Token | that |
Token ID | 326 |
Feature activation | -5.97e-01 |
Pos logit contributions | |
Amen | +0.002 |
fires | +0.002 |
stretched | +0.002 |
bears | +0.002 |
scar | +0.002 |
Neg logit contributions | |
ork | -0.003 |
oph | -0.003 |
ally | -0.002 |
way | -0.002 |
handed | -0.002 |
Token | day |
Token ID | 1110 |
Feature activation | +6.39e-01 |
Pos logit contributions | |
Amen | +0.017 |
fires | +0.012 |
stretched | +0.012 |
bears | +0.011 |
smile | +0.011 |
Neg logit contributions | |
ork | -0.020 |
oph | -0.020 |
way | -0.017 |
ally | -0.017 |
handed | -0.017 |
Token | that |
Token ID | 326 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
oph | +0.023 |
ork | +0.023 |
handed | +0.020 |
ally | +0.020 |
way | +0.020 |
Neg logit contributions | |
Amen | -0.015 |
fires | -0.011 |
stretched | -0.011 |
hope | -0.010 |
sometimes | -0.010 |
Token | the |
Token ID | 262 |
Feature activation | +9.33e-01 |
Pos logit contributions | |
Amen | +0.027 |
fires | +0.020 |
sometimes | +0.019 |
bears | +0.019 |
hope | +0.018 |
Neg logit contributions | |
ork | -0.038 |
oph | -0.036 |
ally | -0.032 |
way | -0.032 |
handed | -0.032 |
Token | best |
Token ID | 1266 |
Feature activation | +2.28e+00 |
Pos logit contributions | |
ork | +0.026 |
oph | +0.025 |
way | +0.022 |
handed | +0.022 |
ally | +0.021 |
Neg logit contributions | |
Amen | -0.031 |
fires | -0.024 |
stretched | -0.024 |
bears | -0.022 |
scar | -0.022 |
Token | dessert |
Token ID | 23084 |
Feature activation | +4.11e+00 |
Pos logit contributions | |
ork | +0.065 |
oph | +0.063 |
ally | +0.054 |
way | +0.053 |
handed | +0.053 |
Neg logit contributions | |
Amen | -0.076 |
fires | -0.059 |
stretched | -0.056 |
bears | -0.055 |
smile | -0.054 |
Token | for |
Token ID | 329 |
Feature activation | +1.91e+00 |
Pos logit contributions | |
ork | +0.152 |
oph | +0.150 |
way | +0.134 |
ally | +0.133 |
handed | +0.132 |
Neg logit contributions | |
Amen | -0.098 |
fires | -0.069 |
stretched | -0.064 |
bears | -0.063 |
hope | -0.060 |
Token | her |
Token ID | 607 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
ork | +0.071 |
oph | +0.067 |
way | +0.064 |
handed | +0.061 |
doorstep | +0.060 |
Neg logit contributions | |
Amen | -0.043 |
bears | -0.034 |
fires | -0.034 |
scar | -0.030 |
hope | -0.030 |
Token | was |
Token ID | 373 |
Feature activation | -7.59e-01 |
Pos logit contributions | |
ork | +0.056 |
oph | +0.054 |
way | +0.047 |
handed | +0.047 |
ally | +0.046 |
Neg logit contributions | |
Amen | -0.055 |
fires | -0.041 |
stretched | -0.040 |
bears | -0.037 |
passenger | -0.037 |
Token | the |
Token ID | 262 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
Amen | +0.020 |
fires | +0.015 |
stretched | +0.014 |
bears | +0.013 |
smile | +0.013 |
Neg logit contributions | |
ork | -0.026 |
oph | -0.026 |
way | -0.023 |
ally | -0.022 |
handed | -0.022 |
Token | one |
Token ID | 530 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
ork | +0.051 |
oph | +0.050 |
way | +0.044 |
handed | +0.043 |
ally | +0.043 |
Neg logit contributions | |
Amen | -0.052 |
fires | -0.039 |
stretched | -0.039 |
bears | -0.035 |
paddle | -0.035 |
Token | bird |
Token ID | 6512 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
ork | +0.043 |
oph | +0.041 |
way | +0.037 |
ally | +0.037 |
handed | +0.035 |
Neg logit contributions | |
Amen | -0.042 |
fires | -0.031 |
stretched | -0.030 |
bears | -0.027 |
paddle | -0.026 |
Token | worked |
Token ID | 3111 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
ork | +0.032 |
oph | +0.031 |
way | +0.028 |
ally | +0.027 |
handed | +0.027 |
Neg logit contributions | |
Amen | -0.036 |
fires | -0.027 |
stretched | -0.026 |
bears | -0.024 |
passenger | -0.024 |
Token | hard |
Token ID | 1327 |
Feature activation | -6.55e-01 |
Pos logit contributions | |
Amen | +0.040 |
fires | +0.025 |
passenger | +0.024 |
stretched | +0.024 |
bears | +0.022 |
Neg logit contributions | |
ork | -0.052 |
oph | -0.047 |
way | -0.047 |
ally | -0.043 |
her | -0.042 |
Token | until |
Token ID | 1566 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
Amen | +0.021 |
fires | +0.015 |
stretched | +0.015 |
bears | +0.014 |
passenger | +0.014 |
Neg logit contributions | |
ork | -0.020 |
oph | -0.019 |
way | -0.018 |
handed | -0.017 |
ally | -0.017 |
Token | the |
Token ID | 262 |
Feature activation | +6.03e-01 |
Pos logit contributions | |
Amen | +0.051 |
fires | +0.038 |
stretched | +0.037 |
bears | +0.035 |
passenger | +0.033 |
Neg logit contributions | |
ork | -0.054 |
oph | -0.053 |
way | -0.046 |
ally | -0.045 |
handed | -0.045 |
Token | mud |
Token ID | 17492 |
Feature activation | +4.07e+00 |
Pos logit contributions | |
oph | +0.017 |
ork | +0.017 |
handed | +0.014 |
way | +0.014 |
ally | +0.014 |
Neg logit contributions | |
Amen | -0.020 |
fires | -0.016 |
stretched | -0.015 |
bears | -0.015 |
smile | -0.014 |
Token | was |
Token ID | 373 |
Feature activation | +3.12e-01 |
Pos logit contributions | |
oph | +0.152 |
ork | +0.137 |
handed | +0.128 |
ally | +0.124 |
Kat | +0.122 |
Neg logit contributions | |
Amen | -0.077 |
fires | -0.070 |
sometimes | -0.069 |
bears | -0.068 |
hope | -0.067 |
Token | nice |
Token ID | 3621 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
ork | +0.010 |
oph | +0.010 |
handed | +0.009 |
way | +0.009 |
ally | +0.009 |
Neg logit contributions | |
Amen | -0.009 |
fires | -0.007 |
stretched | -0.007 |
bears | -0.006 |
smile | -0.006 |
Token | and |
Token ID | 290 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
ork | +0.042 |
oph | +0.042 |
ally | +0.037 |
handed | +0.036 |
way | +0.036 |
Neg logit contributions | |
Amen | -0.029 |
fires | -0.022 |
stretched | -0.022 |
bears | -0.020 |
smile | -0.019 |
Token | soft |
Token ID | 2705 |
Feature activation | +6.57e-01 |
Pos logit contributions | |
ork | +0.005 |
oph | +0.005 |
way | +0.004 |
ally | +0.004 |
handed | +0.004 |
Neg logit contributions | |
Amen | -0.004 |
fires | -0.003 |
stretched | -0.003 |
bears | -0.003 |
passenger | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | +5.20e-02 |
Pos logit contributions | |
ork | +0.022 |
oph | +0.021 |
way | +0.018 |
ally | +0.018 |
handed | +0.018 |
Neg logit contributions | |
Amen | -0.019 |
fires | -0.014 |
stretched | -0.014 |
bears | -0.013 |
passenger | -0.012 |
Token | it |
Token ID | 340 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
ork | +0.008 |
oph | +0.008 |
way | +0.007 |
handed | +0.007 |
ally | +0.007 |
Neg logit contributions | |
Amen | -0.006 |
fires | -0.004 |
stretched | -0.004 |
bears | -0.004 |
passenger | -0.004 |
Token | was |
Token ID | 373 |
Feature activation | +2.67e-01 |
Pos logit contributions | |
ork | +0.051 |
oph | +0.050 |
handed | +0.044 |
ally | +0.043 |
keeping | +0.043 |
Neg logit contributions | |
Amen | -0.043 |
fires | -0.033 |
stretched | -0.032 |
bears | -0.031 |
paddle | -0.029 |
Token | all |
Token ID | 477 |
Feature activation | +2.19e+00 |
Pos logit contributions | |
ork | +0.009 |
oph | +0.009 |
way | +0.008 |
ally | +0.008 |
handed | +0.008 |
Neg logit contributions | |
Amen | -0.008 |
fires | -0.006 |
stretched | -0.005 |
bears | -0.005 |
passenger | -0.005 |
Token | dry |
Token ID | 5894 |
Feature activation | +2.11e+00 |
Pos logit contributions | |
ork | +0.060 |
oph | +0.059 |
way | +0.053 |
handed | +0.051 |
ally | +0.050 |
Neg logit contributions | |
Amen | -0.074 |
fires | -0.056 |
stretched | -0.055 |
bears | -0.052 |
scar | -0.050 |
Token | and |
Token ID | 290 |
Feature activation | +7.94e-01 |
Pos logit contributions | |
ork | +0.079 |
oph | +0.077 |
ally | +0.067 |
way | +0.066 |
handed | +0.066 |
Neg logit contributions | |
Amen | -0.049 |
fires | -0.037 |
stretched | -0.035 |
bears | -0.034 |
sometimes | -0.031 |
Token | mud |
Token ID | 17492 |
Feature activation | +4.05e+00 |
Pos logit contributions | |
ork | +0.026 |
oph | +0.026 |
way | +0.023 |
ally | +0.023 |
handed | +0.022 |
Neg logit contributions | |
Amen | -0.023 |
fires | -0.016 |
stretched | -0.016 |
bears | -0.015 |
passenger | -0.014 |
Token | ! |
Token ID | 0 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
ork | +0.136 |
oph | +0.135 |
ally | +0.117 |
way | +0.116 |
handed | +0.115 |
Neg logit contributions | |
Amen | -0.108 |
fires | -0.083 |
stretched | -0.080 |
bears | -0.077 |
scar | -0.072 |
Token | |
Token ID | 220 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
Amen | +0.003 |
fires | +0.002 |
stretched | +0.002 |
passenger | +0.002 |
nod | +0.002 |
Neg logit contributions | |
ork | -0.006 |
oph | -0.006 |
ally | -0.005 |
handed | -0.005 |
way | -0.005 |
Token |
|
Token ID | 198 |
Feature activation | +1.84e-01 |
Pos logit contributions | |
Amen | +0.027 |
fires | +0.021 |
exc | +0.019 |
stretched | +0.019 |
Sometimes | +0.019 |
Neg logit contributions | |
oph | -0.044 |
ork | -0.040 |
doorstep | -0.036 |
ally | -0.036 |
keeping | -0.035 |
Token |
|
Token ID | 198 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
oph | +0.006 |
ork | +0.006 |
ally | +0.005 |
way | +0.005 |
handed | +0.005 |
Neg logit contributions | |
Amen | -0.005 |
fires | -0.004 |
stretched | -0.004 |
passenger | -0.003 |
paddle | -0.003 |
Token | He |
Token ID | 1544 |
Feature activation | -9.26e-01 |
Pos logit contributions | |
Amen | +0.004 |
fires | +0.003 |
stretched | +0.003 |
bears | +0.003 |
scar | +0.003 |
Neg logit contributions | |
ork | -0.005 |
oph | -0.004 |
way | -0.004 |
handed | -0.004 |
ally | -0.004 |
Token | even |
Token ID | 772 |
Feature activation | -6.02e-01 |
Pos logit contributions | |
ork | +0.004 |
oph | +0.004 |
doorstep | +0.004 |
ally | +0.003 |
n | +0.003 |
Neg logit contributions | |
Amen | -0.005 |
fires | -0.004 |
stretched | -0.004 |
bears | -0.004 |
Does | -0.004 |
Token | see |
Token ID | 766 |
Feature activation | +5.28e-01 |
Pos logit contributions | |
Amen | +0.016 |
fires | +0.011 |
stretched | +0.011 |
bears | +0.010 |
spoiler | +0.009 |
Neg logit contributions | |
ork | -0.021 |
oph | -0.021 |
way | -0.019 |
handed | -0.018 |
ally | -0.018 |
Token | other |
Token ID | 584 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
ork | +0.017 |
oph | +0.017 |
way | +0.015 |
handed | +0.015 |
ally | +0.015 |
Neg logit contributions | |
Amen | -0.015 |
fires | -0.011 |
stretched | -0.011 |
bears | -0.010 |
paddle | -0.009 |
Token | people |
Token ID | 661 |
Feature activation | +1.57e-02 |
Pos logit contributions | |
ork | +0.061 |
oph | +0.060 |
way | +0.052 |
ally | +0.052 |
handed | +0.051 |
Neg logit contributions | |
Amen | -0.058 |
fires | -0.043 |
stretched | -0.042 |
bears | -0.039 |
passenger | -0.037 |
Token | having |
Token ID | 1719 |
Feature activation | +8.12e-01 |
Pos logit contributions | |
ork | +0.000 |
oph | +0.000 |
way | +0.000 |
handed | +0.000 |
ally | +0.000 |
Neg logit contributions | |
Amen | -0.000 |
fires | -0.000 |
stretched | -0.000 |
Does | -0.000 |
scar | -0.000 |
Token | pic |
Token ID | 8301 |
Feature activation | +4.03e+00 |
Pos logit contributions | |
ork | +0.026 |
oph | +0.026 |
way | +0.022 |
ally | +0.022 |
handed | +0.022 |
Neg logit contributions | |
Amen | -0.024 |
fires | -0.018 |
stretched | -0.017 |
bears | -0.017 |
hope | -0.016 |
Token | n |
Token ID | 77 |
Feature activation | -1.89e-01 |
Pos logit contributions | |
oph | +0.066 |
ork | +0.064 |
handed | +0.048 |
orman | +0.043 |
anger | +0.043 |
Neg logit contributions | |
Amen | -0.175 |
stretched | -0.143 |
yes | -0.143 |
smile | -0.142 |
laugh | -0.141 |
Token | ics |
Token ID | 873 |
Feature activation | +1.91e+00 |
Pos logit contributions | |
Amen | +0.006 |
stretched | +0.005 |
fires | +0.005 |
exc | +0.005 |
smile | +0.005 |
Neg logit contributions | |
oph | -0.005 |
ork | -0.005 |
handed | -0.004 |
doorstep | -0.004 |
ally | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | +3.73e-01 |
Pos logit contributions | |
ork | +0.064 |
oph | +0.062 |
way | +0.054 |
ally | +0.054 |
handed | +0.054 |
Neg logit contributions | |
Amen | -0.054 |
fires | -0.040 |
stretched | -0.038 |
bears | -0.036 |
passenger | -0.034 |
Token |
|
Token ID | 198 |
Feature activation | +6.57e-01 |
Pos logit contributions | |
ork | +0.015 |
oph | +0.013 |
handed | +0.013 |
lor | +0.013 |
anger | +0.013 |
Neg logit contributions | |
Amen | -0.007 |
Everyday | -0.005 |
wonder | -0.005 |
Sometimes | -0.005 |
nod | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | +2.75e-01 |
Pos logit contributions | |
oph | +0.022 |
ork | +0.021 |
keeping | +0.019 |
handed | +0.019 |
doorstep | +0.018 |
Neg logit contributions | |
Amen | -0.018 |
stretched | -0.013 |
fires | -0.013 |
wonder | -0.012 |
exc | -0.012 |
Token | |
Token ID | 220 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
ork | +0.017 |
oph | +0.017 |
ally | +0.015 |
ige | +0.015 |
ilt | +0.015 |
Neg logit contributions | |
Amen | -0.009 |
fires | -0.005 |
stretched | -0.005 |
smile | -0.004 |
nod | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | +9.25e-01 |
Pos logit contributions | |
Amen | +0.022 |
Sometimes | +0.015 |
exc | +0.014 |
stretched | +0.014 |
fires | +0.014 |
Neg logit contributions | |
oph | -0.045 |
ork | -0.041 |
ally | -0.037 |
doorstep | -0.037 |
keeping | -0.036 |
Token |
|
Token ID | 198 |
Feature activation | +3.42e-01 |
Pos logit contributions | |
oph | +0.033 |
ork | +0.031 |
ally | +0.028 |
ige | +0.028 |
doorstep | +0.028 |
Neg logit contributions | |
Amen | -0.023 |
stretched | -0.015 |
fires | -0.014 |
sled | -0.014 |
He | -0.014 |
Token | When |
Token ID | 2215 |
Feature activation | -8.54e-01 |
Pos logit contributions | |
ork | +0.011 |
oph | +0.011 |
way | +0.009 |
handed | +0.009 |
ally | +0.009 |
Neg logit contributions | |
Amen | -0.010 |
fires | -0.008 |
stretched | -0.008 |
bears | -0.007 |
scar | -0.007 |
Token | the |
Token ID | 262 |
Feature activation | +2.20e-01 |
Pos logit contributions | |
Amen | +0.020 |
fires | +0.013 |
stretched | +0.013 |
bears | +0.012 |
passenger | +0.011 |
Neg logit contributions | |
ork | -0.033 |
oph | -0.032 |
way | -0.029 |
ally | -0.029 |
handed | -0.029 |
Token | fog |
Token ID | 19558 |
Feature activation | +3.96e+00 |
Pos logit contributions | |
ork | +0.007 |
oph | +0.007 |
way | +0.006 |
handed | +0.006 |
ally | +0.006 |
Neg logit contributions | |
Amen | -0.006 |
fires | -0.005 |
stretched | -0.004 |
spoiler | -0.004 |
bears | -0.004 |
Token | was |
Token ID | 373 |
Feature activation | +5.29e-01 |
Pos logit contributions | |
oph | +0.136 |
ork | +0.130 |
handed | +0.116 |
ige | +0.113 |
ally | +0.113 |
Neg logit contributions | |
Amen | -0.099 |
bears | -0.074 |
fires | -0.074 |
stretched | -0.074 |
paddle | -0.072 |
Token | gone |
Token ID | 3750 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
ork | +0.017 |
oph | +0.017 |
handed | +0.015 |
ally | +0.014 |
way | +0.014 |
Neg logit contributions | |
Amen | -0.015 |
fires | -0.012 |
stretched | -0.012 |
bears | -0.011 |
smile | -0.011 |
Token | , |
Token ID | 11 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
ork | +0.044 |
oph | +0.043 |
handed | +0.039 |
ally | +0.038 |
way | +0.038 |
Neg logit contributions | |
Amen | -0.025 |
fires | -0.017 |
stretched | -0.016 |
bears | -0.015 |
smile | -0.014 |
Token | all |
Token ID | 477 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
ork | +0.046 |
oph | +0.045 |
way | +0.040 |
handed | +0.039 |
ally | +0.039 |
Neg logit contributions | |
Amen | -0.032 |
fires | -0.022 |
stretched | -0.021 |
bears | -0.019 |
passenger | -0.018 |
Token | his |
Token ID | 465 |
Feature activation | +2.52e+00 |
Pos logit contributions | |
ork | +0.036 |
oph | +0.036 |
way | +0.033 |
ally | +0.032 |
handed | +0.032 |
Neg logit contributions | |
Amen | -0.034 |
fires | -0.023 |
stretched | -0.023 |
scar | -0.022 |
argue | -0.021 |
Token | soon |
Token ID | 2582 |
Feature activation | -8.77e-01 |
Pos logit contributions | |
Amen | +0.001 |
bears | +0.001 |
fires | +0.001 |
sometimes | +0.001 |
scar | +0.001 |
Neg logit contributions | |
ork | -0.004 |
oph | -0.003 |
handed | -0.003 |
way | -0.003 |
lor | -0.003 |
Token | the |
Token ID | 262 |
Feature activation | +4.53e-01 |
Pos logit contributions | |
Amen | +0.009 |
bears | +0.008 |
smile | +0.008 |
fires | +0.008 |
sometimes | +0.007 |
Neg logit contributions | |
ork | -0.038 |
handed | -0.035 |
oph | -0.035 |
way | -0.035 |
doorstep | -0.035 |
Token | dough |
Token ID | 15756 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
ork | +0.014 |
oph | +0.014 |
handed | +0.012 |
way | +0.012 |
ally | +0.012 |
Neg logit contributions | |
Amen | -0.014 |
fires | -0.010 |
bears | -0.010 |
stretched | -0.010 |
smile | -0.010 |
Token | was |
Token ID | 373 |
Feature activation | +3.98e-01 |
Pos logit contributions | |
oph | +0.052 |
ork | +0.052 |
handed | +0.046 |
way | +0.045 |
ally | +0.045 |
Neg logit contributions | |
Amen | -0.043 |
stretched | -0.033 |
fires | -0.033 |
smile | -0.032 |
bears | -0.032 |
Token | all |
Token ID | 477 |
Feature activation | +2.04e+00 |
Pos logit contributions | |
oph | +0.013 |
ork | +0.013 |
handed | +0.012 |
way | +0.011 |
ally | +0.011 |
Neg logit contributions | |
Amen | -0.011 |
stretched | -0.009 |
fires | -0.009 |
smile | -0.008 |
bears | -0.008 |
Token | back |
Token ID | 736 |
Feature activation | +3.94e+00 |
Pos logit contributions | |
ork | +0.064 |
oph | +0.061 |
ally | +0.051 |
way | +0.051 |
handed | +0.051 |
Neg logit contributions | |
Amen | -0.062 |
fires | -0.050 |
stretched | -0.048 |
smile | -0.046 |
bears | -0.046 |
Token | . |
Token ID | 13 |
Feature activation | +4.02e-01 |
Pos logit contributions | |
ork | +0.141 |
oph | +0.140 |
ally | +0.115 |
lor | +0.114 |
handed | +0.114 |
Neg logit contributions | |
Amen | -0.086 |
smile | -0.073 |
fires | -0.072 |
stretched | -0.071 |
hope | -0.067 |
Token |
|
Token ID | 198 |
Feature activation | +5.97e-01 |
Pos logit contributions | |
ork | +0.016 |
oph | +0.016 |
way | +0.015 |
handed | +0.014 |
doorstep | +0.014 |
Neg logit contributions | |
Amen | -0.008 |
Sometimes | -0.005 |
Everyday | -0.004 |
stretched | -0.004 |
smile | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | +1.99e-01 |
Pos logit contributions | |
oph | +0.020 |
ork | +0.019 |
way | +0.017 |
handed | +0.017 |
ally | +0.017 |
Neg logit contributions | |
Amen | -0.017 |
stretched | -0.012 |
fires | -0.012 |
exc | -0.011 |
smile | -0.011 |
Token | The |
Token ID | 464 |
Feature activation | -7.58e-01 |
Pos logit contributions | |
ork | +0.006 |
oph | +0.006 |
way | +0.005 |
ally | +0.005 |
handed | +0.005 |
Neg logit contributions | |
Amen | -0.006 |
fires | -0.005 |
stretched | -0.005 |
bears | -0.004 |
scar | -0.004 |
Token | little |
Token ID | 1310 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
Amen | +0.027 |
fires | +0.021 |
stretched | +0.021 |
bears | +0.019 |
paddle | +0.019 |
Neg logit contributions | |
ork | -0.020 |
oph | -0.020 |
ally | -0.017 |
way | -0.017 |
handed | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | +4.44e-01 |
Pos logit contributions | |
Amen | +0.011 |
fires | +0.008 |
stretched | +0.008 |
bears | +0.007 |
smile | +0.007 |
Neg logit contributions | |
ork | -0.018 |
oph | -0.017 |
handed | -0.015 |
ally | -0.015 |
way | -0.015 |
Token | As |
Token ID | 1081 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
ork | +0.015 |
oph | +0.015 |
way | +0.013 |
handed | +0.013 |
ally | +0.013 |
Neg logit contributions | |
Amen | -0.013 |
fires | -0.009 |
stretched | -0.009 |
bears | -0.008 |
passenger | -0.008 |
Token | the |
Token ID | 262 |
Feature activation | +4.09e-01 |
Pos logit contributions | |
Amen | +0.039 |
fires | +0.027 |
stretched | +0.026 |
bears | +0.024 |
scar | +0.022 |
Neg logit contributions | |
ork | -0.062 |
oph | -0.061 |
way | -0.054 |
ally | -0.054 |
handed | -0.054 |
Token | dirt |
Token ID | 13647 |
Feature activation | +3.23e+00 |
Pos logit contributions | |
ork | +0.012 |
oph | +0.011 |
way | +0.010 |
ally | +0.010 |
handed | +0.010 |
Neg logit contributions | |
Amen | -0.014 |
fires | -0.010 |
stretched | -0.010 |
passenger | -0.009 |
bears | -0.009 |
Token | and |
Token ID | 290 |
Feature activation | +9.16e-01 |
Pos logit contributions | |
ork | +0.102 |
oph | +0.098 |
way | +0.087 |
ally | +0.085 |
handed | +0.084 |
Neg logit contributions | |
Amen | -0.099 |
fires | -0.073 |
stretched | -0.071 |
bears | -0.066 |
passenger | -0.065 |
Token | mud |
Token ID | 17492 |
Feature activation | +3.92e+00 |
Pos logit contributions | |
oph | +0.027 |
ork | +0.026 |
ally | +0.023 |
way | +0.023 |
keeping | +0.023 |
Neg logit contributions | |
Amen | -0.029 |
stretched | -0.021 |
fires | -0.019 |
passenger | -0.019 |
exc | -0.018 |
Token | washed |
Token ID | 18989 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
ork | +0.126 |
oph | +0.122 |
way | +0.107 |
ally | +0.106 |
handed | +0.105 |
Neg logit contributions | |
Amen | -0.117 |
fires | -0.086 |
stretched | -0.084 |
bears | -0.078 |
passenger | -0.076 |
Token | away |
Token ID | 1497 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
ork | +0.041 |
oph | +0.041 |
way | +0.036 |
handed | +0.036 |
ally | +0.035 |
Neg logit contributions | |
Amen | -0.028 |
fires | -0.021 |
stretched | -0.019 |
bears | -0.019 |
hope | -0.017 |
Token | , |
Token ID | 11 |
Feature activation | +7.36e-01 |
Pos logit contributions | |
ork | +0.057 |
oph | +0.056 |
way | +0.050 |
ally | +0.049 |
handed | +0.049 |
Neg logit contributions | |
Amen | -0.040 |
fires | -0.028 |
stretched | -0.027 |
bears | -0.025 |
passenger | -0.024 |
Token | Pe |
Token ID | 2631 |
Feature activation | +4.17e-01 |
Pos logit contributions | |
ork | +0.025 |
oph | +0.025 |
way | +0.022 |
ally | +0.022 |
handed | +0.021 |
Neg logit contributions | |
Amen | -0.020 |
fires | -0.015 |
stretched | -0.014 |
bears | -0.014 |
scar | -0.013 |
Token | ep |
Token ID | 538 |
Feature activation | +8.10e-01 |
Pos logit contributions | |
ork | +0.015 |
oph | +0.015 |
way | +0.013 |
handed | +0.013 |
ally | +0.012 |
Neg logit contributions | |
Amen | -0.011 |
fires | -0.008 |
stretched | -0.007 |
bears | -0.007 |
scar | -0.007 |
Token | sun |
Token ID | 4252 |
Feature activation | +1.96e+00 |
Pos logit contributions | |
Amen | +0.020 |
fires | +0.012 |
stretched | +0.011 |
bears | +0.010 |
passenger | +0.009 |
Neg logit contributions | |
ork | -0.045 |
oph | -0.044 |
way | -0.041 |
ally | -0.040 |
handed | -0.040 |
Token | was |
Token ID | 373 |
Feature activation | +8.65e-01 |
Pos logit contributions | |
ork | +0.060 |
oph | +0.058 |
way | +0.051 |
ally | +0.050 |
handed | +0.050 |
Neg logit contributions | |
Amen | -0.061 |
fires | -0.046 |
stretched | -0.045 |
bears | -0.042 |
passenger | -0.041 |
Token | shining |
Token ID | 22751 |
Feature activation | +3.45e-01 |
Pos logit contributions | |
ork | +0.028 |
oph | +0.028 |
way | +0.025 |
ally | +0.025 |
handed | +0.024 |
Neg logit contributions | |
Amen | -0.024 |
fires | -0.017 |
stretched | -0.016 |
bears | -0.016 |
passenger | -0.015 |
Token | and |
Token ID | 290 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
ork | +0.011 |
oph | +0.011 |
way | +0.010 |
ally | +0.010 |
handed | +0.009 |
Neg logit contributions | |
Amen | -0.010 |
fires | -0.007 |
stretched | -0.007 |
bears | -0.006 |
passenger | -0.006 |
Token | the |
Token ID | 262 |
Feature activation | +9.11e-01 |
Pos logit contributions | |
ork | +0.035 |
oph | +0.033 |
handed | +0.030 |
way | +0.029 |
ally | +0.029 |
Neg logit contributions | |
Amen | -0.029 |
fires | -0.022 |
stretched | -0.020 |
bears | -0.020 |
smile | -0.019 |
Token | sand |
Token ID | 6450 |
Feature activation | +3.91e+00 |
Pos logit contributions | |
ork | +0.039 |
oph | +0.037 |
ally | +0.034 |
handed | +0.033 |
way | +0.033 |
Neg logit contributions | |
Amen | -0.017 |
