Token | like |
Token ID | 588 |
Feature activation | -3.17e-03 |
Pos logit contributions | |
packs | +0.073 |
ouses | +0.068 |
days | +0.059 |
wore | +0.055 |
owers | +0.050 |
Neg logit contributions | |
louder | -0.125 |
harder | -0.124 |
angrily | -0.121 |
loudly | -0.117 |
beast | -0.110 |
Token | to |
Token ID | 284 |
Feature activation | +1.31e-02 |
Pos logit contributions | |
louder | +0.005 |
angrily | +0.005 |
trigger | +0.005 |
harder | +0.005 |
loudly | +0.005 |
Neg logit contributions | |
days | -0.006 |
am | -0.006 |
wore | -0.006 |
packs | -0.005 |
ouses | -0.005 |
Token | pick |
Token ID | 2298 |
Feature activation | -1.02e-02 |
Pos logit contributions | |
days | +0.018 |
packs | +0.018 |
ouses | +0.018 |
wore | +0.017 |
am | +0.017 |
Neg logit contributions | |
louder | -0.027 |
harder | -0.026 |
angrily | -0.026 |
trigger | -0.026 |
loudly | -0.025 |
Token | flowers |
Token ID | 12734 |
Feature activation | +4.02e-02 |
Pos logit contributions | |
angrily | +0.018 |
louder | +0.018 |
trigger | +0.017 |
amus | +0.017 |
harder | +0.017 |
Neg logit contributions | |
am | -0.016 |
wore | -0.015 |
packs | -0.015 |
wear | -0.015 |
ouses | -0.015 |
Token | on |
Token ID | 319 |
Feature activation | +4.32e-02 |
Pos logit contributions | |
days | +0.083 |
wore | +0.080 |
am | +0.079 |
ouses | +0.079 |
packs | +0.078 |
Neg logit contributions | |
louder | -0.055 |
harder | -0.055 |
angrily | -0.050 |
loudly | -0.050 |
trigger | -0.046 |
Token | Tues |
Token ID | 48496 |
Feature activation | +8.68e-02 |
Pos logit contributions | |
days | +0.073 |
am | +0.072 |
packs | +0.071 |
wore | +0.071 |
ouses | +0.068 |
Neg logit contributions | |
louder | -0.076 |
angrily | -0.075 |
trigger | -0.073 |
harder | -0.073 |
beast | -0.069 |
Token | days |
Token ID | 12545 |
Feature activation | +3.69e-02 |
Pos logit contributions | |
wore | +0.054 |
ouses | +0.052 |
sizes | +0.044 |
wear | +0.044 |
freshly | +0.043 |
Neg logit contributions | |
angrily | -0.189 |
harder | -0.188 |
louder | -0.187 |
again | -0.186 |
amus | -0.186 |
Token | ." |
Token ID | 526 |
Feature activation | -5.58e-04 |
Pos logit contributions | |
days | +0.061 |
am | +0.060 |
wore | +0.060 |
packs | +0.058 |
ouses | +0.058 |
Neg logit contributions | |
louder | -0.065 |
harder | -0.064 |
angrily | -0.062 |
loudly | -0.060 |
trigger | -0.058 |
Token | |
Token ID | 220 |
Feature activation | +4.00e-02 |
Pos logit contributions | |
louder | +0.001 |
angrily | +0.001 |
harder | +0.001 |
trigger | +0.001 |
beast | +0.001 |
Neg logit contributions | |
days | -0.001 |
am | -0.001 |
wore | -0.001 |
packs | -0.001 |
ouses | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | +6.59e-03 |
Pos logit contributions | |
days | +0.056 |
wore | +0.052 |
am | +0.052 |
packs | +0.050 |
ouses | +0.050 |
Neg logit contributions | |
louder | -0.083 |
angrily | -0.083 |
harder | -0.082 |
trigger | -0.078 |
loudly | -0.078 |
Token |
|
Token ID | 198 |
Feature activation | -1.11e-02 |
Pos logit contributions | |
days | +0.007 |
am | +0.007 |
wore | +0.007 |
packs | +0.007 |
ouses | +0.006 |
Neg logit contributions | |
louder | -0.016 |
angrily | -0.015 |
harder | -0.015 |
trigger | -0.015 |
beast | -0.015 |
Token | love |
Token ID | 1842 |
Feature activation | -4.17e-04 |
Pos logit contributions | |
louder | +0.017 |
harder | +0.016 |
angrily | +0.016 |
trigger | +0.016 |
loudly | +0.015 |
Neg logit contributions | |
days | -0.013 |
am | -0.013 |
wore | -0.012 |
packs | -0.012 |
ouses | -0.012 |
Token | her |
Token ID | 607 |
Feature activation | +1.03e-02 |
Pos logit contributions | |
louder | +0.001 |
angrily | +0.001 |
harder | +0.001 |
trigger | +0.001 |
loudly | +0.001 |
Neg logit contributions | |
days | -0.001 |
am | -0.001 |
wore | -0.001 |
packs | -0.001 |
ouses | -0.001 |
Token | anyway |
Token ID | 6949 |
Feature activation | +3.47e-02 |
Pos logit contributions | |
days | +0.018 |
am | +0.017 |
wore | +0.017 |
packs | +0.017 |
ouses | +0.016 |
Neg logit contributions | |
angrily | -0.019 |
louder | -0.019 |
trigger | -0.018 |
harder | -0.018 |
beast | -0.017 |
Token | . |
Token ID | 13 |
Feature activation | +3.54e-02 |
Pos logit contributions | |
days | +0.054 |
am | +0.052 |
packs | +0.051 |
wore | +0.051 |
ouses | +0.050 |
Neg logit contributions | |
louder | -0.067 |
angrily | -0.065 |
trigger | -0.065 |
harder | -0.064 |
beast | -0.062 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +4.01e-02 |
Pos logit contributions | |
days | +0.076 |
ouses | +0.071 |
atmeal | +0.069 |
kins | +0.067 |
packs | +0.067 |
Neg logit contributions | |
louder | -0.052 |
harder | -0.051 |
angrily | -0.049 |
loudly | -0.047 |
beast | -0.040 |
Token | Once |
Token ID | 7454 |
Feature activation | +8.53e-02 |
Pos logit contributions | |
ouses | +0.064 |
days | +0.062 |
packs | +0.054 |
wore | +0.054 |
wear | +0.053 |
Neg logit contributions | |
harder | -0.073 |
louder | -0.069 |
beast | -0.068 |
angrily | -0.067 |
again | -0.065 |
Token | there |
Token ID | 612 |
Feature activation | +5.02e-02 |
Pos logit contributions | |
days | +0.154 |
ouses | +0.152 |
wore | +0.134 |
bows | +0.133 |
atmeal | +0.130 |
Neg logit contributions | |
harder | -0.133 |
louder | -0.123 |
loudly | -0.118 |
curiously | -0.118 |
angrily | -0.118 |
Token | was |
Token ID | 373 |
Feature activation | +6.69e-03 |
Pos logit contributions | |
ouses | +0.128 |
packs | +0.118 |
days | +0.114 |
aj | +0.108 |
wore | +0.104 |
Neg logit contributions | |
angrily | -0.050 |
harder | -0.048 |
again | -0.046 |
sadly | -0.043 |
curiously | -0.043 |
Token | a |
Token ID | 257 |
Feature activation | -3.96e-03 |
Pos logit contributions | |
days | +0.016 |
ouses | +0.016 |
wore | +0.015 |
am | +0.015 |
packs | +0.015 |
Neg logit contributions | |
harder | -0.007 |
louder | -0.007 |
angrily | -0.006 |
loudly | -0.006 |
beast | -0.005 |
Token | girl |
Token ID | 2576 |
Feature activation | +1.31e-02 |
Pos logit contributions | |
louder | +0.006 |
angrily | +0.006 |
harder | +0.006 |
trigger | +0.006 |
amus | +0.005 |
Neg logit contributions | |
days | -0.008 |
am | -0.008 |
wore | -0.008 |
packs | -0.007 |
ouses | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | +2.80e-02 |
Pos logit contributions | |
ouses | +0.023 |
days | +0.023 |
am | +0.023 |
packs | +0.022 |
'm | +0.020 |
Neg logit contributions | |
louder | -0.021 |
loudly | -0.020 |
angrily | -0.020 |
harder | -0.020 |
beast | -0.018 |
Token | all |
Token ID | 477 |
Feature activation | +3.45e-02 |
Pos logit contributions | |
days | +0.002 |
am | +0.002 |
wore | +0.002 |
packs | +0.002 |
ouses | +0.002 |
Neg logit contributions | |
trigger | -0.002 |
angrily | -0.002 |
louder | -0.002 |
harder | -0.002 |
beast | -0.002 |
Token | very |
Token ID | 845 |
Feature activation | +3.15e-02 |
Pos logit contributions | |
ouses | +0.059 |
days | +0.058 |
packs | +0.058 |
am | +0.056 |
wore | +0.055 |
Neg logit contributions | |
louder | -0.060 |
harder | -0.058 |
angrily | -0.056 |
loudly | -0.055 |
beast | -0.052 |
Token | fair |
Token ID | 3148 |
Feature activation | +1.49e-02 |
Pos logit contributions | |
days | +0.052 |
am | +0.051 |
wore | +0.050 |
ouses | +0.049 |
packs | +0.049 |
Neg logit contributions | |
louder | -0.058 |
angrily | -0.056 |
trigger | -0.056 |
harder | -0.056 |
beast | -0.053 |
Token | . |
Token ID | 13 |
Feature activation | +3.05e-02 |
Pos logit contributions | |
days | +0.025 |
am | +0.025 |
wore | +0.024 |
packs | +0.024 |
ouses | +0.023 |
Neg logit contributions | |
louder | -0.027 |
angrily | -0.026 |
harder | -0.026 |
trigger | -0.025 |
loudly | -0.024 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +3.88e-02 |
Pos logit contributions | |
days | +0.062 |
packs | +0.059 |
am | +0.056 |
ouses | +0.055 |
wore | +0.054 |
Neg logit contributions | |
angrily | -0.043 |
harder | -0.042 |
loudly | -0.040 |
louder | -0.040 |
curiously | -0.039 |
Token | Once |
Token ID | 7454 |
Feature activation | +8.42e-02 |
Pos logit contributions | |
ouses | +0.056 |
days | +0.056 |
packs | +0.051 |
wore | +0.051 |
wear | +0.050 |
Neg logit contributions | |
harder | -0.074 |
angrily | -0.073 |
louder | -0.072 |
beast | -0.069 |
trigger | -0.068 |
Token | upon |
Token ID | 2402 |
Feature activation | +2.05e-02 |
Pos logit contributions | |
ouses | +0.143 |
days | +0.140 |
wore | +0.128 |
am | +0.127 |
bows | +0.123 |
Neg logit contributions | |
harder | -0.139 |
curiously | -0.131 |
louder | -0.131 |
angrily | -0.129 |
loudly | -0.127 |
Token | a |
Token ID | 257 |
Feature activation | +2.93e-02 |
Pos logit contributions | |
days | +0.046 |
ouses | +0.045 |
packs | +0.044 |
wore | +0.044 |
am | +0.044 |
Neg logit contributions | |
louder | -0.026 |
harder | -0.025 |
angrily | -0.024 |
loudly | -0.023 |
trigger | -0.021 |
Token | time |
Token ID | 640 |
Feature activation | +3.01e-02 |
Pos logit contributions | |
days | +0.045 |
ouses | +0.044 |
wore | +0.043 |
am | +0.043 |
packs | +0.042 |
Neg logit contributions | |
harder | -0.057 |
louder | -0.056 |
angrily | -0.056 |
loudly | -0.054 |
beast | -0.051 |
Token | there |
Token ID | 612 |
Feature activation | +3.66e-02 |
Pos logit contributions | |
ouses | +0.058 |
days | +0.056 |
wore | +0.056 |
am | +0.054 |
packs | +0.054 |
Neg logit contributions | |
angrily | -0.045 |
louder | -0.044 |
harder | -0.044 |
loudly | -0.042 |
beast | -0.039 |
Token | was |
Token ID | 373 |
Feature activation | +2.54e-04 |
Pos logit contributions | |
ouses | +0.084 |
packs | +0.079 |
days | +0.076 |
wore | +0.069 |
aj | +0.069 |
Neg logit contributions | |
angrily | -0.045 |
harder | -0.042 |
loudly | -0.041 |
beast | -0.041 |
louder | -0.040 |
Token | ma |
Token ID | 2611 |
Feature activation | +2.61e-02 |
Pos logit contributions | |
ouses | +0.040 |
am | +0.040 |
packs | +0.040 |
wore | +0.040 |
days | +0.039 |
Neg logit contributions | |
louder | -0.045 |
harder | -0.044 |
angrily | -0.044 |
beast | -0.041 |
loudly | -0.040 |
Token | very |
Token ID | 845 |
Feature activation | +5.60e-02 |
Pos logit contributions | |
days | +0.054 |
am | +0.053 |
packs | +0.053 |
ouses | +0.052 |
wore | +0.051 |
Neg logit contributions | |
louder | -0.035 |
harder | -0.035 |
angrily | -0.034 |
loudly | -0.032 |
beast | -0.030 |
Token | much |
Token ID | 881 |
Feature activation | +2.86e-02 |
Pos logit contributions | |
packs | +0.102 |
days | +0.099 |
am | +0.097 |
wore | +0.096 |
ouses | +0.093 |
Neg logit contributions | |
angrily | -0.090 |
louder | -0.090 |
harder | -0.090 |
loudly | -0.090 |
beast | -0.079 |
Token | ! |
Token ID | 0 |
Feature activation | +3.32e-02 |
Pos logit contributions | |
days | +0.047 |
am | +0.046 |
wore | +0.046 |
ouses | +0.043 |
packs | +0.043 |
Neg logit contributions | |
trigger | -0.053 |
amus | -0.051 |
louder | -0.050 |
angrily | -0.050 |
throttle | -0.049 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +4.22e-02 |
Pos logit contributions | |
days | +0.062 |
ouses | +0.060 |
wore | +0.058 |
packs | +0.057 |
am | +0.057 |
Neg logit contributions | |
harder | -0.047 |
angrily | -0.046 |
louder | -0.045 |
loudly | -0.043 |
Whoever | -0.041 |
Token | Once |
Token ID | 7454 |
Feature activation | +8.33e-02 |
Pos logit contributions | |
ouses | +0.055 |
days | +0.055 |
packs | +0.050 |
wear | +0.049 |
wore | +0.049 |
Neg logit contributions | |
harder | -0.087 |
angrily | -0.086 |
louder | -0.086 |
beast | -0.082 |
loudly | -0.081 |
Token | upon |
Token ID | 2402 |
Feature activation | +2.09e-02 |
Pos logit contributions | |
ouses | +0.137 |
days | +0.133 |
wore | +0.125 |
am | +0.122 |
packs | +0.115 |
Neg logit contributions | |
harder | -0.143 |
louder | -0.136 |
angrily | -0.134 |
curiously | -0.133 |
loudly | -0.133 |
Token | a |
Token ID | 257 |
Feature activation | +2.91e-02 |
Pos logit contributions | |
days | +0.046 |
ouses | +0.045 |
packs | +0.044 |
wore | +0.044 |
am | +0.044 |
Neg logit contributions | |
louder | -0.027 |
harder | -0.026 |
angrily | -0.026 |
loudly | -0.024 |
trigger | -0.023 |
Token | time |
Token ID | 640 |
Feature activation | +3.18e-02 |
Pos logit contributions | |
days | +0.043 |
ouses | +0.042 |
am | +0.041 |
wore | +0.041 |
packs | +0.041 |
Neg logit contributions | |
louder | -0.058 |
harder | -0.057 |
angrily | -0.057 |
loudly | -0.055 |
beast | -0.052 |
Token | there |
Token ID | 612 |
Feature activation | +3.95e-02 |
Pos logit contributions | |
ouses | +0.062 |
days | +0.060 |
wore | +0.059 |
packs | +0.058 |
am | +0.057 |
Neg logit contributions | |
angrily | -0.047 |
louder | -0.046 |
harder | -0.046 |
loudly | -0.044 |
beast | -0.041 |
Token | was |
Token ID | 373 |
Feature activation | -4.02e-03 |
Pos logit contributions | |
ouses | +0.097 |
packs | +0.089 |
days | +0.086 |
aj | +0.080 |
wore | +0.078 |
Neg logit contributions | |
angrily | -0.044 |
harder | -0.041 |
loudly | -0.040 |
beast | -0.040 |
louder | -0.039 |
Token | their |
Token ID | 511 |
Feature activation | +2.05e-02 |
Pos logit contributions | |
days | +0.060 |
am | +0.057 |
wore | +0.057 |
ouses | +0.057 |
packs | +0.056 |
Neg logit contributions | |
louder | -0.062 |
harder | -0.061 |
angrily | -0.060 |
trigger | -0.057 |
loudly | -0.056 |
Token | memories |
Token ID | 9846 |
Feature activation | +4.12e-02 |
Pos logit contributions | |
days | +0.032 |
am | +0.031 |
wore | +0.031 |
packs | +0.030 |
ouses | +0.030 |
Neg logit contributions | |
louder | -0.039 |
harder | -0.038 |
angrily | -0.038 |
trigger | -0.037 |
loudly | -0.036 |
Token | forever |
Token ID | 8097 |
Feature activation | +3.78e-02 |
Pos logit contributions | |
days | +0.073 |
am | +0.072 |
wore | +0.070 |
packs | +0.070 |
ouses | +0.069 |
Neg logit contributions | |
louder | -0.070 |
harder | -0.068 |
angrily | -0.067 |
trigger | -0.065 |
loudly | -0.064 |
Token | . |
Token ID | 13 |
Feature activation | +4.12e-02 |
Pos logit contributions | |
days | +0.066 |
am | +0.064 |
wore | +0.064 |
packs | +0.063 |
ouses | +0.063 |
Neg logit contributions | |
louder | -0.065 |
harder | -0.064 |
angrily | -0.064 |
trigger | -0.060 |
loudly | -0.060 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +4.43e-02 |
Pos logit contributions | |
days | +0.074 |
packs | +0.070 |
ouses | +0.065 |
wore | +0.065 |
wear | +0.061 |
Neg logit contributions | |
harder | -0.070 |
louder | -0.069 |
angrily | -0.064 |
instructions | -0.062 |
loudly | -0.062 |
Token | Once |
Token ID | 7454 |
Feature activation | +8.32e-02 |
Pos logit contributions | |
ouses | +0.065 |
days | +0.064 |
packs | +0.060 |
wear | +0.058 |
wore | +0.057 |
Neg logit contributions | |
harder | -0.082 |
louder | -0.080 |
angrily | -0.079 |
beast | -0.077 |
again | -0.075 |
Token | there |
Token ID | 612 |
Feature activation | +4.75e-02 |
Pos logit contributions | |
days | +0.133 |
ouses | +0.132 |
wore | +0.124 |
packs | +0.118 |
am | +0.117 |
Neg logit contributions | |
harder | -0.140 |
curiously | -0.134 |
louder | -0.133 |
closely | -0.132 |
loudly | -0.129 |
Token | was |
Token ID | 373 |
Feature activation | -4.07e-03 |
Pos logit contributions | |
ouses | +0.110 |
packs | +0.102 |
days | +0.098 |
wore | +0.091 |
aj | +0.091 |
Neg logit contributions | |
angrily | -0.058 |
harder | -0.056 |
louder | -0.052 |
loudly | -0.051 |
curiously | -0.051 |
Token | a |
Token ID | 257 |
Feature activation | -5.97e-03 |
Pos logit contributions | |
louder | +0.005 |
harder | +0.005 |
angrily | +0.005 |
loudly | +0.005 |
trigger | +0.005 |
Neg logit contributions | |
days | -0.009 |
