044 |
sharp | -0.043 |
Token | ot |
Token ID | 30972 |
Feature activation | +3.43e+00 |
Pos logit contributions | |
Suz | +0.016 |
Su | +0.016 |
Mill | +0.015 |
Sus | +0.015 |
Alf | +0.014 |
Neg logit contributions | |
ruined | -0.038 |
wy | -0.037 |
sharp | -0.037 |
hurt | -0.036 |
pain | -0.036 |
Token | ter |
Token ID | 353 |
Feature activation | +6.95e-01 |
Pos logit contributions | |
Suz | +0.057 |
Su | +0.057 |
Mill | +0.056 |
Sus | +0.056 |
Alf | +0.054 |
Neg logit contributions | |
ruined | -0.090 |
wy | -0.088 |
ggy | -0.085 |
sharp | -0.085 |
uch | -0.084 |
Token | was |
Token ID | 373 |
Feature activation | -4.51e+00 |
Pos logit contributions | |
Suz | +0.018 |
Su | +0.018 |
Mill | +0.018 |
Sus | +0.017 |
Alf | +0.017 |
Neg logit contributions | |
wy | -0.012 |
ruined | -0.012 |
ggy | -0.011 |
sharp | -0.011 |
istered | -0.011 |
Token | gone |
Token ID | 3750 |
Feature activation | -8.55e-01 |
Pos logit contributions | |
wy | +0.084 |
istered | +0.077 |
uch | +0.076 |
ggy | +0.074 |
arest | +0.073 |
Neg logit contributions | |
Sus | -0.114 |
Su | -0.114 |
Suz | -0.113 |
Mill | -0.112 |
Alf | -0.106 |
Token | , |
Token ID | 11 |
Feature activation | +3.77e+00 |
Pos logit contributions | |
wy | +0.018 |
ruined | +0.017 |
ggy | +0.017 |
ggie | +0.017 |
istered | +0.017 |
Neg logit contributions | |
Suz | -0.019 |
Su | -0.019 |
Mill | -0.019 |
Sus | -0.018 |
Alf | -0.018 |
Token | but |
Token ID | 475 |
Feature activation | +4.69e+00 |
Pos logit contributions | |
Suz | +0.088 |
Alf | +0.084 |
Su | +0.084 |
Mill | +0.083 |
Jan | +0.081 |
Neg logit contributions | |
ruined | -0.076 |
sharp | -0.074 |
hurt | -0.072 |
pain | -0.070 |
bad | -0.070 |
Token | . |
Token ID | 13 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
Su | +0.019 |
Suz | +0.019 |
Mill | +0.018 |
Alf | +0.018 |
Sus | +0.018 |
Neg logit contributions | |
ruined | -0.009 |
sharp | -0.008 |
ggy | -0.008 |
burns | -0.008 |
hurt | -0.008 |
Token | |
Token ID | 220 |
Feature activation | -5.15e+00 |
Pos logit contributions | |
ho | +0.031 |
Suz | +0.031 |
Su | +0.030 |
ress | +0.030 |
iked | +0.030 |
Neg logit contributions | |
two | -0.019 |
A | -0.018 |
ruined | -0.018 |
Deal | -0.018 |
big | -0.018 |
Token |
|
Token ID | 198 |
Feature activation | -4.75e+00 |
Pos logit contributions | |
ruined | +0.098 |
ggy | +0.096 |
wy | +0.096 |
ggie | +0.092 |
sharp | +0.092 |
Neg logit contributions | |
Suz | -0.118 |
Su | -0.117 |
Mill | -0.116 |
Sus | -0.114 |
Alf | -0.112 |
Token |
|
Token ID | 198 |
Feature activation | -3.95e+00 |
Pos logit contributions | |
ggy | +0.088 |
ruined | +0.088 |
wy | +0.088 |
ggie | +0.085 |
sharp | +0.084 |
Neg logit contributions | |
Suz | -0.112 |
Su | -0.110 |
Mill | -0.109 |
Sus | -0.108 |
Alf | -0.107 |
Token | On |
Token ID | 2202 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
ruined | +0.048 |
wy | +0.048 |
ggy | +0.047 |
ggie | +0.045 |
sharp | +0.044 |
Neg logit contributions | |
Suz | -0.120 |
Su | -0.119 |
Mill | -0.119 |
Sus | -0.117 |
Alf | -0.116 |
Token | Monday |
Token ID | 3321 |
Feature activation | +4.16e+00 |
Pos logit contributions | |
ruined | +0.035 |
wy | +0.035 |
ggy | +0.034 |
sharp | +0.033 |
ggie | +0.033 |
Neg logit contributions | |
Suz | -0.032 |
Su | -0.031 |
Mill | -0.031 |
Sus | -0.031 |
Alf | -0.030 |
Token | morning |
Token ID | 3329 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
Suz | +0.109 |
Cr | +0.105 |
Su | +0.104 |
Alf | +0.102 |
Jan | +0.099 |
Neg logit contributions | |
big | -0.058 |
ggie | -0.056 |
ggy | -0.056 |
two | -0.055 |
time | -0.055 |
Token | , |
Token ID | 11 |
Feature activation | +4.29e+00 |
Pos logit contributions | |
Suz | +0.040 |
Su | +0.040 |
Mill | +0.039 |
Alf | +0.039 |
Sus | +0.038 |
Neg logit contributions | |
ruined | -0.041 |
ggy | -0.040 |
wy | -0.039 |
sharp | -0.039 |
ggie | -0.039 |
Token | the |
Token ID | 262 |
Feature activation | +6.72e-01 |
Pos logit contributions | |
Suz | +0.087 |
Su | +0.085 |
Mill | +0.084 |
Alf | +0.083 |
Sus | +0.081 |
Neg logit contributions | |
ruined | -0.090 |
sharp | -0.087 |
ggy | -0.086 |
ggie | -0.084 |
bad | -0.084 |
Token | family |
Token ID | 1641 |
Feature activation | +6.76e-01 |
Pos logit contributions | |
Su | +0.016 |
Suz | +0.016 |
Sus | +0.015 |
Mill | +0.015 |
Alf | +0.015 |
Neg logit contributions | |
ruined | -0.013 |
sharp | -0.013 |
wy | -0.013 |
pain | -0.012 |
naughty | -0.012 |
Token | gathered |
Token ID | 9272 |
Feature activation | +2.07e+00 |
Pos logit contributions | |
Suz | +0.017 |
Su | +0.017 |
Mill | +0.016 |
Sus | +0.016 |
Alf | +0.016 |
Neg logit contributions | |
ruined | -0.012 |
wy | -0.012 |
sharp | -0.011 |
burns | -0.011 |
ggy | -0.011 |
Token | , |
Token ID | 11 |
Feature activation | +2.55e+00 |
Pos logit contributions | |
sharp | +0.001 |
ruined | +0.001 |
bad | +0.001 |
pain | +0.001 |
hurt | +0.001 |
Neg logit contributions | |
Suz | -0.002 |
Alf | -0.002 |
Su | -0.002 |
Mill | -0.002 |
Sus | -0.002 |
Token | but |
Token ID | 475 |
Feature activation | +4.21e+00 |
Pos logit contributions | |
Suz | +0.064 |
ress | +0.064 |
Sus | +0.062 |
Alf | +0.062 |
Su | +0.061 |
Neg logit contributions | |
sharp | -0.047 |
hurt | -0.045 |
bad | -0.044 |
ruined | -0.043 |
not | -0.043 |
Token | she |
Token ID | 673 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
Suz | +0.091 |
Su | +0.090 |
Alf | +0.089 |
Sus | +0.089 |
Mill | +0.088 |
Neg logit contributions | |
ruined | -0.090 |
sharp | -0.089 |
hurt | -0.086 |
ggy | -0.084 |