fires | -0.011 |
smile | -0.011 |
paddle | -0.011 |
wave | -0.011 |
Token | was |
Token ID | 373 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
ork | +0.122 |
oph | +0.120 |
ally | +0.103 |
handed | +0.103 |
way | +0.103 |
Neg logit contributions | |
Amen | -0.116 |
fires | -0.089 |
stretched | -0.087 |
bears | -0.082 |
smile | -0.079 |
Token | warm |
Token ID | 5814 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
ork | +0.035 |
oph | +0.035 |
way | +0.031 |
ally | +0.030 |
handed | +0.029 |
Neg logit contributions | |
Amen | -0.032 |
fires | -0.023 |
stretched | -0.022 |
bears | -0.021 |
passenger | -0.021 |
Token | . |
Token ID | 13 |
Feature activation | +3.52e-01 |
Pos logit contributions | |
ork | +0.063 |
oph | +0.061 |
way | +0.054 |
handed | +0.054 |
ally | +0.054 |
Neg logit contributions | |
Amen | -0.049 |
fires | -0.036 |
stretched | -0.035 |
bears | -0.033 |
smile | -0.031 |
Token | He |
Token ID | 679 |
Feature activation | -6.93e-01 |
Pos logit contributions | |
ork | +0.013 |
oph | +0.012 |
anger | +0.011 |
ally | +0.011 |
ilt | +0.011 |
Neg logit contributions | |
Amen | -0.010 |
fires | -0.006 |
stretched | -0.006 |
wonder | -0.006 |
smile | -0.006 |
Token | felt |
Token ID | 2936 |
Feature activation | -5.09e-01 |
Pos logit contributions | |
Amen | +0.020 |
fires | +0.015 |
stretched | +0.014 |
bears | +0.013 |
passenger | +0.013 |
Neg logit contributions | |
ork | -0.023 |
oph | -0.022 |
way | -0.019 |
ally | -0.019 |
handed | -0.019 |
Token | felt |
Token ID | 2936 |
Feature activation | -8.53e-01 |
Pos logit contributions | |
Amen | +0.015 |
fires | +0.011 |
stretched | +0.011 |
bears | +0.010 |
passenger | +0.009 |
Neg logit contributions | |
ork | -0.016 |
oph | -0.015 |
way | -0.013 |
ally | -0.013 |
handed | -0.013 |
Token | really |
Token ID | 1107 |
Feature activation | +3.92e-01 |
Pos logit contributions | |
Amen | +0.025 |
fires | +0.018 |
stretched | +0.017 |
bears | +0.017 |
passenger | +0.017 |
Neg logit contributions | |
ork | -0.027 |
oph | -0.026 |
handed | -0.024 |
way | -0.024 |
ally | -0.023 |
Token | sad |
Token ID | 6507 |
Feature activation | -3.82e-01 |
Pos logit contributions | |
ork | +0.015 |
oph | +0.015 |
way | +0.013 |
ally | +0.013 |
handed | +0.013 |
Neg logit contributions | |
Amen | -0.009 |
fires | -0.006 |
stretched | -0.006 |
bears | -0.006 |
passenger | -0.005 |
Token | because |
Token ID | 780 |
Feature activation | +5.69e-01 |
Pos logit contributions | |
Amen | +0.012 |
fires | +0.008 |
stretched | +0.008 |
bears | +0.007 |
passenger | +0.007 |
Neg logit contributions | |
ork | -0.012 |
oph | -0.012 |
way | -0.011 |
ally | -0.010 |
handed | -0.010 |
Token | the |
Token ID | 262 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
ork | +0.020 |
oph | +0.019 |
way | +0.017 |
ally | +0.017 |
handed | +0.017 |
Neg logit contributions | |
Amen | -0.015 |
fires | -0.011 |
stretched | -0.011 |
bears | -0.010 |
smile | -0.010 |
Token | mud |
Token ID | 17492 |
Feature activation | +3.89e+00 |
Pos logit contributions | |
ork | +0.041 |
oph | +0.040 |
way | +0.036 |
handed | +0.035 |
ally | +0.035 |
Neg logit contributions | |
Amen | -0.029 |
fires | -0.021 |
bears | -0.020 |
stretched | -0.020 |
scar | -0.020 |
Token | had |
Token ID | 550 |
Feature activation | +2.39e+00 |
Pos logit contributions | |
oph | +0.124 |
ork | +0.122 |
handed | +0.105 |
way | +0.104 |
ally | +0.103 |
Neg logit contributions | |
Amen | -0.106 |
fires | -0.084 |
stretched | -0.084 |
bears | -0.080 |
smile | -0.077 |
Token | made |
Token ID | 925 |
Feature activation | +2.21e-01 |
Pos logit contributions | |
oph | +0.071 |
ork | +0.069 |
handed | +0.062 |
ally | +0.061 |
way | +0.058 |
Neg logit contributions | |
Amen | -0.059 |
stretched | -0.058 |
fires | -0.055 |
hope | -0.053 |
smile | -0.053 |
Token | her |
Token ID | 607 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
oph | +0.008 |
ork | +0.008 |
handed | +0.007 |
way | +0.007 |
ally | +0.007 |
Neg logit contributions | |
Amen | -0.005 |
fires | -0.004 |
stretched | -0.004 |
bears | -0.003 |
hope | -0.003 |
Token | wool |
Token ID | 25749 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
ork | +0.040 |
oph | +0.037 |
way | +0.034 |
doorstep | +0.034 |
handed | +0.033 |
Neg logit contributions | |
Amen | -0.034 |
fires | -0.024 |
stretched | -0.022 |
bears | -0.020 |
passenger | -0.020 |
Token | very |
Token ID | 845 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
ork | +0.032 |
oph | +0.028 |
way | +0.027 |
doorstep | +0.026 |
handed | +0.026 |
Neg logit contributions | |
Amen | -0.035 |
fires | -0.024 |
stretched | -0.023 |
bears | -0.022 |
passenger | -0.022 |
Token | |
Token ID | 220 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
ork | +0.007 |
oph | +0.007 |
ally | +0.006 |
handed | +0.006 |
way | +0.006 |
Neg logit contributions | |
Amen | -0.004 |
fires | -0.003 |
stretched | -0.002 |
nod | -0.002 |
smile | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | +5.95e-01 |
Pos logit contributions | |
Amen | +0.025 |
fires | +0.017 |
Sometimes | +0.016 |
exc | +0.016 |
sled | +0.016 |
Neg logit contributions | |
oph | -0.048 |
ork | -0.043 |
ally | -0.040 |
doorstep | -0.039 |
handed | -0.038 |
Token |
|
Token ID | 198 |
Feature activation | +2.32e-01 |
Pos logit contributions | |
oph | +0.021 |
ork | +0.020 |
ally | +0.018 |
way | +0.017 |
handed | +0.017 |
Neg logit contributions | |
Amen | -0.016 |
stretched | -0.011 |
fires | -0.011 |
exc | -0.010 |
smile | -0.010 |
Token | When |
Token ID | 2215 |
Feature activation | -8.89e-01 |
Pos logit contributions | |
ork | +0.007 |
oph | +0.007 |
way | +0.006 |
ally | +0.006 |
handed | +0.006 |
Neg logit contributions | |
Amen | -0.007 |
fires | -0.005 |
stretched | -0.005 |
bears | -0.005 |
passenger | -0.005 |
Token | the |
Token ID | 262 |
Feature activation | +4.84e-01 |
Pos logit contributions | |
Amen | +0.021 |
fires | +0.015 |
stretched | +0.014 |
bears | +0.013 |
hope | +0.012 |
Neg logit contributions | |
ork | -0.034 |
oph | -0.033 |
handed | -0.030 |
ally | -0.030 |
way | -0.029 |
Token | rain |
Token ID | 6290 |
Feature activation | +3.85e+00 |
Pos logit contributions | |
ork | +0.016 |
oph | +0.016 |
way | +0.014 |
handed | +0.014 |
ally | +0.014 |
Neg logit contributions | |
Amen | -0.014 |
fires | -0.010 |
stretched | -0.010 |
bears | -0.009 |
scar | -0.009 |
Token | stopped |
Token ID | 5025 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
oph | +0.142 |
ork | +0.141 |
handed | +0.137 |
ige | +0.132 |
keeping | +0.131 |
Neg logit contributions | |
Amen | -0.064 |
smile | -0.056 |
sometimes | -0.056 |
ne | -0.053 |
hon | -0.053 |
Token | , |
Token ID | 11 |
Feature activation | +7.15e-01 |
Pos logit contributions | |
ork | +0.033 |
oph | +0.029 |
way | +0.029 |
ally | +0.028 |
handed | +0.026 |
Neg logit contributions | |
Amen | -0.032 |
stretched | -0.022 |
fires | -0.021 |
passenger | -0.021 |
bears | -0.020 |
Token | the |
Token ID | 262 |
Feature activation | +4.85e-01 |
Pos logit contributions | |
ork | +0.028 |
oph | +0.027 |
handed | +0.024 |
ally | +0.024 |
way | +0.024 |
Neg logit contributions | |
Amen | -0.016 |
fires | -0.011 |
stretched | -0.010 |
bears | -0.010 |
paddle | -0.009 |
Token | farmer |
Token ID | 18739 |
Feature activation | +3.62e-01 |
Pos logit contributions | |
ork | +0.018 |
oph | +0.017 |
way | +0.015 |
handed | +0.015 |
ally | +0.015 |
Neg logit contributions | |
Amen | -0.013 |
fires | -0.009 |
bears | -0.008 |
stretched | -0.008 |
scar | -0.008 |
Token | and |
Token ID | 290 |
Feature activation | -4.08e-01 |
Pos logit contributions | |
ork | +0.012 |
oph | +0.012 |
way | +0.011 |
handed | +0.010 |
ally | +0.010 |
Neg logit contributions | |
Amen | -0.010 |
fires | -0.007 |
stretched | -0.007 |
bears | -0.007 |
smile | -0.006 |
Token | in |
Token ID | 287 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
Amen | +0.025 |
fires | +0.018 |
stretched | +0.017 |
bears | +0.016 |
passenger | +0.015 |
Neg logit contributions | |
ork | -0.033 |
oph | -0.032 |
way | -0.028 |
ally | -0.028 |
handed | -0.028 |
Token | need |
Token ID | 761 |
Feature activation | -3.33e-01 |
Pos logit contributions | |
Amen | +0.028 |
stretched | +0.019 |
fires | +0.019 |
bears | +0.017 |
paddle | +0.017 |
Neg logit contributions | |
ork | -0.042 |
oph | -0.040 |
handed | -0.036 |
way | -0.036 |
ally | -0.035 |
Token | . |
Token ID | 13 |
Feature activation | +3.17e-01 |
Pos logit contributions | |
Amen | +0.008 |
fires | +0.006 |
hope | +0.005 |
sometimes | +0.005 |
bears | +0.005 |
Neg logit contributions | |
oph | -0.013 |
ork | -0.012 |
ally | -0.011 |
liv | -0.011 |
way | -0.011 |
Token | We |
Token ID | 775 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
ork | +0.010 |
oph | +0.010 |
way | +0.008 |
ally | +0.008 |
handed | +0.008 |
Neg logit contributions | |
Amen | -0.010 |
fires | -0.007 |
stretched | -0.007 |
bears | -0.007 |
scar | -0.006 |
Token | all |
Token ID | 477 |
Feature activation | -5.05e-04 |
Pos logit contributions | |
ork | +0.040 |
oph | +0.037 |
way | +0.035 |
n | +0.034 |
ally | +0.034 |
Neg logit contributions | |
Amen | -0.027 |
stretched | -0.022 |
fires | -0.021 |
sled | -0.019 |
spoiler | -0.019 |
Token | belong |
Token ID | 5594 |
Feature activation | +3.85e+00 |
Pos logit contributions | |
Amen | +0.000 |
stretched | +0.000 |
fires | +0.000 |
sled | +0.000 |
scar | +0.000 |
Neg logit contributions | |
ork | -0.000 |
oph | -0.000 |
way | -0.000 |
handed | -0.000 |
ally | -0.000 |
Token | to |
Token ID | 284 |
Feature activation | +2.80e-02 |
Pos logit contributions | |
ork | +0.124 |
oph | +0.123 |
ally | +0.106 |
way | +0.105 |
handed | +0.101 |
Neg logit contributions | |
Amen | -0.111 |
fires | -0.087 |
hope | -0.081 |
bears | -0.080 |
stretched | -0.079 |
Token | one |
Token ID | 530 |
Feature activation | -9.32e-01 |
Pos logit contributions | |
ork | +0.001 |
oph | +0.001 |
way | +0.001 |
ally | +0.001 |
handed | +0.001 |
Neg logit contributions | |
Amen | -0.001 |
fires | -0.001 |
bears | -0.001 |
hope | -0.000 |
sometimes | -0.000 |
Token | big |
Token ID | 1263 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
Amen | +0.028 |
stretched | +0.021 |
fires | +0.021 |
bears | +0.019 |
paddle | +0.019 |
Neg logit contributions | |
ork | -0.029 |
oph | -0.029 |
way | -0.025 |
handed | -0.025 |
ally | -0.025 |
Token | family |
Token ID | 1641 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
Amen | +0.005 |
stretched | +0.004 |
paddle | +0.003 |
fires | +0.003 |
Does | +0.003 |
Neg logit contributions | |
ork | -0.006 |
oph | -0.005 |
handed | -0.005 |
keeping | -0.005 |
doorstep | -0.005 |
Token | and |
Token ID | 290 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
Amen | +0.032 |
stretched | +0.024 |
fires | +0.024 |
bears | +0.021 |
paddle | +0.021 |
Neg logit contributions | |
ork | -0.032 |
oph | -0.031 |
way | -0.027 |
handed | -0.027 |
ally | -0.027 |
Token | and |
Token ID | 290 |
Feature activation | +5.76e-01 |
Pos logit contributions | |
Amen | +0.012 |
fires | +0.008 |
stretched | +0.008 |
bears | +0.008 |
passenger | +0.008 |
Neg logit contributions | |
ork | -0.012 |
oph | -0.011 |
way | -0.010 |
ally | -0.010 |
handed | -0.009 |
Token | waited |
Token ID | 13488 |
Feature activation | -3.13e-01 |
Pos logit contributions | |
ork | +0.021 |
oph | +0.020 |
handed | +0.018 |
way | +0.018 |
ally | +0.017 |
Neg logit contributions | |
Amen | -0.015 |
fires | -0.011 |
stretched | -0.010 |
hope | -0.010 |
bears | -0.010 |
Token | and |
Token ID | 290 |
Feature activation | +4.46e-01 |
Pos logit contributions | |
Amen | +0.009 |
fires | +0.007 |
stretched | +0.006 |
bears | +0.006 |
passenger | +0.006 |
Neg logit contributions | |
ork | -0.010 |
oph | -0.010 |
way | -0.009 |
ally | -0.009 |
handed | -0.009 |
Token | soon |
Token ID | 2582 |
Feature activation | -6.05e-01 |
Pos logit contributions | |
ork | +0.016 |
oph | +0.015 |
handed | +0.014 |
ally | +0.014 |
way | +0.014 |
Neg logit contributions | |
Amen | -0.012 |
fires | -0.009 |
hope | -0.008 |
stretched | -0.008 |
smile | -0.008 |
Token | the |
Token ID | 262 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
Amen | +0.006 |
stretched | +0.005 |
smile | +0.005 |
fires | +0.005 |
bears | +0.005 |
Neg logit contributions | |
ork | -0.026 |
oph | -0.026 |
handed | -0.026 |
doorstep | -0.025 |
keeping | -0.024 |
Token | mud |
Token ID | 17492 |
Feature activation | +3.83e+00 |
Pos logit contributions | |
ork | +0.005 |
oph | +0.005 |
way | +0.004 |
ally | +0.004 |
handed | +0.004 |
Neg logit contributions | |
Amen | -0.006 |
fires | -0.004 |
stretched | -0.004 |
bears | -0.004 |
passenger | -0.004 |
Token | and |
Token ID | 290 |
Feature activation | +9.58e-01 |
Pos logit contributions | |
oph | +0.132 |
ork | +0.126 |
handed | +0.114 |
ally | +0.110 |
way | +0.107 |
Neg logit contributions | |
Amen | -0.092 |
fires | -0.077 |
stretched | -0.075 |
bears | -0.071 |
paddle | -0.071 |
Token | the |
Token ID | 262 |
Feature activation | +3.22e-01 |
Pos logit contributions | |
ork | +0.033 |
oph | +0.033 |
way | +0.029 |
ally | +0.029 |
handed | +0.028 |
Neg logit contributions | |
Amen | -0.026 |
fires | -0.018 |
stretched | -0.018 |
bears | -0.016 |
passenger | -0.016 |
Token | p |
Token ID | 279 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
ork | +0.009 |
oph | +0.009 |
way | +0.008 |
ally | +0.008 |
handed | +0.008 |
Neg logit contributions | |
Amen | -0.011 |
fires | -0.008 |
stretched | -0.008 |
bears | -0.007 |
passenger | -0.007 |
Token | udd |
Token ID | 4185 |
Feature activation | -7.12e-02 |
Pos logit contributions | |
oph | +0.052 |
ork | +0.045 |
keeping | +0.042 |
handed | +0.042 |
orman | +0.040 |
Neg logit contributions | |
Amen | -0.050 |
stretched | -0.045 |
fires | -0.045 |
sled | -0.042 |
paddle | -0.041 |
Token | les |
Token ID | 829 |
Feature activation | +6.18e-01 |
Pos logit contributions | |
Amen | +0.002 |
fires | +0.002 |
bears | +0.001 |
stretched | +0.001 |
paddle | +0.001 |
Neg logit contributions | |
oph | -0.002 |
ork | -0.002 |
doorstep | -0.002 |
handed | -0.002 |
keeping | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | -3.54e-03 |
Pos logit contributions | |
ork | +0.015 |
oph | +0.014 |
anger | +0.014 |
keeping | +0.014 |
doorstep | +0.013 |
Neg logit contributions | |
Amen | -0.009 |
stretched | -0.006 |
He | -0.005 |
Every | -0.005 |
Everyday | -0.005 |
Token | Once |
Token ID | 7454 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
Amen | +0.000 |
stretched | +0.000 |
fires | +0.000 |
sometimes | +0.000 |
yes | +0.000 |
Neg logit contributions | |
ork | -0.000 |
oph | -0.000 |
keeping | -0.000 |
anger | -0.000 |
handed | -0.000 |
Token | they |
Token ID | 484 |
Feature activation | +7.56e-01 |
Pos logit contributions | |
Amen | +0.021 |
fires | +0.015 |
sometimes | +0.013 |
stretched | +0.013 |
smile | +0.013 |
Neg logit contributions | |
ork | -0.040 |
oph | -0.040 |
handed | -0.038 |
keeping | -0.036 |
lor | -0.035 |
Token | were |
Token ID | 547 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
ork | +0.025 |
oph | +0.024 |
way | +0.021 |
handed | +0.021 |
ally | +0.020 |
Neg logit contributions | |
Amen | -0.022 |
fires | -0.017 |
stretched | -0.016 |
bears | -0.015 |
smile | -0.015 |
Token | all |
Token ID | 477 |
Feature activation | +8.64e-01 |
Pos logit contributions | |
ork | +0.034 |
oph | +0.033 |
ally | +0.029 |
way | +0.029 |
handed | +0.028 |
Neg logit contributions | |
Amen | -0.030 |
fires | -0.023 |
stretched | -0.022 |
bears | -0.022 |
smile | -0.021 |
Token | back |
Token ID | 736 |
Feature activation | +3.82e+00 |
Pos logit contributions | |
ork | +0.024 |
oph | +0.024 |
way | +0.022 |
handed | +0.022 |
keeping | +0.021 |
Neg logit contributions | |
Amen | -0.027 |
stretched | -0.020 |
fires | -0.020 |
Does | -0.019 |
spoiler | -0.018 |
Token | home |
Token ID | 1363 |
Feature activation | +3.00e+00 |
Pos logit contributions | |
ork | +0.135 |
oph | +0.133 |
lor | +0.111 |
handed | +0.110 |
ally | +0.110 |
Neg logit contributions | |
Amen | -0.088 |
smile | -0.077 |
hope | -0.072 |
fires | -0.071 |
stretched | -0.069 |
Token | , |
Token ID | 11 |
Feature activation | +7.16e-01 |
Pos logit contributions | |
ork | +0.121 |
oph | +0.121 |
ally | +0.106 |
handed | +0.106 |
way | +0.105 |
Neg logit contributions | |
Amen | -0.059 |
stretched | -0.039 |
fires | -0.038 |
smile | -0.037 |
bears | -0.035 |
Token | Amy |
Token ID | 14235 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
ork | +0.018 |
oph | +0.018 |
way | +0.015 |
handed | +0.015 |
ally | +0.015 |
Neg logit contributions | |
Amen | -0.026 |
fires | -0.020 |
stretched | -0.020 |
bears | -0.019 |
smile | -0.019 |
Token | thanked |
Token ID | 26280 |
Feature activation | -9.10e-01 |
Pos logit contributions | |
ork | +0.048 |
oph | +0.047 |
way | +0.040 |
ally | +0.040 |
handed | +0.040 |
Neg logit contributions | |
Amen | -0.054 |
fires | -0.041 |
stretched | -0.040 |
bears | -0.038 |
passenger | -0.037 |
Token | her |
Token ID | 607 |
Feature activation | -8.68e-01 |
Pos logit contributions | |
Amen | +0.029 |
fires | +0.022 |
stretched | +0.022 |
passenger | +0.020 |
paddle | +0.020 |
Neg logit contributions | |
oph | -0.027 |
ork | -0.027 |
ally | -0.023 |
way | -0.022 |
handed | -0.022 |
Token | was |
Token ID | 373 |
Feature activation | +7.90e-01 |
Pos logit contributions | |
oph | +0.069 |
ork | +0.069 |
keeping | +0.062 |
handed | +0.062 |
ally | +0.060 |
Neg logit contributions | |
Amen | -0.059 |
stretched | -0.045 |
fires | -0.044 |
bears | -0.043 |
smile | -0.042 |
Token | almost |
Token ID | 2048 |
Feature activation | +1.74e+00 |
Pos logit contributions | |
ork | +0.023 |
oph | +0.021 |
handed | +0.019 |
keeping | +0.018 |
ally | +0.018 |
Neg logit contributions | |
Amen | -0.026 |
fires | -0.022 |
stretched | -0.021 |
smile | -0.020 |
bears | -0.019 |
Token | dark |
Token ID | 3223 |
Feature activation | +2.03e+00 |
Pos logit contributions | |
ork | +0.056 |
oph | +0.053 |
handed | +0.049 |
keeping | +0.047 |
ally | +0.046 |
Neg logit contributions | |
Amen | -0.050 |
fires | -0.041 |
stretched | -0.040 |
smile | -0.038 |
hope | -0.035 |
Token | , |
Token ID | 11 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
ork | +0.079 |
oph | +0.077 |
handed | +0.068 |
ally | +0.068 |
way | +0.067 |
Neg logit contributions | |
Amen | -0.045 |
fires | -0.033 |
stretched | -0.031 |
bears | -0.029 |
smile | -0.027 |
Token | the |
Token ID | 262 |
Feature activation | +5.22e-01 |
Pos logit contributions | |
ork | +0.038 |
oph | +0.037 |
way | +0.032 |
ally | +0.032 |
handed | +0.031 |
Neg logit contributions | |
Amen | -0.046 |
fires | -0.035 |
stretched | -0.034 |
bears | -0.032 |
passenger | -0.031 |
Token | fog |
Token ID | 19558 |
Feature activation | +3.82e+00 |
Pos logit contributions | |
ork | +0.016 |
oph | +0.015 |
way | +0.013 |
handed | +0.013 |
ally | +0.013 |
Neg logit contributions | |
Amen | -0.016 |
fires | -0.012 |
stretched | -0.012 |
bears | -0.011 |
scar | -0.011 |
Token | finally |
Token ID | 3443 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
oph | +0.122 |
ork | +0.119 |
handed | +0.104 |
ally | +0.103 |
way | +0.099 |
Neg logit contributions | |
Amen | -0.110 |
stretched | -0.084 |
fires | -0.083 |
smile | -0.077 |
bears | -0.077 |
Token | started |
Token ID | 2067 |
Feature activation | +1.85e+00 |
Pos logit contributions | |
ork | +0.043 |
handed | +0.042 |
keeping | +0.041 |
oph | +0.041 |
ally | +0.038 |
Neg logit contributions | |
wave | -0.021 |
stretched | -0.021 |
smile | -0.020 |
Amen | -0.020 |
ne | -0.018 |
Token | to |
Token ID | 284 |
Feature activation | +5.65e-02 |
Pos logit contributions | |
ork | +0.049 |
oph | +0.047 |
way | +0.041 |
ally | +0.040 |
handed | +0.039 |
Neg logit contributions | |
Amen | -0.066 |
fires | -0.051 |
stretched | -0.049 |
bears | -0.047 |
passenger | -0.046 |
Token | clear |
Token ID | 1598 |
Feature activation | +5.76e-01 |
Pos logit contributions | |
oph | +0.002 |
ork | +0.002 |
way | +0.002 |
doorstep | +0.002 |
handed | +0.002 |
Neg logit contributions | |
Amen | -0.002 |
stretched | -0.001 |
fires | -0.001 |
bears | -0.001 |
passenger | -0.001 |
Token | and |
Token ID | 290 |
Feature activation | -4.19e-01 |
Pos logit contributions | |
ork | +0.017 |
oph | +0.016 |
way | +0.015 |
handed | +0.014 |
ally | +0.014 |
Neg logit contributions | |
Amen | -0.019 |
fires | -0.013 |
stretched | -0.013 |
passenger | -0.013 |
exc | -0.013 |
Token | because |
Token ID | 780 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
ork | +0.007 |
oph | +0.007 |
way | +0.006 |
ally | +0.006 |
handed | +0.006 |
Neg logit contributions | |
Amen | -0.006 |
fires | -0.004 |
stretched | -0.004 |
bears | -0.004 |
smile | -0.004 |
Token | she |
Token ID | 673 |
Feature activation | +9.91e-01 |
Pos logit contributions | |
ork | +0.005 |
oph | +0.005 |
way | +0.004 |
ally | +0.004 |
handed | +0.004 |
Neg logit contributions | |
Amen | -0.004 |
fires | -0.003 |
stretched | -0.003 |
bears | -0.003 |
passenger | -0.003 |
Token | knew |
Token ID | 2993 |
Feature activation | +4.28e-01 |
Pos logit contributions | |
ork | +0.033 |
oph | +0.032 |
way | +0.028 |
ally | +0.028 |
handed | +0.028 |
Neg logit contributions | |
Amen | -0.028 |
fires | -0.021 |
stretched | -0.020 |
bears | -0.019 |
passenger | -0.018 |
Token | she |
Token ID | 673 |
Feature activation | +8.74e-01 |
Pos logit contributions | |
ork | +0.015 |
oph | +0.015 |
way | +0.013 |
ally | +0.013 |
handed | +0.013 |
Neg logit contributions | |
Amen | -0.012 |
fires | -0.009 |
stretched | -0.008 |
bears | -0.008 |
hope | -0.007 |
Token | was |
Token ID | 373 |
Feature activation | -3.76e-01 |
Pos logit contributions | |
ork | +0.029 |
oph | +0.029 |
way | +0.025 |
handed | +0.025 |
ally | +0.025 |
Neg logit contributions | |
Amen | -0.025 |
fires | -0.018 |
stretched | -0.017 |
bears | -0.017 |
hope | -0.016 |
Token | supposed |
Token ID | 4385 |
Feature activation | +3.82e+00 |
Pos logit contributions | |
Amen | +0.009 |
fires | +0.006 |
stretched | +0.005 |
bears | +0.005 |
smile | +0.005 |
Neg logit contributions | |
ork | -0.015 |
oph | -0.015 |
way | -0.013 |
ally | -0.013 |
handed | -0.013 |
Token | to |
Token ID | 284 |
Feature activation | +4.63e-01 |
Pos logit contributions | |
ork | +0.113 |
oph | +0.111 |
ally | +0.094 |
way | +0.093 |
handed | +0.092 |
Neg logit contributions | |
Amen | -0.122 |
fires | -0.096 |
stretched | -0.091 |
bears | -0.087 |
hope | -0.085 |
Token | clean |
Token ID | 3424 |
Feature activation | +3.78e-01 |
Pos logit contributions | |
ork | +0.018 |
oph | +0.018 |
way | +0.016 |
ally | +0.015 |
handed | +0.015 |
Neg logit contributions | |
Amen | -0.011 |
fires | -0.007 |
stretched | -0.007 |
smile | -0.007 |
hope | -0.007 |
Token | her |
Token ID | 607 |
Feature activation | -7.71e-01 |
Pos logit contributions | |
ork | +0.012 |
oph | +0.011 |
way | +0.010 |
ally | +0.010 |
handed | +0.010 |
Neg logit contributions | |
Amen | -0.012 |
fires | -0.009 |
stretched | -0.008 |
bears | -0.008 |
smile | -0.008 |
Token | room |
Token ID | 2119 |
Feature activation | -8.52e-01 |
Pos logit contributions | |
Amen | +0.025 |
fires | +0.020 |
stretched | +0.019 |
bears | +0.018 |
smile | +0.017 |
Neg logit contributions | |
ork | -0.022 |
oph | -0.022 |
way | -0.019 |
ally | -0.018 |
handed | -0.018 |
Token | . |
Token ID | 13 |
Feature activation | +4.22e-01 |
Pos logit contributions | |
Amen | +0.026 |
fires | +0.019 |
stretched | +0.018 |
bears | +0.017 |
passenger | +0.017 |
Neg logit contributions | |
ork | -0.027 |
oph | -0.026 |
way | -0.023 |
handed | -0.023 |
ally | -0.023 |
Token | pretty |