am | -0.009 |
ouses | -0.009 |
wore | -0.008 |
packs | -0.008 |
Token | tree |
Token ID | 5509 |
Feature activation | +1.10e-02 |
Pos logit contributions | |
angrily | +0.008 |
louder | +0.008 |
trigger | +0.008 |
harder | +0.008 |
amus | +0.008 |
Neg logit contributions | |
wore | -0.012 |
am | -0.012 |
days | -0.012 |
wear | -0.012 |
ouses | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | +1.12e-02 |
Pos logit contributions | |
days | +0.019 |
am | +0.019 |
wore | +0.018 |
packs | +0.018 |
ouses | +0.018 |
Neg logit contributions | |
louder | -0.019 |
angrily | -0.019 |
harder | -0.019 |
trigger | -0.018 |
loudly | -0.017 |
Token | the |
Token ID | 262 |
Feature activation | +3.45e-02 |
Pos logit contributions | |
days | +0.031 |
packs | +0.029 |
ouses | +0.029 |
am | +0.028 |
wore | +0.027 |
Neg logit contributions | |
harder | -0.015 |
louder | -0.015 |
loudly | -0.012 |
amus | -0.012 |
angrily | -0.012 |
Token | prett |
Token ID | 46442 |
Feature activation | +6.53e-02 |
Pos logit contributions | |
days | +0.057 |
packs | +0.054 |
am | +0.054 |
wore | +0.054 |
ouses | +0.053 |
Neg logit contributions | |
louder | -0.065 |
harder | -0.063 |
angrily | -0.062 |
trigger | -0.061 |
loudly | -0.059 |
Token | iest |
Token ID | 6386 |
Feature activation | +3.69e-02 |
Pos logit contributions | |
packs | +0.116 |
days | +0.108 |
wore | +0.106 |
| | +0.097 |
ouses | +0.097 |
Neg logit contributions | |
harder | -0.104 |
ly | -0.103 |
louder | -0.102 |
rier | -0.101 |
lever | -0.090 |
Token | a |
Token ID | 257 |
Feature activation | +1.83e-02 |
Pos logit contributions | |
days | +0.070 |
packs | +0.067 |
am | +0.066 |
ouses | +0.065 |
wore | +0.065 |
Neg logit contributions | |
louder | -0.060 |
harder | -0.059 |
angrily | -0.054 |
trigger | -0.053 |
loudly | -0.053 |
Token | pron |
Token ID | 31186 |
Feature activation | +5.34e-02 |
Pos logit contributions | |
days | +0.029 |
am | +0.028 |
wore | +0.028 |
ouses | +0.027 |
packs | +0.026 |
Neg logit contributions | |
angrily | -0.034 |
louder | -0.034 |
trigger | -0.034 |
harder | -0.034 |
amus | -0.032 |
Token | I |
Token ID | 314 |
Feature activation | +8.30e-02 |
Pos logit contributions | |
days | +0.096 |
packs | +0.096 |
ouses | +0.092 |
wore | +0.091 |
am | +0.088 |
Neg logit contributions | |
louder | -0.084 |
angrily | -0.082 |
harder | -0.082 |
loudly | -0.078 |
trigger | -0.076 |
Token | have |
Token ID | 423 |
Feature activation | +4.21e-02 |
Pos logit contributions | |
packs | +0.129 |
ouses | +0.118 |
aj | +0.115 |
ained | +0.108 |
days | +0.106 |
Neg logit contributions | |
harder | -0.132 |
louder | -0.131 |
angrily | -0.127 |
Whoever | -0.124 |
carefully | -0.122 |
Token | ever |
Token ID | 1683 |
Feature activation | +4.81e-02 |
Pos logit contributions | |
days | +0.078 |
packs | +0.076 |
am | +0.075 |
ouses | +0.074 |
wore | +0.072 |
Neg logit contributions | |
louder | -0.062 |
harder | -0.061 |
angrily | -0.060 |
loudly | -0.058 |
beast | -0.054 |
Token | seen |
Token ID | 1775 |
Feature activation | +1.24e-02 |
Pos logit contributions | |
days | +0.070 |
am | +0.070 |
packs | +0.068 |
ouses | +0.067 |
wear | +0.060 |
Neg logit contributions | |
harder | -0.093 |
louder | -0.093 |
angrily | -0.084 |
loudly | -0.080 |
ly | -0.077 |
Token | !" |
Token ID | 2474 |
Feature activation | +1.26e-02 |
Pos logit contributions | |
days | +0.021 |
am | +0.021 |
wore | +0.020 |
packs | +0.020 |
ouses | +0.020 |
Neg logit contributions | |
louder | -0.022 |
angrily | -0.021 |
harder | -0.021 |
trigger | -0.020 |
loudly | -0.020 |
Token | exclaimed |
Token ID | 33552 |
Feature activation | -2.45e-03 |
Pos logit contributions | |
days | +0.024 |
packs | +0.023 |
am | +0.023 |
ouses | +0.021 |
owers | +0.020 |
Neg logit contributions | |
louder | -0.021 |
angrily | -0.021 |
harder | -0.021 |
loudly | -0.020 |
sadly | -0.018 |
Token | treat |
Token ID | 2190 |
Feature activation | +2.47e-02 |
Pos logit contributions | |
days | +0.010 |
am | +0.010 |
wore | +0.010 |
wear | +0.009 |
packs | +0.009 |
Neg logit contributions | |
louder | -0.015 |
angrily | -0.015 |
trigger | -0.015 |
harder | -0.014 |
amus | -0.014 |
Token | to |
Token ID | 284 |
Feature activation | +3.08e-02 |
Pos logit contributions | |
days | +0.043 |
am | +0.042 |
wore | +0.041 |
packs | +0.041 |
ouses | +0.040 |
Neg logit contributions | |
louder | -0.043 |
trigger | -0.043 |
angrily | -0.042 |
harder | -0.041 |
amus | -0.040 |
Token | celebrate |
Token ID | 10648 |
Feature activation | +3.72e-02 |
Pos logit contributions | |
days | +0.046 |
am | +0.044 |
wore | +0.044 |
packs | +0.043 |
ouses | +0.042 |
Neg logit contributions | |
louder | -0.061 |
angrily | -0.060 |
harder | -0.060 |
trigger | -0.059 |
loudly | -0.057 |
Token | ! |
Token ID | 0 |
Feature activation | +3.90e-02 |
Pos logit contributions | |
days | +0.070 |
am | +0.067 |
wore | +0.066 |
packs | +0.066 |
ouses | +0.065 |
Neg logit contributions | |
louder | -0.061 |
harder | -0.059 |
angrily | -0.058 |
loudly | -0.056 |
beast | -0.052 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +3.89e-02 |
Pos logit contributions | |
days | +0.074 |
packs | +0.069 |
am | +0.065 |
ouses | +0.065 |
wore | +0.065 |
Neg logit contributions | |
harder | -0.061 |
louder | -0.060 |
angrily | -0.057 |
loudly | -0.054 |
throttle | -0.052 |
Token | Once |
Token ID | 7454 |
Feature activation | +8.28e-02 |
Pos logit contributions | |
ouses | +0.061 |
days | +0.059 |
packs | +0.055 |
wear | +0.054 |
wore | +0.053 |
Neg logit contributions | |
harder | -0.070 |
angrily | -0.069 |
louder | -0.068 |
beast | -0.066 |
loudly | -0.064 |
Token | upon |
Token ID | 2402 |
Feature activation | +2.10e-02 |
Pos logit contributions | |
ouses | +0.136 |
days | +0.134 |
wore | +0.123 |
am | +0.118 |
packs | +0.116 |
Neg logit contributions | |
harder | -0.142 |
louder | -0.134 |
angrily | -0.133 |
curiously | -0.131 |
loudly | -0.130 |
Token | a |
Token ID | 257 |
Feature activation | +2.99e-02 |
Pos logit contributions | |
days | +0.046 |
ouses | +0.045 |
packs | +0.044 |
wore | +0.044 |
am | +0.044 |
Neg logit contributions | |
louder | -0.028 |
harder | -0.027 |
angrily | -0.026 |
loudly | -0.025 |
trigger | -0.024 |
Token | time |
Token ID | 640 |
Feature activation | +3.08e-02 |
Pos logit contributions | |
days | +0.047 |
ouses | +0.046 |
packs | +0.045 |
wore | +0.044 |
am | +0.044 |
Neg logit contributions | |
harder | -0.057 |
louder | -0.056 |
angrily | -0.055 |
loudly | -0.054 |
beast | -0.051 |
Token | , |
Token ID | 11 |
Feature activation | +2.04e-02 |
Pos logit contributions | |
ouses | +0.063 |
days | +0.060 |
wore | +0.060 |
packs | +0.058 |
wear | +0.056 |
Neg logit contributions | |
angrily | -0.043 |
louder | -0.042 |
harder | -0.042 |
loudly | -0.040 |
beast | -0.037 |
Token | there |
Token ID | 612 |
Feature activation | +3.71e-02 |
Pos logit contributions | |
ouses | +0.040 |
days | +0.037 |
packs | +0.035 |
wore | +0.034 |
am | +0.034 |
Neg logit contributions | |
louder | -0.033 |
angrily | -0.032 |
harder | -0.032 |
loudly | -0.031 |
closer | -0.027 |
Token | looked |
Token ID | 3114 |
Feature activation | -4.41e-03 |
Pos logit contributions | |
days | +0.034 |
packs | +0.034 |
ouses | +0.032 |
am | +0.032 |
wore | +0.031 |
Neg logit contributions | |
louder | -0.078 |
angrily | -0.078 |
harder | -0.076 |
trigger | -0.075 |
loudly | -0.074 |
Token | like |
Token ID | 588 |
Feature activation | -1.12e-02 |
Pos logit contributions | |
trigger | +0.008 |
louder | +0.008 |
angrily | +0.008 |
beast | +0.008 |
harder | +0.008 |
Neg logit contributions | |
wore | -0.007 |
am | -0.007 |
days | -0.007 |
ouses | -0.006 |
packs | -0.006 |
Token | circles |
Token ID | 13332 |
Feature activation | +6.62e-03 |
Pos logit contributions | |
louder | +0.022 |
angrily | +0.021 |
trigger | +0.021 |
harder | +0.021 |
beast | +0.020 |
Neg logit contributions | |
days | -0.017 |
wore | -0.017 |
am | -0.017 |
packs | -0.016 |
ouses | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | +2.39e-02 |
Pos logit contributions | |
days | +0.011 |
wore | +0.011 |
am | +0.011 |
packs | +0.011 |
ouses | +0.010 |
Neg logit contributions | |
louder | -0.012 |
trigger | -0.012 |
angrily | -0.012 |
harder | -0.011 |
beast | -0.011 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +4.94e-02 |
Pos logit contributions | |
days | +0.040 |
am | +0.038 |
packs | +0.037 |
wore | +0.034 |
ouses | +0.034 |
Neg logit contributions | |
louder | -0.045 |
harder | -0.044 |
angrily | -0.044 |
loudly | -0.041 |
trigger | -0.040 |
Token | Once |
Token ID | 7454 |
Feature activation | +8.28e-02 |
Pos logit contributions | |
ouses | +0.091 |
days | +0.090 |
packs | +0.085 |
wore | +0.084 |
wear | +0.080 |
Neg logit contributions | |
harder | -0.078 |
angrily | -0.075 |
louder | -0.075 |
loudly | -0.070 |
beast | -0.067 |
Token | upon |
Token ID | 2402 |
Feature activation | +2.59e-02 |
Pos logit contributions | |
days | +0.134 |
ouses | +0.129 |
am | +0.121 |
wore | +0.119 |
packs | +0.114 |
Neg logit contributions | |
harder | -0.147 |
louder | -0.140 |
angrily | -0.135 |
loudly | -0.134 |
curiously | -0.130 |
Token | a |
Token ID | 257 |
Feature activation | +3.56e-02 |
Pos logit contributions | |
days | +0.058 |
ouses | +0.057 |
packs | +0.056 |
wore | +0.055 |
am | +0.055 |
Neg logit contributions | |
louder | -0.033 |
harder | -0.032 |
angrily | -0.031 |
loudly | -0.029 |
trigger | -0.028 |
Token | time |
Token ID | 640 |
Feature activation | +3.54e-02 |
Pos logit contributions | |
days | +0.060 |
ouses | +0.058 |
packs | +0.056 |
wore | +0.056 |
am | +0.055 |
Neg logit contributions | |
harder | -0.064 |
angrily | -0.062 |
louder | -0.062 |
loudly | -0.060 |
beast | -0.056 |
Token | , |
Token ID | 11 |
Feature activation | +3.35e-02 |
Pos logit contributions | |
ouses | +0.077 |
days | +0.072 |
wore | +0.072 |
packs | +0.070 |
wear | +0.068 |
Neg logit contributions | |
angrily | -0.044 |
harder | -0.043 |
louder | -0.042 |
loudly | -0.041 |
beast | -0.036 |
Token | there |
Token ID | 612 |
Feature activation | +4.69e-02 |
Pos logit contributions | |
ouses | +0.073 |
days | +0.061 |
packs | +0.061 |
atmeal | +0.060 |
wore | +0.059 |
Neg logit contributions | |
louder | -0.048 |
angrily | -0.046 |
harder | -0.046 |
loudly | -0.045 |
closer | -0.041 |
Token | and |
Token ID | 290 |
Feature activation | +3.83e-02 |
Pos logit contributions | |
days | +0.035 |
am | +0.034 |
wore | +0.034 |
packs | +0.033 |
ouses | +0.033 |
Neg logit contributions | |
louder | -0.035 |
angrily | -0.034 |
harder | -0.034 |
trigger | -0.033 |
loudly | -0.032 |
Token | her |
Token ID | 607 |
Feature activation | +1.88e-02 |
Pos logit contributions | |
days | +0.070 |
ouses | +0.063 |
packs | +0.059 |
am | +0.057 |
owers | +0.054 |
Neg logit contributions | |
louder | -0.068 |
harder | -0.068 |
angrily | -0.065 |
loudly | -0.065 |
beast | -0.058 |
Token | friend |
Token ID | 1545 |
Feature activation | +5.77e-03 |
Pos logit contributions | |
days | +0.037 |
am | +0.036 |
wore | +0.035 |
packs | +0.035 |
ouses | +0.035 |
Neg logit contributions | |
louder | -0.029 |
harder | -0.028 |
angrily | -0.028 |
trigger | -0.027 |
loudly | -0.026 |
Token | . |
Token ID | 13 |
Feature activation | +3.33e-02 |
Pos logit contributions | |
days | +0.011 |
am | +0.010 |
ouses | +0.010 |
packs | +0.010 |
wore | +0.010 |
Neg logit contributions | |
louder | -0.010 |
harder | -0.009 |
angrily | -0.009 |
loudly | -0.009 |
trigger | -0.008 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +3.71e-02 |
Pos logit contributions | |
days | +0.081 |
ouses | +0.072 |
atmeal | +0.069 |
packs | +0.069 |
kins | +0.068 |
Neg logit contributions | |
louder | -0.041 |
harder | -0.039 |
loudly | -0.039 |
angrily | -0.038 |
softly | -0.035 |
Token | Once |
Token ID | 7454 |
Feature activation | +8.26e-02 |
Pos logit contributions | |
ouses | +0.063 |
days | +0.060 |
wore | +0.053 |
packs | +0.053 |
wear | +0.053 |
Neg logit contributions | |
harder | -0.065 |
louder | -0.060 |
again | -0.060 |
beast | -0.059 |
angrily | -0.058 |
Token | upon |
Token ID | 2402 |
Feature activation | +1.93e-02 |
Pos logit contributions | |
days | +0.146 |
ouses | +0.146 |
wore | +0.128 |
bows | +0.125 |
atmeal | +0.125 |
Neg logit contributions | |
harder | -0.132 |
louder | -0.122 |
loudly | -0.119 |
closely | -0.117 |
angrily | -0.115 |
Token | a |
Token ID | 257 |
Feature activation | +3.30e-02 |
Pos logit contributions | |
ouses | +0.047 |
days | +0.047 |
packs | +0.045 |
wore | +0.044 |
am | +0.042 |
Neg logit contributions | |
louder | -0.021 |
harder | -0.021 |
angrily | -0.019 |
loudly | -0.019 |
beast | -0.016 |
Token | time |
Token ID | 640 |
Feature activation | +2.86e-02 |
Pos logit contributions | |
days | +0.056 |
ouses | +0.055 |
wore | +0.053 |
packs | +0.052 |
am | +0.051 |
Neg logit contributions | |
harder | -0.059 |
louder | -0.057 |
angrily | -0.056 |
loudly | -0.055 |
beast | -0.051 |
Token | , |
Token ID | 11 |
Feature activation | +1.90e-02 |
Pos logit contributions | |
ouses | +0.067 |
wore | +0.061 |
days | +0.061 |
packs | +0.059 |
wear | +0.057 |
Neg logit contributions | |
harder | -0.032 |
angrily | -0.031 |
louder | -0.030 |
loudly | -0.029 |
beast | -0.026 |
Token | there |
Token ID | 612 |
Feature activation | +3.84e-02 |
Pos logit contributions | |
ouses | +0.043 |
days | +0.038 |
packs | +0.037 |
atmeal | +0.036 |
wore | +0.035 |
Neg logit contributions | |
louder | -0.026 |
harder | -0.026 |
angrily | -0.025 |
loudly | -0.025 |
closer | -0.023 |
Token | They |
Token ID | 1119 |
Feature activation | +3.98e-02 |
Pos logit contributions | |
days | +0.059 |
wore | +0.057 |
ouses | +0.057 |
atmeal | +0.056 |
kins | +0.055 |
Neg logit contributions | |
louder | -0.040 |
angrily | -0.038 |
harder | -0.037 |
loudly | -0.035 |
Whoever | -0.032 |
Token | love |
Token ID | 1842 |
Feature activation | +9.32e-03 |
Pos logit contributions | |
days | +0.052 |
packs | +0.051 |
ouses | +0.050 |
am | +0.048 |
wore | +0.048 |
Neg logit contributions | |
louder | -0.085 |
harder | -0.084 |
angrily | -0.083 |
trigger | -0.080 |
loudly | -0.079 |
Token | Mom |
Token ID | 11254 |
Feature activation | +2.17e-02 |
Pos logit contributions | |
days | +0.015 |
am | +0.015 |
wore | +0.014 |
packs | +0.014 |
ouses | +0.014 |
Neg logit contributions | |
louder | -0.018 |
harder | -0.017 |
angrily | -0.017 |
trigger | -0.016 |
loudly | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | +3.21e-02 |
Pos logit contributions | |
days | +0.045 |
am | +0.044 |
ouses | +0.043 |
packs | +0.043 |
wore | +0.042 |
Neg logit contributions | |
louder | -0.030 |
harder | -0.030 |
angrily | -0.029 |
loudly | -0.027 |
beast | -0.024 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +4.20e-02 |
Pos logit contributions | |
atmeal | +0.072 |
days | +0.071 |
kins | +0.071 |
ouses | +0.070 |
kin | +0.069 |
Neg logit contributions | |
louder | -0.036 |
angrily | -0.032 |
harder | -0.032 |
loudly | -0.030 |
Whoever | -0.026 |
Token | Once |
Token ID | 7454 |
Feature activation | +8.25e-02 |
Pos logit contributions | |
ouses | +0.064 |
days | +0.061 |
wore | +0.056 |
wear | +0.054 |
packs | +0.054 |
Neg logit contributions | |
harder | -0.079 |
louder | -0.076 |
beast | -0.074 |
angrily | -0.073 |
again | -0.070 |
Token | upon |
Token ID | 2402 |
Feature activation | +1.91e-02 |
Pos logit contributions | |
days | +0.142 |
ouses | +0.141 |
wore | +0.126 |
am | +0.123 |