bad | -0.083 |
Token | was |
Token ID | 373 |
Feature activation | -5.06e+00 |
Pos logit contributions | |
wy | +0.032 |
istered | +0.031 |
ps | +0.030 |
arest | +0.029 |
burns | +0.029 |
Neg logit contributions | |
Suz | -0.027 |
Su | -0.026 |
Mill | -0.026 |
Sus | -0.026 |
Alf | -0.025 |
Token | brave |
Token ID | 14802 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
wy | +0.097 |
uch | +0.090 |
istered | +0.086 |
burns | +0.084 |
itch | +0.083 |
Neg logit contributions | |
Suz | -0.127 |
Su | -0.126 |
Mill | -0.125 |
Sus | -0.124 |
K | -0.118 |
Token | and |
Token ID | 290 |
Feature activation | +3.73e+00 |
Pos logit contributions | |
ruined | +0.002 |
wy | +0.002 |
ggy | +0.002 |
sharp | +0.002 |
istered | +0.002 |
Neg logit contributions | |
Suz | -0.003 |
Su | -0.003 |
Mill | -0.003 |
Sus | -0.003 |
Alf | -0.003 |
Token | decided |
Token ID | 3066 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
Suz | +0.097 |
Su | +0.096 |
Sus | +0.095 |
Mill | +0.095 |
Alf | +0.095 |
Neg logit contributions | |
ruined | -0.064 |
sharp | -0.062 |
ggy | -0.060 |
wy | -0.059 |
hurt | -0.058 |
Token | to |
Token ID | 284 |
Feature activation | -3.13e-01 |
Pos logit contributions | |
Suz | +0.036 |
Alf | +0.036 |
Su | +0.034 |
Jos | +0.034 |
Mill | +0.034 |
Neg logit contributions | |
sharp | -0.031 |
hurt | -0.031 |
ruined | -0.030 |
ggy | -0.030 |
bad | -0.030 |
Token | go |
Token ID | 467 |
Feature activation | +8.08e-01 |
Pos logit contributions | |
wy | +0.006 |
ruined | +0.006 |
istered | +0.006 |
ggy | +0.005 |
sharp | +0.005 |
Neg logit contributions | |
Suz | -0.008 |
Mill | -0.007 |
Su | -0.007 |
Sus | -0.007 |
Alf | -0.007 |
Token | in |
Token ID | 287 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
Suz | +0.019 |
Su | +0.018 |
Mill | +0.018 |
Sus | +0.018 |
Alf | +0.018 |
Neg logit contributions | |
ruined | -0.016 |
wy | -0.016 |
sharp | -0.015 |
ggy | -0.015 |
hurt | -0.015 |
Token | anyway |
Token ID | 6949 |
Feature activation | +8.17e-01 |
Pos logit contributions | |
Suz | +0.035 |
Su | +0.035 |
Mill | +0.034 |
Alf | +0.034 |
Sus | +0.034 |
Neg logit contributions | |
ruined | -0.018 |
sharp | -0.017 |
ggy | -0.017 |
pain | -0.016 |
hurt | -0.016 |
Token | was |
Token ID | 373 |
Feature activation | -5.58e+00 |
Pos logit contributions | |
ruined | +0.054 |
wy | +0.053 |
ggy | +0.050 |
sharp | +0.050 |
istered | +0.049 |
Neg logit contributions | |
Suz | -0.088 |
Su | -0.087 |
Mill | -0.086 |
Sus | -0.086 |
Alf | -0.085 |
Token | messy |
Token ID | 24097 |
Feature activation | -8.85e-01 |
Pos logit contributions | |
wy | +0.083 |
arest | +0.080 |
istered | +0.078 |
uch | +0.078 |
ggy | +0.076 |
Neg logit contributions | |
Suz | -0.158 |
Su | -0.157 |
Mill | -0.156 |
Sus | -0.154 |
Alf | -0.150 |
Token | , |
Token ID | 11 |
Feature activation | +3.38e+00 |
Pos logit contributions | |
wy | +0.017 |
ruined | +0.017 |
ggy | +0.016 |
sharp | +0.016 |
ggie | +0.016 |
Neg logit contributions | |
Suz | -0.021 |
Su | -0.021 |
Mill | -0.021 |
Sus | -0.020 |
Alf | -0.020 |
Token | sticks |
Token ID | 16461 |
Feature activation | -8.37e-02 |
Pos logit contributions | |
Suz | +0.081 |
Mill | +0.081 |
Alf | +0.080 |
Su | +0.079 |
Sus | +0.079 |
Neg logit contributions | |
ruined | -0.066 |
sharp | -0.064 |
bad | -0.060 |
hurt | -0.060 |
pain | -0.059 |
Token | poking |
Token ID | 39048 |
Feature activation | +3.26e+00 |
Pos logit contributions | |
wy | +0.002 |
ruined | +0.002 |
ggy | +0.002 |
ggie | +0.002 |
sharp | +0.002 |
Neg logit contributions | |
Suz | -0.002 |
Su | -0.002 |
Mill | -0.002 |
Sus | -0.002 |
Alf | -0.002 |
Token | out |
Token ID | 503 |
Feature activation | +2.37e+00 |
Pos logit contributions | |
Suz | +0.075 |
Su | +0.075 |
Mill | +0.073 |
Sus | +0.073 |
Alf | +0.072 |
Neg logit contributions | |
sharp | -0.065 |
ruined | -0.065 |
wy | -0.061 |
burns | -0.060 |
bad | -0.060 |
Token | and |
Token ID | 290 |
Feature activation | +6.28e+00 |
Pos logit contributions | |
Suz | +0.063 |
Su | +0.063 |
Mill | +0.063 |
Sus | +0.062 |
Alf | +0.061 |
Neg logit contributions | |
ruined | -0.038 |
sharp | -0.036 |
wy | -0.035 |
burns | -0.034 |
pain | -0.033 |
Token | leaves |
Token ID | 5667 |
Feature activation | +3.07e-01 |
Pos logit contributions | |
Su | +0.154 |
Suz | +0.152 |
Mill | +0.151 |
Alf | +0.151 |
Sus | +0.149 |
Neg logit contributions | |
ruined | -0.122 |
sharp | -0.114 |
hurt | -0.113 |
sting | -0.109 |
burns | -0.108 |
Token | all |
Token ID | 477 |
Feature activation | +2.75e+00 |
Pos logit contributions | |
Suz | +0.008 |
Su | +0.008 |
Mill | +0.008 |
Sus | +0.008 |
Alf | +0.007 |
Neg logit contributions | |
wy | -0.005 |
ruined | -0.005 |
ggy | -0.005 |
sharp | -0.005 |
ggie | -0.005 |
Token | over |
Token ID | 625 |
Feature activation | +4.12e+00 |
Pos logit contributions | |
Alf | +0.058 |
Su | +0.057 |
Mill | +0.057 |
Suz | +0.057 |
ress | +0.055 |
Neg logit contributions | |
ruined | -0.063 |
hurt | -0.057 |
sharp | -0.056 |
wy | -0.056 |
bad | -0.056 |
Token | the |
Token ID | 262 |
Feature activation | +3.42e+00 |
Pos logit contributions | |
Suz | +0.095 |
Su | +0.094 |
Alf | +0.094 |
Mill | +0.094 |
Sus | +0.092 |
Neg logit contributions | |
ruined | -0.080 |
sharp | -0.078 |
hurt | -0.073 |
pain | -0.073 |
bad | -0.073 |
Token | , |
Token ID | 11 |
Feature activation | +3.32e+00 |
Pos logit contributions | |
ruined | +0.017 |
wy | +0.017 |
ggy | +0.016 |
sharp | +0.016 |
istered | +0.016 |
Neg logit contributions | |
Suz | -0.014 |