Token ID | 2495 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
ork | +0.047 |
oph | +0.045 |
way | +0.040 |
ally | +0.039 |
handed | +0.039 |
Neg logit contributions | |
Amen | -0.050 |
fires | -0.037 |
stretched | -0.037 |
bears | -0.034 |
passenger | -0.033 |
Token | flowers |
Token ID | 12734 |
Feature activation | +2.23e-01 |
Pos logit contributions | |
ork | +0.042 |
oph | +0.041 |
way | +0.036 |
ally | +0.035 |
handed | +0.034 |
Neg logit contributions | |
Amen | -0.052 |
fires | -0.038 |
stretched | -0.037 |
passenger | -0.035 |
exc | -0.034 |
Token | . |
Token ID | 13 |
Feature activation | +5.13e-02 |
Pos logit contributions | |
ork | +0.007 |
oph | +0.006 |
way | +0.006 |
handed | +0.006 |
ally | +0.006 |
Neg logit contributions | |
Amen | -0.007 |
fires | -0.005 |
stretched | -0.005 |
passenger | -0.005 |
spoiler | -0.005 |
Token | But |
Token ID | 887 |
Feature activation | -8.44e-01 |
Pos logit contributions | |
ork | +0.002 |
oph | +0.002 |
ally | +0.002 |
way | +0.002 |
handed | +0.002 |
Neg logit contributions | |
Amen | -0.001 |
fires | -0.001 |
stretched | -0.001 |
bears | -0.000 |
passenger | -0.000 |
Token | the |
Token ID | 262 |
Feature activation | -6.41e-02 |
Pos logit contributions | |
Amen | +0.020 |
fires | +0.014 |
stretched | +0.013 |
bears | +0.012 |
passenger | +0.011 |
Neg logit contributions | |
ork | -0.032 |
oph | -0.031 |
way | -0.028 |
ally | -0.028 |
handed | -0.028 |
Token | mud |
Token ID | 17492 |
Feature activation | +3.81e+00 |
Pos logit contributions | |
Amen | +0.002 |
fires | +0.002 |
stretched | +0.002 |
passenger | +0.001 |
spoiler | +0.001 |
Neg logit contributions | |
ork | -0.002 |
oph | -0.002 |
way | -0.002 |
ally | -0.002 |
handed | -0.002 |
Token | was |
Token ID | 373 |
Feature activation | +7.70e-01 |
Pos logit contributions | |
oph | +0.118 |
ork | +0.117 |
handed | +0.101 |
way | +0.099 |
ally | +0.099 |
Neg logit contributions | |
Amen | -0.108 |
fires | -0.086 |
stretched | -0.084 |
bears | -0.082 |
smile | -0.077 |
Token | still |
Token ID | 991 |
Feature activation | +9.74e-01 |
Pos logit contributions | |
ork | +0.028 |
oph | +0.027 |
way | +0.024 |
ally | +0.024 |
handed | +0.023 |
Neg logit contributions | |
Amen | -0.020 |
fires | -0.014 |
stretched | -0.013 |
bears | -0.012 |
passenger | -0.012 |
Token | in |
Token ID | 287 |
Feature activation | +7.99e-01 |
Pos logit contributions | |
ork | +0.032 |
oph | +0.031 |
way | +0.028 |
ally | +0.027 |
handed | +0.026 |
Neg logit contributions | |
Amen | -0.029 |
fires | -0.020 |
stretched | -0.020 |
passenger | -0.018 |
bears | -0.018 |
Token | the |
Token ID | 262 |
Feature activation | +7.12e-01 |
Pos logit contributions | |
ork | +0.027 |
oph | +0.027 |
way | +0.024 |
handed | +0.024 |
ally | +0.023 |
Neg logit contributions | |
Amen | -0.022 |
fires | -0.015 |
stretched | -0.015 |
bears | -0.014 |
passenger | -0.013 |
Token | way |
Token ID | 835 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
ork | +0.020 |
oph | +0.019 |
way | +0.016 |
ally | +0.016 |
handed | +0.016 |
Neg logit contributions | |
Amen | -0.024 |
fires | -0.019 |
stretched | -0.018 |
bears | -0.018 |
passenger | -0.017 |
Token | |
Token ID | 220 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
ork | +0.011 |
oph | +0.011 |
handed | +0.010 |
way | +0.009 |
anger | +0.009 |
Neg logit contributions | |
Amen | -0.007 |
fires | -0.004 |
Sometimes | -0.004 |
stretched | -0.004 |
bears | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | +5.76e-01 |
Pos logit contributions | |
Amen | +0.023 |
Sometimes | +0.015 |
fires | +0.015 |
exc | +0.014 |
stretched | +0.013 |
Neg logit contributions | |
oph | -0.048 |
ork | -0.043 |
doorstep | -0.041 |
ally | -0.040 |
keeping | -0.040 |
Token |
|
Token ID | 198 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
oph | +0.020 |
ork | +0.019 |
ally | +0.016 |
way | +0.016 |
handed | +0.016 |
Neg logit contributions | |
Amen | -0.017 |
stretched | -0.011 |
fires | -0.011 |
exc | -0.010 |
Does | -0.010 |
Token | When |
Token ID | 2215 |
Feature activation | -8.08e-01 |
Pos logit contributions | |
ork | +0.006 |
oph | +0.006 |
way | +0.005 |
ally | +0.005 |
handed | +0.005 |
Neg logit contributions | |
Amen | -0.006 |
fires | -0.004 |
stretched | -0.004 |
bears | -0.004 |
passenger | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | +4.11e-01 |
Pos logit contributions | |
Amen | +0.021 |
fires | +0.015 |
bears | +0.014 |
stretched | +0.014 |
hope | +0.013 |
Neg logit contributions | |
ork | -0.029 |
oph | -0.029 |
handed | -0.026 |
ally | -0.025 |
way | -0.025 |
Token | rain |
Token ID | 6290 |
Feature activation | +3.81e+00 |
Pos logit contributions | |
ork | +0.011 |
oph | +0.011 |
way | +0.009 |
ally | +0.009 |
handed | +0.009 |
Neg logit contributions | |
Amen | -0.014 |
fires | -0.011 |
stretched | -0.011 |
passenger | -0.010 |
paddle | -0.010 |
Token | stopped |
Token ID | 5025 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
ork | +0.142 |
oph | +0.139 |
handed | +0.139 |
keeping | +0.133 |
ige | +0.128 |
Neg logit contributions | |
Amen | -0.063 |
sometimes | -0.060 |
smile | -0.057 |
stretched | -0.054 |
zoom | -0.052 |
Token | , |
Token ID | 11 |
Feature activation | +8.40e-01 |
Pos logit contributions | |
ork | +0.034 |
oph | +0.032 |
way | +0.030 |
ally | +0.030 |
handed | +0.028 |
Neg logit contributions | |
Amen | -0.031 |
fires | -0.021 |
stretched | -0.021 |
passenger | -0.020 |
bears | -0.019 |
Token | they |
Token ID | 484 |
Feature activation | +6.79e-01 |
Pos logit contributions | |
ork | +0.030 |
oph | +0.029 |
handed | +0.026 |
ally | +0.026 |
way | +0.026 |
Neg logit contributions | |
Amen | -0.022 |
fires | -0.016 |
stretched | -0.015 |
bears | -0.015 |
passenger | -0.013 |
Token | could |
Token ID | 714 |
Feature activation | +4.26e-01 |
Pos logit contributions | |
ork | +0.025 |
oph | +0.024 |
handed | +0.021 |
way | +0.021 |
ally | +0.021 |
Neg logit contributions | |
Amen | -0.017 |
stretched | -0.012 |
fires | -0.012 |
smile | -0.011 |
bears | -0.011 |
Token | still |
Token ID | 991 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
ork | +0.016 |
oph | +0.015 |
way | +0.014 |
ally | +0.013 |
handed | +0.013 |
Neg logit contributions | |
Amen | -0.011 |
fires | -0.008 |
stretched | -0.007 |
bears | -0.007 |
scar | -0.006 |
Token | and |
Token ID | 290 |
Feature activation | +5.68e-01 |
Pos logit contributions | |
ork | +0.011 |
oph | +0.011 |
way | +0.010 |
ally | +0.010 |
handed | +0.009 |
Neg logit contributions | |
Amen | -0.009 |
stretched | -0.006 |
fires | -0.006 |
bears | -0.006 |
passenger | -0.006 |
Token | bright |
Token ID | 6016 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
ork | +0.020 |
oph | +0.020 |
way | +0.017 |
handed | +0.017 |
ally | +0.017 |
Neg logit contributions | |
Amen | -0.015 |
fires | -0.011 |
stretched | -0.010 |
bears | -0.009 |
passenger | -0.009 |
Token | colors |
Token ID | 7577 |
Feature activation | -8.97e-02 |
Pos logit contributions | |
ork | +0.006 |
oph | +0.006 |
ally | +0.005 |
way | +0.005 |
handed | +0.005 |
Neg logit contributions | |
Amen | -0.008 |
fires | -0.005 |
exc | -0.005 |
stretched | -0.005 |
Does | -0.005 |
Token | they |
Token ID | 484 |
Feature activation | +9.41e-01 |
Pos logit contributions | |
Amen | +0.003 |
fires | +0.002 |
stretched | +0.002 |
bears | +0.002 |
scar | +0.002 |
Neg logit contributions | |
ork | -0.003 |
oph | -0.003 |
way | -0.002 |
ally | -0.002 |
handed | -0.002 |
Token | were |
Token ID | 547 |
Feature activation | +6.84e-01 |
Pos logit contributions | |
ork | +0.028 |
oph | +0.028 |
ally | +0.024 |
way | +0.024 |
handed | +0.023 |
Neg logit contributions | |
Amen | -0.030 |
fires | -0.023 |
stretched | -0.021 |
bears | -0.020 |
sled | -0.020 |
Token | able |
Token ID | 1498 |
Feature activation | +3.81e+00 |
Pos logit contributions | |
ork | +0.022 |
oph | +0.022 |
way | +0.019 |
ally | +0.019 |
handed | +0.019 |
Neg logit contributions | |
Amen | -0.020 |
fires | -0.014 |
stretched | -0.014 |
bears | -0.013 |
scar | -0.012 |
Token | to |
Token ID | 284 |
Feature activation | +8.48e-02 |
Pos logit contributions | |
oph | +0.129 |
ork | +0.125 |
ally | +0.111 |
handed | +0.108 |
anger | +0.105 |
Neg logit contributions | |
Amen | -0.095 |
fires | -0.079 |
stretched | -0.078 |
smile | -0.073 |
hope | -0.070 |
Token | create |
Token ID | 2251 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
ork | +0.003 |
oph | +0.003 |
ally | +0.002 |
way | +0.002 |
doorstep | +0.002 |
Neg logit contributions | |
Amen | -0.002 |
fires | -0.002 |
bears | -0.002 |
stretched | -0.002 |
scar | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | +2.88e-01 |
Pos logit contributions | |
Amen | +0.037 |
fires | +0.028 |
stretched | +0.026 |
bears | +0.025 |
scar | +0.024 |
Neg logit contributions | |
ork | -0.045 |
oph | -0.045 |
way | -0.039 |
ally | -0.039 |
handed | -0.039 |
Token |
|
Token ID | 198 |
Feature activation | +5.41e-01 |
Pos logit contributions | |
ork | +0.010 |
oph | +0.009 |
way | +0.008 |
ally | +0.008 |
handed | +0.008 |
Neg logit contributions | |
Amen | -0.008 |
fires | -0.006 |
stretched | -0.006 |
bears | -0.005 |
passenger | -0.005 |
Token |
|
Token ID | 198 |
Feature activation | +1.74e-01 |
Pos logit contributions | |
ork | +0.016 |
oph | +0.016 |
way | +0.013 |
ally | +0.013 |
handed | +0.013 |
Neg logit contributions | |
Amen | -0.018 |
fires | -0.013 |
stretched | -0.013 |
bears | -0.012 |
smile | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | +3.96e-01 |
Pos logit contributions | |
oph | +0.056 |
ork | +0.054 |
ally | +0.049 |
handed | +0.047 |
way | +0.045 |
Neg logit contributions | |
Amen | -0.040 |
fires | -0.030 |
stretched | -0.029 |
bears | -0.027 |
smile | -0.027 |
Token |
|
Token ID | 198 |
Feature activation | +7.19e-01 |
Pos logit contributions | |
ork | +0.015 |
oph | +0.015 |
anger | +0.013 |
way | +0.013 |
handed | +0.013 |
Neg logit contributions | |
Amen | -0.010 |
fires | -0.005 |
Sometimes | -0.005 |
nod | -0.005 |
Everyday | -0.005 |
Token |
|
Token ID | 198 |
Feature activation | +3.74e-01 |
Pos logit contributions | |
oph | +0.025 |
ork | +0.024 |
keeping | +0.022 |
way | +0.022 |
ally | +0.021 |
Neg logit contributions | |
Amen | -0.019 |
fires | -0.013 |
stretched | -0.012 |
sled | -0.012 |
smile | -0.012 |
Token | When |
Token ID | 2215 |
Feature activation | -9.95e-01 |
Pos logit contributions | |
ork | +0.013 |
oph | +0.013 |
keeping | +0.011 |
way | +0.011 |
ally | +0.011 |
Neg logit contributions | |
Amen | -0.010 |
fires | -0.007 |
stretched | -0.007 |
passenger | -0.006 |
Does | -0.006 |
Token | the |
Token ID | 262 |
Feature activation | +2.35e-01 |
Pos logit contributions | |
Amen | +0.021 |
fires | +0.015 |
bears | +0.013 |
stretched | +0.012 |
smile | +0.011 |
Neg logit contributions | |
ork | -0.040 |
oph | -0.039 |
handed | -0.037 |
ally | -0.035 |
way | -0.035 |
Token | rain |
Token ID | 6290 |
Feature activation | +3.80e+00 |
Pos logit contributions | |
ork | +0.007 |
oph | +0.007 |
way | +0.006 |
ally | +0.006 |
handed | +0.006 |
Neg logit contributions | |
Amen | -0.007 |
fires | -0.006 |
stretched | -0.006 |
bears | -0.005 |
passenger | -0.005 |
Token | had |
Token ID | 550 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
oph | +0.137 |
ork | +0.136 |
handed | +0.135 |
ige | +0.131 |
keeping | +0.127 |
Neg logit contributions | |
Amen | -0.062 |
sometimes | -0.056 |
smile | -0.056 |
bears | -0.052 |
zoom | -0.051 |
Token | stopped |
Token ID | 5025 |
Feature activation | +8.51e-01 |
Pos logit contributions | |
ork | +0.056 |
oph | +0.054 |
handed | +0.051 |
ally | +0.049 |
anger | +0.048 |
Neg logit contributions | |
Amen | -0.040 |
fires | -0.037 |
smile | -0.037 |
hope | -0.033 |
stretched | -0.033 |
Token | , |
Token ID | 11 |
Feature activation | +8.41e-01 |
Pos logit contributions | |
ork | +0.028 |
oph | +0.026 |
way | +0.024 |
ally | +0.024 |
handed | +0.023 |
Neg logit contributions | |
Amen | -0.025 |
stretched | -0.017 |
fires | -0.017 |
bears | -0.016 |
passenger | -0.015 |
Token | the |
Token ID | 262 |
Feature activation | +3.42e-01 |
Pos logit contributions | |
ork | +0.031 |
oph | +0.031 |
way | +0.027 |
ally | +0.027 |
handed | +0.027 |
Neg logit contributions | |
Amen | -0.021 |
fires | -0.015 |
stretched | -0.014 |
bears | -0.013 |
passenger | -0.012 |
Token | children |
Token ID | 1751 |
Feature activation | +7.96e-01 |
Pos logit contributions | |
ork | +0.011 |
oph | +0.011 |
way | +0.009 |
ally | +0.009 |
handed | +0.009 |
Neg logit contributions | |
Amen | -0.010 |
fires | -0.008 |
stretched | -0.008 |
bears | -0.007 |
passenger | -0.007 |
Token | with |
Token ID | 351 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
Amen | +0.020 |
fires | +0.014 |
stretched | +0.014 |
bears | +0.013 |
paddle | +0.012 |
Neg logit contributions | |
ork | -0.024 |
oph | -0.023 |
way | -0.020 |
ally | -0.020 |
handed | -0.019 |
Token | the |
Token ID | 262 |
Feature activation | -5.81e-02 |
Pos logit contributions | |
Amen | +0.004 |
fires | +0.003 |
stretched | +0.003 |
passenger | +0.003 |
bears | +0.003 |
Neg logit contributions | |
ork | -0.005 |
oph | -0.005 |
way | -0.004 |
handed | -0.004 |
ally | -0.004 |
Token | machine |
Token ID | 4572 |
Feature activation | -6.00e-01 |
Pos logit contributions | |
Amen | +0.002 |
fires | +0.001 |
stretched | +0.001 |
bears | +0.001 |
passenger | +0.001 |
Neg logit contributions | |
ork | -0.002 |
oph | -0.002 |
way | -0.002 |
handed | -0.002 |
ally | -0.002 |
Token | until |
Token ID | 1566 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
Amen | +0.019 |
fires | +0.014 |
stretched | +0.013 |
bears | +0.012 |
Does | +0.012 |
Neg logit contributions | |
ork | -0.018 |
oph | -0.017 |
way | -0.016 |
ally | -0.015 |
handed | -0.015 |
Token | the |
Token ID | 262 |
Feature activation | +4.55e-01 |
Pos logit contributions | |
Amen | +0.043 |
fires | +0.032 |
stretched | +0.031 |
bears | +0.029 |
smile | +0.028 |
Neg logit contributions | |
ork | -0.045 |
oph | -0.044 |
handed | -0.038 |
ally | -0.038 |
way | -0.038 |
Token | rain |
Token ID | 6290 |
Feature activation | +3.80e+00 |
Pos logit contributions | |
ork | +0.014 |
oph | +0.013 |
way | +0.012 |
ally | +0.012 |
handed | +0.012 |
Neg logit contributions | |
Amen | -0.014 |
fires | -0.011 |
stretched | -0.010 |
bears | -0.010 |
passenger | -0.009 |
Token | stopped |
Token ID | 5025 |
Feature activation | +7.20e-01 |
Pos logit contributions | |
oph | +0.138 |
ork | +0.137 |
handed | +0.136 |
keeping | +0.123 |
ally | +0.121 |
Neg logit contributions | |
Amen | -0.063 |
smile | -0.056 |
stretched | -0.054 |
wave | -0.054 |
sometimes | -0.054 |
Token | pouring |
Token ID | 23147 |
Feature activation | +7.31e-01 |
Pos logit contributions | |
ork | +0.021 |
oph | +0.019 |
way | +0.018 |
ally | +0.017 |
handed | +0.016 |
Neg logit contributions | |
Amen | -0.024 |
fires | -0.017 |
stretched | -0.017 |
bears | -0.016 |
passenger | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
ork | +0.024 |
oph | +0.023 |
way | +0.020 |
ally | +0.020 |
handed | +0.020 |
Neg logit contributions | |
Amen | -0.022 |
fires | -0.016 |
stretched | -0.016 |
bears | -0.015 |
passenger | -0.014 |
Token | Then |
Token ID | 3244 |
Feature activation | +4.51e-02 |
Pos logit contributions | |
oph | +0.006 |
ork | +0.006 |
handed | +0.005 |
ally | +0.005 |
keeping | +0.005 |
Neg logit contributions | |
Amen | -0.005 |
fires | -0.003 |
stretched | -0.003 |
nod | -0.003 |
passenger | -0.003 |
Token | the |
Token ID | 262 |
Feature activation | +2.77e-03 |
Pos logit contributions | |
ork | +0.002 |
oph | +0.001 |
way | +0.001 |
ally | +0.001 |
handed | +0.001 |
Neg logit contributions | |
Amen | -0.001 |
fires | -0.001 |
stretched | -0.001 |
bears | -0.001 |
passenger | -0.001 |
Token | mom |
Token ID | 1995 |
Feature activation | -1.92e+00 |
Pos logit contributions | |
Amen | +0.010 |
stretched | +0.008 |
fires | +0.007 |
helmet | +0.007 |
bears | +0.007 |
Neg logit contributions | |
ork | -0.010 |
oph | -0.009 |
ally | -0.009 |
way | -0.008 |
doorstep | -0.008 |
Token | and |
Token ID | 290 |
Feature activation | -8.62e-01 |
Pos logit contributions | |
Amen | +0.065 |
stretched | +0.049 |
fires | +0.046 |
paddle | +0.045 |
spoiler | +0.045 |
Neg logit contributions | |
ork | -0.053 |
oph | -0.051 |
ally | -0.046 |
way | -0.045 |
handed | -0.044 |
Token | to |
Token ID | 284 |
Feature activation | -4.31e-01 |
Pos logit contributions | |
Amen | +0.030 |
fires | +0.023 |
stretched | +0.023 |
bears | +0.021 |
spoiler | +0.021 |
Neg logit contributions | |
ork | -0.023 |
oph | -0.022 |
way | -0.019 |
ally | -0.019 |
handed | -0.018 |
Token | the |
Token ID | 262 |
Feature activation | -9.50e-01 |
Pos logit contributions | |
Amen | +0.011 |
fires | +0.008 |
stretched | +0.008 |
bears | +0.007 |
scar | +0.007 |
Neg logit contributions | |
ork | -0.015 |
oph | -0.015 |
way | -0.013 |
ally | -0.013 |
handed | -0.013 |
Token | ost |
Token ID | 23619 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
Amen | +0.027 |
fires | +0.020 |
stretched | +0.019 |
bears | +0.018 |
passenger | +0.017 |
Neg logit contributions | |
oph | -0.032 |
ork | -0.032 |
ally | -0.028 |
way | -0.027 |
handed | -0.027 |
Token | ric |
Token ID | 1173 |
Feature activation | -5.39e+00 |
Pos logit contributions | |
ork | +0.006 |
oph | +0.006 |
way | +0.005 |
handed | +0.005 |
ally | +0.005 |
Neg logit contributions | |
Amen | -0.002 |
fires | -0.001 |
stretched | -0.001 |
bears | -0.001 |
passenger | -0.001 |
Token | hes |
Token ID | 956 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
Amen | +0.134 |
fires | +0.108 |
bears | +0.087 |
stretched | +0.086 |
exc | +0.081 |
Neg logit contributions | |
oph | -0.213 |
ork | -0.188 |
ally | -0.184 |
doorstep | -0.178 |
way | -0.169 |
Token | . |
Token ID | 13 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
Amen | +0.046 |
stretched | +0.033 |
fires | +0.033 |
bears | +0.031 |
scar | +0.030 |
Neg logit contributions | |
ork | -0.047 |
oph | -0.043 |
way | -0.039 |
handed | -0.038 |
ally | -0.038 |
Token | They |
Token ID | 1119 |
Feature activation | -5.92e-01 |
Pos logit contributions | |
Amen | +0.005 |
fires | +0.004 |
stretched | +0.004 |
bears | +0.003 |
paddle | +0.003 |
Neg logit contributions | |
ork | -0.006 |
oph | -0.006 |
way | -0.005 |
ally | -0.005 |
handed | -0.005 |
Token | learned |
Token ID | 4499 |
Feature activation | -4.80e-01 |
Pos logit contributions | |
Amen | +0.019 |
fires | +0.015 |
stretched | +0.014 |
bears | +0.013 |
passenger | +0.012 |
Neg logit contributions | |
oph | -0.018 |
ork | -0.017 |
ally | -0.015 |
way | -0.015 |
handed | -0.015 |
Token | their |
Token ID | 511 |
Feature activation | +2.25e-01 |
Pos logit contributions | |
Amen | +0.014 |
stretched | +0.010 |
fires | +0.010 |
bears | +0.009 |
spoiler | +0.009 |
Neg logit contributions | |
ork | -0.016 |
oph | -0.015 |
way | -0.014 |
handed | -0.013 |
ally | -0.013 |
Token | and |
Token ID | 290 |
Feature activation | +6.66e-02 |
Pos logit contributions | |
ork | +0.005 |
oph | +0.005 |
way | +0.005 |
handed | +0.004 |
ally | +0.004 |
Neg logit contributions | |
Amen | -0.005 |
fires | -0.004 |
stretched | -0.003 |
bears | -0.003 |
scar | -0.003 |
Token | run |
Token ID | 1057 |
Feature activation | +6.70e-01 |
Pos logit contributions | |
ork | +0.002 |
oph | +0.002 |
doorstep | +0.002 |
way | +0.002 |
keeping | +0.002 |
Neg logit contributions | |
Amen | -0.002 |
stretched | -0.002 |
fires | -0.001 |
bears | -0.001 |
Does | -0.001 |
Token | to |
Token ID | 284 |
Feature activation | -5.10e-01 |
Pos logit contributions | |
ork | +0.020 |
oph | +0.019 |
way | +0.017 |
ally | +0.017 |
handed | +0.017 |
Neg logit contributions | |
Amen | -0.021 |
fires | -0.016 |
stretched | -0.016 |
bears | -0.015 |
passenger | -0.014 |
Token | the |
Token ID | 262 |
Feature activation | -8.55e-01 |
Pos logit contributions | |
Amen | +0.014 |
fires | +0.010 |
stretched | +0.010 |
bears | +0.009 |
scar | +0.008 |
Neg logit contributions | |
ork | -0.018 |
oph | -0.017 |
way | -0.016 |
handed | -0.015 |
ally | -0.015 |
Token | ost |
Token ID | 23619 |
Feature activation | +2.43e-01 |
Pos logit contributions | |
Amen | +0.025 |
fires | +0.020 |
bears | +0.019 |
scar | +0.018 |
stretched | +0.018 |
Neg logit contributions | |
oph | -0.027 |
ork | -0.026 |
ally | -0.023 |
way | -0.023 |
handed | -0.023 |
Token | ric |
Token ID | 1173 |
Feature activation | -5.25e+00 |
Pos logit contributions | |
ork | +0.011 |
oph | +0.011 |
handed | +0.010 |
way | +0.010 |
ally | +0.010 |
Neg logit contributions | |
Amen | -0.004 |
fires | -0.002 |
stretched | -0.002 |
bears | -0.002 |
passenger | -0.002 |
Token | hes |
Token ID | 956 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
Amen | +0.143 |
fires | +0.113 |
stretched | +0.101 |
bears | +0.095 |
exc | +0.091 |
Neg logit contributions | |
oph | -0.185 |
ork | -0.171 |
ally | -0.161 |
doorstep | -0.155 |
handed | -0.152 |
Token | . |
Token ID | 13 |
Feature activation | +2.04e-01 |
Pos logit contributions | |
Amen | +0.037 |
fires | +0.027 |
stretched | +0.026 |
bears | +0.025 |
scar | +0.025 |
Neg logit contributions | |
ork | -0.036 |
oph | -0.032 |
way | -0.030 |
handed | -0.028 |
ally | -0.028 |
Token |
|
Token ID | 198 |
Feature activation | +2.51e-01 |
Pos logit contributions | |
oph | +0.008 |
ork | +0.008 |
ally | +0.007 |
handed | +0.007 |
way | +0.007 |
Neg logit contributions | |
Amen | -0.005 |
fires | -0.003 |
stretched | -0.003 |
paddle | -0.003 |
hope | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | -2.42e-03 |
Pos logit contributions | |
oph | +0.009 |
ork | +0.008 |
ally | +0.007 |
handed | +0.007 |
doorstep | +0.007 |
Neg logit contributions | |
Amen | -0.007 |
fires | -0.005 |
stretched | -0.005 |
exc | -0.005 |
sled | -0.005 |
Token | " |
Token ID | 1 |
Feature activation | +3.62e-01 |
Pos logit contributions | |
Amen | +0.000 |
fires | +0.000 |
stretched | +0.000 |
bears | +0.000 |
passenger | +0.000 |
Neg logit contributions | |
ork | -0.000 |
oph | -0.000 |
way | -0.000 |
ally | -0.000 |
handed | -0.000 |
Token | should |
Token ID | 815 |
Feature activation | +2.75e-01 |
Pos logit contributions | |
Amen | +0.022 |
stretched | +0.016 |
fires | +0.016 |
passenger | +0.014 |
bears | +0.014 |
Neg logit contributions | |
ork | -0.026 |
oph | -0.025 |
handed | -0.022 |
ally | -0.022 |
way | -0.022 |
Token | not |
Token ID | 407 |
Feature activation | +7.52e-01 |
Pos logit contributions | |
ork | +0.009 |
oph | +0.009 |
way | +0.008 |
ally | +0.008 |
handed | +0.008 |
Neg logit contributions | |
Amen | -0.008 |
fires | -0.006 |
stretched | -0.005 |
bears | -0.005 |
passenger | -0.005 |
Token | tease |
Token ID | 34691 |
Feature activation | +8.99e-01 |
Pos logit contributions | |
ork | +0.029 |
oph | +0.029 |
handed | +0.025 |
way | +0.025 |
ally | +0.025 |
Neg logit contributions | |
Amen | -0.017 |
fires | -0.012 |
stretched | -0.011 |
bears | -0.010 |
smile | -0.010 |
Token | the |
Token ID | 262 |
Feature activation | +3.41e-02 |
Pos logit contributions | |
ork | +0.030 |
oph | +0.029 |
way | +0.025 |
ally | +0.025 |
handed | +0.025 |
Neg logit contributions | |
Amen | -0.025 |
fires | -0.020 |
bears | -0.019 |
stretched | -0.019 |
scar | -0.017 |
Token | ost |
Token ID | 23619 |
Feature activation | +2.65e-01 |
Pos logit contributions | |
oph | +0.001 |
ork | +0.001 |
ally | +0.001 |
handed | +0.001 |
way | +0.001 |
Neg logit contributions | |
Amen | -0.001 |
fires | -0.001 |
bears | -0.001 |
stretched | -0.001 |
passenger | -0.001 |
Token | ric |
Token ID | 1173 |
Feature activation | -5.13e+00 |
Pos logit contributions | |
oph | +0.012 |