atmeal | +0.120 |
Neg logit contributions | |
harder | -0.135 |
louder | -0.125 |
loudly | -0.122 |
closely | -0.122 |
angrily | -0.120 |
Token | a |
Token ID | 257 |
Feature activation | +3.16e-02 |
Pos logit contributions | |
ouses | +0.046 |
days | +0.045 |
packs | +0.044 |
wore | +0.043 |
am | +0.042 |
Neg logit contributions | |
louder | -0.021 |
harder | -0.021 |
angrily | -0.019 |
loudly | -0.018 |
beast | -0.016 |
Token | time |
Token ID | 640 |
Feature activation | +3.44e-02 |
Pos logit contributions | |
days | +0.053 |
ouses | +0.052 |
wore | +0.050 |
packs | +0.049 |
am | +0.049 |
Neg logit contributions | |
harder | -0.057 |
louder | -0.056 |
angrily | -0.055 |
loudly | -0.053 |
beast | -0.050 |
Token | , |
Token ID | 11 |
Feature activation | +2.55e-02 |
Pos logit contributions | |
ouses | +0.080 |
wore | +0.073 |
days | +0.073 |
packs | +0.071 |
wear | +0.068 |
Neg logit contributions | |
harder | -0.038 |
angrily | -0.038 |
louder | -0.036 |
loudly | -0.035 |
beast | -0.030 |
Token | there |
Token ID | 612 |
Feature activation | +4.46e-02 |
Pos logit contributions | |
ouses | +0.059 |
days | +0.051 |
atmeal | +0.049 |
packs | +0.049 |
parties | +0.047 |
Neg logit contributions | |
louder | -0.034 |
angrily | -0.034 |
harder | -0.034 |
loudly | -0.033 |
closer | -0.031 |
Token | in |
Token ID | 287 |
Feature activation | +6.13e-02 |
Pos logit contributions | |
days | +0.040 |
am | +0.040 |
wore | +0.040 |
packs | +0.038 |
ouses | +0.037 |
Neg logit contributions | |
trigger | -0.038 |
louder | -0.037 |
angrily | -0.037 |
harder | -0.036 |
amus | -0.036 |
Token | the |
Token ID | 262 |
Feature activation | +1.32e-02 |
Pos logit contributions | |
ouses | +0.112 |
days | +0.110 |
wore | +0.104 |
am | +0.104 |
packs | +0.102 |
Neg logit contributions | |
louder | -0.101 |
harder | -0.098 |
angrily | -0.096 |
loudly | -0.094 |
beast | -0.092 |
Token | office |
Token ID | 2607 |
Feature activation | +2.27e-02 |
Pos logit contributions | |
am | +0.022 |
days | +0.022 |
wore | +0.021 |
packs | +0.020 |
wear | +0.019 |
Neg logit contributions | |
trigger | -0.025 |
angrily | -0.025 |
louder | -0.024 |
harder | -0.023 |
amus | -0.023 |
Token | . |
Token ID | 13 |
Feature activation | +2.72e-02 |
Pos logit contributions | |
days | +0.036 |
wore | +0.035 |
am | +0.035 |
packs | +0.033 |
ouses | +0.033 |
Neg logit contributions | |
trigger | -0.043 |
louder | -0.043 |
angrily | -0.042 |
harder | -0.042 |
amus | -0.041 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +4.01e-02 |
Pos logit contributions | |
days | +0.052 |
packs | +0.049 |
wore | +0.048 |
ouses | +0.047 |
am | +0.047 |
Neg logit contributions | |
angrily | -0.043 |
harder | -0.041 |
louder | -0.041 |
cautiously | -0.038 |
loudly | -0.038 |
Token | Once |
Token ID | 7454 |
Feature activation | +8.24e-02 |
Pos logit contributions | |
ouses | +0.059 |
days | +0.058 |
wore | +0.054 |
wear | +0.053 |
packs | +0.053 |
Neg logit contributions | |
harder | -0.075 |
angrily | -0.075 |
louder | -0.073 |
beast | -0.069 |
loudly | -0.069 |
Token | upon |
Token ID | 2402 |
Feature activation | +1.94e-02 |
Pos logit contributions | |
ouses | +0.138 |
days | +0.135 |
wore | +0.125 |
am | +0.123 |
atmeal | +0.121 |
Neg logit contributions | |
harder | -0.136 |
louder | -0.128 |
curiously | -0.128 |
angrily | -0.127 |
loudly | -0.125 |
Token | a |
Token ID | 257 |
Feature activation | +2.76e-02 |
Pos logit contributions | |
days | +0.043 |
ouses | +0.042 |
packs | +0.041 |
wore | +0.041 |
am | +0.041 |
Neg logit contributions | |
louder | -0.025 |
harder | -0.024 |
angrily | -0.023 |
loudly | -0.022 |
trigger | -0.020 |
Token | time |
Token ID | 640 |
Feature activation | +3.01e-02 |
Pos logit contributions | |
days | +0.041 |
ouses | +0.040 |
am | +0.040 |
wore | +0.039 |
packs | +0.039 |
Neg logit contributions | |
louder | -0.054 |
harder | -0.054 |
angrily | -0.053 |
loudly | -0.051 |
beast | -0.049 |
Token | , |
Token ID | 11 |
Feature activation | +1.71e-02 |
Pos logit contributions | |
ouses | +0.059 |
days | +0.057 |
wore | +0.057 |
packs | +0.056 |
am | +0.054 |
Neg logit contributions | |
angrily | -0.043 |
louder | -0.043 |
harder | -0.043 |
loudly | -0.041 |
beast | -0.037 |
Token | there |
Token ID | 612 |
Feature activation | +3.45e-02 |
Pos logit contributions | |
ouses | +0.034 |
days | +0.031 |
packs | +0.030 |
wore | +0.029 |
am | +0.029 |
Neg logit contributions | |
louder | -0.027 |
harder | -0.027 |
angrily | -0.027 |
loudly | -0.026 |
closer | -0.023 |
Token | dress |
Token ID | 6576 |
Feature activation | +3.47e-02 |
Pos logit contributions | |
days | +0.041 |
am | +0.038 |
packs | +0.036 |
ouses | +0.035 |
wore | +0.034 |
Neg logit contributions | |
harder | -0.033 |
louder | -0.032 |
trigger | -0.031 |
angrily | -0.030 |
throttle | -0.030 |
Token | and |
Token ID | 290 |
Feature activation | +4.69e-02 |
Pos logit contributions | |
days | +0.062 |
am | +0.061 |
wore | +0.060 |
packs | +0.059 |
ouses | +0.058 |
Neg logit contributions | |
louder | -0.059 |
angrily | -0.057 |
harder | -0.057 |
trigger | -0.056 |
loudly | -0.053 |
Token | chain |
Token ID | 6333 |
Feature activation | +1.18e-02 |
Pos logit contributions | |
days | +0.087 |
packs | +0.082 |
am | +0.078 |
ouses | +0.078 |
owers | +0.076 |
Neg logit contributions | |
louder | -0.080 |
harder | -0.076 |
loudly | -0.069 |
instructions | -0.065 |
faster | -0.065 |
Token | . |
Token ID | 13 |
Feature activation | +2.40e-02 |
Pos logit contributions | |
days | +0.019 |
wore | +0.019 |
am | +0.019 |
packs | +0.018 |
ouses | +0.018 |
Neg logit contributions | |
louder | -0.022 |
angrily | -0.021 |
trigger | -0.021 |
harder | -0.021 |
beast | -0.020 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +4.01e-02 |
Pos logit contributions | |
packs | +0.051 |
days | +0.050 |
ouses | +0.048 |
am | +0.047 |
kins | +0.046 |
Neg logit contributions | |
loudly | -0.030 |
angrily | -0.028 |
louder | -0.028 |
harder | -0.028 |
curiously | -0.025 |
Token | Once |
Token ID | 7454 |
Feature activation | +8.21e-02 |
Pos logit contributions | |
ouses | +0.077 |
days | +0.074 |
packs | +0.071 |
wore | +0.069 |
wear | +0.067 |
Neg logit contributions | |
harder | -0.062 |
louder | -0.058 |
angrily | -0.058 |
loudly | -0.054 |
again | -0.053 |
Token | upon |
Token ID | 2402 |
Feature activation | +1.84e-02 |
Pos logit contributions | |
ouses | +0.140 |
days | +0.137 |
am | +0.125 |
wore | +0.123 |
bows | +0.121 |
Neg logit contributions | |
harder | -0.138 |
louder | -0.130 |
loudly | -0.124 |
curiously | -0.124 |
angrily | -0.123 |
Token | a |
Token ID | 257 |
Feature activation | +3.27e-02 |
Pos logit contributions | |
days | +0.042 |
ouses | +0.041 |
packs | +0.040 |
wore | +0.040 |
am | +0.040 |
Neg logit contributions | |
louder | -0.023 |
harder | -0.022 |
angrily | -0.021 |
loudly | -0.020 |
trigger | -0.018 |
Token | time |
Token ID | 640 |
Feature activation | +2.90e-02 |
Pos logit contributions | |
days | +0.054 |
ouses | +0.053 |
packs | +0.051 |
am | +0.051 |
wore | +0.051 |
Neg logit contributions | |
harder | -0.059 |
louder | -0.058 |
angrily | -0.058 |
loudly | -0.056 |
beast | -0.051 |
Token | , |
Token ID | 11 |
Feature activation | +2.12e-02 |
Pos logit contributions | |
ouses | +0.066 |
days | +0.062 |
wore | +0.060 |
packs | +0.059 |
wear | +0.057 |
Neg logit contributions | |
harder | -0.034 |
angrily | -0.034 |
louder | -0.033 |
loudly | -0.032 |
beast | -0.028 |
Token | there |
Token ID | 612 |
Feature activation | +3.49e-02 |
Pos logit contributions | |
ouses | +0.047 |
days | +0.041 |
packs | +0.040 |
wore | +0.037 |
atmeal | +0.037 |
Neg logit contributions | |
louder | -0.031 |
harder | -0.031 |
loudly | -0.029 |
angrily | -0.029 |
closer | -0.027 |
Token | good |
Token ID | 922 |
Feature activation | +1.30e-02 |
Pos logit contributions | |
louder | +0.020 |
harder | +0.020 |
angrily | +0.019 |
trigger | +0.018 |
loudly | +0.018 |
Neg logit contributions | |
days | -0.020 |
packs | -0.020 |
ouses | -0.019 |
wore | -0.019 |
am | -0.019 |
Token | time |
Token ID | 640 |
Feature activation | +2.66e-02 |
Pos logit contributions | |
days | +0.018 |
ouses | +0.017 |
packs | +0.017 |
am | +0.017 |
wore | +0.016 |
Neg logit contributions | |
harder | -0.027 |
louder | -0.026 |
angrily | -0.025 |
loudly | -0.024 |
trigger | -0.024 |
Token | together |
Token ID | 1978 |
Feature activation | +2.30e-02 |
Pos logit contributions | |
days | +0.038 |
am | +0.037 |
wore | +0.036 |
packs | +0.036 |
ouses | +0.035 |
Neg logit contributions | |
louder | -0.055 |
angrily | -0.053 |
harder | -0.053 |
trigger | -0.051 |
loudly | -0.051 |
Token | . |
Token ID | 13 |
Feature activation | +2.12e-02 |
Pos logit contributions | |
days | +0.041 |
am | +0.040 |
ouses | +0.039 |
packs | +0.039 |
wore | +0.038 |
Neg logit contributions | |
louder | -0.039 |
harder | -0.038 |
angrily | -0.038 |
loudly | -0.036 |
trigger | -0.035 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +4.29e-02 |
Pos logit contributions | |
days | +0.041 |
am | +0.040 |
packs | +0.039 |
ouses | +0.037 |
wore | +0.036 |
Neg logit contributions | |
louder | -0.032 |
harder | -0.032 |
angrily | -0.031 |
loudly | -0.030 |
Whoever | -0.027 |
Token | Once |
Token ID | 7454 |
Feature activation | +8.17e-02 |
Pos logit contributions | |
days | +0.075 |
ouses | +0.074 |
packs | +0.070 |
wore | +0.070 |
wear | +0.066 |
Neg logit contributions | |
harder | -0.072 |
angrily | -0.070 |
louder | -0.070 |
loudly | -0.065 |
beast | -0.063 |
Token | upon |
Token ID | 2402 |
Feature activation | +2.34e-02 |
Pos logit contributions | |
days | +0.132 |
ouses | +0.129 |
am | +0.123 |
wore | +0.118 |
packs | +0.115 |
Neg logit contributions | |
harder | -0.145 |
louder | -0.139 |
loudly | -0.132 |
angrily | -0.131 |
sadly | -0.128 |
Token | a |
Token ID | 257 |
Feature activation | +3.19e-02 |
Pos logit contributions | |
days | +0.054 |
ouses | +0.054 |
packs | +0.053 |
wore | +0.052 |
am | +0.051 |
Neg logit contributions | |
louder | -0.028 |
harder | -0.027 |
angrily | -0.025 |
loudly | -0.025 |
trigger | -0.021 |
Token | time |
Token ID | 640 |
Feature activation | +3.54e-02 |
Pos logit contributions | |
days | +0.051 |
ouses | +0.049 |
am | +0.048 |
packs | +0.048 |
wore | +0.048 |
Neg logit contributions | |
harder | -0.060 |
louder | -0.059 |
angrily | -0.059 |
loudly | -0.057 |
beast | -0.053 |
Token | , |
Token ID | 11 |
Feature activation | +2.27e-02 |
Pos logit contributions | |
ouses | +0.076 |
days | +0.072 |
wore | +0.071 |
packs | +0.068 |
wear | +0.067 |
Neg logit contributions | |
harder | -0.045 |
angrily | -0.045 |
louder | -0.044 |
loudly | -0.042 |
beast | -0.038 |
Token | there |
Token ID | 612 |
Feature activation | +3.65e-02 |
Pos logit contributions | |
ouses | +0.047 |
days | +0.042 |
packs | +0.041 |
wore | +0.039 |
am | +0.038 |
Neg logit contributions | |
louder | -0.036 |
harder | -0.035 |
angrily | -0.033 |
loudly | -0.033 |
closer | -0.030 |
Token | you |
Token ID | 345 |
Feature activation | +5.58e-03 |
Pos logit contributions | |
louder | +0.001 |
angrily | +0.001 |
harder | +0.001 |
trigger | +0.001 |
loudly | +0.001 |
Neg logit contributions | |
days | -0.001 |
am | -0.001 |
wore | -0.001 |
packs | -0.001 |
ouses | -0.001 |
Token | , |
Token ID | 11 |
Feature activation | -2.46e-02 |
Pos logit contributions | |
days | +0.008 |
am | +0.007 |
wore | +0.007 |
ouses | +0.007 |
packs | +0.007 |
Neg logit contributions | |
trigger | -0.012 |
angrily | -0.011 |
louder | -0.011 |
harder | -0.011 |
throttle | -0.011 |
Token | Daisy |
Token ID | 40355 |
Feature activation | +5.93e-03 |
Pos logit contributions | |
trigger | +0.048 |
angrily | +0.048 |
louder | +0.047 |
harder | +0.047 |
throttle | +0.046 |
Neg logit contributions | |
wore | -0.036 |
am | -0.035 |
days | -0.034 |
wear | -0.033 |
packs | -0.031 |
Token | . |
Token ID | 13 |
Feature activation | +2.81e-02 |
Pos logit contributions | |
days | +0.011 |
am | +0.010 |
packs | +0.010 |
wore | +0.010 |
ouses | +0.010 |
Neg logit contributions | |
louder | -0.010 |
angrily | -0.009 |
harder | -0.009 |
trigger | -0.009 |
loudly | -0.009 |
Token | You |
Token ID | 921 |
Feature activation | +5.01e-02 |
Pos logit contributions | |
packs | +0.054 |
days | +0.051 |
ouses | +0.050 |
wore | +0.048 |
am | +0.048 |
Neg logit contributions | |
louder | -0.042 |
angrily | -0.040 |
harder | -0.040 |
amus | -0.039 |
trigger | -0.038 |
Token | really |
Token ID | 1107 |
Feature activation | +8.17e-02 |
Pos logit contributions | |
packs | +0.061 |
days | +0.058 |
ouses | +0.057 |
wore | +0.050 |
am | +0.049 |
Neg logit contributions | |
louder | -0.112 |
harder | -0.110 |
angrily | -0.107 |
amus | -0.105 |
trigger | -0.105 |
Token | have |
Token ID | 423 |
Feature activation | +1.92e-02 |
Pos logit contributions | |
packs | +0.133 |
ouses | +0.117 |
days | +0.110 |
wore | +0.099 |
am | +0.093 |
Neg logit contributions | |
harder | -0.158 |
louder | -0.158 |
angrily | -0.154 |
loudly | -0.151 |
beast | -0.144 |
Token | a |
Token ID | 257 |
Feature activation | +3.17e-03 |
Pos logit contributions | |
days | +0.035 |
packs | +0.033 |
am | +0.033 |
ouses | +0.033 |
wore | +0.032 |
Neg logit contributions | |
louder | -0.032 |
harder | -0.032 |
angrily | -0.031 |
loudly | -0.029 |
beast | -0.029 |
Token | talent |
Token ID | 7401 |
Feature activation | +2.39e-02 |
Pos logit contributions | |
am | +0.005 |
days | +0.005 |
wore | +0.005 |
ouses | +0.004 |
packs | +0.004 |
Neg logit contributions | |
trigger | -0.006 |
louder | -0.006 |
angrily | -0.006 |
harder | -0.006 |
amus | -0.006 |
Token | for |
Token ID | 329 |
Feature activation | +3.56e-02 |
Pos logit contributions | |
days | +0.045 |
packs | +0.044 |
am | +0.043 |
wore | +0.043 |
ouses | +0.042 |
Neg logit contributions | |
louder | -0.038 |
harder | -0.037 |
angrily | -0.036 |
loudly | -0.034 |
trigger | -0.034 |
Token | baking |
Token ID | 16871 |
Feature activation | +3.68e-02 |
Pos logit contributions | |
days | +0.057 |
am | +0.055 |
wore | +0.054 |
packs | +0.053 |
ouses | +0.052 |
Neg logit contributions | |
louder | -0.068 |
angrily | -0.066 |
trigger | -0.066 |
harder | -0.066 |
beast | -0.062 |
Token | you |
Token ID | 345 |
Feature activation | +2.30e-02 |
Pos logit contributions | |
days | +0.013 |
wore | +0.013 |
am | +0.013 |
wear | +0.012 |
packs | +0.012 |
Neg logit contributions | |
trigger | -0.014 |
angrily | -0.014 |
louder | -0.014 |
harder | -0.014 |
amus | -0.013 |
Token | so |
Token ID | 523 |
Feature activation | +3.88e-02 |
Pos logit contributions | |
days | +0.041 |
am | +0.040 |
wore | +0.040 |
packs | +0.039 |
ouses | +0.038 |
Neg logit contributions | |
louder | -0.039 |
angrily | -0.038 |
harder | -0.038 |
trigger | -0.037 |
loudly | -0.035 |
Token | much |
Token ID | 881 |
Feature activation | +2.66e-02 |
Pos logit contributions | |
days | +0.064 |
am | +0.063 |
packs | +0.063 |
wore | +0.062 |
ouses | +0.060 |
Neg logit contributions | |
louder | -0.071 |
angrily | -0.069 |
harder | -0.068 |
loudly | -0.066 |
trigger | -0.065 |
Token | !" |
Token ID | 2474 |
Feature activation | +2.41e-02 |
Pos logit contributions | |
days | +0.042 |
am | +0.041 |
wore | +0.041 |
packs | +0.039 |
ouses | +0.039 |
Neg logit contributions | |
louder | -0.050 |
angrily | -0.050 |
trigger | -0.050 |
harder | -0.048 |
amus | -0.047 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +3.37e-02 |
Pos logit contributions | |