Su | -0.014 |
Mill | -0.014 |
Sus | -0.014 |
Alf | -0.014 |
Token | her |
Token ID | 607 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
Suz | +0.054 |
Su | +0.054 |
Mill | +0.053 |
Alf | +0.053 |
Sus | +0.051 |
Neg logit contributions | |
ruined | -0.088 |
sharp | -0.084 |
ggy | -0.083 |
wy | -0.083 |
hurt | -0.082 |
Token | mom |
Token ID | 1995 |
Feature activation | +6.57e-01 |
Pos logit contributions | |
Suz | +0.003 |
Su | +0.003 |
Sus | +0.003 |
Jan | +0.003 |
Alf | +0.003 |
Neg logit contributions | |
wy | -0.004 |
arest | -0.003 |
istered | -0.003 |
ery | -0.003 |
uch | -0.003 |
Token | my |
Token ID | 1820 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
Suz | +0.015 |
Su | +0.015 |
Mill | +0.015 |
Sus | +0.014 |
Alf | +0.014 |
Neg logit contributions | |
ruined | -0.013 |
wy | -0.013 |
ggy | -0.012 |
sharp | -0.012 |
hurt | -0.012 |
Token | helped |
Token ID | 4193 |
Feature activation | +4.56e+00 |
Pos logit contributions | |
ruined | +0.021 |
wy | +0.021 |
ggy | +0.020 |
sharp | +0.019 |
ggie | +0.019 |
Neg logit contributions | |
Suz | -0.030 |
Su | -0.029 |
Mill | -0.029 |
Sus | -0.029 |
Alf | -0.029 |
Token | her |
Token ID | 607 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
Suz | +0.085 |
Su | +0.084 |
Mill | +0.082 |
Alf | +0.081 |
Sus | +0.081 |
Neg logit contributions | |
ruined | -0.111 |
wy | -0.109 |
ggy | -0.106 |
sharp | -0.106 |
sting | -0.104 |
Token | get |
Token ID | 651 |
Feature activation | -2.57e+00 |
Pos logit contributions | |
Su | +0.028 |
Suz | +0.028 |
Sus | +0.027 |
Mill | +0.027 |
Alf | +0.026 |
Neg logit contributions | |
wy | -0.025 |
ruined | -0.023 |
istered | -0.023 |
uch | -0.022 |
sharp | -0.022 |
Token | ready |
Token ID | 3492 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
ruined | +0.045 |
wy | +0.044 |
sharp | +0.042 |
ggy | +0.042 |
istered | +0.041 |
Neg logit contributions | |
Suz | -0.066 |
Su | -0.065 |
Mill | -0.065 |
Sus | -0.064 |
Alf | -0.063 |
Token | for |
Token ID | 329 |
Feature activation | -4.65e-02 |
Pos logit contributions | |
Suz | +0.025 |
Su | +0.024 |
Mill | +0.024 |
Sus | +0.023 |
Alf | +0.023 |
Neg logit contributions | |
ruined | -0.029 |
wy | -0.029 |
sharp | -0.028 |
ggy | -0.028 |
burns | -0.027 |
Token | class |
Token ID | 1398 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
wy | +0.001 |
ruined | +0.001 |
ggy | +0.001 |
istered | +0.001 |
sharp | +0.001 |
Neg logit contributions | |
Suz | -0.001 |
Su | -0.001 |
Sus | -0.001 |
Mill | -0.001 |
Alf | -0.001 |
Token | by |
Token ID | 416 |
Feature activation | +7.28e-01 |
Pos logit contributions | |
ruined | +0.026 |
wy | +0.026 |
ggy | +0.025 |
sharp | +0.024 |
ggie | +0.024 |
Neg logit contributions | |
Suz | -0.044 |
Su | -0.043 |
Mill | -0.043 |
Sus | -0.043 |
Alf | -0.042 |
Token | big |
Token ID | 1263 |
Feature activation | -2.39e-01 |
Pos logit contributions | |
wy | +0.053 |
ruined | +0.048 |
istered | +0.046 |
ps | +0.045 |
burns | +0.045 |
Neg logit contributions | |
Suz | -0.107 |
Su | -0.106 |
Mill | -0.105 |
Sus | -0.105 |
Ally | -0.100 |
Token | k |
Token ID | 479 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
ruined | +0.005 |
sharp | +0.005 |
wy | +0.005 |
pain | +0.005 |
ggy | +0.005 |
Neg logit contributions | |
Suz | -0.005 |
Su | -0.005 |
Alf | -0.005 |
Mill | -0.005 |
Sus | -0.005 |
Token | ite |
Token ID | 578 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
Suz | +0.026 |
Su | +0.026 |
Mill | +0.025 |
Sus | +0.025 |
Alf | +0.024 |
Neg logit contributions | |
ruined | -0.036 |
wy | -0.036 |
ggy | -0.035 |
sharp | -0.035 |
istered | -0.034 |
Token | with |
Token ID | 351 |
Feature activation | +6.11e-01 |
Pos logit contributions | |
Suz | +0.004 |
Su | +0.004 |
Mill | +0.004 |
Sus | +0.004 |
Alf | +0.004 |
Neg logit contributions | |
ruined | -0.002 |
wy | -0.002 |
ggy | -0.002 |
sharp | -0.002 |
istered | -0.002 |
Token | a |
Token ID | 257 |
Feature activation | -3.69e+00 |
Pos logit contributions | |
Suz | +0.017 |
Su | +0.016 |
Mill | +0.016 |
Sus | +0.016 |
Alf | +0.016 |
Neg logit contributions | |
wy | -0.010 |
ruined | -0.010 |
ggy | -0.009 |
istered | -0.009 |
ggie | -0.009 |
Token | colorful |
Token ID | 20239 |
Feature activation | -7.36e-01 |
Pos logit contributions | |
wy | +0.070 |
istered | +0.056 |
ruined | +0.056 |
burns | +0.056 |
ggy | +0.056 |
Neg logit contributions | |
Mill | -0.096 |
Suz | -0.095 |
Su | -0.095 |
Sus | -0.095 |
Alf | -0.094 |
Token | tail |
Token ID | 7894 |
Feature activation | -9.20e-02 |
Pos logit contributions | |
wy | +0.012 |
ruined | +0.012 |
ggy | +0.011 |
istered | +0.011 |
ggie | +0.011 |
Neg logit contributions | |
Suz | -0.019 |
Su | -0.019 |
Mill | -0.019 |
Sus | -0.019 |
Alf | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | +2.53e+00 |
Pos logit contributions | |
wy | +0.002 |
ruined | +0.002 |
istered | +0.002 |
ggy | +0.002 |
uch | +0.002 |
Neg logit contributions | |
Suz | -0.002 |
Su | -0.002 |
Mill | -0.002 |
Sus | -0.002 |
Alf | -0.002 |
Token | Anna |
Token ID | 11735 |
Feature activation | -9.40e-01 |
Pos logit contributions | |
Suz | +0.061 |
Su | +0.060 |
Mill | +0.059 |
Sus | +0.058 |
Alf | +0.058 |
Neg logit contributions | |
ruined | -0.047 |
wy | -0.045 |
ggy | -0.045 |
ggie | -0.044 |
sharp | -0.044 |
Token | and |
Token ID | 290 |
Feature activation | +5.65e+00 |
Pos logit contributions | |
wy | +0.018 |
ruined | +0.017 |
istered | +0.017 |
ggy | +0.016 |
burns | +0.016 |
Neg logit contributions | |
Suz | -0.023 |