ork | +0.012 |
handed | +0.011 |
way | +0.011 |
ally | +0.011 |
Neg logit contributions | |
Amen | -0.004 |
fires | -0.002 |
stretched | -0.002 |
bears | -0.002 |
passenger | -0.001 |
Token | hes |
Token ID | 956 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
Amen | +0.138 |
fires | +0.113 |
stretched | +0.098 |
bears | +0.096 |
exc | +0.089 |
Neg logit contributions | |
oph | -0.182 |
ork | -0.168 |
ally | -0.157 |
doorstep | -0.155 |
handed | -0.148 |
Token | . |
Token ID | 13 |
Feature activation | -4.14e-01 |
Pos logit contributions | |
Amen | +0.046 |
stretched | +0.033 |
fires | +0.032 |
bears | +0.030 |
scar | +0.030 |
Neg logit contributions | |
ork | -0.046 |
oph | -0.042 |
way | -0.038 |
handed | -0.037 |
ally | -0.037 |
Token | They |
Token ID | 1119 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
Amen | +0.012 |
fires | +0.009 |
stretched | +0.009 |
bears | +0.008 |
scar | +0.008 |
Neg logit contributions | |
ork | -0.014 |
oph | -0.013 |
way | -0.012 |
ally | -0.012 |
handed | -0.011 |
Token | are |
Token ID | 389 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
Amen | +0.003 |
stretched | +0.002 |
fires | +0.002 |
passenger | +0.001 |
bears | +0.001 |
Neg logit contributions | |
ork | -0.004 |
oph | -0.004 |
way | -0.003 |
handed | -0.003 |
ally | -0.003 |
Token | not |
Token ID | 407 |
Feature activation | +7.36e-01 |
Pos logit contributions | |
ork | +0.006 |
oph | +0.005 |
way | +0.005 |
ally | +0.005 |
handed | +0.005 |
Neg logit contributions | |
Amen | -0.005 |
fires | -0.004 |
stretched | -0.004 |
bears | -0.004 |
passenger | -0.004 |
Token | and |
Token ID | 290 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
Amen | +0.019 |
spoiler | +0.013 |
fires | +0.013 |
stretched | +0.013 |
helmet | +0.013 |
Neg logit contributions | |
ork | -0.014 |
way | -0.013 |
oph | -0.012 |
ally | -0.012 |
handed | -0.011 |
Token | looked |
Token ID | 3114 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
Amen | +0.004 |
fires | +0.003 |
stretched | +0.003 |
bears | +0.002 |
paddle | +0.002 |
Neg logit contributions | |
ork | -0.005 |
oph | -0.005 |
way | -0.005 |
handed | -0.005 |
ally | -0.005 |
Token | at |
Token ID | 379 |
Feature activation | -5.59e-01 |
Pos logit contributions | |
Amen | +0.051 |
stretched | +0.038 |
fires | +0.036 |
passenger | +0.035 |
Does | +0.035 |
Neg logit contributions | |
ork | -0.038 |
oph | -0.036 |
way | -0.033 |
ally | -0.031 |
handed | -0.030 |
Token | the |
Token ID | 262 |
Feature activation | -3.69e-01 |
Pos logit contributions | |
Amen | +0.017 |
stretched | +0.012 |
fires | +0.012 |
bears | +0.010 |
passenger | +0.010 |
Neg logit contributions | |
ork | -0.018 |
oph | -0.017 |
way | -0.015 |
ally | -0.015 |
handed | -0.015 |
Token | ost |
Token ID | 23619 |
Feature activation | +4.81e-01 |
Pos logit contributions | |
Amen | +0.010 |
fires | +0.007 |
stretched | +0.007 |
bears | +0.007 |
passenger | +0.006 |
Neg logit contributions | |
oph | -0.013 |
ork | -0.013 |
ally | -0.012 |
handed | -0.011 |
way | -0.011 |
Token | ric |
Token ID | 1173 |
Feature activation | -5.12e+00 |
Pos logit contributions | |
ork | +0.022 |
oph | +0.022 |
handed | +0.020 |
way | +0.020 |
ally | +0.020 |
Neg logit contributions | |
Amen | -0.007 |
fires | -0.004 |
stretched | -0.004 |
bears | -0.003 |
passenger | -0.003 |
Token | hes |
Token ID | 956 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
Amen | +0.139 |
fires | +0.109 |
stretched | +0.098 |
bears | +0.092 |
exc | +0.087 |
Neg logit contributions | |
oph | -0.182 |
ork | -0.169 |
ally | -0.159 |
doorstep | -0.152 |
handed | -0.149 |
Token | . |
Token ID | 13 |
Feature activation | -1.97e-01 |
Pos logit contributions | |
Amen | +0.041 |
fires | +0.030 |
stretched | +0.029 |
bears | +0.027 |
scar | +0.026 |
Neg logit contributions | |
ork | -0.043 |
oph | -0.041 |
way | -0.037 |
ally | -0.036 |
handed | -0.035 |
Token | They |
Token ID | 1119 |
Feature activation | +1.42e-02 |
Pos logit contributions | |
Amen | +0.003 |
fires | +0.002 |
bears | +0.002 |
stretched | +0.002 |
whine | +0.002 |
Neg logit contributions | |
oph | -0.008 |
ork | -0.008 |
handed | -0.008 |
ally | -0.008 |
way | -0.007 |
Token | saw |
Token ID | 2497 |
Feature activation | -2.91e-01 |
Pos logit contributions | |
ork | +0.000 |
oph | +0.000 |
ally | +0.000 |
way | +0.000 |
handed | +0.000 |
Neg logit contributions | |
Amen | -0.000 |
fires | -0.000 |
stretched | -0.000 |
bears | -0.000 |
passenger | -0.000 |
Token | one |
Token ID | 530 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
Amen | +0.009 |
stretched | +0.006 |
fires | +0.006 |
bears | +0.005 |
passenger | +0.005 |
Neg logit contributions | |
ork | -0.010 |
oph | -0.009 |
way | -0.008 |
handed | -0.008 |
ally | -0.008 |
Token | wanted |
Token ID | 2227 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
Amen | +0.010 |
fires | +0.008 |
stretched | +0.007 |
bears | +0.007 |
passenger | +0.006 |
Neg logit contributions | |
oph | -0.010 |
ork | -0.010 |
ally | -0.009 |
way | -0.009 |
handed | -0.008 |
Token | to |
Token ID | 284 |
Feature activation | +4.90e-02 |
Pos logit contributions | |
oph | +0.007 |
ork | +0.007 |
way | +0.006 |
ally | +0.006 |
handed | +0.006 |
Neg logit contributions | |
Amen | -0.007 |
fires | -0.005 |
bears | -0.005 |
stretched | -0.005 |
hope | -0.005 |
Token | touch |
Token ID | 3638 |
Feature activation | +6.04e-01 |
Pos logit contributions | |
ork | +0.002 |
oph | +0.002 |
way | +0.002 |
ally | +0.002 |
handed | +0.002 |
Neg logit contributions | |
Amen | -0.001 |
fires | -0.001 |
stretched | -0.001 |
bears | -0.001 |
passenger | -0.001 |
Token | the |
Token ID | 262 |
Feature activation | +6.97e-02 |
Pos logit contributions | |
ork | +0.019 |
oph | +0.018 |
way | +0.016 |
handed | +0.016 |
ally | +0.016 |
Neg logit contributions | |
Amen | -0.018 |
stretched | -0.013 |
fires | -0.012 |
passenger | -0.011 |
exc | -0.011 |
Token | ost |
Token ID | 23619 |
Feature activation | +2.83e-01 |
Pos logit contributions | |
oph | +0.003 |
ork | +0.002 |
handed | +0.002 |
ally | +0.002 |
way | +0.002 |
Neg logit contributions | |
Amen | -0.002 |
fires | -0.001 |
bears | -0.001 |
scar | -0.001 |
stretched | -0.001 |
Token | ric |
Token ID | 1173 |
Feature activation | -5.06e+00 |
Pos logit contributions | |
oph | +0.013 |
ork | +0.013 |
handed | +0.012 |
way | +0.012 |
ally | +0.012 |
Neg logit contributions | |
Amen | -0.004 |
fires | -0.002 |
stretched | -0.002 |
bears | -0.002 |
passenger | -0.001 |
Token | hes |
Token ID | 956 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
Amen | +0.123 |
fires | +0.099 |
stretched | +0.084 |
bears | +0.080 |
exc | +0.078 |
Neg logit contributions | |
oph | -0.195 |
ork | -0.174 |
ally | -0.168 |
doorstep | -0.167 |
keeping | -0.159 |
Token | . |
Token ID | 13 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
Amen | +0.048 |
fires | +0.034 |
stretched | +0.034 |
bears | +0.031 |
passenger | +0.031 |
Neg logit contributions | |
ork | -0.048 |
oph | -0.045 |
way | -0.040 |
ally | -0.039 |
handed | -0.038 |
Token | They |
Token ID | 1119 |
Feature activation | -2.69e-01 |
Pos logit contributions | |
Amen | +0.003 |
fires | +0.002 |
stretched | +0.002 |
hope | +0.002 |
sometimes | +0.002 |
Neg logit contributions | |
oph | -0.005 |
ork | -0.005 |
handed | -0.005 |
ally | -0.005 |
way | -0.004 |
Token | reached |
Token ID | 4251 |
Feature activation | -5.81e-01 |
Pos logit contributions | |
Amen | +0.008 |
fires | +0.006 |
stretched | +0.006 |
bears | +0.005 |
passenger | +0.005 |
Neg logit contributions | |
ork | -0.009 |
oph | -0.008 |
ally | -0.007 |
way | -0.007 |
handed | -0.007 |
Token | out |
Token ID | 503 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
Amen | +0.022 |
fires | +0.017 |
stretched | +0.017 |
bears | +0.015 |
spoiler | +0.015 |
Neg logit contributions | |
ork | -0.014 |
oph | -0.014 |
way | -0.012 |
ally | -0.011 |
doorstep | -0.011 |
Token | loved |
Token ID | 6151 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
ork | +0.034 |
oph | +0.033 |
way | +0.029 |
ally | +0.028 |
handed | +0.028 |
Neg logit contributions | |
Amen | -0.033 |
fires | -0.025 |
stretched | -0.024 |
bears | -0.022 |
passenger | -0.021 |
Token | to |
Token ID | 284 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
Amen | +0.046 |
stretched | +0.035 |
fires | +0.035 |
passenger | +0.033 |
spoiler | +0.032 |
Neg logit contributions | |
ork | -0.034 |
oph | -0.033 |
way | -0.028 |
ally | -0.028 |
handed | -0.027 |
Token | play |
Token ID | 711 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
Amen | +0.005 |
fires | +0.004 |
stretched | +0.004 |
passenger | +0.004 |
bears | +0.004 |
Neg logit contributions | |
ork | -0.005 |
oph | -0.005 |
ally | -0.004 |
n | -0.004 |
doorstep | -0.004 |
Token | make |
Token ID | 787 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
Amen | +0.037 |
stretched | +0.029 |
fires | +0.029 |
bears | +0.026 |
passenger | +0.026 |
Neg logit contributions | |
ork | -0.030 |
oph | -0.028 |
way | -0.024 |
ally | -0.024 |
handed | -0.023 |
Token | - |
Token ID | 12 |
Feature activation | +5.88e-01 |
Pos logit contributions | |
Amen | +0.029 |
fires | +0.024 |
bears | +0.023 |
stretched | +0.021 |
scar | +0.021 |
Neg logit contributions | |
oph | -0.040 |
ork | -0.040 |
way | -0.035 |
ally | -0.035 |
handed | -0.034 |
Token | bel |
Token ID | 6667 |
Feature activation | -4.80e+00 |
Pos logit contributions | |
ork | +0.018 |
oph | +0.017 |
way | +0.015 |
handed | +0.015 |
ally | +0.015 |
Neg logit contributions | |
Amen | -0.018 |
fires | -0.014 |
stretched | -0.014 |
bears | -0.013 |
paddle | -0.012 |
Token | ieve |
Token ID | 12311 |
Feature activation | -4.90e-01 |
Pos logit contributions | |
Amen | +0.118 |
stretched | +0.080 |
fires | +0.078 |
paddle | +0.071 |
bears | +0.071 |
Neg logit contributions | |
ork | -0.178 |
oph | -0.172 |
handed | -0.155 |
way | -0.155 |
ally | -0.151 |
Token | . |
Token ID | 13 |
Feature activation | -4.20e-01 |
Pos logit contributions | |
Amen | +0.016 |
stretched | +0.012 |
fires | +0.012 |
paddle | +0.011 |
spoiler | +0.011 |
Neg logit contributions | |
ork | -0.015 |
oph | -0.014 |
way | -0.012 |
handed | -0.012 |
ally | -0.011 |
Token | Today |
Token ID | 6288 |
Feature activation | +8.16e-01 |
Pos logit contributions | |
Amen | +0.011 |
fires | +0.008 |
stretched | +0.007 |
bears | +0.007 |
scar | +0.007 |
Neg logit contributions | |
ork | -0.015 |
oph | -0.015 |
way | -0.013 |
ally | -0.013 |
handed | -0.013 |
Token | she |
Token ID | 673 |
Feature activation | +9.73e-01 |
Pos logit contributions | |
oph | +0.035 |
ork | +0.034 |
handed | +0.032 |
keeping | +0.032 |
ige | +0.031 |
Neg logit contributions | |
Amen | -0.011 |
sometimes | -0.008 |
smile | -0.007 |
fires | -0.007 |
stretched | -0.007 |
Token | was |
Token ID | 373 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
ork | +0.030 |
oph | +0.029 |
way | +0.025 |
ally | +0.025 |
handed | +0.025 |
Neg logit contributions | |
Amen | -0.030 |
fires | -0.023 |
stretched | -0.022 |
bears | -0.021 |
passenger | -0.020 |
Token | They |
Token ID | 1119 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
Amen | +0.002 |
stretched | +0.002 |
fires | +0.002 |
bears | +0.001 |
scar | +0.001 |
Neg logit contributions | |
ork | -0.003 |
oph | -0.003 |
way | -0.003 |
handed | -0.002 |
ally | -0.002 |
Token | do |
Token ID | 466 |
Feature activation | -2.74e-01 |
Pos logit contributions | |
Amen | +0.005 |
stretched | +0.004 |
fires | +0.003 |
bears | +0.003 |
spoiler | +0.003 |
Neg logit contributions | |
ork | -0.005 |
oph | -0.005 |
doorstep | -0.005 |
handed | -0.005 |
ally | -0.005 |
Token | not |
Token ID | 407 |
Feature activation | +9.55e-01 |
Pos logit contributions | |
Amen | +0.010 |
stretched | +0.008 |
fires | +0.007 |
bears | +0.007 |
passenger | +0.007 |
Neg logit contributions | |
ork | -0.008 |
oph | -0.007 |
way | -0.006 |
handed | -0.006 |
ally | -0.006 |
Token | pack |
Token ID | 2353 |
Feature activation | +8.23e-01 |
Pos logit contributions | |
ork | +0.036 |
oph | +0.034 |
way | +0.032 |
ally | +0.031 |
handed | +0.031 |
Neg logit contributions | |
Amen | -0.023 |
stretched | -0.016 |
fires | -0.015 |
bears | -0.014 |
passenger | -0.013 |
Token | ost |
Token ID | 23619 |
Feature activation | +4.81e-01 |
Pos logit contributions | |
oph | +0.031 |
ork | +0.031 |
ally | +0.027 |
way | +0.027 |
handed | +0.027 |
Neg logit contributions | |
Amen | -0.019 |
fires | -0.015 |
stretched | -0.013 |
bears | -0.013 |
hope | -0.012 |
Token | ric |
Token ID | 1173 |
Feature activation | -4.48e+00 |
Pos logit contributions | |
oph | +0.020 |
ork | +0.020 |
way | +0.018 |
handed | +0.018 |
ally | +0.018 |
Neg logit contributions | |
Amen | -0.009 |
fires | -0.006 |
stretched | -0.006 |
bears | -0.005 |
scar | -0.005 |
Token | hes |
Token ID | 956 |
Feature activation | -6.87e-01 |
Pos logit contributions | |
Amen | +0.125 |
fires | +0.103 |
stretched | +0.090 |
bears | +0.090 |
passenger | +0.081 |
Neg logit contributions | |
oph | -0.153 |
ork | -0.146 |
ally | -0.132 |
doorstep | -0.127 |
way | -0.127 |
Token | anymore |
Token ID | 7471 |
Feature activation | +3.77e-01 |
Pos logit contributions | |
Amen | +0.019 |
stretched | +0.013 |
fires | +0.013 |
bears | +0.012 |
passenger | +0.012 |
Neg logit contributions | |
ork | -0.024 |
oph | -0.023 |
way | -0.020 |
handed | -0.020 |
ally | -0.020 |
Token | . |
Token ID | 13 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
oph | +0.014 |
ork | +0.013 |
ally | +0.012 |
way | +0.012 |
handed | +0.012 |
Neg logit contributions | |
Amen | -0.010 |
fires | -0.007 |
stretched | -0.007 |
bears | -0.007 |
exc | -0.006 |
Token | They |
Token ID | 1119 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
Amen | +0.003 |
fires | +0.002 |
stretched | +0.002 |
bears | +0.002 |
passenger | +0.002 |
Neg logit contributions | |
ork | -0.005 |
oph | -0.005 |
ally | -0.004 |
way | -0.004 |
handed | -0.004 |
Token | pack |
Token ID | 2353 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
Amen | +0.005 |
stretched | +0.004 |
fires | +0.004 |
bears | +0.004 |
Does | +0.003 |
Neg logit contributions | |
ork | -0.005 |
oph | -0.005 |
doorstep | -0.005 |
handed | -0.005 |
n | -0.005 |
Token | " |
Token ID | 366 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
ork | +0.041 |
oph | +0.039 |
way | +0.034 |
ally | +0.033 |
handed | +0.031 |
Neg logit contributions | |
Amen | -0.047 |
fires | -0.037 |
stretched | -0.036 |
bears | -0.034 |
passenger | -0.033 |
Token | Please |
Token ID | 5492 |
Feature activation | -2.46e-01 |
Pos logit contributions | |
ork | +0.004 |
oph | +0.004 |
way | +0.004 |
ally | +0.004 |
handed | +0.004 |
Neg logit contributions | |
Amen | -0.004 |
fires | -0.003 |
stretched | -0.003 |
bears | -0.003 |
passenger | -0.003 |
Token | keep |
Token ID | 1394 |
Feature activation | +7.26e-01 |
Pos logit contributions | |
Amen | +0.007 |
fires | +0.005 |
stretched | +0.005 |
bears | +0.004 |
passenger | +0.004 |
Neg logit contributions | |
ork | -0.009 |
oph | -0.008 |
way | -0.008 |
ally | -0.007 |
handed | -0.007 |
Token | your |
Token ID | 534 |
Feature activation | +6.56e-01 |
Pos logit contributions | |
ork | +0.024 |
oph | +0.023 |
way | +0.020 |
ally | +0.020 |
handed | +0.020 |
Neg logit contributions | |
Amen | -0.021 |
fires | -0.016 |
stretched | -0.015 |
bears | -0.014 |
passenger | -0.014 |
Token | seat |
Token ID | 5852 |
Feature activation | -6.84e-01 |
Pos logit contributions | |
ork | +0.021 |
oph | +0.018 |
way | +0.017 |
doorstep | +0.017 |
handed | +0.016 |
Neg logit contributions | |
Amen | -0.021 |
stretched | -0.015 |
fires | -0.014 |
Does | -0.014 |
bears | -0.014 |
Token | bel |
Token ID | 6667 |
Feature activation | -4.47e+00 |
Pos logit contributions | |
Amen | +0.023 |
stretched | +0.017 |
fires | +0.017 |
bears | +0.016 |
Does | +0.016 |
Neg logit contributions | |
ork | -0.020 |
oph | -0.017 |
way | -0.017 |
handed | -0.016 |
doorstep | -0.016 |
Token | ts |
Token ID | 912 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
Amen | +0.109 |
fires | +0.075 |
stretched | +0.074 |
bears | +0.068 |
paddle | +0.065 |
Neg logit contributions | |
ork | -0.166 |
oph | -0.160 |
way | -0.145 |
handed | -0.144 |
ally | -0.141 |
Token | on |
Token ID | 319 |
Feature activation | +4.04e-01 |
Pos logit contributions | |
Amen | +0.050 |
fires | +0.037 |
stretched | +0.036 |
bears | +0.034 |
passenger | +0.032 |
Neg logit contributions | |
ork | -0.051 |
oph | -0.049 |
way | -0.044 |
handed | -0.043 |
ally | -0.043 |
Token | . |
Token ID | 13 |
Feature activation | -2.30e-01 |
Pos logit contributions | |
ork | +0.013 |
oph | +0.012 |
way | +0.011 |
handed | +0.011 |
ally | +0.010 |
Neg logit contributions | |
Amen | -0.012 |
stretched | -0.009 |
fires | -0.009 |
bears | -0.008 |
scar | -0.008 |
Token | We |
Token ID | 775 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
Amen | +0.007 |
stretched | +0.006 |
fires | +0.006 |
bears | +0.006 |
scar | +0.006 |
Neg logit contributions | |
ork | -0.006 |
oph | -0.006 |
way | -0.005 |
handed | -0.005 |
doorstep | -0.005 |
Token | will |
Token ID | 481 |
Feature activation | +6.92e-01 |
Pos logit contributions | |
ork | +0.046 |
oph | +0.040 |
way | +0.040 |
n | +0.038 |
handed | +0.037 |
Neg logit contributions | |
Amen | -0.030 |
stretched | -0.022 |
fires | -0.020 |
Does | -0.019 |
bears | -0.018 |
Token | couldn |
Token ID | 3521 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
oph | +0.018 |
ork | +0.018 |
handed | +0.016 |
keeping | +0.016 |
way | +0.016 |
Neg logit contributions | |
Amen | -0.013 |
stretched | -0.010 |
fires | -0.010 |
bears | -0.010 |
sometimes | -0.009 |
Token | 't |
Token ID | 470 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
Amen | +0.043 |
fires | +0.033 |
stretched | +0.032 |
bears | +0.031 |
passenger | +0.029 |
Neg logit contributions | |
ork | -0.034 |
oph | -0.033 |
way | -0.028 |
ally | -0.028 |
handed | -0.028 |
Token | get |
Token ID | 651 |
Feature activation | +8.73e-01 |
Pos logit contributions | |
ork | +0.004 |
oph | +0.004 |
way | +0.003 |
ally | +0.003 |
handed | +0.003 |
Neg logit contributions | |
Amen | -0.003 |
fires | -0.002 |
stretched | -0.002 |
bears | -0.002 |
passenger | -0.002 |
Token | above |
Token ID | 2029 |
Feature activation | -1.90e+00 |
Pos logit contributions | |
ork | +0.028 |
oph | +0.026 |
way | +0.025 |
handed | +0.024 |
ally | +0.023 |
Neg logit contributions | |
Amen | -0.026 |
stretched | -0.018 |
fires | -0.018 |
passenger | -0.017 |
bears | -0.016 |
Token | the |
Token ID | 262 |
Feature activation | -6.65e-01 |
Pos logit contributions | |
Amen | +0.060 |
stretched | +0.042 |
passenger | +0.040 |
exc | +0.039 |
whine | +0.039 |
Neg logit contributions | |
ork | -0.060 |
oph | -0.054 |
way | -0.049 |
handed | -0.048 |
ally | -0.047 |
Token | tre |
Token ID | 2054 |
Feature activation | -4.44e+00 |
Pos logit contributions | |
Amen | +0.019 |
fires | +0.014 |
stretched | +0.014 |
bears | +0.013 |
smile | +0.013 |
Neg logit contributions | |
ork | -0.022 |
oph | -0.022 |
ally | -0.019 |
way | -0.019 |
handed | -0.019 |
Token | et |
Token ID | 316 |
Feature activation | -5.63e-01 |
Pos logit contributions | |
Amen | +0.136 |
fires | +0.104 |
stretched | +0.098 |
exc | +0.090 |
passenger | +0.090 |
Neg logit contributions | |
ork | -0.140 |
oph | -0.135 |
way | -0.115 |
handed | -0.115 |
ally | -0.115 |
Token | ops |
Token ID | 2840 |
Feature activation | -2.37e+00 |
Pos logit contributions | |
Amen | +0.018 |
fires | +0.013 |
stretched | +0.012 |
bears | +0.012 |
scar | +0.012 |
Neg logit contributions | |
ork | -0.018 |
oph | -0.017 |
way | -0.015 |
ally | -0.015 |
handed | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | -2.43e-01 |
Pos logit contributions | |
Amen | +0.066 |
fires | +0.049 |
stretched | +0.047 |
bears | +0.044 |
smile | +0.042 |
Neg logit contributions | |
ork | -0.079 |
oph | -0.078 |
way | -0.068 |
ally | -0.068 |
handed | -0.067 |
Token | He |
Token ID | 679 |
Feature activation | -5.89e-01 |
Pos logit contributions | |
Amen | +0.005 |
fires | +0.004 |
stretched | +0.004 |
bears | +0.003 |
paddle | +0.003 |
Neg logit contributions | |
ork | -0.009 |
oph | -0.009 |
ally | -0.008 |
handed | -0.008 |
way | -0.008 |
Token | was |
Token ID | 373 |
Feature activation | +8.32e-02 |
Pos logit contributions | |
Amen | +0.018 |
fires | +0.013 |
stretched | +0.013 |
bears | +0.012 |
passenger | +0.011 |
Neg logit contributions | |
ork | -0.019 |
oph | -0.018 |
way | -0.016 |
ally | -0.016 |
handed | -0.016 |
Token | selfish |
Token ID | 20363 |
Feature activation | +4.06e-01 |
Pos logit contributions | |
ork | +0.014 |
oph | +0.013 |
way | +0.012 |
ally | +0.012 |
handed | +0.012 |
Neg logit contributions | |
Amen | -0.013 |
stretched | -0.010 |
fires | -0.010 |
passenger | -0.009 |
sled | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | -3.15e-01 |
Pos logit contributions | |
ork | +0.013 |
oph | +0.013 |
way | +0.011 |
ally | +0.011 |
handed | +0.011 |
Neg logit contributions | |
Amen | -0.012 |
fires | -0.009 |
stretched | -0.009 |
bears | -0.008 |
passenger | -0.008 |
Token | She |
Token ID | 1375 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
Amen | +0.007 |
fires | +0.005 |
stretched | +0.005 |
bears | +0.004 |
smile | +0.004 |
Neg logit contributions | |
ork | -0.012 |
oph | -0.012 |
way | -0.011 |
handed | -0.011 |
ally | -0.011 |
Token | thanked |
Token ID | 26280 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
Amen | +0.041 |
fires | +0.032 |
stretched | +0.031 |
passenger | +0.028 |
bears | +0.027 |
Neg logit contributions | |
ork | -0.039 |
oph | -0.039 |
ally | -0.033 |
way | -0.032 |
handed | -0.031 |
Token | her |
Token ID | 607 |
Feature activation | -7.19e-01 |
Pos logit contributions | |
Amen | +0.029 |
fires | +0.022 |
stretched | +0.021 |
bears | +0.020 |
passenger | +0.019 |
Neg logit contributions | |
ork | -0.033 |
oph | -0.032 |
ally | -0.028 |
way | -0.028 |
handed | -0.028 |
Token | brothers |
Token ID | 9397 |
Feature activation | -4.40e+00 |
Pos logit contributions | |
Amen | +0.026 |
stretched | +0.020 |
fires | +0.019 |
spoiler | +0.018 |
passenger | +0.018 |
Neg logit contributions | |
ork | -0.019 |
oph | -0.018 |
ally | -0.016 |
doorstep | -0.015 |
way | -0.014 |
Token | and |
Token ID | 290 |
Feature activation | -2.72e-01 |
Pos logit contributions | |
Amen | +0.145 |
fires | +0.108 |
stretched | +0.106 |
spoiler | +0.098 |
Does | +0.097 |
Neg logit contributions | |
ork | -0.123 |
oph | -0.121 |
way | -0.110 |
ally | -0.104 |
handed | -0.102 |
Token | sisters |
Token ID | 15153 |
Feature activation | -2.40e+00 |
Pos logit contributions | |
Amen | +0.008 |
fires | +0.006 |
stretched | +0.006 |
bears | +0.005 |
passenger | +0.005 |
Neg logit contributions | |
oph | -0.009 |
ork | -0.009 |
ally | -0.008 |
way | -0.007 |
handed | -0.007 |
Token | for |
Token ID | 329 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
Amen | +0.078 |
fires | +0.060 |
stretched | +0.057 |
bears | +0.054 |
scar | +0.053 |
Neg logit contributions | |
ork | -0.069 |
oph | -0.067 |
way | -0.061 |
handed | -0.059 |
ally | -0.057 |
Token | saving |
Token ID | 8914 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
ork | +0.038 |
oph | +0.037 |
way | +0.033 |
handed | +0.033 |
ally | +0.033 |
Neg logit contributions | |
Amen | -0.036 |
fires | -0.026 |
stretched | -0.026 |
bears | -0.024 |
passenger | -0.023 |
Token | her |
Token ID | 607 |
Feature activation | -3.56e-01 |
Pos logit contributions | |
ork | +0.007 |
oph | +0.006 |
way | +0.006 |
lor | +0.006 |
ally | +0.006 |
Neg logit contributions | |
Amen | -0.004 |