am | +0.041 |
packs | +0.041 |
days | +0.040 |
ouses | +0.038 |
wore | +0.036 |
Neg logit contributions | |
louder | -0.040 |
angrily | -0.039 |
harder | -0.038 |
loudly | -0.038 |
curiously | -0.036 |
Token | Once |
Token ID | 7454 |
Feature activation | +8.17e-02 |
Pos logit contributions | |
days | +0.045 |
ouses | +0.044 |
packs | +0.041 |
wear | +0.040 |
wore | +0.039 |
Neg logit contributions | |
harder | -0.069 |
angrily | -0.069 |
louder | -0.069 |
beast | -0.066 |
trigger | -0.065 |
Token | upon |
Token ID | 2402 |
Feature activation | +1.52e-02 |
Pos logit contributions | |
ouses | +0.136 |
days | +0.134 |
am | +0.125 |
wore | +0.124 |
owers | +0.121 |
Neg logit contributions | |
harder | -0.138 |
louder | -0.133 |
curiously | -0.127 |
angrily | -0.127 |
loudly | -0.125 |
Token | a |
Token ID | 257 |
Feature activation | +3.14e-02 |
Pos logit contributions | |
days | +0.034 |
ouses | +0.033 |
packs | +0.033 |
wore | +0.032 |
am | +0.032 |
Neg logit contributions | |
louder | -0.019 |
harder | -0.019 |
angrily | -0.018 |
loudly | -0.017 |
trigger | -0.016 |
Token | time |
Token ID | 640 |
Feature activation | +3.32e-02 |
Pos logit contributions | |
days | +0.049 |
ouses | +0.047 |
am | +0.046 |
packs | +0.046 |
wore | +0.046 |
Neg logit contributions | |
harder | -0.060 |
louder | -0.060 |
angrily | -0.059 |
loudly | -0.057 |
beast | -0.054 |
Token | , |
Token ID | 11 |
Feature activation | +2.02e-02 |
Pos logit contributions | |
ouses | +0.067 |
days | +0.064 |
wore | +0.063 |
packs | +0.062 |
am | +0.060 |
Neg logit contributions | |
angrily | -0.047 |
louder | -0.047 |
harder | -0.047 |
loudly | -0.044 |
beast | -0.041 |
Token | there |
Token ID | 612 |
Feature activation | +3.54e-02 |
Pos logit contributions | |
ouses | +0.038 |
days | +0.035 |
packs | +0.034 |
wore | +0.033 |
am | +0.033 |
Neg logit contributions | |
louder | -0.035 |
harder | -0.034 |
angrily | -0.033 |
loudly | -0.033 |
trigger | -0.029 |
Token | sun |
Token ID | 4252 |
Feature activation | +5.27e-02 |
Pos logit contributions | |
days | +0.061 |
ouses | +0.059 |
am | +0.058 |
packs | +0.057 |
wore | +0.055 |
Neg logit contributions | |
louder | -0.050 |
harder | -0.047 |
angrily | -0.047 |
loudly | -0.045 |
trigger | -0.043 |
Token | fl |
Token ID | 2704 |
Feature activation | +7.83e-02 |
Pos logit contributions | |
days | +0.081 |
ouses | +0.078 |
am | +0.077 |
wore | +0.074 |
packs | +0.072 |
Neg logit contributions | |
louder | -0.098 |
harder | -0.094 |
angrily | -0.093 |
loudly | -0.090 |
trigger | -0.089 |
Token | owers |
Token ID | 3618 |
Feature activation | +5.46e-02 |
Pos logit contributions | |
days | +0.077 |
wore | +0.074 |
am | +0.072 |
wear | +0.070 |
ouses | +0.066 |
Neg logit contributions | |
angrily | -0.175 |
louder | -0.174 |
rus | -0.170 |
amus | -0.169 |
loudly | -0.169 |
Token | , |
Token ID | 11 |
Feature activation | +3.23e-02 |
Pos logit contributions | |
days | +0.106 |
ouses | +0.105 |
packs | +0.100 |
am | +0.096 |
wore | +0.095 |
Neg logit contributions | |
louder | -0.078 |
harder | -0.075 |
angrily | -0.075 |
loudly | -0.072 |
cautiously | -0.065 |
Token | and |
Token ID | 290 |
Feature activation | +4.05e-02 |
Pos logit contributions | |
days | +0.069 |
am | +0.066 |
ouses | +0.066 |
packs | +0.065 |
wore | +0.064 |
Neg logit contributions | |
louder | -0.046 |
harder | -0.043 |
angrily | -0.043 |
loudly | -0.041 |
trigger | -0.039 |
Token | tul |
Token ID | 48373 |
Feature activation | +8.15e-02 |
Pos logit contributions | |
days | +0.076 |
ouses | +0.073 |
am | +0.072 |
packs | +0.071 |
wore | +0.069 |
Neg logit contributions | |
louder | -0.069 |
harder | -0.065 |
angrily | -0.064 |
loudly | -0.061 |
trigger | -0.059 |
Token | ips |
Token ID | 2419 |
Feature activation | +4.55e-02 |
Pos logit contributions | |
days | +0.136 |
am | +0.133 |
wore | +0.123 |
packs | +0.118 |
wear | +0.117 |
Neg logit contributions | |
louder | -0.133 |
harder | -0.133 |
angrily | -0.128 |
iously | -0.123 |
amus | -0.122 |
Token | . |
Token ID | 13 |
Feature activation | +2.29e-02 |
Pos logit contributions | |
days | +0.077 |
am | +0.075 |
wore | +0.074 |
packs | +0.073 |
ouses | +0.072 |
Neg logit contributions | |
louder | -0.081 |
angrily | -0.079 |
harder | -0.078 |
trigger | -0.077 |
loudly | -0.074 |
Token | They |
Token ID | 1119 |
Feature activation | +4.74e-02 |
Pos logit contributions | |
days | +0.032 |
am | +0.030 |
wore | +0.030 |
ouses | +0.030 |
packs | +0.029 |
Neg logit contributions | |
louder | -0.048 |
angrily | -0.047 |
harder | -0.046 |
trigger | -0.045 |
loudly | -0.045 |
Token | see |
Token ID | 766 |
Feature activation | -1.28e-03 |
Pos logit contributions | |
ouses | +0.072 |
days | +0.071 |
packs | +0.068 |
ained | +0.059 |
am | +0.059 |
Neg logit contributions | |
louder | -0.094 |
harder | -0.092 |
angrily | -0.089 |
loudly | -0.087 |
cautiously | -0.083 |
Token | pine |
Token ID | 20161 |
Feature activation | +4.07e-02 |
Pos logit contributions | |
louder | +0.002 |
angrily | +0.002 |
harder | +0.002 |
trigger | +0.002 |
loudly | +0.002 |
Neg logit contributions | |
days | -0.002 |
am | -0.002 |
wore | -0.002 |
packs | -0.002 |
ouses | -0.002 |
Token | here |
Token ID | 994 |
Feature activation | +8.85e-04 |
Pos logit contributions | |
days | +0.033 |
am | +0.032 |
ouses | +0.032 |
packs | +0.032 |
wore | +0.032 |
Neg logit contributions | |
louder | -0.029 |
harder | -0.028 |
angrily | -0.028 |
loudly | -0.026 |
trigger | -0.026 |
Token | for |
Token ID | 329 |
Feature activation | +1.29e-02 |
Pos logit contributions | |
days | +0.002 |
am | +0.002 |
packs | +0.002 |
wore | +0.002 |
ouses | +0.002 |
Neg logit contributions | |
louder | -0.001 |
harder | -0.001 |
angrily | -0.001 |
loudly | -0.001 |
trigger | -0.001 |
Token | you |
Token ID | 345 |
Feature activation | +2.00e-02 |
Pos logit contributions | |
days | +0.023 |
am | +0.022 |
wore | +0.022 |
wear | +0.021 |
packs | +0.021 |
Neg logit contributions | |
trigger | -0.023 |
angrily | -0.022 |
louder | -0.022 |
harder | -0.021 |
beast | -0.021 |
Token | ." |
Token ID | 526 |
Feature activation | +3.11e-02 |
Pos logit contributions | |
days | +0.034 |
am | +0.032 |
wore | +0.031 |
packs | +0.031 |
ouses | +0.030 |
Neg logit contributions | |
trigger | -0.037 |
louder | -0.037 |
angrily | -0.037 |
harder | -0.036 |
beast | -0.035 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +3.22e-02 |
Pos logit contributions | |
days | +0.056 |
am | +0.054 |
packs | +0.052 |
wore | +0.049 |
ouses | +0.049 |
Neg logit contributions | |
louder | -0.052 |
harder | -0.052 |
angrily | -0.050 |
loudly | -0.046 |
curiously | -0.044 |
Token | Once |
Token ID | 7454 |
Feature activation | +8.15e-02 |
Pos logit contributions | |
days | +0.046 |
ouses | +0.046 |
packs | +0.041 |
wear | +0.040 |
wore | +0.040 |
Neg logit contributions | |
harder | -0.062 |
angrily | -0.062 |
louder | -0.061 |
beast | -0.060 |
loudly | -0.057 |
Token | upon |
Token ID | 2402 |
Feature activation | +1.57e-02 |
Pos logit contributions | |
days | +0.133 |
ouses | +0.133 |
am | +0.122 |
wore | +0.120 |
packs | +0.114 |
Neg logit contributions | |
harder | -0.142 |
louder | -0.135 |
angrily | -0.130 |
curiously | -0.129 |
loudly | -0.128 |
Token | a |
Token ID | 257 |
Feature activation | +2.94e-02 |
Pos logit contributions | |
days | +0.034 |
ouses | +0.033 |
packs | +0.032 |
am | +0.032 |
wore | +0.032 |
Neg logit contributions | |
louder | -0.021 |
harder | -0.020 |
angrily | -0.020 |
loudly | -0.019 |
trigger | -0.019 |
Token | time |
Token ID | 640 |
Feature activation | +3.22e-02 |
Pos logit contributions | |
days | +0.046 |
ouses | +0.044 |
am | +0.043 |
packs | +0.043 |
wore | +0.043 |
Neg logit contributions | |
harder | -0.056 |
louder | -0.056 |
angrily | -0.055 |
loudly | -0.053 |
beast | -0.050 |
Token | there |
Token ID | 612 |
Feature activation | +3.56e-02 |
Pos logit contributions | |
ouses | +0.064 |
days | +0.062 |
wore | +0.061 |
packs | +0.060 |
am | +0.059 |
Neg logit contributions | |
louder | -0.046 |
angrily | -0.046 |
harder | -0.046 |
loudly | -0.044 |
beast | -0.040 |
Token | was |
Token ID | 373 |
Feature activation | -2.97e-03 |
Pos logit contributions | |
ouses | +0.083 |
packs | +0.077 |
days | +0.075 |
wore | +0.068 |
aj | +0.068 |
Neg logit contributions | |
angrily | -0.044 |
harder | -0.042 |
beast | -0.040 |
loudly | -0.040 |
louder | -0.039 |
Token | would |
Token ID | 561 |
Feature activation | -2.54e-03 |
Pos logit contributions | |
days | +0.018 |
am | +0.018 |
wore | +0.018 |
packs | +0.017 |
ouses | +0.016 |
Neg logit contributions | |
louder | -0.037 |
trigger | -0.036 |
harder | -0.036 |
angrily | -0.036 |
amus | -0.035 |
Token | be |
Token ID | 307 |
Feature activation | -5.29e-04 |
Pos logit contributions | |
louder | +0.005 |
angrily | +0.005 |
trigger | +0.005 |
harder | +0.005 |
beast | +0.005 |
Neg logit contributions | |
am | -0.004 |
days | -0.004 |
wore | -0.004 |
wear | -0.004 |
packs | -0.003 |
Token | ok |
Token ID | 12876 |
Feature activation | +1.07e-03 |
Pos logit contributions | |
louder | +0.001 |
angrily | +0.001 |
harder | +0.001 |
trigger | +0.001 |
loudly | +0.001 |
Neg logit contributions | |
days | -0.001 |
am | -0.001 |
wore | -0.001 |
packs | -0.001 |
ouses | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | +2.80e-02 |
Pos logit contributions | |
days | +0.002 |
am | +0.002 |
wore | +0.002 |
packs | +0.002 |
ouses | +0.002 |
Neg logit contributions | |
trigger | -0.002 |
louder | -0.002 |
angrily | -0.002 |
harder | -0.002 |
amus | -0.002 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +4.09e-02 |
Pos logit contributions | |
days | +0.044 |
wore | +0.044 |
am | +0.043 |
packs | +0.043 |
ouses | +0.042 |
Neg logit contributions | |
angrily | -0.052 |
louder | -0.052 |
harder | -0.050 |
loudly | -0.047 |
cautiously | -0.046 |
Token | Once |
Token ID | 7454 |
Feature activation | +8.14e-02 |
Pos logit contributions | |
ouses | +0.055 |
days | +0.055 |
wear | +0.050 |
packs | +0.050 |
wore | +0.050 |
Neg logit contributions | |
angrily | -0.081 |
harder | -0.081 |
louder | -0.079 |
beast | -0.076 |
trigger | -0.075 |
Token | there |
Token ID | 612 |
Feature activation | +4.70e-02 |
Pos logit contributions | |
days | +0.125 |
ouses | +0.124 |
am | +0.117 |
wore | +0.116 |
packs | +0.112 |
Neg logit contributions | |
harder | -0.146 |
louder | -0.141 |
angrily | -0.140 |
curiously | -0.138 |
loudly | -0.135 |
Token | was |
Token ID | 373 |
Feature activation | +9.50e-04 |
Pos logit contributions | |
ouses | +0.104 |
packs | +0.098 |
days | +0.094 |
wore | +0.088 |
wear | +0.087 |
Neg logit contributions | |
angrily | -0.062 |
harder | -0.059 |
louder | -0.055 |
curiously | -0.054 |
loudly | -0.054 |
Token | a |
Token ID | 257 |
Feature activation | -5.35e-03 |
Pos logit contributions | |
days | +0.002 |
ouses | +0.002 |
am | +0.002 |
wore | +0.002 |
packs | +0.002 |
Neg logit contributions | |
louder | -0.001 |
harder | -0.001 |
angrily | -0.001 |
loudly | -0.001 |
trigger | -0.001 |
Token | little |
Token ID | 1310 |
Feature activation | +1.43e-02 |
Pos logit contributions | |
angrily | +0.007 |
louder | +0.007 |
trigger | +0.007 |
harder | +0.007 |
amus | +0.007 |
Neg logit contributions | |
wore | -0.011 |
days | -0.011 |
am | -0.011 |
wear | -0.011 |
ouses | -0.011 |
Token | girl |
Token ID | 2576 |
Feature activation | +8.13e-03 |
Pos logit contributions | |
wore | +0.024 |
days | +0.023 |
am | +0.023 |
packs | +0.022 |
ouses | +0.022 |
Neg logit contributions | |
angrily | -0.026 |
louder | -0.025 |
harder | -0.025 |
trigger | -0.025 |
amus | -0.025 |
Token | in |
Token ID | 287 |
Feature activation | +3.77e-02 |
Pos logit contributions | |
days | +0.056 |
wore | +0.054 |
am | +0.054 |
packs | +0.054 |
ouses | +0.052 |
Neg logit contributions | |
louder | -0.064 |
trigger | -0.063 |
angrily | -0.063 |
harder | -0.062 |
amus | -0.059 |
Token | the |
Token ID | 262 |
Feature activation | -1.87e-03 |
Pos logit contributions | |
ouses | +0.072 |
days | +0.071 |
wore | +0.069 |
am | +0.068 |
packs | +0.066 |
Neg logit contributions | |
louder | -0.062 |
harder | -0.060 |
angrily | -0.058 |
beast | -0.055 |
loudly | -0.055 |
Token | park |
Token ID | 3952 |
Feature activation | +1.22e-02 |
Pos logit contributions | |
angrily | +0.004 |
trigger | +0.004 |
louder | +0.004 |
iously | +0.004 |
harder | +0.004 |
Neg logit contributions | |
am | -0.002 |
wore | -0.002 |
days | -0.002 |
packs | -0.002 |
wear | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | +2.78e-02 |
Pos logit contributions | |
days | +0.017 |
wore | +0.016 |
packs | +0.016 |
am | +0.016 |
ouses | +0.014 |
Neg logit contributions | |
trigger | -0.027 |
louder | -0.026 |
throttle | -0.025 |
harder | -0.025 |
angrily | -0.025 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +3.68e-02 |
Pos logit contributions | |
packs | +0.056 |
days | +0.055 |
ouses | +0.054 |
am | +0.053 |
kin | +0.052 |
Neg logit contributions | |
louder | -0.037 |
harder | -0.036 |
angrily | -0.034 |
loudly | -0.034 |
throttle | -0.032 |
Token | Once |
Token ID | 7454 |
Feature activation | +8.14e-02 |
Pos logit contributions | |
ouses | +0.061 |
days | +0.060 |
packs | +0.056 |
wore | +0.056 |
wear | +0.055 |
Neg logit contributions | |
harder | -0.064 |
angrily | -0.063 |
louder | -0.063 |
beast | -0.059 |
loudly | -0.059 |
Token | there |
Token ID | 612 |
Feature activation | +4.63e-02 |
Pos logit contributions | |
ouses | +0.137 |
days | +0.132 |
wore | +0.125 |
am | +0.124 |
bows | +0.123 |
Neg logit contributions | |
harder | -0.133 |
louder | -0.127 |
curiously | -0.123 |
loudly | -0.122 |
angrily | -0.122 |
Token | was |
Token ID | 373 |
Feature activation | -4.06e-03 |
Pos logit contributions | |
ouses | +0.117 |
packs | +0.108 |
days | +0.101 |
aj | +0.097 |
ectar | +0.095 |
Neg logit contributions | |
angrily | -0.049 |
harder | -0.046 |
louder | -0.042 |
loudly | -0.042 |
curiously | -0.042 |
Token | a |
Token ID | 257 |
Feature activation | -6.81e-03 |
Pos logit contributions | |
louder | +0.005 |
harder | +0.005 |
angrily | +0.005 |
loudly | +0.004 |
trigger | +0.004 |
Neg logit contributions | |
days | -0.009 |
ouses | -0.009 |
am | -0.009 |
wore | -0.009 |
packs | -0.009 |
Token | little |
Token ID | 1310 |
Feature activation | +1.65e-02 |
Pos logit contributions | |
angrily | +0.009 |
louder | +0.009 |
trigger | +0.009 |
harder | +0.009 |
amus | +0.008 |
Neg logit contributions | |
wore | -0.014 |
am | -0.014 |
days | -0.014 |
wear | -0.014 |
ouses | -0.014 |
Token | star |
Token ID | 3491 |
Feature activation | +4.71e-03 |
Pos logit contributions | |
wore | +0.028 |
days | +0.028 |
am | +0.027 |
packs | +0.026 |
ouses | +0.026 |
Neg logit contributions | |
angrily | -0.029 |
louder | -0.029 |
harder | -0.028 |
trigger | -0.028 |
amus | -0.028 |
Token | she |
Token ID | 673 |
Feature activation | +4.30e-02 |
Pos logit contributions | |
days | +0.005 |
wore | +0.005 |
am | +0.005 |
packs | +0.005 |
ouses | +0.005 |
Neg logit contributions | |
trigger | -0.011 |
angrily | -0.011 |
louder | -0.011 |
harder | -0.010 |
beast | -0.010 |
Token | is |
Token ID | 318 |
Feature activation | +3.84e-02 |
Pos logit contributions | |
days | +0.069 |
packs | +0.064 |
ouses | +0.060 |
am | +0.055 |
wore | +0.054 |
Neg logit contributions | |
harder | -0.079 |
louder | -0.078 |
angrily | -0.077 |
loudly | -0.072 |
beast | -0.071 |
Token | the |
Token ID | 262 |