Su | -0.022 |
Mill | -0.022 |
Sus | -0.022 |
Alf | -0.022 |
Token | her |
Token ID | 607 |
Feature activation | +6.48e-01 |
Pos logit contributions | |
Suz | +0.106 |
Su | +0.104 |
Mill | +0.103 |
Sus | +0.101 |
Alf | +0.099 |
Neg logit contributions | |
ruined | -0.139 |
wy | -0.137 |
ggy | -0.133 |
sharp | -0.132 |
ggie | -0.131 |
Token | do |
Token ID | 466 |
Feature activation | -4.27e+00 |
Pos logit contributions | |
wy | +0.080 |
istered | +0.074 |
ps | +0.073 |
sting | +0.072 |
itching | +0.071 |
Neg logit contributions | |
Su | -0.103 |
Sus | -0.102 |
Suz | -0.101 |
Mill | -0.100 |
Jan | -0.100 |
Token | you |
Token ID | 345 |
Feature activation | -4.09e+00 |
Pos logit contributions | |
wy | +0.090 |
ruined | +0.089 |
istered | +0.086 |
ps | +0.082 |
sharp | +0.081 |
Neg logit contributions | |
Suz | -0.096 |
Mill | -0.095 |
Su | -0.094 |
Sus | -0.094 |
Alf | -0.091 |
Token | have |
Token ID | 423 |
Feature activation | -5.20e+00 |
Pos logit contributions | |
istered | +0.077 |
ggy | +0.076 |
wy | +0.075 |
ggie | +0.074 |
burns | +0.070 |
Neg logit contributions | |
Suz | -0.102 |
Mill | -0.100 |
Su | -0.099 |
Sus | -0.098 |
Alf | -0.095 |
Token | in |
Token ID | 287 |
Feature activation | -2.67e-01 |
Pos logit contributions | |
wy | +0.108 |
ruined | +0.105 |
istered | +0.103 |
ggy | +0.102 |
sharp | +0.100 |
Neg logit contributions | |
Suz | -0.117 |
Su | -0.116 |
Mill | -0.115 |
Sus | -0.115 |
Alf | -0.111 |
Token | the |
Token ID | 262 |
Feature activation | +9.70e-01 |
Pos logit contributions | |
wy | +0.007 |
istered | +0.006 |
ruined | +0.006 |
ggy | +0.006 |
ggie | +0.006 |
Neg logit contributions | |
Su | -0.005 |
Suz | -0.005 |
Mill | -0.005 |
Sus | -0.005 |
Alf | -0.005 |
Token | jar |
Token ID | 17379 |
Feature activation | -2.03e+00 |
Pos logit contributions | |
Suz | +0.025 |
Su | +0.024 |
Sus | +0.024 |
Mill | +0.024 |
Alf | +0.023 |
Neg logit contributions | |
wy | -0.017 |
ruined | -0.016 |
ggy | -0.016 |
ggie | -0.016 |
ps | -0.016 |
Token | ?" |
Token ID | 1701 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
wy | +0.034 |
ruined | +0.033 |
istered | +0.032 |
ggy | +0.032 |
sharp | +0.032 |
Neg logit contributions | |
Suz | -0.053 |
Mill | -0.052 |
Su | -0.052 |
Sus | -0.052 |
Alf | -0.050 |
Token | he |
Token ID | 339 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
Suz | +0.039 |
Su | +0.037 |
Mill | +0.035 |
Hil | +0.035 |
Jan | +0.034 |
Neg logit contributions | |
ruined | -0.031 |
hurt | -0.031 |
sharp | -0.030 |
bad | -0.029 |
ggy | -0.028 |
Token | asked |
Token ID | 1965 |
Feature activation | +3.49e+00 |
Pos logit contributions | |
ruined | +0.028 |
wy | +0.027 |
sharp | +0.026 |
ggy | +0.026 |
ggie | +0.026 |
Neg logit contributions | |
Suz | -0.028 |
Su | -0.028 |
Mill | -0.027 |
Sus | -0.027 |
Alf | -0.027 |
Token | . |
Token ID | 13 |
Feature activation | +2.63e+00 |
Pos logit contributions | |
Suz | +0.092 |
Su | +0.088 |
Mill | +0.085 |
Hil | +0.085 |
Ally | +0.084 |
Neg logit contributions | |
ruined | -0.056 |
hurt | -0.054 |
sharp | -0.053 |
ggy | -0.052 |
bad | -0.052 |
Token | |
Token ID | 220 |
Feature activation | -4.28e+00 |
Pos logit contributions | |
Suz | +0.065 |
Su | +0.060 |
Hil | +0.058 |
cities | +0.058 |
Ally | +0.057 |
Neg logit contributions | |
hurt | -0.042 |
big | -0.042 |
sharp | -0.042 |
ruined | -0.042 |
A | -0.041 |
Token | It |
Token ID | 632 |
Feature activation | -3.02e+00 |
Pos logit contributions | |
Suz | +0.034 |
Su | +0.033 |
Mill | +0.032 |
Sus | +0.032 |
Alf | +0.032 |
Neg logit contributions | |
ruined | -0.044 |
wy | -0.044 |
ggy | -0.042 |
sharp | -0.041 |
ggie | -0.041 |
Token | hurts |
Token ID | 20406 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
arest | +0.051 |
wy | +0.051 |
ggie | +0.049 |
istered | +0.049 |
kin | +0.048 |
Neg logit contributions | |
Suz | -0.073 |
Mill | -0.069 |
Alf | -0.068 |
Su | -0.068 |
Sus | -0.067 |
Token | my |
Token ID | 616 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
Suz | +0.005 |
Su | +0.005 |
Sus | +0.005 |
Mill | +0.005 |
Alf | +0.004 |
Neg logit contributions | |
wy | -0.004 |
ruined | -0.004 |
istered | -0.004 |
ggy | -0.004 |
ggie | -0.004 |
Token | mouth |
Token ID | 5422 |
Feature activation | -1.78e+00 |
Pos logit contributions | |
Suz | +0.003 |
Su | +0.003 |
Sus | +0.003 |
Alf | +0.003 |
Mill | +0.003 |
Neg logit contributions | |
wy | -0.002 |
ruined | -0.002 |
ching | -0.002 |
arest | -0.002 |
ggy | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
wy | +0.041 |
ggie | +0.040 |
ggy | +0.040 |
arest | +0.039 |
Jeremy | +0.038 |
Neg logit contributions | |
Suz | -0.030 |
Su | -0.030 |
Sus | -0.029 |
line | -0.028 |
Mill | -0.027 |
Token | It |
Token ID | 632 |
Feature activation | -3.30e+00 |
Pos logit contributions | |
Suz | +0.028 |
Su | +0.027 |
Mill | +0.027 |
Sus | +0.026 |
Alf | +0.026 |
Neg logit contributions | |
ruined | -0.036 |
wy | -0.036 |
ggy | -0.034 |
sharp | -0.034 |
ggie | -0.034 |
Token | is |
Token ID | 318 |
Feature activation | -5.62e+00 |
Pos logit contributions | |
arest | +0.058 |
ggie | +0.057 |
wy | +0.056 |
kin | +0.055 |
ggy | +0.054 |
Neg logit contributions | |
Suz | -0.074 |
Alf | -0.071 |
bank | -0.071 |
Twe | -0.070 |
Mill | -0.069 |
Token | not |
Token ID | 407 |
Feature activation | -5.31e+00 |
Pos logit contributions | |
arest | +0.089 |
uch | +0.079 |
wy | +0.079 |
ggie | +0.079 |
ggy | +0.079 |
Neg logit contributions | |
Suz | -0.151 |
Su | -0.150 |
Mill | -0.146 |
Sus | -0.145 |
Alf | -0.142 |