fires | -0.003 |
bears | -0.003 |
hope | -0.002 |
scar | -0.002 |
Token | " |
Token ID | 366 |
Feature activation | -4.42e-01 |
Pos logit contributions | |
ork | +0.046 |
oph | +0.044 |
ally | +0.041 |
way | +0.040 |
handed | +0.038 |
Neg logit contributions | |
Amen | -0.047 |
stretched | -0.035 |
spoiler | -0.032 |
scar | -0.031 |
fires | -0.031 |
Token | What |
Token ID | 2061 |
Feature activation | -8.24e-01 |
Pos logit contributions | |
Amen | +0.012 |
fires | +0.009 |
stretched | +0.009 |
smile | +0.008 |
scar | +0.007 |
Neg logit contributions | |
oph | -0.015 |
ork | -0.015 |
handed | -0.013 |
ally | -0.013 |
way | -0.013 |
Token | are |
Token ID | 389 |
Feature activation | -2.78e-01 |
Pos logit contributions | |
Amen | +0.022 |
fires | +0.016 |
stretched | +0.015 |
bears | +0.014 |
hope | +0.013 |
Neg logit contributions | |
ork | -0.029 |
oph | -0.029 |
way | -0.025 |
ally | -0.025 |
handed | -0.025 |
Token | you |
Token ID | 345 |
Feature activation | -3.03e-01 |
Pos logit contributions | |
Amen | +0.010 |
fires | +0.008 |
stretched | +0.007 |
bears | +0.007 |
scar | +0.007 |
Neg logit contributions | |
ork | -0.008 |
oph | -0.007 |
way | -0.006 |
handed | -0.006 |
ally | -0.006 |
Token | doing |
Token ID | 1804 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
Amen | +0.008 |
fires | +0.005 |
bears | +0.005 |
smile | +0.005 |
stretched | +0.005 |
Neg logit contributions | |
ork | -0.011 |
oph | -0.011 |
handed | -0.010 |
way | -0.010 |
ally | -0.009 |
Token | |
Token ID | 220 |
Feature activation | -4.35e+00 |
Pos logit contributions | |
Amen | +0.040 |
stretched | +0.029 |
fires | +0.028 |
bears | +0.025 |
passenger | +0.025 |
Neg logit contributions | |
ork | -0.054 |
oph | -0.052 |
way | -0.047 |
ally | -0.046 |
handed | -0.046 |
Token | ?" |
Token ID | 1701 |
Feature activation | +6.35e-01 |
Pos logit contributions | |
Amen | +0.148 |
fires | +0.117 |
stretched | +0.115 |
exc | +0.107 |
bears | +0.104 |
Neg logit contributions | |
oph | -0.111 |
ork | -0.110 |
keeping | -0.094 |
handed | -0.093 |
ally | -0.091 |
Token | The |
Token ID | 383 |
Feature activation | -2.31e+00 |
Pos logit contributions | |
ork | +0.019 |
oph | +0.018 |
way | +0.016 |
ally | +0.016 |
handed | +0.016 |
Neg logit contributions | |
Amen | -0.020 |
fires | -0.016 |
stretched | -0.016 |
bears | -0.014 |
scar | -0.014 |
Token | tube |
Token ID | 12403 |
Feature activation | -2.54e-01 |
Pos logit contributions | |
Amen | +0.076 |
fires | +0.056 |
stretched | +0.054 |
bears | +0.051 |
scar | +0.048 |
Neg logit contributions | |
ork | -0.071 |
oph | -0.065 |
way | -0.064 |
ally | -0.061 |
handed | -0.058 |
Token | didn |
Token ID | 1422 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
Amen | +0.008 |
fires | +0.006 |
stretched | +0.006 |
bears | +0.005 |
smile | +0.005 |
Neg logit contributions | |
ork | -0.008 |
oph | -0.008 |
way | -0.007 |
handed | -0.007 |
ally | -0.007 |
Token | 't |
Token ID | 470 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
Amen | +0.038 |
fires | +0.030 |
stretched | +0.029 |
bears | +0.028 |
scar | +0.027 |
Neg logit contributions | |
ork | -0.028 |
oph | -0.027 |
way | -0.023 |
ally | -0.022 |
handed | -0.022 |
Token | cried |
Token ID | 16896 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
Amen | +0.021 |
fires | +0.017 |
stretched | +0.016 |
bears | +0.015 |
passenger | +0.015 |
Neg logit contributions | |
ork | -0.019 |
oph | -0.018 |
way | -0.016 |
ally | -0.015 |
handed | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | -3.26e-01 |
Pos logit contributions | |
Amen | +0.035 |
fires | +0.025 |
stretched | +0.025 |
passenger | +0.024 |
bears | +0.023 |
Neg logit contributions | |
ork | -0.028 |
oph | -0.025 |
way | -0.023 |
ally | -0.022 |
handed | -0.021 |
Token | " |
Token ID | 366 |
Feature activation | -4.21e-01 |
Pos logit contributions | |
Amen | +0.009 |
fires | +0.007 |
stretched | +0.006 |
bears | +0.006 |
smile | +0.006 |
Neg logit contributions | |
oph | -0.011 |
ork | -0.011 |
handed | -0.010 |
ally | -0.010 |
way | -0.010 |
Token | The |
Token ID | 464 |
Feature activation | -8.56e-01 |
Pos logit contributions | |
Amen | +0.014 |
fires | +0.011 |
stretched | +0.011 |
bears | +0.010 |
scar | +0.010 |
Neg logit contributions | |
ork | -0.012 |
oph | -0.011 |
handed | -0.010 |
way | -0.010 |
ally | -0.009 |
Token | ost |
Token ID | 23619 |
Feature activation | +7.76e-01 |
Pos logit contributions | |
Amen | +0.027 |
stretched | +0.021 |
fires | +0.021 |
bears | +0.019 |
passenger | +0.018 |
Neg logit contributions | |
ork | -0.026 |
oph | -0.024 |
way | -0.021 |
handed | -0.021 |
ally | -0.021 |
Token | ric |
Token ID | 1173 |
Feature activation | -4.34e+00 |
Pos logit contributions | |
ork | +0.033 |
oph | +0.033 |
way | +0.029 |
ally | +0.029 |
handed | +0.029 |
Neg logit contributions | |
Amen | -0.015 |
fires | -0.009 |
stretched | -0.009 |
bears | -0.008 |
passenger | -0.007 |
Token | hes |
Token ID | 956 |
Feature activation | -4.19e-01 |
Pos logit contributions | |
Amen | +0.123 |
fires | +0.097 |
stretched | +0.089 |
bears | +0.085 |
exc | +0.079 |
Neg logit contributions | |
oph | -0.145 |
ork | -0.139 |
ally | -0.125 |
way | -0.121 |
doorstep | -0.121 |
Token | are |
Token ID | 389 |
Feature activation | -2.58e-01 |
Pos logit contributions | |
Amen | +0.012 |
stretched | +0.008 |
fires | +0.008 |
scar | +0.008 |
bears | +0.008 |
Neg logit contributions | |
ork | -0.014 |
oph | -0.013 |
way | -0.012 |
ally | -0.012 |
handed | -0.012 |
Token | mean |
Token ID | 1612 |
Feature activation | +4.66e-01 |
Pos logit contributions | |
Amen | +0.007 |
fires | +0.005 |
stretched | +0.005 |
bears | +0.005 |
passenger | +0.005 |
Neg logit contributions | |
ork | -0.009 |
oph | -0.008 |
way | -0.007 |
ally | -0.007 |
handed | -0.007 |
Token | ! |
Token ID | 0 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
ork | +0.014 |
oph | +0.014 |
way | +0.012 |
ally | +0.012 |
handed | +0.012 |
Neg logit contributions | |
Amen | -0.015 |
fires | -0.011 |
stretched | -0.011 |
bears | -0.010 |
passenger | -0.010 |
Token | They |
Token ID | 1119 |
Feature activation | +5.53e-01 |
Pos logit contributions | |
Amen | +0.037 |
fires | +0.028 |
stretched | +0.028 |
bears | +0.026 |
scar | +0.026 |
Neg logit contributions | |
ork | -0.031 |
oph | -0.029 |
way | -0.025 |
ally | -0.025 |
handed | -0.025 |
Token | together |
Token ID | 1978 |
Feature activation | -7.10e-01 |
Pos logit contributions | |
Amen | +0.022 |
stretched | +0.017 |
fires | +0.016 |
scar | +0.015 |
bears | +0.015 |
Neg logit contributions | |
ork | -0.018 |
oph | -0.017 |
way | -0.015 |
handed | -0.015 |
ally | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | +4.76e-01 |
Pos logit contributions | |
Amen | +0.022 |
fires | +0.016 |
stretched | +0.016 |
bears | +0.015 |
passenger | +0.014 |
Neg logit contributions | |
ork | -0.022 |
oph | -0.021 |
way | -0.019 |
ally | -0.018 |
handed | -0.018 |
Token | They |
Token ID | 1119 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
ork | +0.022 |
oph | +0.021 |
handed | +0.020 |
lor | +0.020 |
anger | +0.018 |
Neg logit contributions | |
Amen | -0.007 |
Sometimes | -0.004 |
sometimes | -0.004 |
Everyday | -0.004 |
wonder | -0.004 |
Token | let |
Token ID | 1309 |
Feature activation | +4.35e-01 |
Pos logit contributions | |
oph | +0.005 |
ally | +0.005 |
ork | +0.005 |
way | +0.005 |
doorstep | +0.004 |
Neg logit contributions | |
Amen | -0.008 |
fires | -0.006 |
stretched | -0.006 |
helmet | -0.005 |
spoiler | -0.005 |
Token | their |
Token ID | 511 |
Feature activation | +4.49e-01 |
Pos logit contributions | |
ork | +0.018 |
oph | +0.018 |
keeping | +0.018 |
lor | +0.017 |
handed | +0.017 |
Neg logit contributions | |
Amen | -0.006 |
cheer | -0.005 |
hope | -0.005 |
pretend | -0.005 |
bears | -0.004 |
Token | imag |
Token ID | 3590 |
Feature activation | -4.33e+00 |
Pos logit contributions | |
ork | +0.016 |
oph | +0.016 |
handed | +0.014 |
way | +0.014 |
ally | +0.014 |
Neg logit contributions | |
Amen | -0.011 |
fires | -0.008 |
bears | -0.008 |
stretched | -0.008 |
smile | -0.007 |
Token | inations |
Token ID | 7352 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
Amen | +0.141 |
fires | +0.107 |
stretched | +0.104 |
bears | +0.099 |
passenger | +0.097 |
Neg logit contributions | |
ork | -0.127 |
oph | -0.123 |
way | -0.109 |
ally | -0.108 |
handed | -0.105 |
Token | take |
Token ID | 1011 |
Feature activation | +5.64e-02 |
Pos logit contributions | |
Amen | +0.032 |
fires | +0.023 |
stretched | +0.022 |
bears | +0.020 |
passenger | +0.019 |
Neg logit contributions | |
ork | -0.043 |
oph | -0.042 |
way | -0.037 |
ally | -0.037 |
handed | -0.037 |
Token | over |
Token ID | 625 |
Feature activation | -3.37e-02 |
Pos logit contributions | |
oph | +0.002 |
ork | +0.002 |
ally | +0.002 |
way | +0.002 |
doorstep | +0.002 |
Neg logit contributions | |
Amen | -0.001 |
fires | -0.001 |
hope | -0.001 |
bears | -0.001 |
g | -0.001 |
Token | and |
Token ID | 290 |
Feature activation | -3.16e-01 |
Pos logit contributions | |
Amen | +0.001 |
stretched | +0.001 |
fires | +0.001 |
passenger | +0.001 |
spoiler | +0.001 |
Neg logit contributions | |
ork | -0.001 |
oph | -0.001 |
way | -0.001 |
ally | -0.001 |
handed | -0.001 |
Token | soon |
Token ID | 2582 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
Amen | +0.008 |
stretched | +0.006 |
fires | +0.006 |
bears | +0.005 |
passenger | +0.005 |
Neg logit contributions | |
ork | -0.011 |
oph | -0.011 |
way | -0.009 |
ally | -0.009 |
handed | -0.009 |
Token | ostr |
Token ID | 42387 |
Feature activation | +2.34e-01 |
Pos logit contributions | |
Amen | +0.023 |
stretched | +0.018 |
fires | +0.017 |
bears | +0.016 |
smile | +0.015 |
Neg logit contributions | |
ork | -0.023 |
oph | -0.021 |
handed | -0.019 |
way | -0.019 |
ally | -0.018 |
Token | ich |
Token ID | 488 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
ork | +0.005 |
oph | +0.004 |
way | +0.003 |
ally | +0.003 |
handed | +0.003 |
Neg logit contributions | |
Amen | -0.010 |
fires | -0.008 |
stretched | -0.008 |
bears | -0.008 |
scar | -0.007 |
Token | pen |
Token ID | 3112 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
Amen | +0.045 |
stretched | +0.036 |
fires | +0.035 |
spoiler | +0.034 |
scar | +0.032 |
Neg logit contributions | |
ork | -0.036 |
oph | -0.033 |
way | -0.031 |
handed | -0.031 |
doorstep | -0.030 |
Token | . |
Token ID | 13 |
Feature activation | -3.40e-01 |
Pos logit contributions | |
Amen | +0.053 |
fires | +0.039 |
stretched | +0.038 |
bears | +0.035 |
paddle | +0.033 |
Neg logit contributions | |
ork | -0.063 |
oph | -0.061 |
way | -0.054 |
ally | -0.053 |
handed | -0.053 |
Token | Ost |
Token ID | 38919 |
Feature activation | -1.70e-01 |
Pos logit contributions | |
Amen | +0.011 |
fires | +0.009 |
stretched | +0.009 |
bears | +0.008 |
scar | +0.008 |
Neg logit contributions | |
ork | -0.009 |
oph | -0.008 |
way | -0.007 |
ess | -0.007 |
ally | -0.007 |
Token | ric |
Token ID | 1173 |
Feature activation | -4.29e+00 |
Pos logit contributions | |
Amen | +0.003 |
fires | +0.002 |
stretched | +0.001 |
bears | +0.001 |
passenger | +0.001 |
Neg logit contributions | |
ork | -0.008 |
oph | -0.008 |
way | -0.007 |
ally | -0.007 |
handed | -0.007 |
Token | hes |
Token ID | 956 |
Feature activation | -5.47e-02 |
Pos logit contributions | |
Amen | +0.121 |
fires | +0.096 |
stretched | +0.087 |
bears | +0.084 |
exc | +0.077 |
Neg logit contributions | |
oph | -0.146 |
ork | -0.138 |
ally | -0.126 |
doorstep | -0.122 |
way | -0.121 |
Token | are |
Token ID | 389 |
Feature activation | +3.63e-01 |
Pos logit contributions | |
Amen | +0.002 |
stretched | +0.001 |
fires | +0.001 |
scar | +0.001 |
passenger | +0.001 |
Neg logit contributions | |
ork | -0.002 |
oph | -0.002 |
way | -0.002 |
handed | -0.002 |
ally | -0.001 |
Token | big |
Token ID | 1263 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
ork | +0.012 |
oph | +0.011 |
way | +0.010 |
ally | +0.010 |
handed | +0.010 |
Neg logit contributions | |
Amen | -0.011 |
stretched | -0.007 |
fires | -0.007 |
spoiler | -0.006 |
passenger | -0.006 |
Token | birds |
Token ID | 10087 |
Feature activation | -4.81e-01 |
Pos logit contributions | |
Amen | +0.006 |
stretched | +0.004 |
paddle | +0.004 |
exc | +0.004 |
Does | +0.004 |
Neg logit contributions | |
ork | -0.005 |
oph | -0.005 |
keeping | -0.004 |
handed | -0.004 |
way | -0.004 |
Token | with |
Token ID | 351 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
Amen | +0.015 |
fires | +0.011 |
stretched | +0.011 |
Does | +0.010 |
scar | +0.010 |
Neg logit contributions | |
ork | -0.014 |
oph | -0.013 |
way | -0.012 |
handed | -0.012 |
ally | -0.011 |
Token | but |
Token ID | 475 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
Amen | +0.009 |
fires | +0.007 |
stretched | +0.007 |
bears | +0.007 |
scar | +0.006 |
Neg logit contributions | |
ork | -0.007 |
oph | -0.007 |
way | -0.006 |
handed | -0.006 |
ally | -0.006 |
Token | be |
Token ID | 307 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
Amen | +0.032 |
fires | +0.023 |
stretched | +0.022 |
bears | +0.021 |
scar | +0.020 |
Neg logit contributions | |
ork | -0.039 |
oph | -0.038 |
handed | -0.033 |
way | -0.033 |
ally | -0.033 |
Token | careful |
Token ID | 8161 |
Feature activation | +2.95e-01 |
Pos logit contributions | |
Amen | +0.005 |
stretched | +0.004 |
fires | +0.004 |
bears | +0.004 |
paddle | +0.004 |
Neg logit contributions | |
ork | -0.006 |
oph | -0.006 |
way | -0.005 |
handed | -0.005 |
ally | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | -3.45e-01 |
Pos logit contributions | |
ork | +0.010 |
oph | +0.009 |
way | +0.008 |
ally | +0.008 |
handed | +0.008 |
Neg logit contributions | |
Amen | -0.009 |
fires | -0.006 |
stretched | -0.006 |
bears | -0.006 |
passenger | -0.006 |
Token | Ost |
Token ID | 38919 |
Feature activation | -5.48e-01 |
Pos logit contributions | |
Amen | +0.010 |
stretched | +0.008 |
fires | +0.008 |
bears | +0.007 |
scar | +0.007 |
Neg logit contributions | |
ork | -0.010 |
oph | -0.010 |
ally | -0.009 |
way | -0.009 |
handed | -0.009 |
Token | ric |
Token ID | 1173 |
Feature activation | -4.26e+00 |
Pos logit contributions | |
Amen | +0.009 |
fires | +0.005 |
bears | +0.004 |
stretched | +0.004 |
passenger | +0.004 |
Neg logit contributions | |
ork | -0.025 |
oph | -0.025 |
way | -0.022 |
ally | -0.022 |
handed | -0.021 |
Token | hes |
Token ID | 956 |
Feature activation | -2.72e-01 |
Pos logit contributions | |
Amen | +0.119 |
fires | +0.095 |
stretched | +0.084 |
bears | +0.083 |
exc | +0.077 |
Neg logit contributions | |
oph | -0.146 |
ork | -0.139 |
ally | -0.127 |
doorstep | -0.123 |
way | -0.122 |
Token | can |
Token ID | 460 |
Feature activation | +4.07e-02 |
Pos logit contributions | |
Amen | +0.008 |
stretched | +0.006 |
fires | +0.005 |
passenger | +0.005 |
scar | +0.005 |
Neg logit contributions | |
ork | -0.009 |
oph | -0.008 |
way | -0.008 |
handed | -0.008 |
ally | -0.008 |
Token | be |
Token ID | 307 |
Feature activation | +4.26e-01 |
Pos logit contributions | |
ork | +0.001 |
oph | +0.001 |
way | +0.001 |
ally | +0.001 |
handed | +0.001 |
Neg logit contributions | |
Amen | -0.001 |
fires | -0.001 |
stretched | -0.001 |
bears | -0.001 |
passenger | -0.001 |
Token | gr |
Token ID | 1036 |
Feature activation | -5.43e-01 |
Pos logit contributions | |
oph | +0.016 |
ork | +0.015 |
ally | +0.013 |
way | +0.013 |
handed | +0.013 |
Neg logit contributions | |
Amen | -0.011 |
fires | -0.008 |
stretched | -0.007 |
bears | -0.007 |
scar | -0.007 |
Token | umpy |
Token ID | 32152 |
Feature activation | -4.72e-02 |
Pos logit contributions | |
Amen | +0.017 |
fires | +0.014 |
stretched | +0.014 |
bears | +0.013 |
exc | +0.012 |
Neg logit contributions | |
oph | -0.015 |
ork | -0.015 |
doorstep | -0.013 |
ally | -0.012 |
handed | -0.012 |
Token | a |
Token ID | 257 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
Amen | +0.028 |
fires | +0.019 |
stretched | +0.019 |
whine | +0.018 |
paddle | +0.018 |
Neg logit contributions | |
ork | -0.030 |
oph | -0.029 |
way | -0.026 |
handed | -0.026 |
ally | -0.025 |
Token | nearby |
Token ID | 6716 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
Amen | +0.034 |
fires | +0.026 |
stretched | +0.025 |
bears | +0.024 |
passenger | +0.023 |
Neg logit contributions | |
ork | -0.031 |
oph | -0.030 |
way | -0.026 |
ally | -0.026 |
handed | -0.026 |
Token | tree |
Token ID | 5509 |
Feature activation | -8.45e-01 |
Pos logit contributions | |
ork | +0.004 |
oph | +0.004 |
way | +0.004 |
ally | +0.004 |
handed | +0.004 |
Neg logit contributions | |
Amen | -0.004 |
fires | -0.003 |
stretched | -0.003 |
bears | -0.003 |
smile | -0.003 |
Token | watched |
Token ID | 7342 |
Feature activation | -1.86e+00 |
Pos logit contributions | |
Amen | +0.026 |
fires | +0.019 |
stretched | +0.018 |
bears | +0.018 |
paddle | +0.017 |
Neg logit contributions | |
ork | -0.026 |
oph | -0.025 |
way | -0.023 |
handed | -0.022 |
ally | -0.022 |
Token | him |
Token ID | 683 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
Amen | +0.051 |
fires | +0.035 |
stretched | +0.035 |
passenger | +0.032 |
bears | +0.032 |
Neg logit contributions | |
ork | -0.064 |
oph | -0.062 |
way | -0.055 |
ally | -0.054 |
handed | -0.054 |
Token | int |
Token ID | 493 |
Feature activation | -4.23e+00 |
Pos logit contributions | |
Amen | +0.045 |
fires | +0.032 |
stretched | +0.031 |
Does | +0.030 |
passenger | +0.029 |
Neg logit contributions | |
ork | -0.041 |
oph | -0.037 |
way | -0.036 |
doorstep | -0.034 |
handed | -0.033 |
Token | ently |
Token ID | 1473 |
Feature activation | -2.83e+00 |
Pos logit contributions | |
Amen | +0.172 |
fires | +0.143 |
stretched | +0.140 |
bears | +0.133 |
scar | +0.128 |
Neg logit contributions | |
ork | -0.087 |
oph | -0.085 |
handed | -0.067 |
ally | -0.066 |
way | -0.066 |
Token | . |
Token ID | 13 |
Feature activation | +4.38e-01 |
Pos logit contributions | |
Amen | +0.097 |
fires | +0.071 |
stretched | +0.068 |
bears | +0.067 |
passenger | +0.066 |
Neg logit contributions | |
ork | -0.078 |
oph | -0.072 |
way | -0.067 |
doorstep | -0.060 |
handed | -0.060 |
Token |
|
Token ID | 198 |
Feature activation | +8.44e-01 |
Pos logit contributions | |
ork | +0.017 |
oph | +0.017 |
ally | +0.015 |
handed | +0.015 |
doorstep | +0.015 |
Neg logit contributions | |
Amen | -0.010 |
fires | -0.006 |
bears | -0.005 |
stretched | -0.005 |
nods | -0.005 |
Token |
|
Token ID | 198 |
Feature activation | +4.30e-01 |
Pos logit contributions | |
oph | +0.031 |
ork | +0.028 |
ige | +0.026 |
ally | +0.026 |
handed | +0.026 |
Neg logit contributions | |
Amen | -0.022 |
stretched | -0.014 |
fires | -0.013 |
sled | -0.013 |
exc | -0.013 |
Token | The |
Token ID | 464 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
ork | +0.014 |
oph | +0.014 |
ally | +0.012 |
way | +0.012 |
handed | +0.012 |
Neg logit contributions | |
Amen | -0.013 |
fires | -0.009 |
stretched | -0.009 |
bears | -0.008 |
passenger | -0.008 |
Token | day |
Token ID | 1110 |
Feature activation | +2.27e-01 |
Pos logit contributions | |
Amen | +0.105 |
fires | +0.085 |
stretched | +0.085 |
bears | +0.080 |
spoiler | +0.078 |
Neg logit contributions | |
ork | -0.080 |
oph | -0.075 |
way | -0.066 |
ally | -0.062 |
handed | -0.060 |
Token | , |
Token ID | 11 |
Feature activation | +2.40e-01 |
Pos logit contributions | |
ork | +0.009 |
oph | +0.009 |
handed | +0.009 |
keeping | +0.009 |
way | +0.009 |
Neg logit contributions | |
Amen | -0.004 |
stretched | -0.002 |
fires | -0.002 |
smile | -0.002 |
bears | -0.002 |
Token | she |
Token ID | 673 |
Feature activation | -4.40e-02 |
Pos logit contributions | |
oph | +0.005 |
ork | +0.005 |
ally | +0.004 |
way | +0.003 |
Sophie | +0.003 |
Neg logit contributions | |
Amen | -0.010 |
fires | -0.008 |
stretched | -0.008 |
paddle | -0.008 |
passenger | -0.008 |
Token | would |
Token ID | 561 |
Feature activation | -7.11e-01 |
Pos logit contributions | |
Amen | +0.001 |
stretched | +0.001 |
spoiler | +0.001 |
fires | +0.001 |
agreement | +0.001 |
Neg logit contributions | |
ork | -0.001 |
oph | -0.001 |
her | -0.001 |
ally | -0.001 |
ess | -0.001 |
Token | sit |
Token ID | 1650 |
Feature activation | -8.09e-01 |
Pos logit contributions | |
Amen | +0.020 |
stretched | +0.018 |
fires | +0.018 |
spoiler | +0.017 |
bears | +0.017 |
Neg logit contributions | |
ork | -0.017 |
doorstep | -0.017 |
n | -0.015 |
oph | -0.015 |
ess | -0.014 |
Token | patiently |
Token ID | 37220 |
Feature activation | -4.19e+00 |
Pos logit contributions | |
Amen | +0.026 |
stretched | +0.022 |
spoiler | +0.020 |
gestures | +0.020 |
paddle | +0.020 |
Neg logit contributions | |
ork | -0.021 |
oph | -0.019 |
ally | -0.017 |
her | -0.016 |
handed | -0.016 |
Token | and |
Token ID | 290 |
Feature activation | -8.07e-01 |
Pos logit contributions | |
Amen | +0.146 |
stretched | +0.109 |
fires | +0.109 |
spoiler | +0.107 |
bears | +0.106 |
Neg logit contributions | |
ork | -0.105 |
way | -0.091 |
oph | -0.091 |
her | -0.085 |
doorstep | -0.082 |
Token | wait |
Token ID | 4043 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
Amen | +0.020 |
stretched | +0.016 |
fires | +0.015 |
bears | +0.014 |
spoiler | +0.013 |
Neg logit contributions | |
ork | -0.027 |
oph | -0.026 |
doorstep | -0.024 |
way | -0.023 |
handed | -0.023 |
Token | for |
Token ID | 329 |
Feature activation | +7.68e-01 |
Pos logit contributions | |
ork | +0.003 |
oph | +0.003 |
way | +0.003 |
her | +0.002 |
ally | +0.002 |
Neg logit contributions | |
Amen | -0.005 |
fires | -0.004 |
bears | -0.004 |
stretched | -0.004 |
spoiler | -0.004 |
Token | her |
Token ID | 607 |
Feature activation | +7.19e-01 |
Pos logit contributions | |
ork | +0.028 |
oph | +0.028 |
way | +0.025 |
ally | +0.024 |
handed | +0.024 |
Neg logit contributions | |
Amen | -0.020 |
fires | -0.014 |
stretched | -0.013 |
bears | -0.013 |
scar | -0.012 |
Token | mom |
Token ID | 1995 |
Feature activation | -6.24e-01 |
Pos logit contributions | |
ork | +0.021 |
oph | +0.018 |
doorstep | +0.018 |
way | +0.017 |
handed | +0.016 |
Neg logit contributions | |
Amen | -0.023 |
stretched | -0.018 |
fires | -0.017 |
spoiler | -0.016 |
paddle | -0.015 |
Token | mom |
Token ID | 1995 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
ork | +0.033 |
oph | +0.033 |
way | +0.029 |
ally | +0.028 |
handed | +0.028 |
Neg logit contributions | |
Amen | -0.028 |
fires | -0.020 |
stretched | -0.020 |
bears | -0.018 |
passenger | -0.017 |
Token | said |
Token ID | 531 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
ork | +0.005 |
oph | +0.005 |
way | +0.004 |
handed | +0.004 |
ally | +0.004 |
Neg logit contributions | |
Amen | -0.005 |
fires | -0.003 |
stretched | -0.003 |
bears | -0.003 |
scar | -0.003 |
Token | in |
Token ID | 287 |
Feature activation | -2.03e+00 |
Pos logit contributions | |
oph | +0.052 |
ork | +0.052 |
handed | +0.047 |
way | +0.046 |
ally | +0.046 |
Neg logit contributions | |
Amen | -0.029 |
fires | -0.019 |
stretched | -0.018 |
bears | -0.017 |
smile | -0.017 |
Token | a |
Token ID | 257 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
Amen | +0.058 |
fires | +0.042 |
stretched | +0.040 |
paddle | +0.039 |
bears | +0.039 |
Neg logit contributions | |
ork | -0.068 |
oph | -0.066 |
ally | -0.057 |
handed | -0.057 |
way | -0.057 |
Token | much |
Token ID | 881 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
Amen | +0.043 |
fires | +0.033 |
bears | +0.031 |
stretched | +0.030 |
paddle | +0.029 |
Neg logit contributions | |
ork | -0.049 |
oph | -0.045 |
way | -0.040 |
handed | -0.039 |
ally | -0.039 |
Token | gent |
Token ID | 25049 |
Feature activation | -4.18e+00 |