Feature activation | +2.76e-02 |
Pos logit contributions | |
days | +0.084 |
packs | +0.083 |
ouses | +0.080 |
am | +0.078 |
akes | +0.073 |
Neg logit contributions | |
louder | -0.058 |
harder | -0.053 |
loudly | -0.048 |
angrily | -0.048 |
amus | -0.044 |
Token | richest |
Token ID | 24348 |
Feature activation | +2.22e-02 |
Pos logit contributions | |
days | +0.041 |
am | +0.040 |
wore | +0.040 |
packs | +0.039 |
ouses | +0.038 |
Neg logit contributions | |
louder | -0.055 |
angrily | -0.054 |
harder | -0.053 |
trigger | -0.053 |
loudly | -0.051 |
Token | girl |
Token ID | 2576 |
Feature activation | +4.84e-02 |
Pos logit contributions | |
days | +0.045 |
am | +0.043 |
ouses | +0.043 |
packs | +0.041 |
wore | +0.041 |
Neg logit contributions | |
louder | -0.032 |
harder | -0.031 |
angrily | -0.029 |
trigger | -0.028 |
beast | -0.028 |
Token | in |
Token ID | 287 |
Feature activation | +8.13e-02 |
Pos logit contributions | |
days | +0.090 |
ouses | +0.087 |
packs | +0.086 |
am | +0.085 |
wore | +0.080 |
Neg logit contributions | |
louder | -0.072 |
angrily | -0.070 |
harder | -0.070 |
loudly | -0.068 |
beast | -0.065 |
Token | the |
Token ID | 262 |
Feature activation | +2.91e-02 |
Pos logit contributions | |
ouses | +0.187 |
days | +0.177 |
am | +0.166 |
atmeal | +0.163 |
wore | +0.160 |
Neg logit contributions | |
louder | -0.092 |
harder | -0.091 |
loudly | -0.084 |
beast | -0.082 |
angrily | -0.081 |
Token | school |
Token ID | 1524 |
Feature activation | +4.91e-02 |
Pos logit contributions | |
days | +0.038 |
am | +0.037 |
wore | +0.036 |
packs | +0.036 |
ouses | +0.035 |
Neg logit contributions | |
louder | -0.063 |
harder | -0.062 |
angrily | -0.061 |
trigger | -0.060 |
loudly | -0.058 |
Token | . |
Token ID | 13 |
Feature activation | +3.04e-02 |
Pos logit contributions | |
days | +0.086 |
am | +0.084 |
packs | +0.083 |
ouses | +0.083 |
wore | +0.082 |
Neg logit contributions | |
louder | -0.081 |
harder | -0.079 |
angrily | -0.077 |
loudly | -0.074 |
beast | -0.072 |
Token |
|
Token ID | 198 |
Feature activation | +2.54e-02 |
Pos logit contributions | |
days | +0.062 |
ouses | +0.056 |
packs | +0.055 |
wore | +0.053 |
am | +0.051 |
Neg logit contributions | |
angrily | -0.048 |
louder | -0.047 |
loudly | -0.045 |
harder | -0.044 |
softly | -0.040 |
Token |
|
Token ID | 198 |
Feature activation | +1.21e-02 |
Pos logit contributions | |
days | +0.043 |
ouses | +0.041 |
packs | +0.040 |
wore | +0.040 |
am | +0.038 |
Neg logit contributions | |
angrily | -0.045 |
harder | -0.045 |
louder | -0.045 |
loudly | -0.043 |
amus | -0.040 |
Token | . |
Token ID | 13 |
Feature activation | +1.34e-02 |
Pos logit contributions | |
beast | +0.087 |
amus | +0.085 |
throttle | +0.083 |
ote | +0.081 |
zee | +0.080 |
Neg logit contributions | |
am | -0.037 |
packs | -0.035 |
wore | -0.033 |
wear | -0.030 |
days | -0.028 |
Token | The |
Token ID | 383 |
Feature activation | -3.18e-02 |
Pos logit contributions | |
am | +0.017 |
wore | +0.017 |
days | +0.016 |
ouses | +0.016 |
packs | +0.016 |
Neg logit contributions | |
louder | -0.029 |
trigger | -0.028 |
harder | -0.028 |
angrily | -0.028 |
beast | -0.028 |
Token | toy |
Token ID | 13373 |
Feature activation | -3.87e-02 |
Pos logit contributions | |
angrily | +0.044 |
iously | +0.044 |
cautiously | +0.042 |
louder | +0.041 |
harder | +0.041 |
Neg logit contributions | |
am | -0.069 |
wore | -0.062 |
wear | -0.061 |
packs | -0.055 |
wears | -0.055 |
Token | gun |
Token ID | 2485 |
Feature activation | -5.37e-02 |
Pos logit contributions | |
iously | +0.054 |
louder | +0.053 |
angrily | +0.052 |
harder | +0.051 |
rier | +0.051 |
Neg logit contributions | |
wore | -0.080 |
am | -0.080 |
packs | -0.071 |
lived | -0.070 |
wear | -0.069 |
Token | made |
Token ID | 925 |
Feature activation | -4.56e-02 |
Pos logit contributions | |
amus | +0.108 |
louder | +0.105 |
adult | +0.105 |
beast | +0.103 |
ote | +0.102 |
Neg logit contributions | |
wore | -0.077 |
am | -0.075 |
wear | -0.064 |
lived | -0.060 |
wears | -0.060 |
Token | a |
Token ID | 257 |
Feature activation | -8.36e-02 |
Pos logit contributions | |
beast | +0.095 |
ote | +0.093 |
zee | +0.092 |
iously | +0.091 |
amus | +0.090 |
Neg logit contributions | |
am | -0.053 |
wear | -0.052 |
wore | -0.052 |
packs | -0.044 |
have | -0.041 |
Token | loud |
Token ID | 7812 |
Feature activation | -6.25e-02 |
Pos logit contributions | |
iously | +0.154 |
amus | +0.132 |
ote | +0.130 |
arted | +0.130 |
face | +0.128 |
Neg logit contributions | |
am | -0.141 |
have | -0.113 |
'm | -0.109 |
wear | -0.109 |
wore | -0.103 |
Token | noise |
Token ID | 7838 |
Feature activation | -3.96e-02 |
Pos logit contributions | |
amus | +0.098 |
zee | +0.092 |
rus | +0.092 |
throttle | +0.092 |
ote | +0.092 |
Neg logit contributions | |
am | -0.118 |
wear | -0.096 |
have | -0.096 |
wore | -0.092 |
are | -0.090 |
Token | and |
Token ID | 290 |
Feature activation | -6.18e-03 |
Pos logit contributions | |
amus | +0.084 |
trigger | +0.081 |
throttle | +0.080 |
rus | +0.077 |
angrily | +0.077 |
Neg logit contributions | |
am | -0.051 |
wore | -0.050 |
wear | -0.046 |
days | -0.045 |
packs | -0.041 |
Token | a |
Token ID | 257 |
Feature activation | -6.64e-02 |
Pos logit contributions | |
amus | +0.011 |
angrily | +0.011 |
throttle | +0.011 |
trigger | +0.011 |
beast | +0.011 |
Neg logit contributions | |
wore | -0.010 |
am | -0.009 |
wear | -0.008 |
packs | -0.008 |
days | -0.008 |
Token | plastic |
Token ID | 7309 |
Feature activation | -5.22e-02 |
Pos logit contributions | |
iously | +0.111 |
amus | +0.103 |
angrily | +0.094 |
zee | +0.091 |
harder | +0.091 |
Neg logit contributions | |
am | -0.129 |
wore | -0.107 |
'm | -0.106 |
wear | -0.102 |
have | -0.098 |
Token | . |
Token ID | 13 |
Feature activation | -4.12e-02 |
Pos logit contributions | |
throttle | +0.117 |
trigger | +0.114 |
amus | +0.114 |
rier | +0.111 |
louder | +0.110 |
Neg logit contributions | |
wore | -0.036 |
am | -0.035 |
packs | -0.034 |
days | -0.033 |
wear | -0.027 |
Token | The |
Token ID | 383 |
Feature activation | -2.40e-02 |
Pos logit contributions | |
louder | +0.095 |
harder | +0.092 |
trigger | +0.092 |
beast | +0.090 |
throttle | +0.090 |
Neg logit contributions | |
am | -0.047 |
wore | -0.046 |
days | -0.040 |
packs | -0.040 |
ouses | -0.038 |
Token | cat |
Token ID | 3797 |
Feature activation | -5.25e-02 |
Pos logit contributions | |
angrily | +0.045 |
iously | +0.042 |
amus | +0.041 |
louder | +0.041 |
harder | +0.041 |
Neg logit contributions | |
am | -0.041 |
wore | -0.037 |
days | -0.036 |
wear | -0.034 |
'm | -0.033 |
Token | tried |
Token ID | 3088 |
Feature activation | -5.04e-02 |
Pos logit contributions | |
trigger | +0.136 |
rier | +0.134 |
throttle | +0.131 |
lever | +0.126 |
louder | +0.124 |
Neg logit contributions | |
wore | -0.066 |
lived | -0.052 |
am | -0.048 |
had | -0.042 |
wear | -0.039 |
Token | to |
Token ID | 284 |
Feature activation | -3.72e-02 |
Pos logit contributions | |
trigger | +0.129 |
rier | +0.122 |
amus | +0.117 |
rus | +0.116 |
throttle | +0.115 |
Neg logit contributions | |
am | -0.056 |
wore | -0.051 |
wear | -0.047 |
'm | -0.043 |
packs | -0.043 |
Token | catch |
Token ID | 4929 |
Feature activation | -7.97e-02 |
Pos logit contributions | |
throttle | +0.076 |
rier | +0.074 |
angrily | +0.074 |
trigger | +0.072 |
der | +0.071 |
Neg logit contributions | |
am | -0.055 |
wear | -0.054 |
have | -0.044 |
live | -0.044 |
'm | -0.042 |
Token | them |
Token ID | 606 |
Feature activation | -4.04e-02 |
Pos logit contributions | |
throttle | +0.186 |
accelerator | +0.180 |
rier | +0.175 |
ote | +0.174 |
rus | +0.174 |
Neg logit contributions | |
am | -0.079 |
have | -0.065 |
wear | -0.060 |
live | -0.052 |
wore | -0.050 |
Token | , |
Token ID | 11 |
Feature activation | -2.20e-02 |
Pos logit contributions | |
trigger | +0.111 |
throttle | +0.110 |
beast | +0.109 |
amus | +0.106 |
accelerator | +0.105 |
Neg logit contributions | |
am | -0.030 |
wear | -0.024 |
days | -0.023 |
wore | -0.023 |
packs | -0.019 |
Token | but |
Token ID | 475 |
Feature activation | -8.22e-03 |
Pos logit contributions | |
trigger | +0.051 |
amus | +0.049 |
throttle | +0.048 |
rus | +0.047 |
beast | +0.047 |
Neg logit contributions | |
wore | -0.028 |
am | -0.024 |
wear | -0.023 |
days | -0.020 |
'm | -0.020 |
Token | they |
Token ID | 484 |
Feature activation | -1.55e-02 |
Pos logit contributions | |
louder | +0.015 |
angrily | +0.014 |
trigger | +0.014 |
harder | +0.014 |
amus | +0.014 |
Neg logit contributions | |
am | -0.014 |
wore | -0.013 |
days | -0.013 |
packs | -0.012 |
wear | -0.012 |
Token | were |
Token ID | 547 |
Feature activation | -1.07e-02 |
Pos logit contributions | |
louder | +0.038 |
harder | +0.037 |
trigger | +0.036 |
angrily | +0.036 |
throttle | +0.036 |
Neg logit contributions | |
wore | -0.017 |
am | -0.017 |
days | -0.016 |
wear | -0.014 |
packs | -0.014 |
Token | picked |
Token ID | 6497 |
Feature activation | -4.87e-02 |
Pos logit contributions | |
trigger | +0.092 |
amus | +0.089 |
rier | +0.087 |
rules | +0.086 |
beast | +0.082 |
Neg logit contributions | |
wore | -0.041 |
had | -0.024 |
lived | -0.024 |
days | -0.023 |
shone | -0.022 |
Token | up |
Token ID | 510 |
Feature activation | -2.32e-02 |
Pos logit contributions | |
ote | +0.096 |
beast | +0.091 |
amus | +0.090 |
iously | +0.089 |
accelerator | +0.089 |
Neg logit contributions | |
wore | -0.058 |
wear | -0.057 |
am | -0.056 |
packs | -0.049 |
have | -0.049 |
Token | the |
Token ID | 262 |
Feature activation | -2.58e-02 |
Pos logit contributions | |
trigger | +0.054 |
amus | +0.053 |
beast | +0.053 |
louder | +0.052 |
ote | +0.052 |
Neg logit contributions | |
wore | -0.025 |
wear | -0.022 |
packs | -0.021 |
days | -0.021 |
am | -0.020 |
Token | car |
Token ID | 1097 |
Feature activation | -2.01e-02 |
Pos logit contributions | |
angrily | +0.043 |
louder | +0.043 |
loudly | +0.040 |
harder | +0.040 |
trigger | +0.039 |
Neg logit contributions | |
am | -0.047 |
wore | -0.046 |
packs | -0.046 |
days | -0.045 |
wear | -0.043 |
Token | and |
Token ID | 290 |
Feature activation | -1.76e-02 |
Pos logit contributions | |
trigger | +0.048 |
beast | +0.047 |
amus | +0.047 |
ote | +0.046 |
ISE | +0.044 |
Neg logit contributions | |
packs | -0.021 |
wore | -0.021 |
days | -0.020 |
am | -0.018 |
wear | -0.017 |
Token | showed |
Token ID | 3751 |
Feature activation | -7.94e-02 |
Pos logit contributions | |
trigger | +0.040 |
amus | +0.039 |
angrily | +0.038 |
beast | +0.038 |
rier | +0.037 |
Neg logit contributions | |
wore | -0.024 |
wear | -0.020 |
am | -0.019 |
days | -0.019 |
packs | -0.019 |
Token | Tim |
Token ID | 5045 |
Feature activation | -4.73e-02 |
Pos logit contributions | |
ote | +0.184 |
king | +0.183 |
beast | +0.176 |
iously | +0.172 |
louder | +0.170 |
Neg logit contributions | |
am | -0.073 |
lived | -0.068 |
wear | -0.067 |
have | -0.063 |
live | -0.060 |
Token | my |
Token ID | 1820 |
Feature activation | -3.29e-02 |
Pos logit contributions | |
trigger | +0.098 |
louder | +0.098 |
angrily | +0.097 |
beast | +0.094 |
amus | +0.091 |
Neg logit contributions | |
days | -0.064 |
wore | -0.063 |
am | -0.062 |
packs | -0.062 |
wear | -0.058 |
Token | how |
Token ID | 703 |
Feature activation | -9.11e-03 |
Pos logit contributions | |
trigger | +0.058 |
louder | +0.056 |
beast | +0.055 |
angrily | +0.054 |
amus | +0.053 |
Neg logit contributions | |
packs | -0.056 |
days | -0.056 |
wore | -0.055 |
am | -0.055 |
ouses | -0.053 |
Token | to |
Token ID | 284 |
Feature activation | -4.46e-03 |
Pos logit contributions | |
louder | +0.015 |
trigger | +0.014 |
angrily | +0.014 |
harder | +0.014 |
amus | +0.014 |
Neg logit contributions | |
days | -0.017 |
am | -0.017 |
wore | -0.017 |
packs | -0.016 |
ouses | -0.016 |
Token | reverse |
Token ID | 9575 |
Feature activation | -2.38e-02 |
Pos logit contributions | |
louder | +0.009 |
angrily | +0.008 |
trigger | +0.008 |
harder | +0.008 |
loudly | +0.008 |
Neg logit contributions | |
am | -0.007 |
wear | -0.007 |
wore | -0.007 |
days | -0.007 |
packs | -0.006 |
Token | noises |
Token ID | 26782 |
Feature activation | -2.77e-02 |
Pos logit contributions | |
amus | +0.032 |
trigger | +0.032 |
throttle | +0.031 |
rus | +0.029 |
adult | +0.029 |
Neg logit contributions | |
am | -0.057 |
days | -0.055 |
wore | -0.055 |
packs | -0.052 |
wear | -0.051 |
Token | . |
Token ID | 13 |
Feature activation | -3.32e-02 |
Pos logit contributions | |
amus | +0.064 |
trigger | +0.062 |
throttle | +0.061 |
beast | +0.060 |
iously | +0.060 |
Neg logit contributions | |
wore | -0.031 |
days | -0.029 |
am | -0.029 |
wear | -0.029 |
packs | -0.026 |
Token | He |
Token ID | 679 |
Feature activation | -2.45e-02 |
Pos logit contributions | |
trigger | +0.080 |
louder | +0.080 |
beast | +0.078 |
harder | +0.078 |
throttle | +0.077 |
Neg logit contributions | |
wore | -0.034 |
am | -0.026 |
lived | -0.025 |
wear | -0.025 |
ouses | -0.024 |
Token | tried |
Token ID | 3088 |
Feature activation | -4.26e-02 |
Pos logit contributions | |
rier | +0.066 |
trigger | +0.062 |
throttle | +0.058 |
instructions | +0.058 |
amus | +0.057 |
Neg logit contributions | |
wore | -0.034 |
wear | -0.024 |
lived | -0.024 |
am | -0.022 |
wears | -0.020 |
Token | to |
Token ID | 284 |
Feature activation | -2.92e-02 |
Pos logit contributions | |
trigger | +0.099 |
rier | +0.094 |
amus | +0.091 |
rus | +0.090 |
ote | +0.087 |
Neg logit contributions | |
am | -0.055 |
wore | -0.052 |
wear | -0.048 |
days | -0.047 |
'm | -0.044 |
Token | catch |
Token ID | 4929 |
Feature activation | -7.92e-02 |
Pos logit contributions | |
rier | +0.058 |
angrily | +0.057 |
throttle | +0.057 |
trigger | +0.056 |
louder | +0.055 |
Neg logit contributions | |
wear | -0.044 |
am | -0.043 |
days | -0.038 |
wore | -0.037 |
have | -0.035 |
Token | it |
Token ID | 340 |
Feature activation | -3.43e-02 |
Pos logit contributions | |
iously | +0.198 |
ote | +0.192 |
rier | +0.189 |
rus | +0.187 |
accelerator | +0.187 |
Neg logit contributions | |
have | -0.061 |
am | -0.060 |
wear | -0.050 |
enjoy | -0.042 |
wore | -0.039 |
Token | , |
Token ID | 11 |
Feature activation | -1.53e-02 |
Pos logit contributions | |
throttle | +0.096 |
rus | +0.094 |
trigger | +0.094 |
amus | +0.093 |
beast | +0.093 |
Neg logit contributions | |
am | -0.021 |
wear | -0.019 |
wore | -0.016 |
days | -0.014 |
have | -0.012 |
Token | but |
Token ID | 475 |
Feature activation | -7.89e-03 |
Pos logit contributions | |
trigger | +0.034 |
amus | +0.034 |
throttle | +0.033 |
rus | +0.033 |
beast | +0.032 |
Neg logit contributions | |
wore | -0.019 |
wear | -0.017 |
am | -0.017 |
days | -0.014 |
have | -0.014 |
Token | it |
Token ID | 340 |
Feature activation | -1.48e-02 |
Pos logit contributions | |
angrily | +0.012 |
trigger | +0.012 |
louder | +0.012 |
amus | +0.012 |
harder | +0.012 |
Neg logit contributions | |
wore | -0.015 |
am | -0.015 |
days | -0.014 |
wear | -0.014 |
packs | -0.013 |
Token | was |
Token ID | 373 |
Feature activation | -1.59e-02 |
Pos logit contributions | |
throttle | +0.033 |
trigger | +0.033 |
louder | +0.033 |
angrily | +0.032 |
harder | +0.032 |
Neg logit contributions | |
wore | -0.018 |
am | -0.018 |
days | -0.015 |
wear | -0.014 |
lived | -0.014 |
Token | my |
Token ID | 1820 |
Feature activation | -5.67e-02 |
Pos logit contributions | |
louder | +0.100 |
trigger | +0.098 |
angrily | +0.098 |
harder | +0.096 |
loudly | +0.092 |