Token | tasty |
Token ID | 25103 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
ggy | +0.070 |
wy | +0.070 |
uch | +0.070 |
istered | +0.069 |
ggie | +0.069 |
Neg logit contributions | |
Suz | -0.152 |
Su | -0.151 |
Mill | -0.149 |
Sus | -0.149 |
Alf | -0.145 |
Token | . |
Token ID | 13 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
ruined | +0.033 |
wy | +0.033 |
ggy | +0.032 |
uch | +0.031 |
istered | +0.031 |
Neg logit contributions | |
Suz | -0.039 |
Su | -0.039 |
Sus | -0.039 |
Mill | -0.038 |
Alf | -0.037 |
Token | It |
Token ID | 632 |
Feature activation | -3.30e+00 |
Pos logit contributions | |
Suz | +0.024 |
Su | +0.023 |
Mill | +0.023 |
Sus | +0.023 |
Alf | +0.022 |
Neg logit contributions | |
ruined | -0.034 |
wy | -0.033 |
ggy | -0.032 |
sharp | -0.031 |
ggie | -0.031 |
Token | wise |
Token ID | 10787 |
Feature activation | +3.70e+00 |
Pos logit contributions | |
Suz | +0.028 |
Su | +0.028 |
Mill | +0.028 |
Sus | +0.027 |
Alf | +0.027 |
Neg logit contributions | |
ruined | -0.023 |
wy | -0.023 |
ggy | -0.022 |
sharp | -0.021 |
istered | -0.021 |
Token | owl |
Token ID | 39610 |
Feature activation | +5.66e-01 |
Pos logit contributions | |
Suz | +0.087 |
Su | +0.086 |
Sus | +0.083 |
Mill | +0.082 |
Alf | +0.082 |
Neg logit contributions | |
sharp | -0.074 |
ruined | -0.072 |
pain | -0.070 |
hurt | -0.070 |
bad | -0.069 |
Token | knew |
Token ID | 2993 |
Feature activation | +6.25e-01 |
Pos logit contributions | |
Suz | +0.014 |
Su | +0.014 |
Mill | +0.014 |
Sus | +0.014 |
Alf | +0.014 |
Neg logit contributions | |
ruined | -0.010 |
wy | -0.010 |
ggy | -0.009 |
sharp | -0.009 |
istered | -0.009 |
Token | what |
Token ID | 644 |
Feature activation | -8.83e-01 |
Pos logit contributions | |
Suz | +0.014 |
Su | +0.014 |
Mill | +0.014 |
Alf | +0.014 |
Sus | +0.014 |
Neg logit contributions | |
ruined | -0.012 |
sharp | -0.012 |
ggy | -0.012 |
bad | -0.011 |
ggie | -0.011 |
Token | to |
Token ID | 284 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
ruined | +0.019 |
ggy | +0.018 |
wy | +0.018 |
sharp | +0.018 |
ggie | +0.018 |
Neg logit contributions | |
Suz | -0.019 |
Su | -0.019 |
Mill | -0.019 |
Sus | -0.019 |
Alf | -0.018 |
Token | do |
Token ID | 466 |
Feature activation | -2.87e+00 |
Pos logit contributions | |
Suz | +0.003 |
Mill | +0.003 |
Su | +0.003 |
Sus | +0.003 |
Ally | +0.003 |
Neg logit contributions | |
wy | -0.002 |
istered | -0.002 |
ifying | -0.002 |
obb | -0.002 |
ider | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | +2.40e+00 |
Pos logit contributions | |
wy | +0.056 |
ruined | +0.054 |
istered | +0.053 |
ggy | +0.051 |
sting | +0.051 |
Neg logit contributions | |
Suz | -0.067 |
Sus | -0.066 |
Su | -0.066 |
Mill | -0.066 |
Alf | -0.063 |
Token | He |
Token ID | 679 |
Feature activation | -3.29e-01 |
Pos logit contributions | |
Suz | +0.058 |
Su | +0.056 |
Hil | +0.055 |
Mill | +0.054 |
Alf | +0.054 |
Neg logit contributions | |
sharp | -0.039 |
ruined | -0.034 |
big | -0.033 |
Luckily | -0.033 |
A | -0.033 |
Token | took |
Token ID | 1718 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
wy | +0.007 |
istered | +0.007 |
uch | +0.007 |
ggy | +0.007 |
ruined | +0.007 |
Neg logit contributions | |
Suz | -0.007 |
Mill | -0.007 |
Su | -0.007 |
Alf | -0.007 |
Sus | -0.007 |
Token | the |
Token ID | 262 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
Suz | +0.034 |
Su | +0.034 |
Mill | +0.033 |
Sus | +0.033 |
Alf | +0.032 |
Neg logit contributions | |
ruined | -0.027 |
sharp | -0.026 |
wy | -0.026 |
pain | -0.025 |
ggy | -0.025 |
Token | nail |
Token ID | 17864 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
Suz | +0.028 |
Mill | +0.028 |
Su | +0.028 |
Sus | +0.027 |
Alf | +0.027 |
Neg logit contributions | |
wy | -0.032 |
istered | -0.030 |
ggy | -0.030 |
ggie | -0.030 |
ruined | -0.029 |
Token | with |
Token ID | 351 |
Feature activation | +3.94e-01 |
Pos logit contributions | |
Suz | +0.004 |
Su | +0.004 |
Mill | +0.004 |
Sus | +0.004 |
Alf | +0.004 |
Neg logit contributions | |
ruined | -0.003 |
wy | -0.003 |
ggy | -0.003 |
sharp | -0.003 |
ggie | -0.002 |
Token | her |
Token ID | 607 |
Feature activation | +9.12e-01 |
Pos logit contributions | |
Suz | +0.007 |
Su | +0.007 |
Mill | +0.007 |
Sus | +0.007 |
Alf | +0.007 |
Neg logit contributions | |
ruined | -0.009 |
wy | -0.009 |
ggy | -0.009 |
sharp | -0.009 |
ggie | -0.009 |
Token | new |
Token ID | 649 |
Feature activation | +2.25e+00 |
Pos logit contributions | |
Suz | +0.024 |
Su | +0.024 |
Mill | +0.023 |
Sus | +0.023 |
Alf | +0.023 |
Neg logit contributions | |
wy | -0.015 |
ruined | -0.015 |
ggy | -0.014 |
istered | -0.014 |
sharp | -0.014 |
Token | friend |
Token ID | 1545 |
Feature activation | +2.16e+00 |
Pos logit contributions | |
Suz | +0.057 |
Su | +0.056 |
Sus | +0.056 |
Mill | +0.056 |
Alf | +0.055 |
Neg logit contributions | |
wy | -0.041 |
ruined | -0.040 |
istered | -0.038 |
ggy | -0.037 |
burns | -0.036 |
Token | . |
Token ID | 13 |
Feature activation | +2.31e+00 |
Pos logit contributions | |
Suz | +0.062 |
Su | +0.061 |
Mill | +0.060 |
Sus | +0.060 |
Alf | +0.059 |
Neg logit contributions | |
ruined | -0.030 |
wy | -0.029 |
ggy | -0.029 |
ggie | -0.028 |
sharp | -0.028 |
Token | They |
Token ID | 1119 |
Feature activation | -6.60e-01 |
Pos logit contributions | |
Suz | +0.052 |
Su | +0.050 |
Mill | +0.050 |
Sus | +0.049 |
Alf | +0.048 |
Neg logit contributions | |
ggy | -0.043 |
ruined | -0.043 |
ggie | -0.042 |
burns | -0.041 |
sharp | -0.040 |