Pos logit contributions | |
Amen | +0.052 |
spoiler | +0.036 |
fires | +0.036 |
passenger | +0.036 |
bears | +0.036 |
Neg logit contributions | |
ork | -0.055 |
oph | -0.051 |
way | -0.051 |
handed | -0.045 |
ally | -0.044 |
Token | ler |
Token ID | 1754 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
Amen | +0.115 |
fires | +0.084 |
stretched | +0.081 |
bears | +0.076 |
scar | +0.074 |
Neg logit contributions | |
ork | -0.144 |
oph | -0.138 |
way | -0.127 |
ally | -0.122 |
handed | -0.121 |
Token | voice |
Token ID | 3809 |
Feature activation | -2.20e+00 |
Pos logit contributions | |
Amen | +0.032 |
fires | +0.024 |
stretched | +0.023 |
bears | +0.021 |
scar | +0.021 |
Neg logit contributions | |
ork | -0.034 |
oph | -0.032 |
way | -0.029 |
ally | -0.028 |
handed | -0.028 |
Token | , |
Token ID | 11 |
Feature activation | +1.00e-01 |
Pos logit contributions | |
Amen | +0.057 |
fires | +0.041 |
stretched | +0.040 |
bears | +0.037 |
smile | +0.035 |
Neg logit contributions | |
ork | -0.078 |
oph | -0.078 |
handed | -0.068 |
ally | -0.068 |
way | -0.067 |
Token | " |
Token ID | 366 |
Feature activation | -3.35e-01 |
Pos logit contributions | |
ork | +0.003 |
oph | +0.003 |
way | +0.003 |
ally | +0.003 |
handed | +0.003 |
Neg logit contributions | |
Amen | -0.003 |
fires | -0.002 |
stretched | -0.002 |
bears | -0.002 |
passenger | -0.002 |
Token | It |
Token ID | 1026 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
Amen | +0.010 |
stretched | +0.007 |
fires | +0.007 |
Does | +0.007 |
passenger | +0.006 |
Neg logit contributions | |
ork | -0.011 |
oph | -0.011 |
doorstep | -0.009 |
handed | -0.009 |
way | -0.009 |
Token | He |
Token ID | 679 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
Amen | +0.020 |
fires | +0.014 |
stretched | +0.014 |
scar | +0.013 |
bears | +0.013 |
Neg logit contributions | |
ork | -0.030 |
oph | -0.029 |
way | -0.027 |
handed | -0.026 |
ally | -0.026 |
Token | loved |
Token ID | 6151 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
Amen | +0.036 |
stretched | +0.029 |
fires | +0.028 |
paddle | +0.026 |
scar | +0.026 |
Neg logit contributions | |
ork | -0.028 |
oph | -0.027 |
way | -0.023 |
ally | -0.022 |
handed | -0.022 |
Token | playing |
Token ID | 2712 |
Feature activation | -9.80e-01 |
Pos logit contributions | |
Amen | +0.042 |
stretched | +0.033 |
spoiler | +0.031 |
passenger | +0.031 |
fires | +0.031 |
Neg logit contributions | |
ork | -0.023 |
oph | -0.021 |
keeping | -0.019 |
way | -0.019 |
handed | -0.018 |
Token | make |
Token ID | 787 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
Amen | +0.034 |
stretched | +0.026 |
fires | +0.024 |
whine | +0.023 |
passenger | +0.023 |
Neg logit contributions | |
ork | -0.027 |
oph | -0.025 |
handed | -0.022 |
way | -0.022 |
ally | -0.021 |
Token | - |
Token ID | 12 |
Feature activation | +8.13e-01 |
Pos logit contributions | |
Amen | +0.033 |
fires | +0.025 |
stretched | +0.023 |
bears | +0.023 |
scar | +0.021 |
Neg logit contributions | |
ork | -0.041 |
oph | -0.040 |
way | -0.035 |
ally | -0.035 |
handed | -0.034 |
Token | bel |
Token ID | 6667 |
Feature activation | -4.17e+00 |
Pos logit contributions | |
ork | +0.029 |
oph | +0.028 |
handed | +0.026 |
way | +0.025 |
ally | +0.025 |
Neg logit contributions | |
Amen | -0.022 |
stretched | -0.015 |
fires | -0.015 |
bears | -0.014 |
paddle | -0.013 |
Token | ieve |
Token ID | 12311 |
Feature activation | -6.01e-01 |
Pos logit contributions | |
Amen | +0.101 |
stretched | +0.068 |
fires | +0.067 |
paddle | +0.061 |
bears | +0.061 |
Neg logit contributions | |
ork | -0.155 |
oph | -0.149 |
handed | -0.137 |
way | -0.136 |
ally | -0.132 |
Token | with |
Token ID | 351 |
Feature activation | +4.37e-01 |
Pos logit contributions | |
Amen | +0.021 |
stretched | +0.015 |
fires | +0.014 |
paddle | +0.014 |
whine | +0.014 |
Neg logit contributions | |
ork | -0.018 |
oph | -0.016 |
way | -0.015 |
handed | -0.014 |
keeping | -0.014 |
Token | his |
Token ID | 465 |
Feature activation | +4.69e-01 |
Pos logit contributions | |
ork | +0.016 |
oph | +0.016 |
handed | +0.014 |
way | +0.014 |
ally | +0.014 |
Neg logit contributions | |
Amen | -0.011 |
stretched | -0.007 |
fires | -0.006 |
passenger | -0.006 |
paddle | -0.006 |
Token | friends |
Token ID | 2460 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
ork | +0.014 |
oph | +0.013 |
handed | +0.012 |
way | +0.012 |
doorstep | +0.012 |
Neg logit contributions | |
Amen | -0.015 |
stretched | -0.011 |
fires | -0.011 |
Does | -0.010 |
paddle | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | -2.80e-01 |
Pos logit contributions | |
Amen | +0.058 |
stretched | +0.042 |
fires | +0.041 |
scar | +0.041 |
Does | +0.041 |
Neg logit contributions | |
ork | -0.033 |
way | -0.027 |
oph | -0.027 |
handed | -0.026 |
her | -0.025 |
Token | but |
Token ID | 475 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
ork | +0.024 |
oph | +0.024 |
way | +0.021 |
ally | +0.021 |
handed | +0.021 |
Neg logit contributions | |
Amen | -0.020 |
fires | -0.014 |
stretched | -0.014 |
bears | -0.013 |
passenger | -0.012 |
Token | it |
Token ID | 340 |
Feature activation | +1.74e+00 |
Pos logit contributions | |
Amen | +0.004 |
fires | +0.003 |
stretched | +0.003 |
bears | +0.003 |
hope | +0.002 |
Neg logit contributions | |
ork | -0.007 |
oph | -0.007 |
handed | -0.006 |
ally | -0.006 |
way | -0.006 |
Token | stayed |
Token ID | 9658 |
Feature activation | +3.44e-01 |
Pos logit contributions | |
ork | +0.053 |
oph | +0.052 |
handed | +0.044 |
ally | +0.044 |
way | +0.044 |
Neg logit contributions | |
Amen | -0.054 |
fires | -0.041 |
stretched | -0.040 |
bears | -0.039 |
hope | -0.038 |
Token | in |
Token ID | 287 |
Feature activation | -5.58e-01 |
Pos logit contributions | |
ork | +0.010 |
oph | +0.009 |
way | +0.009 |
ally | +0.008 |
handed | +0.008 |
Neg logit contributions | |
Amen | -0.011 |
stretched | -0.008 |
bears | -0.008 |
fires | -0.008 |
whine | -0.008 |
Token | their |
Token ID | 511 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
Amen | +0.015 |
fires | +0.011 |
stretched | +0.011 |
bears | +0.010 |
scar | +0.009 |
Neg logit contributions | |
ork | -0.019 |
oph | -0.019 |
way | -0.017 |
handed | -0.016 |
ally | -0.016 |
Token | imag |
Token ID | 3590 |
Feature activation | -4.16e+00 |
Pos logit contributions | |
ork | +0.004 |
oph | +0.004 |
way | +0.004 |
handed | +0.004 |
ally | +0.003 |
Neg logit contributions | |
Amen | -0.005 |
fires | -0.004 |
stretched | -0.004 |
bears | -0.004 |
paddle | -0.003 |
Token | inations |
Token ID | 7352 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
Amen | +0.130 |
fires | +0.098 |
stretched | +0.095 |
bears | +0.092 |
passenger | +0.087 |
Neg logit contributions | |
ork | -0.128 |
oph | -0.124 |
way | -0.109 |
ally | -0.107 |
handed | -0.106 |
Token | for |
Token ID | 329 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
Amen | +0.030 |
fires | +0.022 |
stretched | +0.021 |
bears | +0.020 |
smile | +0.020 |
Neg logit contributions | |
ork | -0.043 |
oph | -0.043 |
ally | -0.038 |
handed | -0.037 |
way | -0.037 |
Token | many |
Token ID | 867 |
Feature activation | +7.23e-01 |
Pos logit contributions | |
oph | +0.067 |
ork | +0.067 |
ally | +0.059 |
way | +0.058 |
handed | +0.058 |
Neg logit contributions | |
Amen | -0.043 |
fires | -0.031 |
bears | -0.028 |
stretched | -0.027 |
hope | -0.027 |
Token | years |
Token ID | 812 |
Feature activation | -8.87e-02 |
Pos logit contributions | |
ork | +0.019 |
oph | +0.017 |
way | +0.016 |
handed | +0.015 |
ally | +0.015 |
Neg logit contributions | |
Amen | -0.026 |
fires | -0.019 |
stretched | -0.019 |
paddle | -0.019 |
spoiler | -0.019 |
Token | to |
Token ID | 284 |
Feature activation | +2.41e-01 |
Pos logit contributions | |
Amen | +0.002 |
fires | +0.002 |
stretched | +0.002 |
bears | +0.001 |
smile | +0.001 |
Neg logit contributions | |
oph | -0.003 |
ork | -0.003 |
handed | -0.003 |
ally | -0.003 |
liv | -0.003 |
Token | tired |
Token ID | 10032 |
Feature activation | +5.47e-01 |
Pos logit contributions | |
ork | +0.010 |
oph | +0.010 |
way | +0.009 |
handed | +0.009 |
ally | +0.009 |
Neg logit contributions | |
Amen | -0.009 |
stretched | -0.007 |
fires | -0.007 |
sled | -0.007 |
passenger | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
ork | +0.018 |
oph | +0.018 |
way | +0.016 |
ally | +0.016 |
handed | +0.016 |
Neg logit contributions | |
Amen | -0.015 |
fires | -0.011 |
stretched | -0.011 |
bears | -0.010 |
passenger | -0.010 |
Token | He |
Token ID | 679 |
Feature activation | -7.59e-01 |
Pos logit contributions | |
ork | +0.006 |
oph | +0.006 |
way | +0.005 |
ally | +0.005 |
handed | +0.005 |
Neg logit contributions | |
Amen | -0.004 |
fires | -0.003 |
stretched | -0.003 |
bears | -0.003 |
passenger | -0.002 |
Token | was |
Token ID | 373 |
Feature activation | -3.60e-03 |
Pos logit contributions | |
Amen | +0.024 |
stretched | +0.019 |
fires | +0.018 |
passenger | +0.017 |
spoiler | +0.017 |
Neg logit contributions | |
ork | -0.022 |
oph | -0.021 |
way | -0.018 |
handed | -0.018 |
doorstep | -0.017 |
Token | looking |
Token ID | 2045 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
Amen | +0.000 |
fires | +0.000 |
stretched | +0.000 |
bears | +0.000 |
paddle | +0.000 |
Neg logit contributions | |
ork | -0.000 |
oph | -0.000 |
way | -0.000 |
handed | -0.000 |
ally | -0.000 |
Token | for |
Token ID | 329 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
Amen | +0.037 |
stretched | +0.028 |
spoiler | +0.027 |
passenger | +0.027 |
paddle | +0.026 |
Neg logit contributions | |
ork | -0.024 |
oph | -0.023 |
way | -0.020 |
handed | -0.019 |
ally | -0.019 |
Token | something |
Token ID | 1223 |
Feature activation | +2.84e-01 |
Pos logit contributions | |
ork | +0.064 |
oph | +0.064 |
way | +0.056 |
ally | +0.055 |
handed | +0.052 |
Neg logit contributions | |
Amen | -0.051 |
fires | -0.043 |
bears | -0.040 |
hope | -0.039 |
stretched | -0.037 |
Token | in |
Token ID | 287 |
Feature activation | -8.75e-02 |
Pos logit contributions | |
oph | +0.010 |
ork | +0.009 |
ally | +0.008 |
handed | +0.008 |
keeping | +0.008 |
Neg logit contributions | |
Amen | -0.007 |
fires | -0.006 |
stretched | -0.006 |
hope | -0.006 |
bears | -0.006 |
Token | the |
Token ID | 262 |
Feature activation | -7.45e-02 |
Pos logit contributions | |
Amen | +0.002 |
stretched | +0.002 |
fires | +0.002 |
bears | +0.002 |
passenger | +0.001 |
Neg logit contributions | |
ork | -0.003 |
oph | -0.003 |
handed | -0.003 |
way | -0.003 |
ally | -0.003 |
Token | sand |
Token ID | 6450 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
Amen | +0.003 |
fires | +0.002 |
stretched | +0.002 |
bears | +0.002 |
passenger | +0.002 |
Neg logit contributions | |
ork | -0.002 |
oph | -0.002 |
way | -0.002 |
ally | -0.002 |
handed | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | -2.77e-02 |
Pos logit contributions | |
ork | +0.044 |
oph | +0.043 |
way | +0.038 |
ally | +0.037 |
handed | +0.037 |
Neg logit contributions | |
Amen | -0.036 |
fires | -0.026 |
stretched | -0.025 |
bears | -0.023 |
passenger | -0.022 |
Token | better |
Token ID | 1365 |
Feature activation | +8.29e-01 |
Pos logit contributions | |
oph | +0.018 |
ork | +0.018 |
ally | +0.016 |
way | +0.015 |
handed | +0.015 |
Neg logit contributions | |
Amen | -0.019 |
fires | -0.014 |
stretched | -0.014 |
bears | -0.013 |
passenger | -0.013 |
Token | hotel |
Token ID | 7541 |
Feature activation | +4.82e-01 |
Pos logit contributions | |
ork | +0.020 |
oph | +0.019 |
way | +0.016 |
handed | +0.016 |
ally | +0.016 |
Neg logit contributions | |
Amen | -0.031 |
fires | -0.025 |
stretched | -0.025 |
bears | -0.023 |
passenger | -0.023 |
Token | tomorrow |
Token ID | 9439 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
ork | +0.016 |
oph | +0.016 |
way | +0.014 |
ally | +0.014 |
handed | +0.014 |
Neg logit contributions | |
Amen | -0.013 |
fires | -0.010 |
stretched | -0.009 |
bears | -0.009 |
passenger | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | -6.43e-02 |
Pos logit contributions | |
oph | +0.005 |
ork | +0.005 |
ally | +0.005 |
handed | +0.004 |
way | +0.004 |
Neg logit contributions | |
Amen | -0.003 |
fires | -0.002 |
sometimes | -0.002 |
hope | -0.002 |
bears | -0.002 |
Token | They |
Token ID | 1119 |
Feature activation | -6.86e-01 |
Pos logit contributions | |
Amen | +0.001 |
fires | +0.001 |
stretched | +0.001 |
hope | +0.001 |
whine | +0.001 |
Neg logit contributions | |
ork | -0.003 |
oph | -0.002 |
ally | -0.002 |
handed | -0.002 |
way | -0.002 |
Token | said |
Token ID | 531 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
Amen | +0.025 |
fires | +0.021 |
stretched | +0.020 |
bears | +0.018 |
spoiler | +0.018 |
Neg logit contributions | |
oph | -0.016 |
ork | -0.016 |
ally | -0.014 |
way | -0.013 |
handed | -0.013 |
Token | they |
Token ID | 484 |
Feature activation | +2.94e-01 |
Pos logit contributions | |
ork | +0.057 |
oph | +0.054 |
way | +0.048 |
ally | +0.046 |
handed | +0.045 |
Neg logit contributions | |
Amen | -0.055 |
stretched | -0.040 |
fires | -0.038 |
passenger | -0.037 |
spoiler | -0.036 |
Token | would |
Token ID | 561 |
Feature activation | -4.94e-01 |
Pos logit contributions | |
ork | +0.009 |
oph | +0.008 |
way | +0.007 |
ally | +0.007 |
ess | +0.007 |
Neg logit contributions | |
Amen | -0.009 |
stretched | -0.007 |
fires | -0.007 |
spoiler | -0.006 |
bears | -0.006 |
Token | try |
Token ID | 1949 |
Feature activation | +6.28e-01 |
Pos logit contributions | |
Amen | +0.015 |
stretched | +0.012 |
fires | +0.012 |
bears | +0.011 |
nods | +0.010 |
Neg logit contributions | |
ork | -0.015 |
oph | -0.013 |
doorstep | -0.012 |
way | -0.012 |
n | -0.012 |
Token | to |
Token ID | 284 |
Feature activation | -8.02e-01 |
Pos logit contributions | |
oph | +0.023 |
ork | +0.022 |
ally | +0.020 |
way | +0.020 |
handed | +0.020 |
Neg logit contributions | |
Amen | -0.015 |
fires | -0.013 |
bears | -0.011 |
sled | -0.011 |
scar | -0.011 |
Token | make |
Token ID | 787 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
Amen | +0.022 |
fires | +0.015 |
stretched | +0.015 |
bears | +0.014 |
scar | +0.013 |
Neg logit contributions | |
ork | -0.028 |
oph | -0.027 |
handed | -0.024 |
way | -0.024 |
ally | -0.024 |
Token | The |
Token ID | 464 |
Feature activation | -1.86e+00 |
Pos logit contributions | |
Amen | +0.017 |
fires | +0.013 |
stretched | +0.013 |
bears | +0.012 |
paddle | +0.012 |
Neg logit contributions | |
ork | -0.015 |
oph | -0.014 |
ally | -0.012 |
handed | -0.012 |
way | -0.012 |
Token | rat |
Token ID | 4227 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
Amen | +0.063 |
stretched | +0.050 |
fires | +0.050 |
paddle | +0.046 |
spoiler | +0.045 |
Neg logit contributions | |
ork | -0.051 |
oph | -0.048 |
handed | -0.041 |
way | -0.041 |
doorstep | -0.039 |
Token | was |
Token ID | 373 |
Feature activation | -6.89e-01 |
Pos logit contributions | |
ork | +0.036 |
oph | +0.035 |
way | +0.031 |
ally | +0.031 |
handed | +0.030 |
Neg logit contributions | |
Amen | -0.029 |
fires | -0.021 |
stretched | -0.020 |
bears | -0.019 |
passenger | -0.018 |
Token | delighted |
Token ID | 20707 |
Feature activation | +3.96e-01 |
Pos logit contributions | |
Amen | +0.018 |
fires | +0.013 |
stretched | +0.012 |
bears | +0.012 |
scar | +0.011 |
Neg logit contributions | |
ork | -0.024 |
oph | -0.024 |
way | -0.021 |
ally | -0.021 |
handed | -0.021 |
Token | and |
Token ID | 290 |
Feature activation | +4.29e-01 |
Pos logit contributions | |
ork | +0.015 |
oph | +0.014 |
handed | +0.013 |
way | +0.013 |
doorstep | +0.012 |
Neg logit contributions | |
Amen | -0.009 |
stretched | -0.006 |
fires | -0.006 |
smile | -0.006 |
bears | -0.006 |
Token | said |
Token ID | 531 |
Feature activation | +1.83e+00 |
Pos logit contributions | |
ork | +0.014 |
oph | +0.014 |
way | +0.012 |
handed | +0.012 |
ally | +0.012 |
Neg logit contributions | |
Amen | -0.012 |
fires | -0.009 |
stretched | -0.009 |
bears | -0.008 |
scar | -0.008 |
Token | " |
Token ID | 366 |
Feature activation | -1.98e-01 |
Pos logit contributions | |
ork | +0.057 |
oph | +0.055 |
way | +0.048 |
ally | +0.047 |
handed | +0.046 |
Neg logit contributions | |
Amen | -0.056 |
fires | -0.043 |
stretched | -0.041 |
bears | -0.039 |
scar | -0.038 |
Token | Yes |
Token ID | 5297 |
Feature activation | -5.22e-01 |
Pos logit contributions | |
Amen | +0.005 |
fires | +0.004 |
stretched | +0.004 |
bears | +0.003 |
paddle | +0.003 |
Neg logit contributions | |
oph | -0.007 |
ork | -0.007 |
ally | -0.006 |
way | -0.006 |
handed | -0.006 |
Token | of |
Token ID | 286 |
Feature activation | -5.42e-01 |
Pos logit contributions | |
Amen | +0.014 |
fires | +0.010 |
stretched | +0.010 |
bears | +0.010 |
smile | +0.009 |
Neg logit contributions | |
ork | -0.018 |
oph | -0.017 |
handed | -0.015 |
way | -0.015 |
ally | -0.015 |
Token | course |
Token ID | 1781 |
Feature activation | -9.32e-03 |
Pos logit contributions | |
Amen | +0.013 |
fires | +0.009 |
bears | +0.008 |
stretched | +0.008 |
hope | +0.007 |
Neg logit contributions | |
ork | -0.021 |
oph | -0.021 |
way | -0.018 |
ally | -0.018 |
handed | -0.018 |
Token | !" |
Token ID | 2474 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
Amen | +0.000 |
fires | +0.000 |
stretched | +0.000 |
bears | +0.000 |
passenger | +0.000 |
Neg logit contributions | |
ork | -0.000 |
oph | -0.000 |
way | -0.000 |
ally | -0.000 |
handed | -0.000 |
Token | He |
Token ID | 679 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
Amen | +0.005 |
fires | +0.003 |
stretched | +0.003 |
scar | +0.003 |
bears | +0.003 |
Neg logit contributions | |
ork | -0.007 |
oph | -0.007 |
way | -0.007 |
ally | -0.006 |
handed | -0.006 |
Token | realised |
Token ID | 19169 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
Amen | +0.035 |
fires | +0.027 |
stretched | +0.025 |
bears | +0.024 |
whine | +0.023 |
Neg logit contributions | |
oph | -0.030 |
ork | -0.030 |
way | -0.026 |
ally | -0.026 |
handed | -0.024 |
Token | that |
Token ID | 326 |
Feature activation | -9.10e-01 |
Pos logit contributions | |
Amen | +0.008 |
stretched | +0.006 |
fires | +0.006 |
bears | +0.005 |
passenger | +0.005 |
Neg logit contributions | |
ork | -0.007 |
oph | -0.007 |
way | -0.006 |
handed | -0.006 |
ally | -0.006 |
Token | it |
Token ID | 340 |
Feature activation | +1.73e+00 |
Pos logit contributions | |
Amen | +0.024 |
fires | +0.017 |
stretched | +0.016 |
bears | +0.015 |
passenger | +0.014 |
Neg logit contributions | |
ork | -0.032 |
oph | -0.032 |
way | -0.028 |
ally | -0.028 |
handed | -0.028 |
Token | was |
Token ID | 373 |
Feature activation | +2.63e-02 |
Pos logit contributions | |
ork | +0.050 |
oph | +0.049 |
way | +0.041 |
ally | +0.041 |
handed | +0.041 |
Neg logit contributions | |
Amen | -0.057 |
fires | -0.044 |
stretched | -0.043 |
bears | -0.041 |
smile | -0.039 |
Token | all |
Token ID | 477 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
ork | +0.001 |
oph | +0.001 |
way | +0.001 |
ally | +0.001 |
handed | +0.001 |
Neg logit contributions | |
Amen | -0.001 |
fires | -0.001 |
stretched | -0.001 |
bears | -0.001 |
paddle | -0.001 |
Token | up |
Token ID | 510 |
Feature activation | +2.40e+00 |
Pos logit contributions | |
ork | +0.057 |
oph | +0.056 |
ally | +0.048 |
way | +0.048 |
handed | +0.047 |
Neg logit contributions | |
Amen | -0.055 |
fires | -0.042 |
stretched | -0.040 |
bears | -0.038 |
smile | -0.036 |
Token | to |
Token ID | 284 |
Feature activation | -2.07e-01 |
Pos logit contributions | |
ork | +0.073 |
oph | +0.071 |
way | +0.063 |
handed | +0.062 |
ally | +0.061 |
Neg logit contributions | |
Amen | -0.076 |
fires | -0.054 |
stretched | -0.053 |
bears | -0.051 |
passenger | -0.049 |
Token | him |
Token ID | 683 |
Feature activation | +3.99e-02 |
Pos logit contributions | |
Amen | +0.005 |
fires | +0.003 |
stretched | +0.003 |
hope | +0.003 |
smile | +0.003 |
Neg logit contributions | |
ork | -0.008 |
oph | -0.008 |
way | -0.007 |
ally | -0.007 |
anger | -0.007 |
Token | and |
Token ID | 290 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
ork | +0.001 |
oph | +0.001 |
way | +0.001 |
handed | +0.001 |
ally | +0.001 |
Neg logit contributions | |
Amen | -0.001 |
fires | -0.001 |
stretched | -0.001 |
bears | -0.001 |
passenger | -0.001 |
Token | that |
Token ID | 326 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
Amen | +0.004 |
stretched | +0.003 |
fires | +0.003 |
bears | +0.002 |
passenger | +0.002 |
Neg logit contributions | |
ork | -0.004 |
oph | -0.004 |
way | -0.004 |
handed | -0.004 |
ally | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | -2.29e-01 |
Pos logit contributions | |
ork | +0.013 |
oph | +0.013 |
way | +0.011 |
ally | +0.011 |
handed | +0.011 |
Neg logit contributions | |
Amen | -0.009 |
fires | -0.006 |
stretched | -0.006 |
bears | -0.006 |
scar | -0.005 |
Token | bottle |
Token ID | 9294 |
Feature activation | -2.24e-01 |
Pos logit contributions | |
Amen | +0.006 |
fires | +0.005 |
bears | +0.005 |
smile | +0.005 |
stretched | +0.005 |
Neg logit contributions | |
oph | -0.007 |
ork | -0.007 |
ally | -0.006 |
handed | -0.006 |
way | -0.006 |
Token | of |
Token ID | 286 |
Feature activation | -8.47e-01 |
Pos logit contributions | |
Amen | +0.005 |
stretched | +0.004 |
fires | +0.004 |
smile | +0.003 |
bears | +0.003 |
Neg logit contributions | |
oph | -0.008 |
ork | -0.008 |
handed | -0.007 |
ally | -0.007 |
way | -0.007 |
Token | ink |
Token ID | 16882 |
Feature activation | -5.79e-01 |
Pos logit contributions | |
Amen | +0.030 |
fires | +0.024 |
stretched | +0.023 |
bears | +0.023 |
scar | +0.022 |
Neg logit contributions | |
ork | -0.022 |
oph | -0.021 |
way | -0.018 |
handed | -0.018 |
ally | -0.018 |
Token | , |
Token ID | 11 |
Feature activation | +3.58e-01 |
Pos logit contributions | |
Amen | +0.011 |
stretched | +0.009 |
fires | +0.009 |
bears | +0.008 |
smile | +0.008 |
Neg logit contributions | |
oph | -0.022 |
ork | -0.020 |
ally | -0.019 |
handed | -0.019 |
way | -0.018 |
Token | spilling |
Token ID | 45085 |
Feature activation | +2.21e+00 |
Pos logit contributions | |
ork | +0.012 |
oph | +0.011 |
way | +0.010 |
ally | +0.010 |
handed | +0.010 |
Neg logit contributions | |
Amen | -0.011 |
fires | -0.008 |
stretched | -0.007 |
bears | -0.007 |
passenger | -0.007 |
Token | it |
Token ID | 340 |
Feature activation | +7.36e-01 |
Pos logit contributions | |
oph | +0.076 |
ork | +0.074 |
handed | +0.067 |
ally | +0.066 |
way | +0.064 |
Neg logit contributions | |
Amen | -0.055 |
fires | -0.048 |
stretched | -0.044 |
bears | -0.042 |
hope | -0.040 |
Token | all |
Token ID | 477 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
oph | +0.028 |
ork | +0.026 |
ally | +0.024 |
handed | +0.023 |
orman | +0.022 |
Neg logit contributions | |
Amen | -0.015 |
fires | -0.012 |
stretched | -0.012 |
sometimes | -0.011 |
smile | -0.011 |
Token | over |
Token ID | 625 |
Feature activation | +9.87e-01 |
Pos logit contributions | |
oph | +0.043 |
ork | +0.043 |
lor | +0.037 |
doorstep | +0.037 |
handed | +0.036 |
Neg logit contributions | |
Amen | -0.025 |
fires | -0.021 |
stretched | -0.020 |
sometimes | -0.019 |
smile | -0.019 |
Token | their |
Token ID | 511 |
Feature activation | +8.62e-01 |
Pos logit contributions | |
oph | +0.037 |
ork | +0.037 |
ally | +0.032 |
handed | +0.032 |
way | +0.032 |
Neg logit contributions | |
Amen | -0.022 |
fires | -0.017 |
stretched | -0.016 |
bears | -0.015 |
hope | -0.014 |
Token | drawings |
Token ID | 23388 |
Feature activation | -1.83e+00 |
Pos logit contributions | |
oph | +0.031 |
ork | +0.029 |
liv | +0.027 |
handed | +0.027 |
lor | +0.027 |
Neg logit contributions | |
Amen | -0.017 |
smile | -0.015 |