Neg logit contributions | |
wore | -0.055 |
days | -0.054 |
am | -0.052 |
packs | -0.050 |
wear | -0.047 |
Token | asked |
Token ID | 1965 |
Feature activation | -4.46e-02 |
Pos logit contributions | |
trigger | +0.151 |
rier | +0.148 |
louder | +0.144 |
harder | +0.141 |
throttle | +0.139 |
Neg logit contributions | |
wore | -0.070 |
am | -0.052 |
lived | -0.051 |
days | -0.045 |
wear | -0.045 |
Token | the |
Token ID | 262 |
Feature activation | -5.14e-02 |
Pos logit contributions | |
trigger | +0.111 |
angrily | +0.103 |
amus | +0.102 |
ote | +0.101 |
louder | +0.100 |
Neg logit contributions | |
wore | -0.049 |
am | -0.048 |
days | -0.045 |
wear | -0.043 |
lived | -0.041 |
Token | hunter |
Token ID | 19177 |
Feature activation | -6.01e-02 |
Pos logit contributions | |
angrily | +0.079 |
iously | +0.075 |
harder | +0.067 |
louder | +0.065 |
loudly | +0.063 |
Neg logit contributions | |
am | -0.106 |
wore | -0.099 |
wear | -0.092 |
'm | -0.088 |
live | -0.087 |
Token | , |
Token ID | 11 |
Feature activation | -3.28e-02 |
Pos logit contributions | |
trigger | +0.126 |
louder | +0.119 |
angrily | +0.118 |
throttle | +0.117 |
amus | +0.116 |
Neg logit contributions | |
am | -0.086 |
days | -0.086 |
wore | -0.083 |
packs | -0.082 |
wear | -0.076 |
Token | " |
Token ID | 366 |
Feature activation | -7.92e-02 |
Pos logit contributions | |
trigger | +0.065 |
angrily | +0.061 |
throttle | +0.059 |
amus | +0.059 |
harder | +0.059 |
Neg logit contributions | |
am | -0.050 |
wore | -0.050 |
days | -0.049 |
wear | -0.045 |
'm | -0.043 |
Token | What |
Token ID | 2061 |
Feature activation | +7.29e-03 |
Pos logit contributions | |
angrily | +0.191 |
loudly | +0.185 |
iously | +0.185 |
harder | +0.184 |
louder | +0.182 |
Neg logit contributions | |
days | -0.081 |
am | -0.080 |
wore | -0.078 |
'm | -0.064 |
wear | -0.063 |
Token | are |
Token ID | 389 |
Feature activation | -4.24e-02 |
Pos logit contributions | |
days | +0.012 |
ouses | +0.011 |
wore | +0.011 |
packs | +0.011 |
am | +0.010 |
Neg logit contributions | |
louder | -0.013 |
harder | -0.013 |
angrily | -0.013 |
beast | -0.013 |
loudly | -0.013 |
Token | you |
Token ID | 345 |
Feature activation | +1.73e-02 |
Pos logit contributions | |
louder | +0.078 |
angrily | +0.077 |
harder | +0.076 |
trigger | +0.074 |
loudly | +0.070 |
Neg logit contributions | |
wore | -0.070 |
am | -0.069 |
days | -0.069 |
packs | -0.066 |
ouses | -0.065 |
Token | doing |
Token ID | 1804 |
Feature activation | -4.06e-03 |
Pos logit contributions | |
days | +0.022 |
packs | +0.020 |
am | +0.020 |
ouses | +0.020 |
wore | +0.020 |
Neg logit contributions | |
louder | -0.039 |
harder | -0.038 |
angrily | -0.038 |
trigger | -0.038 |
beast | -0.037 |
Token | ?" |
Token ID | 1701 |
Feature activation | -3.88e-02 |
Pos logit contributions | |
louder | +0.009 |
angrily | +0.009 |
harder | +0.009 |
trigger | +0.009 |
loudly | +0.009 |
Neg logit contributions | |
days | -0.005 |
am | -0.005 |
wore | -0.005 |
packs | -0.004 |
ouses | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | -2.28e-02 |
Pos logit contributions | |
iously | +0.106 |
ote | +0.106 |
angrily | +0.103 |
rier | +0.103 |
rus | +0.102 |
Neg logit contributions | |
wore | -0.054 |
wear | -0.050 |
am | -0.050 |
packs | -0.041 |
have | -0.039 |
Token | cube |
Token ID | 23441 |
Feature activation | -2.95e-02 |
Pos logit contributions | |
louder | +0.045 |
angrily | +0.044 |
harder | +0.043 |
loudly | +0.041 |
amus | +0.041 |
Neg logit contributions | |
am | -0.035 |
days | -0.034 |
wore | -0.034 |
packs | -0.031 |
wear | -0.031 |
Token | and |
Token ID | 290 |
Feature activation | -1.54e-02 |
Pos logit contributions | |
ote | +0.064 |
beast | +0.064 |
amus | +0.062 |
trigger | +0.062 |
angrily | +0.062 |
Neg logit contributions | |
wore | -0.036 |
am | -0.035 |
packs | -0.033 |
wear | -0.032 |
days | -0.030 |
Token | tried |
Token ID | 3088 |
Feature activation | -4.37e-02 |
Pos logit contributions | |
louder | +0.023 |
angrily | +0.022 |
trigger | +0.022 |
harder | +0.022 |
amus | +0.021 |
Neg logit contributions | |
wore | -0.031 |
am | -0.030 |
days | -0.029 |
packs | -0.029 |
wear | -0.029 |
Token | to |
Token ID | 284 |
Feature activation | -2.20e-02 |
Pos logit contributions | |
trigger | +0.105 |
rus | +0.098 |
beast | +0.098 |
rier | +0.097 |
amus | +0.096 |
Neg logit contributions | |
am | -0.052 |
wore | -0.049 |
wear | -0.045 |
packs | -0.040 |
'm | -0.039 |
Token | catch |
Token ID | 4929 |
Feature activation | -7.89e-02 |
Pos logit contributions | |
angrily | +0.045 |
beast | +0.044 |
louder | +0.043 |
iously | +0.043 |
rier | +0.043 |
Neg logit contributions | |
wear | -0.035 |
am | -0.031 |
wore | -0.030 |
days | -0.028 |
have | -0.027 |
Token | it |
Token ID | 340 |
Feature activation | -2.40e-02 |
Pos logit contributions | |
iously | +0.197 |
rus | +0.193 |
ote | +0.188 |
amus | +0.179 |
rier | +0.179 |
Neg logit contributions | |
am | -0.067 |
have | -0.064 |
wear | -0.058 |
wore | -0.048 |
enjoy | -0.042 |
Token | , |
Token ID | 11 |
Feature activation | -1.70e-02 |
Pos logit contributions | |
throttle | +0.059 |
beast | +0.058 |
rus | +0.055 |
ote | +0.055 |
amus | +0.055 |
Neg logit contributions | |
am | -0.025 |
wear | -0.023 |
wore | -0.023 |
days | -0.017 |
have | -0.017 |
Token | but |
Token ID | 475 |
Feature activation | -9.33e-03 |
Pos logit contributions | |
trigger | +0.038 |
amus | +0.038 |
throttle | +0.037 |
rus | +0.037 |
beast | +0.037 |
Neg logit contributions | |
wore | -0.019 |
wear | -0.018 |
am | -0.017 |
have | -0.014 |
days | -0.014 |
Token | he |
Token ID | 339 |
Feature activation | -1.83e-02 |
Pos logit contributions | |
angrily | +0.014 |
louder | +0.014 |
trigger | +0.014 |
amus | +0.013 |
harder | +0.013 |
Neg logit contributions | |
wore | -0.018 |
am | -0.018 |
days | -0.017 |
wear | -0.017 |
packs | -0.017 |
Token | missed |
Token ID | 6825 |
Feature activation | -2.94e-02 |
Pos logit contributions | |
louder | +0.039 |
trigger | +0.037 |
angrily | +0.037 |
harder | +0.037 |
throttle | +0.036 |
Neg logit contributions | |
wore | -0.027 |
am | -0.026 |
days | -0.024 |
wear | -0.023 |
ouses | -0.022 |
Token | butterfly |
Token ID | 35113 |
Feature activation | -2.45e-02 |
Pos logit contributions | |
iously | +0.092 |
angrily | +0.087 |
amus | +0.086 |
harder | +0.084 |
louder | +0.082 |
Neg logit contributions | |
am | -0.075 |
wore | -0.068 |
wear | -0.063 |
days | -0.062 |
'm | -0.060 |
Token | . |
Token ID | 13 |
Feature activation | -5.62e-02 |
Pos logit contributions | |
louder | +0.049 |
angrily | +0.049 |
trigger | +0.048 |
throttle | +0.048 |
harder | +0.048 |
Neg logit contributions | |
am | -0.035 |
wore | -0.034 |
days | -0.033 |
wear | -0.032 |
packs | -0.031 |
Token | He |
Token ID | 679 |
Feature activation | -3.12e-02 |
Pos logit contributions | |
trigger | +0.136 |
louder | +0.135 |
rier | +0.132 |
harder | +0.130 |
angrily | +0.126 |
Neg logit contributions | |
wore | -0.060 |
am | -0.056 |
packs | -0.048 |
days | -0.047 |
lived | -0.047 |
Token | tried |
Token ID | 3088 |
Feature activation | -4.61e-02 |
Pos logit contributions | |
trigger | +0.076 |
rier | +0.074 |
louder | +0.071 |
harder | +0.070 |
throttle | +0.070 |
Neg logit contributions | |
wore | -0.042 |
am | -0.035 |
wear | -0.032 |
lived | -0.031 |
days | -0.029 |
Token | to |
Token ID | 284 |
Feature activation | -3.45e-02 |
Pos logit contributions | |
trigger | +0.123 |
rier | +0.117 |
rus | +0.109 |
amus | +0.108 |
ote | +0.108 |
Neg logit contributions | |
am | -0.046 |
wore | -0.043 |
wear | -0.037 |
'm | -0.036 |
have | -0.031 |
Token | catch |
Token ID | 4929 |
Feature activation | -7.82e-02 |
Pos logit contributions | |
rier | +0.070 |
angrily | +0.070 |
throttle | +0.069 |
trigger | +0.067 |
beast | +0.066 |
Neg logit contributions | |
wear | -0.052 |
am | -0.048 |
wore | -0.043 |
days | -0.040 |
have | -0.039 |
Token | it |
Token ID | 340 |
Feature activation | -3.10e-02 |
Pos logit contributions | |
rier | +0.196 |
ote | +0.195 |
iously | +0.191 |
der | +0.187 |
Days | +0.186 |
Neg logit contributions | |
am | -0.059 |
have | -0.056 |
wear | -0.044 |
are | -0.038 |
live | -0.036 |
Token | , |
Token ID | 11 |
Feature activation | -1.48e-02 |
Pos logit contributions | |
throttle | +0.090 |
trigger | +0.089 |
rus | +0.087 |
amus | +0.087 |
beast | +0.086 |
Neg logit contributions | |
am | -0.017 |
wear | -0.014 |
wore | -0.013 |
have | -0.007 |
days | -0.007 |
Token | but |
Token ID | 475 |
Feature activation | -1.76e-02 |
Pos logit contributions | |
trigger | +0.035 |
amus | +0.033 |
rus | +0.033 |
throttle | +0.032 |
beast | +0.032 |
Neg logit contributions | |
wore | -0.017 |
wear | -0.016 |
am | -0.016 |
wears | -0.013 |
have | -0.012 |
Token | it |
Token ID | 340 |
Feature activation | -1.53e-02 |
Pos logit contributions | |
trigger | +0.034 |
amus | +0.033 |
angrily | +0.033 |
ote | +0.032 |
rier | +0.032 |
Neg logit contributions | |
am | -0.028 |
wore | -0.027 |
wear | -0.024 |
lived | -0.023 |
days | -0.023 |
Token | flew |
Token ID | 13112 |
Feature activation | -3.55e-02 |
Pos logit contributions | |
throttle | +0.034 |
louder | +0.034 |
trigger | +0.034 |
instructions | +0.033 |
angrily | +0.033 |
Neg logit contributions | |
am | -0.019 |
wore | -0.019 |
lived | -0.015 |
wear | -0.015 |
days | -0.014 |
Token | the |
Token ID | 262 |
Feature activation | -8.06e-03 |
Pos logit contributions | |
louder | +0.043 |
amus | +0.043 |
trigger | +0.042 |
angrily | +0.042 |
zee | +0.041 |
Neg logit contributions | |
am | -0.023 |
wore | -0.022 |
wear | -0.022 |
days | -0.021 |
packs | -0.021 |
Token | pond |
Token ID | 16723 |
Feature activation | -3.00e-02 |
Pos logit contributions | |
louder | +0.016 |
angrily | +0.015 |
harder | +0.015 |
amus | +0.015 |
trigger | +0.015 |
Neg logit contributions | |
am | -0.013 |
wore | -0.012 |
days | -0.012 |
packs | -0.011 |
wear | -0.011 |
Token | and |
Token ID | 290 |
Feature activation | -1.99e-02 |
Pos logit contributions | |
trigger | +0.072 |
amus | +0.071 |
throttle | +0.071 |
rus | +0.069 |
beast | +0.068 |
Neg logit contributions | |
wore | -0.032 |
days | -0.029 |
packs | -0.029 |
am | -0.028 |
wear | -0.026 |
Token | tried |
Token ID | 3088 |
Feature activation | -3.92e-02 |
Pos logit contributions | |
trigger | +0.037 |
louder | +0.037 |
amus | +0.037 |
angrily | +0.036 |
throttle | +0.036 |
Neg logit contributions | |
wore | -0.032 |
am | -0.029 |
days | -0.029 |
wear | -0.028 |
packs | -0.027 |
Token | to |
Token ID | 284 |
Feature activation | -2.24e-02 |
Pos logit contributions | |
trigger | +0.084 |
beast | +0.077 |
amus | +0.077 |
throttle | +0.076 |
rus | +0.075 |
Neg logit contributions | |
am | -0.058 |
wore | -0.053 |
days | -0.053 |
packs | -0.053 |
wear | -0.050 |
Token | catch |
Token ID | 4929 |
Feature activation | -7.78e-02 |
Pos logit contributions | |
angrily | +0.045 |
throttle | +0.044 |
trigger | +0.044 |
beast | +0.043 |
louder | +0.043 |
Neg logit contributions | |
wear | -0.034 |
am | -0.033 |
days | -0.031 |
wore | -0.029 |
live | -0.027 |
Token | the |
Token ID | 262 |
Feature activation | -4.27e-02 |
Pos logit contributions | |
throttle | +0.183 |
rus | +0.178 |
accelerator | +0.177 |
iously | +0.176 |
ote | +0.176 |
Neg logit contributions | |
am | -0.080 |
wear | -0.067 |
have | -0.064 |
wore | -0.058 |
live | -0.056 |
Token | real |
Token ID | 1103 |
Feature activation | -4.22e-02 |
Pos logit contributions | |
angrily | +0.073 |
louder | +0.072 |
harder | +0.070 |
throttle | +0.068 |
amus | +0.068 |
Neg logit contributions | |
am | -0.077 |
wore | -0.071 |
days | -0.069 |
wear | -0.066 |
'm | -0.064 |
Token | duck |
Token ID | 22045 |
Feature activation | -2.75e-02 |
Pos logit contributions | |
louder | +0.063 |
angrily | +0.063 |
harder | +0.061 |
trigger | +0.059 |
throttle | +0.058 |
Neg logit contributions | |
am | -0.083 |
days | -0.081 |
wore | -0.080 |
packs | -0.077 |
wear | -0.076 |
Token | with |
Token ID | 351 |
Feature activation | -1.78e-02 |
Pos logit contributions | |
throttle | +0.064 |
beast | +0.062 |
trigger | +0.062 |
accelerator | +0.061 |
louder | +0.060 |
Neg logit contributions | |
am | -0.033 |
days | -0.032 |
packs | -0.030 |
wore | -0.029 |
wear | -0.027 |
Token | his |
Token ID | 465 |
Feature activation | -1.32e-02 |
Pos logit contributions | |
louder | +0.035 |
angrily | +0.035 |
beast | +0.035 |
amus | +0.034 |
rus | +0.034 |
Neg logit contributions | |
wore | -0.024 |
am | -0.024 |
wear | -0.023 |
packs | -0.022 |
days | -0.020 |
Token | too |
Token ID | 1165 |
Feature activation | +1.71e-02 |
Pos logit contributions | |
trigger | +0.061 |
amus | +0.060 |
throttle | +0.058 |
louder | +0.057 |
zee | +0.057 |
Neg logit contributions | |
am | -0.049 |
wore | -0.047 |
days | -0.047 |
packs | -0.044 |
wear | -0.044 |
Token | . |
Token ID | 13 |
Feature activation | -7.64e-03 |
Pos logit contributions | |
am | +0.022 |
wore | +0.021 |
days | +0.020 |
packs | +0.020 |
wear | +0.019 |
Neg logit contributions | |
trigger | -0.039 |
amus | -0.038 |
throttle | -0.037 |
louder | -0.037 |
beast | -0.036 |
Token | She |
Token ID | 1375 |
Feature activation | -1.58e-02 |
Pos logit contributions | |
louder | +0.018 |
harder | +0.017 |
angrily | +0.017 |
trigger | +0.017 |
beast | +0.017 |
Neg logit contributions | |
days | -0.009 |
am | -0.009 |
wore | -0.008 |
packs | -0.008 |
ouses | -0.008 |
Token | tried |
Token ID | 3088 |
Feature activation | -3.78e-02 |
Pos logit contributions | |
trigger | +0.038 |
rier | +0.036 |
louder | +0.035 |
amus | +0.034 |
throttle | +0.034 |
Neg logit contributions | |
wore | -0.022 |
am | -0.018 |
days | -0.016 |
wear | -0.016 |
ouses | -0.015 |
Token | to |
Token ID | 284 |
Feature activation | -3.56e-02 |
Pos logit contributions | |
trigger | +0.089 |
rier | +0.085 |
amus | +0.082 |
rus | +0.081 |
beast | +0.081 |
Neg logit contributions | |
am | -0.047 |
wore | -0.046 |
wear | -0.043 |
days | -0.039 |
'm | -0.038 |
Token | catch |
Token ID | 4929 |
Feature activation | -7.75e-02 |
Pos logit contributions | |
rier | +0.072 |
angrily | +0.069 |
throttle | +0.069 |
trigger | +0.069 |
beast | +0.067 |
Neg logit contributions | |
wear | -0.054 |
am | -0.052 |
wore | -0.045 |
days | -0.044 |
have | -0.043 |
Token | it |
Token ID | 340 |
Feature activation | -2.78e-02 |
Pos logit contributions | |
ote | +0.187 |
rier | +0.183 |
iously | +0.183 |
accelerator | +0.179 |
amus | +0.177 |
Neg logit contributions | |
am | -0.066 |
have | -0.063 |
wear | -0.055 |
enjoy | -0.046 |
live | -0.045 |
Token | , |
Token ID | 11 |
Feature activation | -8.66e-03 |
Pos logit contributions | |
throttle | +0.077 |
rus | +0.076 |
trigger | +0.076 |
beast | +0.076 |
amus | +0.075 |
Neg logit contributions | |
am | -0.019 |
wear | -0.017 |
wore | -0.016 |
days | -0.013 |
have | -0.012 |
Token | but |
Token ID | 475 |
Feature activation | +5.69e-03 |
Pos logit contributions | |
trigger | +0.018 |
amus | +0.017 |
throttle | +0.017 |
beast | +0.017 |
rus | +0.017 |
Neg logit contributions | |
wore | -0.013 |
am | -0.011 |
wear | -0.011 |
days | -0.010 |
'm | -0.009 |
Token | it |
Token ID | 340 |
Feature activation | -8.51e-03 |
Pos logit contributions | |
am | +0.011 |
days | +0.011 |
wore | +0.011 |
packs | +0.011 |
wear | +0.011 |
Neg logit contributions | |
louder | -0.008 |
angrily | -0.008 |
trigger | -0.008 |
harder | -0.008 |
amus | -0.008 |
Token | was |
Token ID | 373 |
Feature activation | -1.13e-02 |