Token | would |
Token ID | 561 |
Feature activation | -2.25e+00 |
Pos logit contributions | |
ruined | +0.012 |
wy | +0.012 |
sharp | +0.011 |
ggy | +0.011 |
hurt | +0.010 |
Neg logit contributions | |
Suz | -0.017 |
Su | -0.017 |
Sus | -0.016 |
Mill | -0.016 |
Alf | -0.016 |
Token | play |
Token ID | 711 |
Feature activation | -9.40e-01 |
Pos logit contributions | |
ruined | +0.041 |
wy | +0.040 |
ggy | +0.039 |
sharp | +0.039 |
ggie | +0.038 |
Neg logit contributions | |
Suz | -0.055 |
Su | -0.055 |
Mill | -0.054 |
Sus | -0.054 |
Alf | -0.053 |
Token | games |
Token ID | 1830 |
Feature activation | +3.70e-01 |
Pos logit contributions | |
ruined | +0.022 |
ggy | +0.022 |
wy | +0.021 |
sharp | +0.021 |
ggie | +0.021 |
Neg logit contributions | |
Suz | -0.018 |
Su | -0.018 |
Mill | -0.018 |
Sus | -0.018 |
Alf | -0.017 |
Token | , |
Token ID | 11 |
Feature activation | +4.02e+00 |
Pos logit contributions | |
Su | +0.009 |
Suz | +0.009 |
Mill | +0.009 |
Sus | +0.008 |
Alf | +0.008 |
Neg logit contributions | |
ruined | -0.007 |
ggy | -0.007 |
wy | -0.007 |
sharp | -0.007 |
ggie | -0.007 |
Token | tell |
Token ID | 1560 |
Feature activation | +3.10e+00 |
Pos logit contributions | |
Mill | +0.103 |
Suz | +0.102 |
Su | +0.101 |
Sus | +0.100 |
Alf | +0.098 |
Neg logit contributions | |
ruined | -0.066 |
sharp | -0.065 |
big | -0.061 |
ggy | -0.060 |
hurt | -0.059 |
Token | vine |
Token ID | 17793 |
Feature activation | +2.65e+00 |
Pos logit contributions | |
Suz | +0.014 |
Su | +0.013 |
Mill | +0.013 |
Sus | +0.013 |
Alf | +0.013 |
Neg logit contributions | |
wy | -0.023 |
ruined | -0.023 |
istered | -0.022 |
ggy | -0.022 |
ggie | -0.021 |
Token | too |
Token ID | 1165 |
Feature activation | -3.21e+00 |
Pos logit contributions | |
Su | +0.072 |
Suz | +0.071 |
Mill | +0.070 |
Sus | +0.070 |
Alf | +0.068 |
Neg logit contributions | |
ruined | -0.044 |
wy | -0.041 |
ggy | -0.040 |
sharp | -0.040 |
hurt | -0.039 |
Token | , |
Token ID | 11 |
Feature activation | +3.75e+00 |
Pos logit contributions | |
wy | +0.067 |
ruined | +0.064 |
istered | +0.063 |
ggy | +0.062 |
ggie | +0.061 |
Neg logit contributions | |
Suz | -0.071 |
Mill | -0.071 |
Su | -0.070 |
Sus | -0.070 |
Alf | -0.067 |
Token | but |
Token ID | 475 |
Feature activation | +4.78e+00 |
Pos logit contributions | |
Mill | +0.083 |
Sus | +0.079 |
Suz | +0.078 |
bank | +0.078 |
Alf | +0.077 |
Neg logit contributions | |
sharp | -0.074 |
ruined | -0.071 |
bad | -0.070 |
hurt | -0.069 |
big | -0.069 |
Token | I |
Token ID | 314 |
Feature activation | -3.07e+00 |
Pos logit contributions | |
Su | +0.119 |
Suz | +0.119 |
Mill | +0.117 |
Sus | +0.116 |
Alf | +0.114 |
Neg logit contributions | |
ruined | -0.086 |
sharp | -0.082 |
wy | -0.079 |
ggy | -0.079 |
hurt | -0.077 |
Token | am |
Token ID | 716 |
Feature activation | -6.54e+00 |
Pos logit contributions | |
wy | +0.067 |
ps | +0.064 |
ggie | +0.063 |
arest | +0.062 |
ggy | +0.061 |
Neg logit contributions | |
Suz | -0.066 |
Sus | -0.064 |
Su | -0.061 |
Mill | -0.061 |
Alf | -0.059 |
Token | too |
Token ID | 1165 |
Feature activation | -7.46e+00 |
Pos logit contributions | |
wy | +0.110 |
ggy | +0.101 |
istered | +0.099 |
ggie | +0.099 |
uch | +0.098 |
Neg logit contributions | |
Suz | -0.179 |
Sus | -0.176 |
Mill | -0.176 |
Su | -0.174 |
Alf | -0.169 |
Token | small |
Token ID | 1402 |
Feature activation | -2.54e+00 |
Pos logit contributions | |
wy | +0.119 |
ggie | +0.108 |
ggy | +0.103 |
ps | +0.101 |
istered | +0.100 |
Neg logit contributions | |
Suz | -0.211 |
Su | -0.210 |
Mill | -0.207 |
Sus | -0.206 |
Jan | -0.197 |
Token | ." |
Token ID | 526 |
Feature activation | +2.03e+00 |
Pos logit contributions | |
wy | +0.052 |
ruined | +0.052 |
ggy | +0.050 |
sharp | +0.048 |
istered | +0.048 |
Neg logit contributions | |
Suz | -0.056 |
Su | -0.056 |
Mill | -0.055 |
Sus | -0.055 |
Alf | -0.054 |
Token | Bob |
Token ID | 5811 |
Feature activation | -3.16e-01 |
Pos logit contributions | |
cities | +0.042 |
ress | +0.038 |
reating | +0.037 |
spe | +0.037 |
line | +0.037 |
Neg logit contributions | |
ggy | -0.045 |
hurt | -0.040 |
ggie | -0.040 |
sharp | -0.040 |
A | -0.039 |
Token | o |
Token ID | 78 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
ruined | +0.009 |
wy | +0.009 |
ggy | +0.009 |
sharp | +0.009 |
ggie | +0.009 |
Neg logit contributions | |
Suz | -0.004 |
Su | -0.004 |
Mill | -0.004 |
Sus | -0.004 |
Alf | -0.004 |
Token | ways |
Token ID | 2842 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
ggie | +0.025 |
ggy | +0.025 |
uch | +0.024 |
istered | +0.024 |
wy | +0.023 |
Neg logit contributions | |
Suz | -0.024 |
Sus | -0.023 |
Mill | -0.023 |
Alf | -0.023 |
Su | -0.022 |
Token | to |
Token ID | 284 |
Feature activation | +3.69e-01 |
Pos logit contributions | |
Suz | +0.030 |
Su | +0.030 |
Mill | +0.029 |
Sus | +0.029 |
Alf | +0.028 |
Neg logit contributions | |
wy | -0.040 |
ruined | -0.039 |
ggy | -0.038 |
istered | -0.038 |
sharp | -0.038 |
Token | enjoy |
Token ID | 2883 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
Suz | +0.007 |
Sus | +0.007 |
Mill | +0.007 |
Su | +0.006 |
Alf | +0.006 |
Neg logit contributions | |
istered | -0.008 |
wy | -0.008 |
ggie | -0.008 |
ruined | -0.008 |
ggy | -0.008 |
Token | broccoli |
Token ID | 44653 |
Feature activation | -4.98e-01 |
Pos logit contributions | |
Suz | +0.005 |
Su | +0.005 |
Mill | +0.005 |
Sus | +0.005 |
Alf | +0.005 |
Neg logit contributions | |
ruined | -0.005 |
wy | -0.005 |
ggy | -0.005 |