fires | -0.015 |
sister | -0.015 |
scar | -0.015 |
Token | help |
Token ID | 1037 |
Feature activation | -4.09e-01 |
Pos logit contributions | |
ork | +0.014 |
oph | +0.014 |
way | +0.012 |
ally | +0.012 |
handed | +0.012 |
Neg logit contributions | |
Amen | -0.010 |
fires | -0.007 |
stretched | -0.007 |
bears | -0.006 |
paddle | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | -9.95e-02 |
Pos logit contributions | |
Amen | +0.011 |
fires | +0.009 |
stretched | +0.008 |
bears | +0.008 |
sometimes | +0.008 |
Neg logit contributions | |
ork | -0.014 |
oph | -0.013 |
way | -0.012 |
handed | -0.012 |
ally | -0.011 |
Token | It |
Token ID | 632 |
Feature activation | +3.90e-01 |
Pos logit contributions | |
Amen | +0.003 |
fires | +0.002 |
stretched | +0.002 |
bears | +0.002 |
passenger | +0.002 |
Neg logit contributions | |
ork | -0.003 |
oph | -0.003 |
way | -0.003 |
ally | -0.003 |
handed | -0.003 |
Token | 's |
Token ID | 338 |
Feature activation | +2.79e-01 |
Pos logit contributions | |
ork | +0.011 |
oph | +0.011 |
way | +0.010 |
handed | +0.009 |
ally | +0.009 |
Neg logit contributions | |
Amen | -0.013 |
fires | -0.010 |
stretched | -0.010 |
bears | -0.009 |
scar | -0.008 |
Token | important |
Token ID | 1593 |
Feature activation | +7.04e-01 |
Pos logit contributions | |
ork | +0.009 |
oph | +0.009 |
way | +0.008 |
ally | +0.008 |
handed | +0.008 |
Neg logit contributions | |
Amen | -0.008 |
fires | -0.006 |
stretched | -0.006 |
bears | -0.005 |
passenger | -0.005 |
Token | to |
Token ID | 284 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
ork | +0.020 |
oph | +0.019 |
way | +0.016 |
ally | +0.016 |
handed | +0.016 |
Neg logit contributions | |
Amen | -0.024 |
fires | -0.019 |
stretched | -0.018 |
bears | -0.017 |
passenger | -0.017 |
Token | use |
Token ID | 779 |
Feature activation | -2.81e-01 |
Pos logit contributions | |
ork | +0.005 |
oph | +0.005 |
way | +0.004 |
ally | +0.004 |
handed | +0.004 |
Neg logit contributions | |
Amen | -0.003 |
fires | -0.002 |
stretched | -0.002 |
bears | -0.002 |
smile | -0.002 |
Token | our |
Token ID | 674 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
Amen | +0.008 |
fires | +0.006 |
stretched | +0.006 |
bears | +0.006 |
passenger | +0.005 |
Neg logit contributions | |
ork | -0.009 |
oph | -0.009 |
way | -0.008 |
ally | -0.008 |
handed | -0.007 |
Token | own |
Token ID | 898 |
Feature activation | +3.30e-01 |
Pos logit contributions | |
ork | +0.041 |
oph | +0.037 |
way | +0.034 |
doorstep | +0.032 |
handed | +0.032 |
Neg logit contributions | |
Amen | -0.043 |
stretched | -0.031 |
fires | -0.030 |
bears | -0.027 |
passenger | -0.027 |
Token | strength |
Token ID | 4202 |
Feature activation | -8.37e-01 |
Pos logit contributions | |
ork | +0.011 |
oph | +0.010 |
way | +0.009 |
handed | +0.009 |
ally | +0.009 |
Neg logit contributions | |
Amen | -0.010 |
stretched | -0.007 |
fires | -0.007 |
bears | -0.006 |
passenger | -0.006 |
Token | and |
Token ID | 290 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
Amen | +0.025 |
fires | +0.018 |
stretched | +0.018 |
bears | +0.017 |
passenger | +0.016 |
Neg logit contributions | |
ork | -0.027 |
oph | -0.026 |
way | -0.023 |
handed | -0.022 |
ally | -0.022 |
Token | on |
Token ID | 319 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
Amen | +0.040 |
fires | +0.029 |
stretched | +0.029 |
bears | +0.026 |
passenger | +0.026 |
Neg logit contributions | |
ork | -0.045 |
oph | -0.043 |
way | -0.038 |
handed | -0.038 |
ally | -0.037 |
Token | her |
Token ID | 607 |
Feature activation | -2.16e-01 |
Pos logit contributions | |
Amen | +0.003 |
fires | +0.002 |
bears | +0.002 |
stretched | +0.002 |
sometimes | +0.002 |
Neg logit contributions | |
oph | -0.006 |
ork | -0.005 |
way | -0.005 |
ally | -0.005 |
handed | -0.005 |
Token | knee |
Token ID | 10329 |
Feature activation | -6.01e-01 |
Pos logit contributions | |
Amen | +0.006 |
fires | +0.004 |
stretched | +0.004 |
bears | +0.004 |
smile | +0.004 |
Neg logit contributions | |
ork | -0.007 |
oph | -0.007 |
way | -0.006 |
ally | -0.006 |
handed | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | -1.58e-02 |
Pos logit contributions | |
Amen | +0.015 |
fires | +0.011 |
stretched | +0.010 |
bears | +0.010 |
smile | +0.009 |
Neg logit contributions | |
oph | -0.021 |
ork | -0.021 |
ally | -0.019 |
handed | -0.018 |
way | -0.018 |
Token | Her |
Token ID | 2332 |
Feature activation | +6.70e-01 |
Pos logit contributions | |
Amen | +0.000 |
Does | +0.000 |
Sometimes | +0.000 |
nod | +0.000 |
smile | +0.000 |
Neg logit contributions | |
oph | -0.001 |
ork | -0.001 |
keeping | -0.001 |
handed | -0.001 |
ilt | -0.001 |
Token | mom |
Token ID | 1995 |
Feature activation | -3.00e-01 |
Pos logit contributions | |
ork | +0.021 |
oph | +0.021 |
ally | +0.018 |
way | +0.018 |
handed | +0.018 |
Neg logit contributions | |
Amen | -0.020 |
fires | -0.015 |
stretched | -0.015 |
bears | -0.013 |
passenger | -0.013 |
Token | took |
Token ID | 1718 |
Feature activation | -6.67e-01 |
Pos logit contributions | |
Amen | +0.010 |
fires | +0.007 |
stretched | +0.007 |
paddle | +0.007 |
spoiler | +0.006 |
Neg logit contributions | |
oph | -0.009 |
ork | -0.009 |
ally | -0.008 |
way | -0.008 |
handed | -0.007 |
Token | out |
Token ID | 503 |
Feature activation | -2.13e+00 |
Pos logit contributions | |
Amen | +0.012 |
fires | +0.009 |
hope | +0.008 |
bears | +0.008 |
scar | +0.007 |
Neg logit contributions | |
ork | -0.029 |
oph | -0.028 |
way | -0.027 |
ally | -0.025 |
doorstep | -0.025 |
Token | a |
Token ID | 257 |
Feature activation | -3.28e-03 |
Pos logit contributions | |
Amen | +0.068 |
stretched | +0.047 |
fires | +0.046 |
spoiler | +0.044 |
paddle | +0.044 |
Neg logit contributions | |
ork | -0.067 |
oph | -0.064 |
ally | -0.055 |
way | -0.055 |
handed | -0.054 |
Token | bottle |
Token ID | 9294 |
Feature activation | -5.52e-01 |
Pos logit contributions | |
Amen | +0.000 |
fires | +0.000 |
stretched | +0.000 |
bears | +0.000 |
passenger | +0.000 |
Neg logit contributions | |
ork | -0.000 |
oph | -0.000 |
way | -0.000 |
ally | -0.000 |
handed | -0.000 |
Token | of |
Token ID | 286 |
Feature activation | -4.19e-01 |
Pos logit contributions | |
Amen | +0.014 |
fires | +0.010 |
stretched | +0.010 |
bears | +0.009 |
smile | +0.009 |
Neg logit contributions | |
ork | -0.020 |
oph | -0.019 |
handed | -0.017 |
way | -0.017 |
ally | -0.017 |
Token | . |
Token ID | 13 |
Feature activation | -4.46e-01 |
Pos logit contributions | |
ork | +0.009 |
oph | +0.009 |
way | +0.008 |
handed | +0.008 |
ally | +0.008 |
Neg logit contributions | |
Amen | -0.009 |
stretched | -0.006 |
fires | -0.006 |
passenger | -0.006 |
whine | -0.005 |
Token | One |
Token ID | 1881 |
Feature activation | -8.05e-01 |
Pos logit contributions | |
Amen | +0.011 |
fires | +0.008 |
stretched | +0.008 |
bears | +0.007 |
scar | +0.007 |
Neg logit contributions | |
ork | -0.016 |
oph | -0.016 |
way | -0.014 |
ally | -0.014 |
handed | -0.014 |
Token | day |
Token ID | 1110 |
Feature activation | -4.25e-02 |
Pos logit contributions | |
Amen | +0.027 |
fires | +0.021 |
stretched | +0.021 |
bears | +0.020 |
passenger | +0.019 |
Neg logit contributions | |
ork | -0.023 |
oph | -0.022 |
way | -0.019 |
ally | -0.019 |
handed | -0.018 |
Token | M |
Token ID | 337 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
Amen | +0.001 |
fires | +0.001 |
stretched | +0.001 |
bears | +0.001 |
smile | +0.001 |
Neg logit contributions | |
ork | -0.002 |
oph | -0.002 |
handed | -0.001 |
way | -0.001 |
ally | -0.001 |
Token | imi |
Token ID | 25236 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
ork | +0.025 |
oph | +0.022 |
handed | +0.021 |
way | +0.021 |
keeping | +0.020 |
Neg logit contributions | |
Amen | -0.038 |
bears | -0.029 |
fires | -0.029 |
stretched | -0.029 |
sister | -0.028 |
Token | decided |
Token ID | 3066 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
ork | +0.046 |
oph | +0.045 |
handed | +0.040 |
way | +0.040 |
ally | +0.039 |
Neg logit contributions | |
Amen | -0.032 |
fires | -0.023 |
bears | -0.022 |
stretched | -0.022 |
hope | -0.021 |
Token | to |
Token ID | 284 |
Feature activation | +2.92e-01 |
Pos logit contributions | |
oph | +0.046 |
ork | +0.046 |
handed | +0.040 |
ally | +0.040 |
way | +0.038 |
Neg logit contributions | |
Amen | -0.038 |
fires | -0.028 |
stretched | -0.027 |
yes | -0.027 |
sometimes | -0.027 |
Token | take |
Token ID | 1011 |
Feature activation | -1.88e-02 |
Pos logit contributions | |
ork | +0.011 |
oph | +0.011 |
way | +0.010 |
ally | +0.010 |
handed | +0.010 |
Neg logit contributions | |
Amen | -0.007 |
fires | -0.004 |
stretched | -0.004 |
bears | -0.004 |
passenger | -0.004 |
Token | a |
Token ID | 257 |
Feature activation | +6.60e-02 |
Pos logit contributions | |
Amen | +0.000 |
fires | +0.000 |
bears | +0.000 |
scar | +0.000 |
hope | +0.000 |
Neg logit contributions | |
oph | -0.001 |
ork | -0.001 |
way | -0.001 |
ally | -0.001 |
handed | -0.001 |
Token | walk |
Token ID | 2513 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
ork | +0.002 |
oph | +0.002 |
way | +0.002 |
ally | +0.002 |
handed | +0.002 |
Neg logit contributions | |
Amen | -0.002 |
fires | -0.001 |
stretched | -0.001 |
bears | -0.001 |
passenger | -0.001 |
Token | in |
Token ID | 287 |
Feature activation | -4.61e-01 |
Pos logit contributions | |
Amen | +0.048 |
stretched | +0.035 |
fires | +0.035 |
spoiler | +0.034 |
bears | +0.034 |
Neg logit contributions | |
ork | -0.037 |
oph | -0.034 |
way | -0.032 |
handed | -0.030 |
ally | -0.030 |
Token | and |
Token ID | 290 |
Feature activation | -6.15e-01 |
Pos logit contributions | |
Amen | +0.025 |
fires | +0.017 |
stretched | +0.017 |
bears | +0.016 |
smile | +0.016 |
Neg logit contributions | |
ork | -0.036 |
oph | -0.034 |
way | -0.031 |
handed | -0.031 |
ally | -0.030 |
Token | said |
Token ID | 531 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
Amen | +0.018 |
fires | +0.013 |
bears | +0.013 |
stretched | +0.013 |
scar | +0.012 |
Neg logit contributions | |
ork | -0.020 |
oph | -0.019 |
way | -0.017 |
handed | -0.017 |
ally | -0.016 |
Token | she |
Token ID | 673 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
ork | +0.054 |
oph | +0.052 |
way | +0.045 |
ally | +0.045 |
handed | +0.043 |
Neg logit contributions | |
Amen | -0.045 |
fires | -0.034 |
stretched | -0.032 |
passenger | -0.030 |
bears | -0.029 |
Token | liked |
Token ID | 8288 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
ork | +0.005 |
oph | +0.005 |
ally | +0.005 |
way | +0.004 |
handed | +0.004 |
Neg logit contributions | |
Amen | -0.005 |
fires | -0.004 |
stretched | -0.004 |
bears | -0.003 |
paddle | -0.003 |
Token | to |
Token ID | 284 |
Feature activation | -5.74e-01 |
Pos logit contributions | |
Amen | +0.045 |
fires | +0.034 |
stretched | +0.033 |
passenger | +0.032 |
paddle | +0.031 |
Neg logit contributions | |
ork | -0.032 |
oph | -0.032 |
ally | -0.027 |
way | -0.026 |
handed | -0.025 |
Token | pretend |
Token ID | 16614 |
Feature activation | +2.52e-02 |
Pos logit contributions | |
Amen | +0.017 |
fires | +0.013 |
stretched | +0.012 |
bears | +0.012 |
weaker | +0.011 |
Neg logit contributions | |
ork | -0.019 |
oph | -0.018 |
ally | -0.016 |
n | -0.016 |
doorstep | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | -1.68e-01 |
Pos logit contributions | |
ork | +0.001 |
oph | +0.001 |
way | +0.001 |
ally | +0.001 |
handed | +0.001 |
Neg logit contributions | |
Amen | -0.001 |
fires | -0.001 |
stretched | -0.001 |
bears | -0.001 |
passenger | -0.001 |
Token | She |
Token ID | 1375 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
Amen | +0.006 |
fires | +0.005 |
stretched | +0.004 |
bears | +0.004 |
paddle | +0.004 |
Neg logit contributions | |
ork | -0.005 |
oph | -0.005 |
way | -0.004 |
ally | -0.004 |
handed | -0.004 |
Token | told |
Token ID | 1297 |
Feature activation | +8.25e-01 |
Pos logit contributions | |
Amen | +0.043 |
fires | +0.033 |
stretched | +0.032 |
bears | +0.029 |
passenger | +0.028 |
Neg logit contributions | |
ork | -0.043 |
oph | -0.043 |
ally | -0.037 |
way | -0.037 |
handed | -0.035 |
Token | Max |
Token ID | 5436 |
Feature activation | +8.75e-01 |
Pos logit contributions | |
ork | +0.025 |
oph | +0.025 |
way | +0.021 |
handed | +0.021 |
ally | +0.021 |
Neg logit contributions | |
Amen | -0.026 |
fires | -0.020 |
stretched | -0.019 |
bears | -0.019 |
scar | -0.018 |
Token | he |
Token ID | 339 |
Feature activation | +5.02e-01 |
Pos logit contributions | |
ork | +0.024 |
oph | +0.023 |
ally | +0.019 |
way | +0.019 |
handed | +0.019 |
Neg logit contributions | |
Amen | -0.031 |
stretched | -0.024 |
fires | -0.024 |
passenger | -0.022 |
spoiler | -0.022 |
Token | inside |
Token ID | 2641 |
Feature activation | -6.23e-01 |
Pos logit contributions | |
Amen | +0.036 |
fires | +0.028 |
stretched | +0.028 |
bears | +0.027 |
spoiler | +0.027 |
Neg logit contributions | |
ork | -0.024 |
oph | -0.021 |
way | -0.019 |
ally | -0.019 |
handed | -0.019 |
Token | the |
Token ID | 262 |
Feature activation | -5.18e-01 |
Pos logit contributions | |
Amen | +0.017 |
fires | +0.012 |
stretched | +0.012 |
bears | +0.011 |
passenger | +0.011 |
Neg logit contributions | |
ork | -0.021 |
oph | -0.021 |
way | -0.019 |
handed | -0.018 |
ally | -0.018 |
Token | door |
Token ID | 3420 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
Amen | +0.018 |
fires | +0.014 |
stretched | +0.013 |
bears | +0.013 |
passenger | +0.012 |
Neg logit contributions | |
ork | -0.014 |
oph | -0.014 |
way | -0.012 |
ally | -0.012 |
handed | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | +6.94e-03 |
Pos logit contributions | |
Amen | +0.035 |
fires | +0.025 |
stretched | +0.023 |
bears | +0.023 |
scar | +0.022 |
Neg logit contributions | |
ork | -0.038 |
oph | -0.037 |
way | -0.033 |
ally | -0.032 |
handed | -0.032 |
Token | It |
Token ID | 632 |
Feature activation | +6.76e-01 |
Pos logit contributions | |
oph | +0.000 |
ork | +0.000 |
ally | +0.000 |
handed | +0.000 |
ige | +0.000 |
Neg logit contributions | |
Amen | -0.000 |
fires | -0.000 |
stretched | -0.000 |
smile | -0.000 |
nod | -0.000 |
Token | was |
Token ID | 373 |
Feature activation | +6.47e-01 |
Pos logit contributions | |
ork | +0.022 |
oph | +0.022 |
handed | +0.020 |
keeping | +0.019 |
way | +0.019 |
Neg logit contributions | |
Amen | -0.019 |
fires | -0.014 |
stretched | -0.014 |
bears | -0.013 |
smile | -0.013 |
Token | dark |
Token ID | 3223 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
ork | +0.023 |
oph | +0.022 |
way | +0.020 |
ally | +0.019 |
handed | +0.019 |
Neg logit contributions | |
Amen | -0.017 |
fires | -0.012 |
stretched | -0.012 |
bears | -0.011 |
passenger | -0.010 |
Token | and |
Token ID | 290 |
Feature activation | +4.64e-01 |
Pos logit contributions | |
ork | +0.048 |
oph | +0.047 |
way | +0.042 |
ally | +0.041 |
handed | +0.041 |
Neg logit contributions | |
Amen | -0.038 |
fires | -0.027 |
stretched | -0.027 |
bears | -0.025 |
passenger | -0.024 |
Token | he |
Token ID | 339 |
Feature activation | +7.18e-01 |
Pos logit contributions | |
ork | +0.016 |
oph | +0.015 |
way | +0.014 |
handed | +0.014 |
ally | +0.013 |
Neg logit contributions | |
Amen | -0.012 |
fires | -0.009 |
stretched | -0.008 |
bears | -0.008 |
passenger | -0.008 |
Token | couldn |
Token ID | 3521 |
Feature activation | -3.95e-01 |
Pos logit contributions | |
ork | +0.023 |
oph | +0.022 |
way | +0.019 |
ally | +0.019 |
handed | +0.019 |
Neg logit contributions | |
Amen | -0.021 |
fires | -0.016 |
stretched | -0.016 |
bears | -0.015 |
passenger | -0.014 |
Token | 't |
Token ID | 470 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
Amen | +0.011 |
fires | +0.007 |
stretched | +0.007 |
sometimes | +0.007 |
exc | +0.007 |
Neg logit contributions | |
oph | -0.014 |
ork | -0.012 |
ally | -0.012 |
keeping | -0.011 |
handed | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | -2.00e-02 |
Pos logit contributions | |
Amen | +0.044 |
fires | +0.034 |
stretched | +0.033 |
paddle | +0.033 |
passenger | +0.033 |
Neg logit contributions | |
ork | -0.029 |
oph | -0.028 |
way | -0.022 |
handed | -0.022 |
her | -0.021 |
Token | It |
Token ID | 632 |
Feature activation | +2.30e-01 |
Pos logit contributions | |
Amen | +0.000 |
stretched | +0.000 |
fires | +0.000 |
nods | +0.000 |
smile | +0.000 |
Neg logit contributions | |
oph | -0.001 |
ork | -0.001 |
handed | -0.001 |
way | -0.001 |
ally | -0.001 |
Token | is |
Token ID | 318 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
ork | +0.006 |
oph | +0.006 |
way | +0.005 |
ally | +0.005 |
her | +0.005 |
Neg logit contributions | |
Amen | -0.008 |
stretched | -0.006 |
fires | -0.006 |
passenger | -0.006 |
paddle | -0.005 |
Token | delicious |
Token ID | 12625 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
ork | +0.004 |
oph | +0.003 |
ally | +0.003 |
way | +0.003 |
handed | +0.003 |
Neg logit contributions | |
Amen | -0.003 |
fires | -0.003 |
stretched | -0.003 |
passenger | -0.002 |
paddle | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
ork | +0.049 |
oph | +0.047 |
way | +0.042 |
handed | +0.042 |
ally | +0.041 |
Neg logit contributions | |
Amen | -0.033 |
fires | -0.024 |
bears | -0.023 |
stretched | -0.022 |
smile | -0.021 |
Token | She |
Token ID | 1375 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
Amen | +0.004 |
stretched | +0.003 |
nods | +0.003 |
Does | +0.003 |
exc | +0.003 |
Neg logit contributions | |
oph | -0.007 |
ork | -0.007 |
way | -0.006 |
handed | -0.006 |
doorstep | -0.006 |
Token | says |
Token ID | 1139 |
Feature activation | +2.24e+00 |
Pos logit contributions | |
Amen | +0.039 |
stretched | +0.030 |
fires | +0.029 |
passenger | +0.028 |
sled | +0.025 |
Neg logit contributions | |
oph | -0.038 |
ork | -0.037 |
her | -0.030 |
ally | -0.030 |
ige | -0.030 |
Token | thank |
Token ID | 5875 |
Feature activation | -7.30e-01 |
Pos logit contributions | |
ork | +0.072 |
oph | +0.068 |
ally | +0.055 |
way | +0.055 |
orman | +0.052 |
Neg logit contributions | |
Amen | -0.068 |
passenger | -0.051 |
fires | -0.051 |
stretched | -0.051 |
paddle | -0.047 |
Token | you |
Token ID | 345 |
Feature activation | -7.96e-01 |
Pos logit contributions | |
Amen | +0.024 |
fires | +0.018 |
stretched | +0.017 |
bears | +0.017 |
smile | +0.017 |
Neg logit contributions | |
ork | -0.021 |
oph | -0.021 |
way | -0.018 |
handed | -0.018 |
ally | -0.017 |
Token | to |
Token ID | 284 |
Feature activation | -7.80e-02 |
Pos logit contributions | |
Amen | +0.024 |
fires | +0.018 |
stretched | +0.018 |
bears | +0.016 |
passenger | +0.016 |
Neg logit contributions | |
ork | -0.025 |
oph | -0.024 |
way | -0.021 |
ally | -0.021 |
handed | -0.021 |
Token | her |
Token ID | 607 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
Amen | +0.002 |
fires | +0.002 |
stretched | +0.002 |
bears | +0.002 |
passenger | +0.001 |
Neg logit contributions | |
ork | -0.003 |
oph | -0.002 |
ally | -0.002 |
way | -0.002 |
handed | -0.002 |
Token | and |
Token ID | 290 |
Feature activation | +3.70e-01 |
Pos logit contributions | |
Amen | +0.019 |
fires | +0.014 |
stretched | +0.014 |
bears | +0.013 |
smile | +0.012 |
Neg logit contributions | |
ork | -0.029 |
oph | -0.028 |
ally | -0.024 |
way | -0.024 |
handed | -0.024 |
Token | faces |
Token ID | 6698 |
Feature activation | +1.71e-01 |
Pos logit contributions | |
ork | +0.011 |
oph | +0.011 |
way | +0.010 |
handed | +0.010 |
ally | +0.010 |
Neg logit contributions | |
Amen | -0.011 |
fires | -0.008 |
stretched | -0.008 |
passenger | -0.007 |
bears | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | +6.41e-01 |
Pos logit contributions | |
ork | +0.005 |
oph | +0.005 |
way | +0.004 |
handed | +0.004 |
ally | +0.004 |
Neg logit contributions | |
Amen | -0.006 |
fires | -0.004 |
stretched | -0.004 |
bears | -0.004 |
passenger | -0.004 |
Token | They |
Token ID | 1119 |
Feature activation | -1.94e-02 |
Pos logit contributions | |
oph | +0.024 |
ork | +0.024 |
handed | +0.020 |
doorstep | +0.020 |
keeping | +0.020 |
Neg logit contributions | |
Amen | -0.015 |
fires | -0.010 |
stretched | -0.010 |
Sometimes | -0.010 |
bears | -0.010 |
Token | all |
Token ID | 477 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
Amen | +0.001 |
fires | +0.000 |
stretched | +0.000 |
passenger | +0.000 |
spoiler | +0.000 |
Neg logit contributions | |
oph | -0.001 |
ork | -0.001 |
ally | -0.001 |
way | -0.000 |
handed | -0.000 |
Token | laughed |
Token ID | 13818 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
oph | +0.003 |
ork | +0.003 |
ally | +0.003 |
way | +0.003 |
handed | +0.003 |
Neg logit contributions | |
Amen | -0.004 |
fires | -0.003 |
stretched | -0.003 |
bears | -0.002 |
passenger | -0.002 |
Token | and |
Token ID | 290 |
Feature activation | -1.80e-01 |
Pos logit contributions | |
Amen | +0.032 |
fires | +0.023 |
stretched | +0.023 |
passenger | +0.022 |
whine | +0.021 |
Neg logit contributions | |
ork | -0.030 |
oph | -0.030 |
way | -0.026 |
ally | -0.026 |
handed | -0.024 |
Token | had |
Token ID | 550 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
Amen | +0.005 |
fires | +0.003 |
stretched | +0.003 |
bears | +0.003 |
passenger | +0.003 |
Neg logit contributions | |
ork | -0.007 |
oph | -0.006 |
way | -0.006 |
ally | -0.006 |
handed | -0.006 |
Token | fun |
Token ID | 1257 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
ork | +0.035 |
oph | +0.034 |
way | +0.030 |
handed | +0.030 |
ally | +0.030 |
Neg logit contributions | |
Amen | -0.027 |
fires | -0.020 |
stretched | -0.019 |
bears | -0.018 |
scar | -0.018 |
Token | playing |
Token ID | 2712 |
Feature activation | -2.03e-01 |
Pos logit contributions | |
ork | +0.034 |
oph | +0.032 |
way | +0.030 |
handed | +0.028 |
ally | +0.028 |
Neg logit contributions | |
Amen | -0.038 |
stretched | -0.027 |
fires | -0.027 |
passenger | -0.026 |
scar | -0.025 |
Token | in |
Token ID | 287 |
Feature activation | +3.72e-02 |
Pos logit contributions | |
Amen | +0.005 |
fires | +0.004 |
bears | +0.003 |
stretched | +0.003 |
hope | +0.003 |
Neg logit contributions | |
oph | -0.007 |
ork | -0.007 |
ally | -0.006 |
way | -0.006 |
handed | -0.006 |
Token | and |
Token ID | 290 |
Feature activation | -7.27e-01 |
Pos logit contributions | |
ork | +0.026 |
oph | +0.025 |
way | +0.022 |
handed | +0.022 |
ally | +0.022 |
Neg logit contributions | |
Amen | -0.019 |
fires | -0.014 |
stretched | -0.014 |
bears | -0.013 |
smile | -0.013 |
Token | Jack |
Token ID | 3619 |
Feature activation | +1.84e-01 |
Pos logit contributions | |
Amen | +0.024 |
fires | +0.019 |
stretched | +0.018 |
bears | +0.017 |
scar | +0.017 |
Neg logit contributions | |
ork | -0.021 |
oph | -0.020 |
way | -0.017 |
ally | -0.017 |
handed | -0.017 |
Token | were |
Token ID | 547 |
Feature activation | -1.59e-02 |
Pos logit contributions | |
oph | +0.006 |
ork | +0.006 |
ally | +0.005 |
way | +0.005 |
handed | +0.005 |
Neg logit contributions | |
Amen | -0.005 |
fires | -0.004 |
stretched | -0.004 |
bears | -0.003 |
scar | -0.003 |
Token | very |
Token ID | 845 |
Feature activation | +8.66e-01 |
Pos logit contributions | |
Amen | +0.000 |
fires | +0.000 |
stretched | +0.000 |
bears | +0.000 |
scar | +0.000 |
Neg logit contributions | |
ork | -0.001 |
oph | -0.001 |
handed | -0.000 |
way | -0.000 |
ally | -0.000 |
Token | happy |
Token ID | 3772 |
Feature activation | -1.72e-01 |
Pos logit contributions | |
ork | +0.028 |
oph | +0.027 |
handed | +0.025 |
way | +0.025 |
ally | +0.024 |
Neg logit contributions | |
Amen | -0.024 |
fires | -0.018 |
bears | -0.017 |
scar | -0.016 |
stretched | -0.016 |
Token | that |
Token ID | 326 |
Feature activation | -9.17e-01 |
Pos logit contributions | |