Pos logit contributions | |
louder | +0.020 |
trigger | +0.019 |
throttle | +0.019 |
angrily | +0.019 |
harder | +0.019 |
Neg logit contributions | |
am | -0.010 |
wore | -0.010 |
days | -0.009 |
wear | -0.008 |
'm | -0.008 |
Token | oct |
Token ID | 19318 |
Feature activation | -4.84e-02 |
Pos logit contributions | |
louder | +0.057 |
angrily | +0.057 |
trigger | +0.052 |
harder | +0.051 |
instructions | +0.050 |
Neg logit contributions | |
wore | -0.056 |
wear | -0.054 |
am | -0.052 |
days | -0.050 |
wears | -0.044 |
Token | opus |
Token ID | 25790 |
Feature activation | -5.21e-02 |
Pos logit contributions | |
harder | +0.100 |
louder | +0.100 |
angrily | +0.093 |
tighter | +0.089 |
trigger | +0.087 |
Neg logit contributions | |
am | -0.078 |
ouses | -0.073 |
days | -0.071 |
wore | -0.070 |
wear | -0.064 |
Token | in |
Token ID | 287 |
Feature activation | +1.24e-02 |
Pos logit contributions | |
louder | +0.100 |
trigger | +0.098 |
angrily | +0.096 |
harder | +0.096 |
amus | +0.094 |
Neg logit contributions | |
am | -0.084 |
days | -0.082 |
wore | -0.080 |
packs | -0.076 |
wear | -0.075 |
Token | trouble |
Token ID | 5876 |
Feature activation | +5.59e-03 |
Pos logit contributions | |
days | +0.021 |
am | +0.020 |
wore | +0.020 |
packs | +0.020 |
ouses | +0.019 |
Neg logit contributions | |
louder | -0.022 |
angrily | -0.022 |
harder | -0.022 |
trigger | -0.021 |
loudly | -0.021 |
Token | !" |
Token ID | 2474 |
Feature activation | -3.76e-02 |
Pos logit contributions | |
days | +0.010 |
am | +0.009 |
wore | +0.009 |
packs | +0.009 |
ouses | +0.009 |
Neg logit contributions | |
louder | -0.010 |
angrily | -0.010 |
harder | -0.009 |
trigger | -0.009 |
loudly | -0.009 |
Token | Fin |
Token ID | 4463 |
Feature activation | -7.73e-02 |
Pos logit contributions | |
louder | +0.067 |
harder | +0.065 |
throttle | +0.064 |
amus | +0.063 |
trigger | +0.063 |
Neg logit contributions | |
am | -0.064 |
wore | -0.063 |
wear | -0.058 |
days | -0.057 |
packs | -0.054 |
Token | exclaimed |
Token ID | 33552 |
Feature activation | -4.01e-02 |
Pos logit contributions | |
trigger | +0.185 |
throttle | +0.185 |
lever | +0.177 |
rier | +0.175 |
explosion | +0.172 |
Neg logit contributions | |
wore | -0.096 |
am | -0.076 |
wear | -0.072 |
days | -0.070 |
'm | -0.067 |
Token | . |
Token ID | 13 |
Feature activation | -5.39e-02 |
Pos logit contributions | |
throttle | +0.103 |
amus | +0.100 |
trigger | +0.099 |
accelerator | +0.097 |
beast | +0.097 |
Neg logit contributions | |
days | -0.036 |
am | -0.034 |
wore | -0.033 |
wear | -0.030 |
packs | -0.028 |
Token | The |
Token ID | 383 |
Feature activation | -2.83e-02 |
Pos logit contributions | |
louder | +0.135 |
throttle | +0.131 |
harder | +0.131 |
trigger | +0.130 |
beast | +0.128 |
Neg logit contributions | |
am | -0.052 |
wore | -0.048 |
'm | -0.040 |
days | -0.039 |
ouses | -0.039 |
Token | fish |
Token ID | 5916 |
Feature activation | -5.21e-02 |
Pos logit contributions | |
angrily | +0.061 |
harder | +0.058 |
louder | +0.057 |
loudly | +0.055 |
amus | +0.054 |
Neg logit contributions | |
am | -0.041 |
wore | -0.039 |
days | -0.039 |
wear | -0.035 |
'm | -0.034 |
Token | all |
Token ID | 477 |
Feature activation | -4.40e-03 |
Pos logit contributions | |
trigger | +0.120 |
throttle | +0.117 |
rier | +0.112 |
accelerator | +0.112 |
lever | +0.111 |
Neg logit contributions | |
wore | -0.072 |
days | -0.062 |
lived | -0.061 |
am | -0.060 |
'm | -0.052 |
Token | yard |
Token ID | 12699 |
Feature activation | +5.17e-03 |
Pos logit contributions | |
louder | +0.020 |
harder | +0.020 |
angrily | +0.019 |
trigger | +0.019 |
loudly | +0.018 |
Neg logit contributions | |
days | -0.022 |
packs | -0.021 |
am | -0.021 |
wore | -0.021 |
ouses | -0.020 |
Token | . |
Token ID | 13 |
Feature activation | -5.15e-02 |
Pos logit contributions | |
days | +0.006 |
wore | +0.005 |
am | +0.005 |
packs | +0.005 |
wear | +0.004 |
Neg logit contributions | |
trigger | -0.012 |
throttle | -0.012 |
amus | -0.012 |
louder | -0.012 |
beast | -0.012 |
Token | He |
Token ID | 679 |
Feature activation | -3.02e-02 |
Pos logit contributions | |
louder | +0.121 |
trigger | +0.116 |
harder | +0.116 |
amus | +0.111 |
angrily | +0.111 |
Neg logit contributions | |
wore | -0.059 |
am | -0.055 |
wear | -0.049 |
days | -0.048 |
ouses | -0.044 |
Token | wanted |
Token ID | 2227 |
Feature activation | -6.60e-02 |
Pos logit contributions | |
rier | +0.076 |
trigger | +0.074 |
throttle | +0.071 |
louder | +0.070 |
lever | +0.070 |
Neg logit contributions | |
wore | -0.040 |
am | -0.031 |
lived | -0.030 |
wear | -0.028 |
wears | -0.024 |
Token | to |
Token ID | 284 |
Feature activation | -4.11e-02 |
Pos logit contributions | |
trigger | +0.160 |
rier | +0.159 |
angrily | +0.151 |
louder | +0.146 |
amus | +0.146 |
Neg logit contributions | |
am | -0.074 |
wore | -0.071 |
wear | -0.066 |
have | -0.057 |
'm | -0.056 |
Token | catch |
Token ID | 4929 |
Feature activation | -7.70e-02 |
Pos logit contributions | |
louder | +0.078 |
harder | +0.075 |
angrily | +0.075 |
trigger | +0.074 |
loudly | +0.070 |
Neg logit contributions | |
am | -0.068 |
days | -0.066 |
wore | -0.064 |
wear | -0.062 |
packs | -0.061 |
Token | the |
Token ID | 262 |
Feature activation | -4.54e-02 |
Pos logit contributions | |
rier | +0.175 |
throttle | +0.175 |
accelerator | +0.171 |
iously | +0.170 |
amus | +0.168 |
Neg logit contributions | |
am | -0.081 |
wear | -0.074 |
have | -0.068 |
wore | -0.068 |
live | -0.062 |
Token | squirrel |
Token ID | 33039 |
Feature activation | -3.51e-02 |
Pos logit contributions | |
louder | +0.072 |
angrily | +0.071 |
harder | +0.068 |
trigger | +0.063 |
amus | +0.063 |
Neg logit contributions | |
am | -0.090 |
wore | -0.085 |
days | -0.083 |
wear | -0.081 |
'm | -0.078 |
Token | and |
Token ID | 290 |
Feature activation | -2.47e-02 |
Pos logit contributions | |
trigger | +0.077 |
throttle | +0.076 |
louder | +0.076 |
beast | +0.074 |
amus | +0.074 |
Neg logit contributions | |
days | -0.047 |
am | -0.046 |
packs | -0.044 |
wore | -0.043 |
wear | -0.041 |
Token | play |
Token ID | 711 |
Feature activation | -4.86e-02 |
Pos logit contributions | |
louder | +0.050 |
angrily | +0.049 |
harder | +0.049 |
trigger | +0.048 |
amus | +0.047 |
Neg logit contributions | |
am | -0.036 |
wore | -0.035 |
wear | -0.034 |
days | -0.034 |
packs | -0.032 |
Token | with |
Token ID | 351 |
Feature activation | -4.74e-02 |
Pos logit contributions | |
throttle | +0.106 |
trigger | +0.103 |
amus | +0.102 |
beast | +0.100 |
accelerator | +0.098 |
Neg logit contributions | |
am | -0.068 |
days | -0.062 |
wore | -0.060 |
wear | -0.059 |
'm | -0.050 |
Token | it |
Token ID | 340 |
Feature activation | -2.00e-02 |
Pos logit contributions | |
throttle | +0.127 |
iously | +0.126 |
accelerator | +0.124 |
beast | +0.123 |
amus | +0.121 |
Neg logit contributions | |
am | -0.095 |
wear | -0.090 |
wore | -0.090 |
have | -0.079 |
days | -0.078 |
Token | . |
Token ID | 13 |
Feature activation | -2.75e-02 |
Pos logit contributions | |
throttle | +0.051 |
beast | +0.050 |
trigger | +0.049 |
accelerator | +0.049 |
rus | +0.048 |
Neg logit contributions | |
am | -0.019 |
wear | -0.018 |
wore | -0.018 |
days | -0.017 |
packs | -0.016 |
Token | He |
Token ID | 679 |
Feature activation | -3.11e-02 |
Pos logit contributions | |
louder | +0.053 |
harder | +0.051 |
angrily | +0.051 |
trigger | +0.051 |
beast | +0.051 |
Neg logit contributions | |
wore | -0.043 |
days | -0.041 |
am | -0.041 |
ouses | -0.039 |
wear | -0.038 |
Token | tried |
Token ID | 3088 |
Feature activation | -4.42e-02 |
Pos logit contributions | |
rier | +0.077 |
trigger | +0.076 |
throttle | +0.071 |
louder | +0.070 |
beast | +0.070 |
Neg logit contributions | |
wore | -0.044 |
wear | -0.032 |
am | -0.030 |
lived | -0.029 |
wears | -0.027 |
Token | to |
Token ID | 284 |
Feature activation | -3.26e-02 |
Pos logit contributions | |
trigger | +0.103 |
rier | +0.100 |
amus | +0.094 |
beast | +0.094 |
throttle | +0.093 |
Neg logit contributions | |
am | -0.055 |
wore | -0.054 |
wear | -0.049 |
'm | -0.045 |
packs | -0.043 |
Token | catch |
Token ID | 4929 |
Feature activation | -7.70e-02 |
Pos logit contributions | |
throttle | +0.065 |
angrily | +0.064 |
rier | +0.063 |
beast | +0.063 |
louder | +0.061 |
Neg logit contributions | |
wear | -0.050 |
am | -0.048 |
wore | -0.043 |
have | -0.039 |
'm | -0.038 |
Token | the |
Token ID | 262 |
Feature activation | -5.09e-02 |
Pos logit contributions | |
rier | +0.176 |
iously | +0.175 |
ote | +0.171 |
der | +0.171 |
beast | +0.167 |
Neg logit contributions | |
wear | -0.072 |
am | -0.071 |
wore | -0.068 |
have | -0.068 |
live | -0.052 |
Token | bird |
Token ID | 6512 |
Feature activation | -3.53e-02 |
Pos logit contributions | |
angrily | +0.092 |
louder | +0.089 |
cautiously | +0.085 |
iously | +0.084 |
harder | +0.083 |
Neg logit contributions | |
am | -0.088 |
wore | -0.076 |
'm | -0.073 |
wear | -0.071 |
have | -0.068 |
Token | , |
Token ID | 11 |
Feature activation | -1.46e-02 |
Pos logit contributions | |
throttle | +0.088 |
trigger | +0.088 |
beast | +0.087 |
accelerator | +0.086 |
amus | +0.084 |
Neg logit contributions | |
am | -0.034 |
days | -0.032 |
wore | -0.031 |
wear | -0.031 |
packs | -0.029 |
Token | but |
Token ID | 475 |
Feature activation | -8.43e-03 |
Pos logit contributions | |
trigger | +0.033 |
amus | +0.033 |
beast | +0.032 |
throttle | +0.032 |
angrily | +0.032 |
Neg logit contributions | |
wore | -0.018 |
wear | -0.016 |
am | -0.016 |
have | -0.013 |
'm | -0.013 |
Token | it |
Token ID | 340 |
Feature activation | -1.91e-02 |
Pos logit contributions | |
angrily | +0.014 |
trigger | +0.013 |
louder | +0.013 |
amus | +0.013 |
beast | +0.013 |
Neg logit contributions | |
wore | -0.016 |
am | -0.016 |
days | -0.015 |
wear | -0.015 |
packs | -0.014 |
Token | saw |
Token ID | 2497 |
Feature activation | -6.09e-02 |
Pos logit contributions | |
rier | +0.180 |
trigger | +0.175 |
amus | +0.174 |
instructions | +0.171 |
louder | +0.170 |
Neg logit contributions | |
wore | -0.072 |
lived | -0.058 |
am | -0.051 |
had | -0.045 |
wears | -0.042 |
Token | the |
Token ID | 262 |
Feature activation | -4.84e-02 |
Pos logit contributions | |
louder | +0.142 |
trigger | +0.140 |
accelerator | +0.140 |
angrily | +0.139 |
harder | +0.139 |
Neg logit contributions | |
am | -0.058 |
wore | -0.054 |
lived | -0.053 |
live | -0.045 |
packs | -0.045 |
Token | small |
Token ID | 1402 |
Feature activation | -3.98e-02 |
Pos logit contributions | |
angrily | +0.071 |
iously | +0.066 |
harder | +0.062 |
louder | +0.062 |
cautiously | +0.061 |
Neg logit contributions | |
am | -0.098 |
wore | -0.095 |
wear | -0.090 |
wears | -0.085 |
live | -0.081 |
Token | fox |
Token ID | 21831 |
Feature activation | -5.03e-02 |
Pos logit contributions | |
angrily | +0.054 |
louder | +0.052 |
amus | +0.050 |
harder | +0.050 |
throttle | +0.049 |
Neg logit contributions | |
wore | -0.082 |
am | -0.081 |
packs | -0.077 |
wear | -0.075 |
wears | -0.073 |
Token | and |
Token ID | 290 |
Feature activation | -4.23e-02 |
Pos logit contributions | |
trigger | +0.107 |
amus | +0.103 |
louder | +0.100 |
rier | +0.099 |
throttle | +0.099 |
Neg logit contributions | |
wore | -0.075 |
days | -0.069 |
am | -0.068 |
wear | -0.067 |
packs | -0.066 |
Token | wanted |
Token ID | 2227 |
Feature activation | -7.66e-02 |
Pos logit contributions | |
trigger | +0.092 |
amus | +0.091 |
harder | +0.090 |
throttle | +0.089 |
louder | +0.089 |
Neg logit contributions | |
wore | -0.060 |
am | -0.051 |
wear | -0.047 |
lived | -0.047 |
days | -0.046 |
Token | to |
Token ID | 284 |
Feature activation | -5.35e-02 |
Pos logit contributions | |
trigger | +0.186 |
rier | +0.185 |
throttle | +0.179 |
angrily | +0.176 |
amus | +0.175 |
Neg logit contributions | |
am | -0.078 |
wear | -0.069 |
wore | -0.067 |
have | -0.060 |
live | -0.057 |
Token | catch |
Token ID | 4929 |
Feature activation | -7.33e-02 |
Pos logit contributions | |
louder | +0.105 |
harder | +0.103 |
angrily | +0.102 |
trigger | +0.100 |
throttle | +0.096 |
Neg logit contributions | |
am | -0.085 |
days | -0.082 |
wore | -0.079 |
wear | -0.078 |
packs | -0.075 |
Token | him |
Token ID | 683 |
Feature activation | -4.54e-02 |
Pos logit contributions | |
throttle | +0.167 |
accelerator | +0.164 |
rus | +0.155 |
iously | +0.155 |
lever | +0.154 |
Neg logit contributions | |
am | -0.086 |
wear | -0.072 |
live | -0.071 |
have | -0.068 |
wore | -0.065 |
Token | . |
Token ID | 13 |
Feature activation | -5.34e-02 |
Pos logit contributions | |
trigger | +0.113 |
throttle | +0.111 |
accelerator | +0.106 |
beast | +0.106 |
louder | +0.105 |
Neg logit contributions | |
am | -0.047 |
days | -0.044 |
packs | -0.044 |
wore | -0.040 |
wear | -0.039 |
Token | The |
Token ID | 383 |
Feature activation | -4.61e-02 |
Pos logit contributions | |
louder | +0.139 |
trigger | +0.135 |
harder | +0.131 |
amus | +0.129 |
throttle | +0.129 |
Neg logit contributions | |
wore | -0.044 |
am | -0.042 |
lived | -0.031 |
ouses | -0.031 |
Cookies | -0.030 |
Token | loves |
Token ID | 10408 |
Feature activation | -3.36e-02 |
Pos logit contributions | |
louder | +0.023 |
trigger | +0.023 |
angrily | +0.022 |
harder | +0.021 |
amus | +0.021 |
Neg logit contributions | |
am | -0.015 |
wore | -0.015 |
wear | -0.014 |
wears | -0.013 |
packs | -0.013 |
Token | the |
Token ID | 262 |
Feature activation | -1.82e-02 |
Pos logit contributions | |
trigger | +0.068 |
louder | +0.067 |
angrily | +0.067 |
harder | +0.065 |
throttle | +0.064 |
Neg logit contributions | |
wore | -0.049 |
am | -0.047 |
wear | -0.045 |
days | -0.045 |
packs | -0.044 |
Token | mole |
Token ID | 9411 |
Feature activation | -2.41e-02 |
Pos logit contributions | |
louder | +0.028 |
angrily | +0.027 |
harder | +0.027 |
throttle | +0.026 |
accelerator | +0.025 |
Neg logit contributions | |
am | -0.037 |
wore | -0.034 |
days | -0.033 |
wear | -0.032 |
packs | -0.032 |
Token | . |
Token ID | 13 |
Feature activation | -9.95e-03 |
Pos logit contributions | |
trigger | +0.051 |
louder | +0.050 |
throttle | +0.050 |
amus | +0.049 |
accelerator | +0.049 |
Neg logit contributions | |
am | -0.032 |
wore | -0.032 |
days | -0.032 |
packs | -0.030 |
wear | -0.028 |
Token | He |
Token ID | 679 |
Feature activation | -4.51e-03 |
Pos logit contributions | |
louder | +0.017 |
angrily | +0.016 |
harder | +0.016 |
trigger | +0.015 |
loudly | +0.015 |
Neg logit contributions | |
days | -0.019 |
wore | -0.018 |
packs | -0.018 |
ouses | -0.017 |
am | -0.017 |
Token | wants |
Token ID | 3382 |
Feature activation | -7.62e-02 |
Pos logit contributions | |
louder | +0.009 |
trigger | +0.009 |
angrily | +0.009 |
harder | +0.009 |
amus | +0.008 |
Neg logit contributions | |
am | -0.007 |
wore | -0.007 |
packs | -0.006 |
days | -0.006 |
wear | -0.006 |
Token | the |
Token ID | 262 |
Feature activation | -2.32e-02 |
Pos logit contributions | |
trigger | +0.182 |
rier | +0.175 |
angrily | +0.174 |
accelerator | +0.172 |
amus | +0.171 |
Neg logit contributions | |
am | -0.076 |
wore | -0.074 |
wear | -0.069 |
have | -0.060 |
packs | -0.058 |
Token | mole |
Token ID | 9411 |
Feature activation | -3.72e-02 |
Pos logit contributions | |
louder | +0.037 |
angrily | +0.036 |
harder | +0.035 |
throttle | +0.034 |
accelerator | +0.033 |
Neg logit contributions | |
am | -0.047 |
wore | -0.042 |
days | -0.042 |
wear | -0.040 |
packs | -0.039 |
Token | to |