istered | -0.005 |
ggie | -0.005 |
Token | ." |
Token ID | 526 |
Feature activation | +6.41e-01 |
Pos logit contributions | |
ruined | +0.011 |
wy | +0.011 |
ggy | +0.010 |
istered | +0.010 |
ggie | +0.010 |
Neg logit contributions | |
Mill | -0.010 |
Suz | -0.010 |
Sus | -0.009 |
Alf | -0.009 |
Su | -0.009 |
Token |
|
Token ID | 198 |
Feature activation | -5.44e+00 |
Pos logit contributions | |
Suz | +0.017 |
Su | +0.017 |
cities | +0.017 |
Alf | +0.017 |
Mill | +0.017 |
Neg logit contributions | |
ggy | -0.009 |
hurt | -0.008 |
pain | -0.008 |
bad | -0.008 |
sting | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | -4.73e+00 |
Pos logit contributions | |
ruined | +0.111 |
wy | +0.110 |
ggy | +0.109 |
sharp | +0.106 |
ggie | +0.105 |
Neg logit contributions | |
Suz | -0.121 |
Su | -0.120 |
Mill | -0.118 |
Sus | -0.118 |
Alf | -0.115 |
Token | L |
Token ID | 43 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
ruined | +0.067 |
wy | +0.066 |
ggy | +0.063 |
sharp | +0.062 |
ggie | +0.060 |
Neg logit contributions | |
Suz | -0.137 |
Su | -0.135 |
Mill | -0.134 |
Sus | -0.133 |
Alf | -0.131 |
Token | ily |
Token ID | 813 |
Feature activation | -1.86e+00 |
Pos logit contributions | |
ruined | +0.022 |
sharp | +0.021 |
wy | +0.021 |
istered | +0.021 |
sting | +0.020 |
Neg logit contributions | |
Su | -0.038 |
Suz | -0.038 |
Sus | -0.037 |
Alf | -0.036 |
Mill | -0.036 |
Token | was |
Token ID | 373 |
Feature activation | -5.91e+00 |
Pos logit contributions | |
wy | +0.041 |
istered | +0.041 |
arest | +0.041 |
ggy | +0.039 |
ruined | +0.039 |
Neg logit contributions | |
Suz | -0.037 |
Su | -0.037 |
Sus | -0.036 |
Mill | -0.035 |
Alf | -0.034 |
Token | still |
Token ID | 991 |
Feature activation | -3.81e+00 |
Pos logit contributions | |
wy | +0.138 |
arest | +0.129 |
uch | +0.126 |
itch | +0.124 |
istered | +0.122 |
Neg logit contributions | |
Su | -0.124 |
Suz | -0.120 |
Sus | -0.117 |
Mill | -0.111 |
K | -0.107 |
Token | rabbit |
Token ID | 22746 |
Feature activation | -8.48e-01 |
Pos logit contributions | |
ruined | +0.058 |
wy | +0.058 |
ggy | +0.052 |
burns | +0.051 |
istered | +0.051 |
Neg logit contributions | |
Suz | -0.156 |
Su | -0.156 |
Mill | -0.153 |
Sus | -0.153 |
Alf | -0.151 |
Token | named |
Token ID | 3706 |
Feature activation | +4.06e+00 |
Pos logit contributions | |
ggy | +0.017 |
ruined | +0.016 |
sharp | +0.016 |
hurt | +0.016 |
ggie | +0.016 |
Neg logit contributions | |
Su | -0.020 |
Suz | -0.020 |
Sus | -0.019 |
Mill | -0.019 |
Alf | -0.019 |
Token | Peter |
Token ID | 5613 |
Feature activation | -9.67e-01 |
Pos logit contributions | |
ress | +0.055 |
cities | +0.052 |
line | +0.052 |
iked | +0.052 |
Su | +0.051 |
Neg logit contributions | |
sharp | -0.114 |
ggy | -0.110 |
wy | -0.108 |
ruined | -0.107 |
big | -0.106 |
Token | . |
Token ID | 13 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
ruined | +0.016 |
wy | +0.015 |
ggy | +0.015 |
sharp | +0.014 |
istered | +0.014 |
Neg logit contributions | |
Suz | -0.026 |
Su | -0.026 |
Mill | -0.025 |
Sus | -0.025 |
Alf | -0.025 |
Token | He |
Token ID | 679 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
Su | +0.019 |
ress | +0.019 |
line | +0.017 |
iked | +0.017 |
Suz | +0.016 |
Neg logit contributions | |
sharp | -0.026 |
big | -0.025 |
funny | -0.024 |
ruined | -0.024 |
burns | -0.024 |
Token | was |
Token ID | 373 |
Feature activation | -6.94e+00 |
Pos logit contributions | |
istered | +0.036 |
wy | +0.036 |
arest | +0.035 |
Deal | +0.035 |
ps | +0.034 |
Neg logit contributions | |
Suz | -0.028 |
Mill | -0.028 |
Su | -0.027 |
Twe | -0.027 |
Alf | -0.027 |
Token | a |
Token ID | 257 |
Feature activation | -6.11e+00 |
Pos logit contributions | |
wy | +0.094 |
ruined | +0.092 |
istered | +0.085 |
ggy | +0.083 |
uch | +0.083 |
Neg logit contributions | |
Suz | -0.209 |
Su | -0.206 |
Mill | -0.205 |
Sus | -0.203 |
Alf | -0.202 |
Token | spoiled |
Token ID | 34781 |
Feature activation | -9.86e-01 |
Pos logit contributions | |
wy | +0.075 |
ruined | +0.074 |
ggy | +0.067 |
ps | +0.067 |
burns | +0.066 |
Neg logit contributions | |
Suz | -0.188 |
Su | -0.186 |
Mill | -0.185 |
Sus | -0.183 |
Alf | -0.181 |
Token | rabbit |
Token ID | 22746 |
Feature activation | -8.37e-01 |
Pos logit contributions | |
sharp | +0.020 |
ruined | +0.019 |
ggy | +0.018 |
bad | +0.018 |
wy | +0.018 |
Neg logit contributions | |
Suz | -0.023 |
Su | -0.022 |
Alf | -0.022 |
Mill | -0.022 |
Sus | -0.022 |
Token | , |
Token ID | 11 |
Feature activation | +2.81e+00 |
Pos logit contributions | |
ruined | +0.014 |
ggy | +0.014 |
sharp | +0.013 |
ggie | +0.013 |
wy | +0.013 |
Neg logit contributions | |
Suz | -0.022 |
Su | -0.022 |
Sus | -0.022 |
Mill | -0.022 |
Alf | -0.021 |
Token | living |
Token ID | 2877 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
Suz | +0.063 |
Su | +0.063 |
Mill | +0.062 |
Sus | +0.061 |
Alf | +0.061 |
Neg logit contributions | |
ruined | -0.057 |
sharp | -0.055 |
ggy | -0.055 |
hurt | -0.053 |
ggie | -0.052 |
Token | the |
Token ID | 262 |
Feature activation | +8.27e-01 |
Pos logit contributions | |
Suz | +0.023 |
Su | +0.023 |
Sus | +0.022 |
Mill | +0.022 |
Alf | +0.021 |
Neg logit contributions | |
wy | -0.031 |
uch | -0.030 |
ggy | -0.030 |
ruined | -0.030 |
istered | -0.029 |
Token | garden |
Token ID | 11376 |
Feature activation | +2.79e+00 |
Pos logit contributions | |
Suz | +0.018 |
Su | +0.018 |
Mill | +0.018 |
Sus | +0.017 |
Alf | +0.017 |
Neg logit contributions | |
ruined | -0.017 |
wy | -0.017 |