Amen | +0.005 |
fires | +0.004 |
stretched | +0.004 |
bears | +0.003 |
passenger | +0.003 |
Neg logit contributions | |
ork | -0.005 |
oph | -0.005 |
way | -0.005 |
ally | -0.005 |
handed | -0.005 |
Token | they |
Token ID | 484 |
Feature activation | +8.64e-01 |
Pos logit contributions | |
Amen | +0.021 |
fires | +0.014 |
stretched | +0.013 |
bears | +0.013 |
smile | +0.012 |
Neg logit contributions | |
ork | -0.036 |
oph | -0.035 |
handed | -0.031 |
way | -0.031 |
ally | -0.031 |
Token | had |
Token ID | 550 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
ork | +0.027 |
oph | +0.027 |
way | +0.023 |
ally | +0.023 |
handed | +0.023 |
Neg logit contributions | |
Amen | -0.026 |
fires | -0.020 |
stretched | -0.019 |
bears | -0.018 |
scar | -0.017 |
Token | cleaned |
Token ID | 20750 |
Feature activation | +6.26e-01 |
Pos logit contributions | |
ork | +0.057 |
anger | +0.053 |
oph | +0.053 |
ess | +0.048 |
way | +0.047 |
Neg logit contributions | |
hope | -0.028 |
smile | -0.026 |
Amen | -0.026 |
yes | -0.025 |
ne | -0.024 |
Token | up |
Token ID | 510 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
ork | +0.022 |
oph | +0.022 |
ally | +0.019 |
way | +0.019 |
handed | +0.019 |
Neg logit contributions | |
Amen | -0.015 |
fires | -0.013 |
bears | -0.011 |
hope | -0.011 |
stretched | -0.010 |
Token | the |
Token ID | 262 |
Feature activation | -2.49e-01 |
Pos logit contributions | |
Amen | +0.004 |
fires | +0.003 |
stretched | +0.003 |
bears | +0.003 |
hope | +0.003 |
Neg logit contributions | |
ork | -0.007 |
oph | -0.007 |
way | -0.007 |
ally | -0.007 |
handed | -0.006 |
Token | three |
Token ID | 1115 |
Feature activation | -6.64e-01 |
Pos logit contributions | |
ork | +0.000 |
oph | +0.000 |
way | +0.000 |
ally | +0.000 |
handed | +0.000 |
Neg logit contributions | |
Amen | -0.000 |
fires | -0.000 |
stretched | -0.000 |
spoiler | -0.000 |
paddle | -0.000 |
Token | and |
Token ID | 290 |
Feature activation | -4.96e-01 |
Pos logit contributions | |
Amen | +0.021 |
fires | +0.014 |
stretched | +0.014 |
paddle | +0.014 |
spoiler | +0.014 |
Neg logit contributions | |
ork | -0.020 |
oph | -0.020 |
ally | -0.018 |
way | -0.018 |
handed | -0.017 |
Token | she |
Token ID | 673 |
Feature activation | +2.52e-01 |
Pos logit contributions | |
Amen | +0.014 |
fires | +0.011 |
stretched | +0.010 |
paddle | +0.010 |
bears | +0.010 |
Neg logit contributions | |
ork | -0.016 |
oph | -0.015 |
ally | -0.014 |
way | -0.013 |
handed | -0.013 |
Token | loved |
Token ID | 6151 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
ork | +0.009 |
oph | +0.008 |
way | +0.007 |
ally | +0.007 |
handed | +0.007 |
Neg logit contributions | |
Amen | -0.007 |
fires | -0.005 |
stretched | -0.005 |
bears | -0.005 |
scar | -0.005 |
Token | to |
Token ID | 284 |
Feature activation | -3.58e-01 |
Pos logit contributions | |
Amen | +0.042 |
stretched | +0.033 |
fires | +0.032 |
spoiler | +0.032 |
passenger | +0.031 |
Neg logit contributions | |
ork | -0.023 |
oph | -0.021 |
keeping | -0.018 |
way | -0.018 |
ally | -0.017 |
Token | imagine |
Token ID | 5967 |
Feature activation | -9.86e-01 |
Pos logit contributions | |
Amen | +0.011 |
stretched | +0.009 |
fires | +0.009 |
weaker | +0.008 |
ang | +0.008 |
Neg logit contributions | |
ork | -0.010 |
oph | -0.009 |
n | -0.009 |
doorstep | -0.009 |
ally | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | -3.56e-01 |
Pos logit contributions | |
Amen | +0.035 |
paddle | +0.025 |
stretched | +0.025 |
passenger | +0.024 |
spoiler | +0.024 |
Neg logit contributions | |
ork | -0.028 |
oph | -0.024 |
way | -0.022 |
ally | -0.020 |
handed | -0.020 |
Token | One |
Token ID | 1881 |
Feature activation | -9.21e-01 |
Pos logit contributions | |
Amen | +0.010 |
stretched | +0.007 |
fires | +0.006 |
smile | +0.006 |
wonder | +0.006 |
Neg logit contributions | |
ork | -0.013 |
oph | -0.012 |
handed | -0.011 |
way | -0.011 |
keeping | -0.011 |
Token | of |
Token ID | 286 |
Feature activation | -5.64e-01 |
Pos logit contributions | |
Amen | +0.030 |
fires | +0.023 |
stretched | +0.022 |
bears | +0.021 |
passenger | +0.021 |
Neg logit contributions | |
ork | -0.027 |
oph | -0.026 |
way | -0.023 |
ally | -0.022 |
handed | -0.022 |
Token | her |
Token ID | 607 |
Feature activation | +1.73e+00 |
Pos logit contributions | |
Amen | +0.010 |
fires | +0.008 |
stretched | +0.007 |
bears | +0.007 |
smile | +0.006 |
Neg logit contributions | |
ork | -0.024 |
oph | -0.022 |
way | -0.021 |
handed | -0.021 |
doorstep | -0.021 |
Token | favorite |
Token ID | 4004 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
ork | +0.058 |
oph | +0.057 |
way | +0.050 |
ally | +0.049 |
handed | +0.049 |
Neg logit contributions | |
Amen | -0.049 |
fires | -0.036 |
stretched | -0.035 |
bears | -0.032 |
paddle | -0.031 |
Token | . |
Token ID | 13 |
Feature activation | +2.81e-01 |
Pos logit contributions | |
Amen | +0.031 |
fires | +0.022 |
hope | +0.021 |
sometimes | +0.020 |
smile | +0.020 |
Neg logit contributions | |
ork | -0.058 |
oph | -0.057 |
handed | -0.049 |
ally | -0.049 |
way | -0.049 |
Token | It |
Token ID | 632 |
Feature activation | +8.03e-01 |
Pos logit contributions | |
ork | +0.010 |
oph | +0.010 |
way | +0.009 |
handed | +0.008 |
ally | +0.008 |
Neg logit contributions | |
Amen | -0.008 |
stretched | -0.005 |
fires | -0.005 |
bears | -0.005 |
smile | -0.005 |
Token | was |
Token ID | 373 |
Feature activation | +5.72e-01 |
Pos logit contributions | |
ork | +0.023 |
oph | +0.023 |
way | +0.020 |
handed | +0.019 |
ally | +0.019 |
Neg logit contributions | |
Amen | -0.026 |
fires | -0.020 |
stretched | -0.020 |
bears | -0.019 |
smile | -0.018 |
Token | a |
Token ID | 257 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
ork | +0.019 |
oph | +0.019 |
way | +0.017 |
ally | +0.017 |
handed | +0.016 |
Neg logit contributions | |
Amen | -0.016 |
fires | -0.011 |
stretched | -0.011 |
bears | -0.010 |
paddle | -0.010 |
Token | pass |
Token ID | 1208 |
Feature activation | +3.22e-01 |
Pos logit contributions | |
ork | +0.033 |
oph | +0.031 |
way | +0.027 |
ally | +0.027 |
handed | +0.026 |
Neg logit contributions | |
Amen | -0.034 |
fires | -0.026 |
stretched | -0.026 |
bears | -0.024 |
nods | -0.023 |
Token | to |
Token ID | 284 |
Feature activation | -6.40e-01 |
Pos logit contributions | |
ork | +0.010 |
oph | +0.010 |
way | +0.009 |
ally | +0.008 |
handed | +0.008 |
Neg logit contributions | |
Amen | -0.010 |
fires | -0.007 |
stretched | -0.007 |
bears | -0.007 |
passenger | -0.006 |
Token | the |
Token ID | 262 |
Feature activation | -1.56e-02 |
Pos logit contributions | |
Amen | +0.016 |
fires | +0.012 |
smile | +0.011 |
bears | +0.011 |
stretched | +0.011 |
Neg logit contributions | |
ork | -0.023 |
oph | -0.023 |
way | -0.021 |
ally | -0.020 |
handed | -0.019 |
Token | swimming |
Token ID | 14899 |
Feature activation | +2.60e-01 |
Pos logit contributions | |
Amen | +0.000 |
fires | +0.000 |
stretched | +0.000 |
passenger | +0.000 |
paddle | +0.000 |
Neg logit contributions | |
oph | -0.001 |
ork | -0.001 |
ally | -0.000 |
handed | -0.000 |
way | -0.000 |
Token | pool |
Token ID | 5933 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
oph | +0.008 |
ork | +0.008 |
ally | +0.007 |
handed | +0.007 |
way | +0.007 |
Neg logit contributions | |
Amen | -0.008 |
fires | -0.006 |
stretched | -0.005 |
bears | -0.005 |
paddle | -0.005 |
Token | ! |
Token ID | 0 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
ork | +0.033 |
oph | +0.032 |
way | +0.029 |
ally | +0.028 |
handed | +0.028 |
Neg logit contributions | |
Amen | -0.030 |
fires | -0.022 |
stretched | -0.022 |
bears | -0.020 |
scar | -0.019 |
Token |
|
Token ID | 198 |
Feature activation | +5.11e-01 |
Pos logit contributions | |
Amen | +0.004 |
fires | +0.003 |
stretched | +0.003 |
bears | +0.003 |
smile | +0.002 |
Neg logit contributions | |
ork | -0.004 |
oph | -0.004 |
way | -0.003 |
handed | -0.003 |
ally | -0.003 |
Token | so |
Token ID | 523 |
Feature activation | +7.68e-01 |
Pos logit contributions | |
Amen | +0.037 |
fires | +0.030 |
stretched | +0.029 |
scar | +0.027 |
bears | +0.027 |
Neg logit contributions | |
oph | -0.034 |
ork | -0.033 |
handed | -0.030 |
way | -0.029 |
ally | -0.029 |
Token | happy |
Token ID | 3772 |
Feature activation | +5.21e-01 |
Pos logit contributions | |
ork | +0.029 |
oph | +0.029 |
way | +0.026 |
ally | +0.026 |
handed | +0.026 |
Neg logit contributions | |
Amen | -0.018 |
fires | -0.013 |
stretched | -0.011 |
bears | -0.011 |
scar | -0.010 |
Token | and |
Token ID | 290 |
Feature activation | +6.10e-01 |
Pos logit contributions | |
ork | +0.021 |
oph | +0.020 |
handed | +0.018 |
ally | +0.017 |
way | +0.017 |
Neg logit contributions | |
Amen | -0.010 |
fires | -0.007 |
sometimes | -0.007 |
smile | -0.007 |
bears | -0.007 |
Token | hugged |
Token ID | 41130 |
Feature activation | +8.71e-01 |
Pos logit contributions | |
ork | +0.024 |
oph | +0.022 |
way | +0.020 |
handed | +0.020 |
ally | +0.020 |
Neg logit contributions | |
Amen | -0.014 |
smile | -0.009 |
stretched | -0.009 |
fires | -0.009 |
exc | -0.009 |
Token | her |
Token ID | 607 |
Feature activation | -7.33e-01 |
Pos logit contributions | |
ork | +0.029 |
oph | +0.029 |
ally | +0.025 |
way | +0.025 |
handed | +0.025 |
Neg logit contributions | |
Amen | -0.025 |
fires | -0.018 |
stretched | -0.018 |
bears | -0.016 |
passenger | -0.016 |
Token | daddy |
Token ID | 35822 |
Feature activation | -3.06e+00 |
Pos logit contributions | |
Amen | +0.023 |
stretched | +0.021 |
fires | +0.020 |
Leave | +0.018 |
ahs | +0.018 |
Neg logit contributions | |
ork | -0.019 |
oph | -0.018 |
doorstep | -0.016 |
ally | -0.015 |
ilda | -0.014 |
Token | tight |
Token ID | 5381 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
Amen | +0.091 |
fires | +0.069 |
stretched | +0.067 |
bears | +0.062 |
passenger | +0.060 |
Neg logit contributions | |
ork | -0.097 |
oph | -0.095 |
way | -0.083 |
handed | -0.082 |
ally | -0.082 |
Token | . |
Token ID | 13 |
Feature activation | +4.29e-01 |
Pos logit contributions | |
Amen | +0.029 |
fires | +0.021 |
stretched | +0.020 |
bears | +0.019 |
passenger | +0.018 |
Neg logit contributions | |
ork | -0.034 |
oph | -0.033 |
way | -0.029 |
ally | -0.029 |
handed | -0.029 |
Token | She |
Token ID | 1375 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
ork | +0.015 |
oph | +0.014 |
way | +0.013 |
handed | +0.013 |
ally | +0.012 |
Neg logit contributions | |
Amen | -0.012 |
fires | -0.008 |
stretched | -0.008 |
smile | -0.007 |
bears | -0.007 |
Token | learned |
Token ID | 4499 |
Feature activation | -1.77e-01 |
Pos logit contributions | |
Amen | +0.038 |
fires | +0.028 |
stretched | +0.027 |
bears | +0.026 |
smile | +0.025 |
Neg logit contributions | |
ork | -0.043 |
oph | -0.042 |
way | -0.037 |
handed | -0.037 |
ally | -0.036 |
Token | that |
Token ID | 326 |
Feature activation | -6.67e-01 |
Pos logit contributions | |
Amen | +0.005 |
fires | +0.004 |
stretched | +0.004 |
bears | +0.004 |
scar | +0.004 |
Neg logit contributions | |
ork | -0.006 |
oph | -0.006 |
way | -0.005 |
ally | -0.005 |
handed | -0.005 |
Token | excited |
Token ID | 6568 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
ork | +0.044 |
oph | +0.044 |
handed | +0.040 |
way | +0.039 |
ally | +0.039 |
Neg logit contributions | |
Amen | -0.030 |
fires | -0.022 |
bears | -0.020 |
stretched | -0.020 |
scar | -0.019 |
Token | , |
Token ID | 11 |
Feature activation | +8.56e-01 |
Pos logit contributions | |
ork | +0.056 |
oph | +0.051 |
handed | +0.049 |
keeping | +0.046 |
doorstep | +0.046 |
Neg logit contributions | |
Amen | -0.022 |
sometimes | -0.019 |
smile | -0.018 |
stretched | -0.017 |
bears | -0.016 |
Token | she |
Token ID | 673 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
ork | +0.029 |
oph | +0.028 |
way | +0.025 |
ally | +0.024 |
handed | +0.024 |
Neg logit contributions | |
Amen | -0.024 |
fires | -0.018 |
stretched | -0.017 |
bears | -0.016 |
passenger | -0.015 |
Token | hugged |
Token ID | 41130 |
Feature activation | +8.45e-01 |
Pos logit contributions | |
ork | +0.035 |
oph | +0.034 |
way | +0.030 |
ally | +0.030 |
handed | +0.029 |
Neg logit contributions | |
Amen | -0.032 |
fires | -0.024 |
stretched | -0.023 |
bears | -0.022 |
passenger | -0.021 |
Token | the |
Token ID | 262 |
Feature activation | -5.07e-01 |
Pos logit contributions | |
ork | +0.030 |
oph | +0.029 |
handed | +0.026 |
way | +0.026 |
ally | +0.026 |
Neg logit contributions | |
Amen | -0.022 |
fires | -0.016 |
stretched | -0.015 |
bears | -0.014 |
hope | -0.014 |
Token | fairy |
Token ID | 25607 |
Feature activation | -3.07e+00 |
Pos logit contributions | |
Amen | +0.014 |
fires | +0.010 |
stretched | +0.010 |
bears | +0.009 |
paddle | +0.009 |
Neg logit contributions | |
ork | -0.017 |
oph | -0.017 |
way | -0.015 |
ally | -0.015 |
handed | -0.015 |
Token | and |
Token ID | 290 |
Feature activation | -5.61e-01 |
Pos logit contributions | |
Amen | +0.093 |
fires | +0.071 |
stretched | +0.069 |
Does | +0.062 |
bears | +0.062 |
Neg logit contributions | |
ork | -0.095 |
oph | -0.092 |
way | -0.080 |
ally | -0.080 |
handed | -0.079 |
Token | thanked |
Token ID | 26280 |
Feature activation | -3.52e-01 |
Pos logit contributions | |
Amen | +0.017 |
fires | +0.012 |
stretched | +0.012 |
bears | +0.011 |
passenger | +0.011 |
Neg logit contributions | |
oph | -0.018 |
ork | -0.018 |
ally | -0.015 |
way | -0.015 |
handed | -0.015 |
Token | her |
Token ID | 607 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
Amen | +0.009 |
fires | +0.007 |
stretched | +0.006 |
bears | +0.006 |
scar | +0.006 |
Neg logit contributions | |
ork | -0.012 |
oph | -0.012 |
way | -0.011 |
handed | -0.011 |
ally | -0.011 |
Token | ! |
Token ID | 0 |
Feature activation | -2.66e-01 |
Pos logit contributions | |
Amen | +0.043 |
stretched | +0.033 |
spoiler | +0.033 |
fires | +0.033 |
whine | +0.032 |
Neg logit contributions | |
ork | -0.029 |
oph | -0.027 |
doorstep | -0.023 |
ally | -0.023 |
way | -0.023 |
Token | |
Token ID | 220 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
Amen | +0.008 |
stretched | +0.006 |
fires | +0.006 |
bears | +0.006 |
passenger | +0.006 |
Neg logit contributions | |
ork | -0.008 |
oph | -0.008 |
way | -0.007 |
handed | -0.007 |
ally | -0.007 |
Token | hugged |
Token ID | 41130 |
Feature activation | +2.18e-01 |
Pos logit contributions | |
Amen | +0.016 |
fires | +0.012 |
stretched | +0.011 |
bears | +0.010 |
passenger | +0.010 |
Neg logit contributions | |
ork | -0.017 |
oph | -0.017 |
ally | -0.014 |
way | -0.014 |
handed | -0.014 |
Token | Spot |
Token ID | 15899 |
Feature activation | -9.78e-01 |
Pos logit contributions | |
ork | +0.007 |
oph | +0.006 |
ally | +0.006 |
way | +0.005 |
handed | +0.005 |
Neg logit contributions | |
Amen | -0.007 |
stretched | -0.005 |
fires | -0.005 |
passenger | -0.005 |
paddle | -0.004 |
Token | and |
Token ID | 290 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
Amen | +0.034 |
stretched | +0.027 |
fires | +0.025 |
spoiler | +0.024 |
Does | +0.024 |
Neg logit contributions | |
ork | -0.026 |
oph | -0.024 |
way | -0.021 |
ally | -0.021 |
handed | -0.021 |
Token | thanked |
Token ID | 26280 |
Feature activation | -9.60e-01 |
Pos logit contributions | |
Amen | +0.033 |
fires | +0.024 |
stretched | +0.024 |
bears | +0.022 |
passenger | +0.021 |
Neg logit contributions | |
ork | -0.035 |
oph | -0.034 |
way | -0.030 |
ally | -0.030 |
handed | -0.030 |
Token | the |
Token ID | 262 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
Amen | +0.028 |
stretched | +0.022 |
fires | +0.021 |
passenger | +0.020 |
spoiler | +0.019 |
Neg logit contributions | |
ork | -0.030 |
oph | -0.029 |
ally | -0.025 |
handed | -0.025 |
way | -0.024 |
Token | man |
Token ID | 582 |
Feature activation | -3.80e+00 |
Pos logit contributions | |
Amen | +0.054 |
stretched | +0.042 |
fires | +0.041 |
bears | +0.038 |
scar | +0.036 |
Neg logit contributions | |
ork | -0.048 |
oph | -0.044 |
handed | -0.040 |
way | -0.039 |
ally | -0.038 |
Token | . |
Token ID | 13 |
Feature activation | -7.01e-02 |
Pos logit contributions | |
Amen | +0.135 |
stretched | +0.108 |
fires | +0.101 |
spoiler | +0.101 |
Does | +0.100 |
Neg logit contributions | |
ork | -0.097 |
oph | -0.086 |
handed | -0.080 |
way | -0.079 |
ess | -0.075 |
Token | They |
Token ID | 1119 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
Amen | +0.002 |
fires | +0.002 |
stretched | +0.002 |
bears | +0.001 |
argue | +0.001 |
Neg logit contributions | |
ork | -0.002 |
oph | -0.002 |
ally | -0.002 |
way | -0.002 |
handed | -0.002 |
Token | went |
Token ID | 1816 |
Feature activation | +3.52e-01 |
Pos logit contributions | |
Amen | +0.033 |
fires | +0.025 |
stretched | +0.024 |
bears | +0.021 |
passenger | +0.021 |
Neg logit contributions | |
oph | -0.033 |
ork | -0.032 |
ally | -0.028 |
handed | -0.027 |
way | -0.027 |
Token | back |
Token ID | 736 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
ork | +0.010 |
oph | +0.009 |
way | +0.008 |
ally | +0.008 |
handed | +0.008 |
Neg logit contributions | |
Amen | -0.012 |
fires | -0.010 |
stretched | -0.009 |
bears | -0.009 |
passenger | -0.009 |
Token | to |
Token ID | 284 |
Feature activation | -5.86e-01 |
Pos logit contributions | |
oph | +0.054 |
ork | +0.049 |
ally | +0.045 |
liv | +0.043 |
way | +0.043 |
Neg logit contributions | |
Amen | -0.035 |
fires | -0.029 |
hope | -0.027 |
bears | -0.026 |
sled | -0.025 |
Token | them |
Token ID | 606 |
Feature activation | -4.64e-01 |
Pos logit contributions | |
ork | +0.022 |
oph | +0.021 |
way | +0.021 |
handed | +0.020 |
keeping | +0.020 |
Neg logit contributions | |
Amen | -0.014 |
bears | -0.011 |
fires | -0.010 |
hope | -0.010 |
g | -0.010 |
Token | ride |
Token ID | 6594 |
Feature activation | -1.89e-01 |
Pos logit contributions | |
Amen | +0.012 |
stretched | +0.008 |
fires | +0.008 |
bears | +0.007 |
spoiler | +0.007 |
Neg logit contributions | |
ork | -0.017 |
oph | -0.016 |
way | -0.015 |
handed | -0.015 |
ally | -0.015 |
Token | on |
Token ID | 319 |
Feature activation | +6.45e-03 |
Pos logit contributions | |
Amen | +0.005 |
fires | +0.004 |
stretched | +0.004 |
bears | +0.004 |
passenger | +0.004 |
Neg logit contributions | |
ork | -0.006 |
oph | -0.006 |
way | -0.005 |
ally | -0.005 |
handed | -0.005 |
Token | her |
Token ID | 607 |
Feature activation | -5.93e-01 |
Pos logit contributions | |
ork | +0.000 |
oph | +0.000 |
way | +0.000 |
ally | +0.000 |
handed | +0.000 |
Neg logit contributions | |
Amen | -0.000 |
fires | -0.000 |
stretched | -0.000 |
bears | -0.000 |
scar | -0.000 |
Token | back |
Token ID | 736 |
Feature activation | +3.88e-01 |
Pos logit contributions | |
Amen | +0.018 |
fires | +0.013 |
stretched | +0.013 |
bears | +0.012 |
passenger | +0.011 |
Neg logit contributions | |
ork | -0.019 |
oph | -0.018 |
way | -0.016 |
handed | -0.016 |
ally | -0.016 |
Token | sometimes |
Token ID | 3360 |
Feature activation | -3.25e+00 |
Pos logit contributions | |
ork | +0.012 |
oph | +0.012 |
way | +0.010 |
handed | +0.010 |
ally | +0.010 |
Neg logit contributions | |
Amen | -0.012 |
fires | -0.009 |
stretched | -0.009 |
bears | -0.008 |
scar | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
Amen | +0.094 |
fires | +0.069 |
stretched | +0.067 |
bears | +0.062 |
passenger | +0.060 |
Neg logit contributions | |
ork | -0.108 |
oph | -0.105 |
way | -0.092 |
ally | -0.091 |
handed | -0.091 |
Token |
|
Token ID | 198 |
Feature activation | +4.22e-01 |
Pos logit contributions | |
ork | +0.007 |
oph | +0.006 |
way | +0.006 |
handed | +0.006 |
ally | +0.006 |
Neg logit contributions | |
Amen | -0.007 |
fires | -0.005 |
stretched | -0.005 |
bears | -0.005 |
smile | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | -7.31e-02 |
Pos logit contributions | |
oph | +0.013 |
ork | +0.013 |
keeping | +0.012 |
handed | +0.012 |
doorstep | +0.012 |
Neg logit contributions | |
Amen | -0.012 |
stretched | -0.009 |
fires | -0.008 |
exc | -0.008 |
sled | -0.008 |
Token | One |
Token ID | 3198 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
Amen | +0.002 |
fires | +0.002 |
bears | +0.001 |
stretched | +0.001 |
smile | +0.001 |
Neg logit contributions | |
ork | -0.002 |
oph | -0.002 |
way | -0.002 |
ally | -0.002 |
handed | -0.002 |
Token | day |
Token ID | 1110 |
Feature activation | -1.97e-01 |
Pos logit contributions | |
Amen | +0.037 |
stretched | +0.029 |
fires | +0.029 |
spoiler | +0.028 |
bears | +0.027 |
Neg logit contributions | |
ork | -0.025 |
oph | -0.024 |
way | -0.021 |
ally | -0.021 |
handed | -0.019 |
Token | ? |
Token ID | 30 |
Feature activation | -9.34e-01 |
Pos logit contributions | |
Amen | +0.064 |
stretched | +0.046 |
fires | +0.045 |
passenger | +0.041 |
bears | +0.041 |
Neg logit contributions | |
ork | -0.086 |
oph | -0.083 |
way | -0.074 |
ally | -0.073 |
handed | -0.071 |
Token | How |
Token ID | 1374 |
Feature activation | -3.47e-01 |
Pos logit contributions | |
Amen | +0.030 |
stretched | +0.026 |
fires | +0.025 |
scar | +0.024 |
smile | +0.023 |
Neg logit contributions | |
ork | -0.024 |
oph | -0.022 |
way | -0.019 |
handed | -0.018 |
anger | -0.018 |
Token | do |
Token ID | 466 |
Feature activation | -2.69e-01 |
Pos logit contributions | |
Amen | +0.010 |
fires | +0.008 |
stretched | +0.007 |
bears | +0.007 |
smile | +0.007 |
Neg logit contributions | |
ork | -0.011 |
oph | -0.011 |
handed | -0.009 |
way | -0.009 |
ally | -0.009 |
Token | they |
Token ID | 484 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
Amen | +0.010 |
fires | +0.008 |
stretched | +0.007 |
bears | +0.007 |
passenger | +0.007 |
Neg logit contributions | |
ork | -0.007 |
oph | -0.007 |
way | -0.006 |
ally | -0.006 |
handed | -0.006 |
Token | do |
Token ID | 466 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
Amen | +0.034 |
stretched | +0.023 |
fires | +0.023 |
bears | +0.021 |
passenger | +0.019 |
Neg logit contributions | |
ork | -0.049 |
oph | -0.047 |
way | -0.043 |
handed | -0.042 |
ally | -0.042 |
Token | that |
Token ID | 326 |
Feature activation | -3.06e+00 |
Pos logit contributions | |
Amen | +0.037 |
stretched | +0.029 |
fires | +0.028 |
bears | +0.027 |
passenger | +0.026 |
Neg logit contributions | |
ork | -0.032 |
oph | -0.029 |
way | -0.026 |
handed | -0.025 |
ally | -0.024 |
Token | ?" |
Token ID | 1701 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
Amen | +0.080 |
stretched | +0.061 |
fires | +0.057 |
bears | +0.052 |
passenger | +0.051 |
Neg logit contributions | |
ork | -0.105 |
oph | -0.101 |
way | -0.093 |
ally | -0.088 |
handed | -0.087 |
Token | Ben |
Token ID | 3932 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
ork | +0.029 |
oph | +0.029 |
way | +0.024 |
handed | +0.024 |
ally | +0.024 |
Neg logit contributions | |
Amen | -0.038 |
fires | -0.030 |
stretched | -0.030 |
bears | -0.027 |
passenger | -0.027 |
Token | asked |
Token ID | 1965 |
Feature activation | +6.50e-01 |
Pos logit contributions | |
Amen | +0.036 |
fires | +0.024 |
stretched | +0.024 |
bears | +0.023 |
smile | +0.022 |
Neg logit contributions | |
ork | -0.048 |
oph | -0.045 |
way | -0.041 |
handed | -0.041 |
ally | -0.040 |
Token | . |
Token ID | 13 |
Feature activation | -8.57e-01 |
Pos logit contributions | |
ork | +0.021 |
oph | +0.020 |
way | +0.018 |
ally | +0.017 |
handed | +0.017 |
Neg logit contributions | |
Amen | -0.020 |
fires | -0.015 |
stretched | -0.014 |
bears | -0.013 |
scar | -0.013 |
Token |
|
Token ID | 198 |
Feature activation | -5.01e-01 |
Pos logit contributions | |
Amen | +0.031 |
fires | +0.025 |
stretched | +0.025 |
bears | +0.023 |
scar | +0.023 |
Neg logit contributions | |
ork | -0.022 |
oph | -0.020 |
way | -0.017 |
handed | -0.017 |
ally | -0.017 |