ggy | -0.017 |
sharp | -0.016 |
ggie | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
Suz | +0.081 |
Su | +0.080 |
Mill | +0.080 |
Sus | +0.079 |
Alf | +0.078 |
Neg logit contributions | |
ruined | -0.041 |
wy | -0.038 |
sharp | -0.037 |
ggy | -0.037 |
burns | -0.036 |
Token | They |
Token ID | 1119 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
Suz | +0.028 |
Mill | +0.028 |
Alf | +0.027 |
Su | +0.027 |
ress | +0.027 |
Neg logit contributions | |
ruined | -0.030 |
burns | -0.029 |
pain | -0.029 |
sharp | -0.028 |
bad | -0.028 |
Token | are |
Token ID | 389 |
Feature activation | -5.43e+00 |
Pos logit contributions | |
wy | +0.025 |
ggie | +0.024 |
ggy | +0.024 |
istered | +0.024 |
uch | +0.023 |
Neg logit contributions | |
Suz | -0.027 |
Su | -0.027 |
Alf | -0.027 |
Sus | -0.026 |
Mill | -0.026 |
Token | not |
Token ID | 407 |
Feature activation | -5.03e+00 |
Pos logit contributions | |
wy | +0.104 |
uch | +0.100 |
arest | +0.098 |
itch | +0.093 |
ggie | +0.091 |
Neg logit contributions | |
Su | -0.131 |
Suz | -0.131 |
Sus | -0.125 |
Mill | -0.124 |
Alf | -0.122 |
Token | happy |
Token ID | 3772 |
Feature activation | -4.83e-01 |
Pos logit contributions | |
wy | +0.093 |
ruined | +0.090 |
ggy | +0.088 |
ggie | +0.086 |
uch | +0.086 |
Neg logit contributions | |
Suz | -0.124 |
Su | -0.124 |
Sus | -0.121 |
Mill | -0.121 |
Alf | -0.118 |
Token | . |
Token ID | 13 |
Feature activation | +6.01e-01 |
Pos logit contributions | |
ruined | +0.008 |
wy | +0.007 |
ggy | +0.007 |
sharp | +0.007 |
burns | +0.007 |
Neg logit contributions | |
Suz | -0.013 |
Su | -0.013 |
Mill | -0.013 |
Sus | -0.013 |
Alf | -0.013 |
Token |
|
Token ID | 198 |
Feature activation | -5.90e+00 |
Pos logit contributions | |
Suz | +0.012 |
Mill | +0.012 |
Su | +0.012 |
Sus | +0.011 |
Alf | +0.011 |
Neg logit contributions | |
ruined | -0.014 |
burns | -0.013 |
ggy | -0.013 |
sharp | -0.013 |
pain | -0.013 |
Token |
|
Token ID | 198 |
Feature activation | -4.76e+00 |
Pos logit contributions | |
wy | +0.131 |
ruined | +0.131 |
ggy | +0.123 |
sharp | +0.123 |
istered | +0.122 |
Neg logit contributions | |
Suz | -0.123 |
Su | -0.122 |
Mill | -0.120 |
Sus | -0.119 |
Alf | -0.117 |
Token | " |
Token ID | 1 |
Feature activation | -2.74e-01 |
Pos logit contributions | |
ruined | +0.077 |
wy | +0.077 |
istered | +0.071 |
sharp | +0.071 |
ggy | +0.070 |
Neg logit contributions | |
Suz | -0.128 |
Su | -0.128 |
Mill | -0.124 |
Sus | -0.124 |
Alf | -0.122 |
Token | kept |
Token ID | 4030 |
Feature activation | +5.53e-01 |
Pos logit contributions | |
wy | +0.012 |
istered | +0.012 |
ruined | +0.012 |
uch | +0.011 |
pain | +0.011 |
Neg logit contributions | |
Suz | -0.013 |
Su | -0.013 |
Sus | -0.013 |
Mill | -0.012 |
Alf | -0.012 |
Token | playing |
Token ID | 2712 |
Feature activation | -4.69e-01 |
Pos logit contributions | |
Suz | +0.013 |
Mill | +0.012 |
Su | +0.012 |
Sus | +0.012 |
Alf | +0.012 |
Neg logit contributions | |
ruined | -0.012 |
sharp | -0.011 |
hurt | -0.011 |
ggy | -0.011 |
pain | -0.011 |
Token | the |
Token ID | 262 |
Feature activation | +8.44e-01 |
Pos logit contributions | |
ruined | +0.008 |
ggy | +0.008 |
sharp | +0.008 |
pain | +0.008 |
ggie | +0.008 |
Neg logit contributions | |
Suz | -0.012 |
Mill | -0.012 |
Su | -0.012 |
Sus | -0.012 |
Alf | -0.012 |
Token | drum |
Token ID | 13026 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
Suz | +0.014 |
Su | +0.013 |
Sus | +0.013 |
Mill | +0.013 |
Alf | +0.013 |
Neg logit contributions | |
wy | -0.022 |
istered | -0.022 |
ruined | -0.021 |
ggy | -0.021 |
ggie | -0.020 |
Token | . |
Token ID | 13 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
Su | +0.047 |
Suz | +0.046 |
Mill | +0.046 |
Sus | +0.045 |
Alf | +0.043 |
Neg logit contributions | |
ruined | -0.031 |
sharp | -0.030 |
ggy | -0.029 |
hurt | -0.029 |
wy | -0.028 |
Token |
|
Token ID | 198 |
Feature activation | -4.78e+00 |
Pos logit contributions | |
ress | +0.040 |
cities | +0.039 |
Mill | +0.039 |
Ally | +0.039 |
Su | +0.038 |
Neg logit contributions | |
sharp | -0.029 |
two | -0.029 |
ggy | -0.028 |
big | -0.028 |
burns | -0.028 |
Token |
|
Token ID | 198 |
Feature activation | -3.91e+00 |
Pos logit contributions | |
ruined | +0.094 |
ggy | +0.094 |
wy | +0.093 |
sharp | +0.090 |
ggie | +0.090 |
Neg logit contributions | |
Suz | -0.107 |
Su | -0.106 |
Mill | -0.106 |
Sus | -0.105 |
Alf | -0.103 |
Token | Joe |
Token ID | 19585 |
Feature activation | -1.73e-01 |
Pos logit contributions | |
ruined | +0.071 |
wy | +0.070 |
ggy | +0.069 |
sharp | +0.067 |
ggie | +0.066 |
Neg logit contributions | |
Suz | -0.096 |
Su | -0.095 |
Mill | -0.095 |
Sus | -0.094 |
Alf | -0.092 |
Token | kept |
Token ID | 4030 |
Feature activation | +6.66e-01 |
Pos logit contributions | |
ruined | +0.003 |
wy | +0.003 |
ggy | +0.003 |
sharp | +0.003 |
istered | +0.003 |
Neg logit contributions | |
Suz | -0.004 |
Su | -0.004 |
Mill | -0.004 |
Sus | -0.004 |
Alf | -0.004 |
Token | playing |
Token ID | 2712 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
Suz | +0.016 |
Mill | +0.016 |
Su | +0.015 |
Sus | +0.015 |
Alf | +0.015 |
Neg logit contributions | |
ruined | -0.013 |
sharp | -0.013 |
hurt | -0.013 |
pain | -0.012 |
broken | -0.012 |
Token | his |
Token ID | 465 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
sharp | +0.003 |
ruined | +0.003 |
ggy | +0.003 |
pain | +0.003 |
bad | +0.003 |
Neg logit contributions | |
Suz | -0.005 |
Mill | -0.005 |
Su | -0.005 |
Sus | -0.004 |
Alf | -0.004 |