Token ID | 284 |
Feature activation | -1.45e-02 |
Pos logit contributions | |
louder | +0.062 |
angrily | +0.061 |
trigger | +0.061 |
harder | +0.060 |
beast | +0.058 |
Neg logit contributions | |
days | -0.067 |
am | -0.066 |
packs | -0.064 |
wore | -0.064 |
ouses | -0.061 |
Token | be |
Token ID | 307 |
Feature activation | -2.32e-02 |
Pos logit contributions | |
louder | +0.026 |
angrily | +0.025 |
harder | +0.025 |
trigger | +0.025 |
loudly | +0.024 |
Neg logit contributions | |
days | -0.024 |
wore | -0.023 |
am | -0.023 |
packs | -0.023 |
ouses | -0.023 |
Token | happy |
Token ID | 3772 |
Feature activation | -1.63e-02 |
Pos logit contributions | |
louder | +0.040 |
angrily | +0.039 |
harder | +0.039 |
trigger | +0.038 |
loudly | +0.036 |
Neg logit contributions | |
days | -0.041 |
am | -0.040 |
wore | -0.040 |
packs | -0.039 |
ouses | -0.039 |
Token | the |
Token ID | 262 |
Feature activation | -2.20e-02 |
Pos logit contributions | |
louder | +0.037 |
trigger | +0.037 |
angrily | +0.036 |
harder | +0.036 |
throttle | +0.036 |
Neg logit contributions | |
am | -0.027 |
days | -0.025 |
wore | -0.025 |
wear | -0.024 |
packs | -0.023 |
Token | dirt |
Token ID | 13647 |
Feature activation | -2.76e-02 |
Pos logit contributions | |
louder | +0.042 |
angrily | +0.040 |
harder | +0.040 |
throttle | +0.039 |
amus | +0.038 |
Neg logit contributions | |
am | -0.036 |
wore | -0.033 |
days | -0.031 |
packs | -0.031 |
wear | -0.031 |
Token | . |
Token ID | 13 |
Feature activation | -6.05e-03 |
Pos logit contributions | |
throttle | +0.056 |
louder | +0.056 |
amus | +0.056 |
trigger | +0.055 |
angrily | +0.054 |
Neg logit contributions | |
packs | -0.037 |
am | -0.036 |
wore | -0.036 |
days | -0.036 |
wear | -0.032 |
Token | The |
Token ID | 383 |
Feature activation | -1.97e-02 |
Pos logit contributions | |
louder | +0.012 |
angrily | +0.011 |
harder | +0.011 |
trigger | +0.011 |
beast | +0.011 |
Neg logit contributions | |
am | -0.009 |
days | -0.009 |
wore | -0.009 |
packs | -0.009 |
ouses | -0.009 |
Token | mole |
Token ID | 9411 |
Feature activation | -3.21e-02 |
Pos logit contributions | |
louder | +0.033 |
angrily | +0.032 |
harder | +0.032 |
throttle | +0.031 |
amus | +0.031 |
Neg logit contributions | |
am | -0.037 |
wore | -0.033 |
days | -0.032 |
wear | -0.031 |
packs | -0.031 |
Token | wants |
Token ID | 3382 |
Feature activation | -7.56e-02 |
Pos logit contributions | |
louder | +0.070 |
trigger | +0.069 |
angrily | +0.067 |
amus | +0.067 |
harder | +0.067 |
Neg logit contributions | |
am | -0.042 |
wore | -0.041 |
days | -0.037 |
packs | -0.037 |
wear | -0.036 |
Token | to |
Token ID | 284 |
Feature activation | -2.57e-02 |
Pos logit contributions | |
trigger | +0.177 |
rier | +0.173 |
angrily | +0.171 |
accelerator | +0.169 |
louder | +0.166 |
Neg logit contributions | |
am | -0.080 |
wore | -0.076 |
wear | -0.071 |
packs | -0.062 |
have | -0.062 |
Token | be |
Token ID | 307 |
Feature activation | -2.33e-02 |
Pos logit contributions | |
louder | +0.051 |
angrily | +0.050 |
harder | +0.050 |
trigger | +0.049 |
loudly | +0.047 |
Neg logit contributions | |
days | -0.038 |
wore | -0.037 |
am | -0.037 |
packs | -0.036 |
ouses | -0.036 |
Token | free |
Token ID | 1479 |
Feature activation | -2.76e-02 |
Pos logit contributions | |
louder | +0.039 |
angrily | +0.038 |
harder | +0.038 |
trigger | +0.037 |
loudly | +0.035 |
Neg logit contributions | |
days | -0.043 |
am | -0.042 |
wore | -0.041 |
packs | -0.041 |
ouses | -0.040 |
Token | . |
Token ID | 13 |
Feature activation | -2.91e-03 |
Pos logit contributions | |
trigger | +0.063 |
throttle | +0.060 |
beast | +0.060 |
amus | +0.059 |
accelerator | +0.059 |
Neg logit contributions | |
packs | -0.034 |
days | -0.033 |
am | -0.032 |
wore | -0.031 |
wear | -0.028 |
Token | Ben |
Token ID | 3932 |
Feature activation | -4.38e-02 |
Pos logit contributions | |
louder | +0.006 |
angrily | +0.006 |
harder | +0.005 |
trigger | +0.005 |
loudly | +0.005 |
Neg logit contributions | |
days | -0.005 |
am | -0.004 |
wore | -0.004 |
packs | -0.004 |
ouses | -0.004 |
Token | it |
Token ID | 340 |
Feature activation | -5.80e-03 |
Pos logit contributions | |
louder | +0.071 |
angrily | +0.069 |
amus | +0.069 |
ote | +0.068 |
throttle | +0.067 |
Neg logit contributions | |
am | -0.057 |
wear | -0.056 |
wore | -0.055 |
days | -0.048 |
packs | -0.048 |
Token | . |
Token ID | 13 |
Feature activation | -3.03e-02 |
Pos logit contributions | |
trigger | +0.012 |
angrily | +0.012 |
throttle | +0.012 |
louder | +0.012 |
beast | +0.012 |
Neg logit contributions | |
wore | -0.008 |
am | -0.008 |
days | -0.007 |
wear | -0.007 |
packs | -0.007 |
Token | Max |
Token ID | 5436 |
Feature activation | -4.83e-02 |
Pos logit contributions | |
louder | +0.061 |
angrily | +0.059 |
harder | +0.059 |
trigger | +0.058 |
beast | +0.056 |
Neg logit contributions | |
days | -0.044 |
am | -0.044 |
wore | -0.044 |
packs | -0.042 |
ouses | -0.042 |
Token | tried |
Token ID | 3088 |
Feature activation | -3.96e-02 |
Pos logit contributions | |
trigger | +0.104 |
louder | +0.100 |
rier | +0.099 |
throttle | +0.098 |
harder | +0.096 |
Neg logit contributions | |
wore | -0.074 |
am | -0.068 |
days | -0.062 |
wear | -0.062 |
lived | -0.057 |
Token | to |
Token ID | 284 |
Feature activation | -2.11e-02 |
Pos logit contributions | |
trigger | +0.093 |
rier | +0.090 |
amus | +0.083 |
throttle | +0.082 |
beast | +0.082 |
Neg logit contributions | |
wore | -0.052 |
am | -0.052 |
wear | -0.046 |
days | -0.043 |
packs | -0.042 |
Token | catch |
Token ID | 4929 |
Feature activation | -7.53e-02 |
Pos logit contributions | |
angrily | +0.039 |
throttle | +0.039 |
beast | +0.039 |
trigger | +0.039 |
louder | +0.038 |
Neg logit contributions | |
wear | -0.033 |
am | -0.033 |
wore | -0.031 |
days | -0.031 |
'm | -0.027 |
Token | the |
Token ID | 262 |
Feature activation | -3.29e-02 |
Pos logit contributions | |
iously | +0.199 |
ote | +0.194 |
rier | +0.193 |
rus | +0.186 |
accelerator | +0.184 |
Neg logit contributions | |
am | -0.055 |
have | -0.052 |
wear | -0.047 |
wore | -0.041 |
enjoy | -0.029 |
Token | bug |
Token ID | 5434 |
Feature activation | -3.56e-02 |
Pos logit contributions | |
angrily | +0.070 |
louder | +0.069 |
accelerator | +0.067 |
throttle | +0.066 |
iously | +0.065 |
Neg logit contributions | |
am | -0.049 |
wore | -0.041 |
wear | -0.039 |
'm | -0.039 |
days | -0.039 |
Token | , |
Token ID | 11 |
Feature activation | -1.60e-02 |
Pos logit contributions | |
trigger | +0.085 |
throttle | +0.084 |
amus | +0.082 |
beast | +0.082 |
accelerator | +0.081 |
Neg logit contributions | |
am | -0.040 |
wore | -0.038 |
wear | -0.036 |
days | -0.035 |
packs | -0.035 |
Token | but |
Token ID | 475 |
Feature activation | -1.15e-02 |
Pos logit contributions | |
trigger | +0.036 |
amus | +0.035 |
throttle | +0.035 |
angrily | +0.034 |
beast | +0.034 |
Neg logit contributions | |
wore | -0.020 |
wear | -0.018 |
am | -0.018 |
have | -0.015 |
wears | -0.015 |
Token | it |
Token ID | 340 |
Feature activation | -1.49e-02 |
Pos logit contributions | |
angrily | +0.019 |
louder | +0.019 |
trigger | +0.019 |
amus | +0.018 |
throttle | +0.018 |
Neg logit contributions | |
am | -0.021 |
wore | -0.020 |
wear | -0.019 |
days | -0.019 |
packs | -0.018 |
Token | He |
Token ID | 679 |
Feature activation | -1.05e-02 |
Pos logit contributions | |
louder | +0.035 |
angrily | +0.034 |
harder | +0.034 |
trigger | +0.033 |
loudly | +0.032 |
Neg logit contributions | |
days | -0.031 |
wore | -0.029 |
am | -0.029 |
packs | -0.029 |
ouses | -0.029 |
Token | sees |
Token ID | 7224 |
Feature activation | -4.84e-02 |
Pos logit contributions | |
louder | +0.022 |
trigger | +0.021 |
harder | +0.021 |
angrily | +0.021 |
amus | +0.020 |
Neg logit contributions | |
am | -0.015 |
wore | -0.015 |
days | -0.014 |
packs | -0.013 |
wear | -0.013 |
Token | the |
Token ID | 262 |
Feature activation | -2.88e-02 |
Pos logit contributions | |
trigger | +0.105 |
amus | +0.104 |
louder | +0.103 |
angrily | +0.102 |
harder | +0.101 |
Neg logit contributions | |
am | -0.055 |
wore | -0.052 |
packs | -0.050 |
wear | -0.044 |
days | -0.043 |
Token | bone |
Token ID | 9970 |
Feature activation | -2.92e-02 |
Pos logit contributions | |
louder | +0.049 |
angrily | +0.048 |
harder | +0.047 |
iously | +0.046 |
amus | +0.046 |
Neg logit contributions | |
am | -0.052 |
wore | -0.048 |
wear | -0.045 |
days | -0.044 |
packs | -0.044 |
Token | and |
Token ID | 290 |
Feature activation | -8.99e-03 |
Pos logit contributions | |
amus | +0.065 |
throttle | +0.063 |
louder | +0.063 |
trigger | +0.061 |
accelerator | +0.061 |
Neg logit contributions | |
am | -0.037 |
wore | -0.036 |
packs | -0.032 |
wear | -0.031 |
wears | -0.029 |
Token | wants |
Token ID | 3382 |
Feature activation | -7.52e-02 |
Pos logit contributions | |
louder | +0.016 |
angrily | +0.015 |
harder | +0.015 |
trigger | +0.015 |
loudly | +0.014 |
Neg logit contributions | |
days | -0.015 |
am | -0.015 |
wore | -0.015 |
packs | -0.015 |
ouses | -0.014 |
Token | it |
Token ID | 340 |
Feature activation | -1.70e-02 |
Pos logit contributions | |
trigger | +0.168 |
ote | +0.165 |
rier | +0.164 |
rus | +0.163 |
amus | +0.163 |
Neg logit contributions | |
am | -0.088 |
wore | -0.076 |
packs | -0.073 |
wear | -0.071 |
have | -0.068 |
Token | too |
Token ID | 1165 |
Feature activation | +1.35e-02 |
Pos logit contributions | |
trigger | +0.032 |
beast | +0.031 |
angrily | +0.031 |
louder | +0.031 |
throttle | +0.030 |
Neg logit contributions | |
am | -0.027 |
days | -0.027 |
packs | -0.027 |
wore | -0.026 |
wear | -0.025 |
Token | . |
Token ID | 13 |
Feature activation | -1.68e-02 |
Pos logit contributions | |
am | +0.019 |
days | +0.018 |
packs | +0.018 |
wore | +0.017 |
ouses | +0.016 |
Neg logit contributions | |
louder | -0.028 |
trigger | -0.028 |
angrily | -0.027 |
amus | -0.027 |
beast | -0.027 |
Token | He |
Token ID | 679 |
Feature activation | -1.91e-02 |
Pos logit contributions | |
louder | +0.034 |
harder | +0.033 |
trigger | +0.033 |
angrily | +0.032 |
amus | +0.031 |
Neg logit contributions | |
am | -0.025 |
days | -0.025 |
wore | -0.024 |
packs | -0.023 |
ouses | -0.023 |
Token | is |
Token ID | 318 |
Feature activation | -1.47e-02 |
Pos logit contributions | |
louder | +0.038 |
trigger | +0.038 |
angrily | +0.037 |
harder | +0.036 |
amus | +0.036 |
Neg logit contributions | |
am | -0.028 |
wore | -0.028 |
wear | -0.025 |
packs | -0.024 |
wears | -0.024 |
Token | sees |
Token ID | 7224 |
Feature activation | -4.97e-02 |
Pos logit contributions | |
louder | +0.052 |
trigger | +0.052 |
angrily | +0.051 |
harder | +0.051 |
amus | +0.049 |
Neg logit contributions | |
am | -0.033 |
wore | -0.032 |
days | -0.030 |
packs | -0.029 |
wear | -0.029 |
Token | the |
Token ID | 262 |
Feature activation | -3.13e-02 |
Pos logit contributions | |
accelerator | +0.110 |
rier | +0.108 |
iously | +0.107 |
angrily | +0.106 |
throttle | +0.106 |
Neg logit contributions | |
am | -0.051 |
wore | -0.050 |
packs | -0.049 |
lived | -0.044 |
wear | -0.042 |
Token | ostr |
Token ID | 42387 |
Feature activation | -3.59e-02 |
Pos logit contributions | |
angrily | +0.058 |
louder | +0.053 |
Whoever | +0.052 |
harder | +0.051 |
loudly | +0.051 |
Neg logit contributions | |
am | -0.052 |
wore | -0.050 |
wear | -0.045 |
packs | -0.044 |
'm | -0.044 |
Token | ich |
Token ID | 488 |
Feature activation | -3.71e-02 |
Pos logit contributions | |
harder | +0.072 |
louder | +0.070 |
angrily | +0.068 |
trigger | +0.067 |
loudly | +0.063 |
Neg logit contributions | |
am | -0.055 |
days | -0.054 |
packs | -0.054 |
wore | -0.052 |
ouses | -0.051 |
Token | and |
Token ID | 290 |
Feature activation | -1.63e-02 |
Pos logit contributions | |
trigger | +0.078 |
amus | +0.074 |
throttle | +0.074 |
louder | +0.072 |
accelerator | +0.072 |
Neg logit contributions | |
am | -0.052 |
wore | -0.052 |
wear | -0.048 |
days | -0.047 |
packs | -0.046 |
Token | wants |
Token ID | 3382 |
Feature activation | -7.52e-02 |
Pos logit contributions | |
trigger | +0.029 |
angrily | +0.029 |
louder | +0.029 |
harder | +0.028 |
amus | +0.028 |
Neg logit contributions | |
am | -0.027 |
wore | -0.026 |
packs | -0.024 |
days | -0.024 |
wear | -0.024 |
Token | to |
Token ID | 284 |
Feature activation | -3.57e-02 |
Pos logit contributions | |
trigger | +0.170 |
rier | +0.166 |
accelerator | +0.165 |
angrily | +0.165 |
rus | +0.163 |
Neg logit contributions | |
am | -0.085 |
wore | -0.075 |
wear | -0.073 |
packs | -0.070 |
have | -0.065 |
Token | catch |
Token ID | 4929 |
Feature activation | -6.55e-02 |
Pos logit contributions | |
louder | +0.065 |
angrily | +0.064 |
harder | +0.064 |
trigger | +0.063 |
loudly | +0.060 |
Neg logit contributions | |
days | -0.059 |
am | -0.058 |
wore | -0.057 |
packs | -0.056 |
ouses | -0.054 |
Token | it |
Token ID | 340 |
Feature activation | -2.47e-02 |
Pos logit contributions | |
accelerator | +0.145 |
throttle | +0.142 |
iously | +0.138 |
ote | +0.137 |
rus | +0.137 |
Neg logit contributions | |
am | -0.080 |
live | -0.068 |
wear | -0.067 |
have | -0.067 |
wore | -0.063 |
Token | . |
Token ID | 13 |
Feature activation | -1.70e-02 |
Pos logit contributions | |
trigger | +0.061 |
throttle | +0.060 |
beast | +0.059 |
rus | +0.058 |
accelerator | +0.058 |
Neg logit contributions | |
am | -0.026 |
packs | -0.024 |
days | -0.024 |
wear | -0.023 |
wore | -0.023 |
Token | It |
Token ID | 632 |
Feature activation | -2.01e-02 |
Pos logit contributions | |
louder | +0.033 |
harder | +0.032 |
angrily | +0.032 |
trigger | +0.032 |
beast | +0.030 |
Neg logit contributions | |
am | -0.027 |
days | -0.026 |
wore | -0.025 |
packs | -0.025 |
ouses | -0.024 |
Token | uddle |
Token ID | 24500 |
Feature activation | -1.07e-02 |
Pos logit contributions | |
days | +0.026 |
am | +0.025 |
wore | +0.025 |
packs | +0.024 |
wear | +0.024 |
Neg logit contributions | |
louder | -0.024 |
angrily | -0.024 |
harder | -0.023 |
trigger | -0.022 |
loudly | -0.022 |
Token | . |
Token ID | 13 |
Feature activation | -5.81e-02 |
Pos logit contributions | |
throttle | +0.024 |
trigger | +0.024 |
amus | +0.024 |
louder | +0.023 |
beast | +0.023 |
Neg logit contributions | |
days | -0.012 |
am | -0.012 |
wore | -0.012 |
packs | -0.011 |
wear | -0.009 |
Token | He |
Token ID | 679 |
Feature activation | -4.19e-02 |
Pos logit contributions | |
louder | +0.151 |
trigger | +0.146 |
harder | +0.145 |
throttle | +0.141 |
amus | +0.139 |
Neg logit contributions | |
wore | -0.049 |
am | -0.041 |
lived | -0.037 |
wear | -0.031 |
'm | -0.031 |
Token | wanted |
Token ID | 2227 |
Feature activation | -7.18e-02 |
Pos logit contributions | |
rier | +0.104 |
trigger | +0.104 |
throttle | +0.097 |
louder | +0.095 |
harder | +0.095 |
Neg logit contributions | |
wore | -0.057 |
am | -0.045 |
lived | -0.044 |
wear | -0.038 |
'm | -0.037 |
Token | to |
Token ID | 284 |
Feature activation | -4.20e-02 |
Pos logit contributions | |
trigger | +0.187 |
rier | +0.186 |
angrily | +0.179 |
accelerator | +0.168 |
iously | +0.167 |
Neg logit contributions | |
am | -0.061 |
wore | -0.059 |
wear | -0.055 |
have | -0.049 |
'm | -0.043 |
Token | catch |
Token ID | 4929 |
Feature activation | -7.51e-02 |
Pos logit contributions | |
louder | +0.079 |
angrily | +0.078 |
harder | +0.077 |
trigger | +0.076 |
loudly | +0.072 |
Neg logit contributions | |
am | -0.068 |
days | -0.068 |
wore | -0.065 |
wear | -0.063 |
packs | -0.062 |
Token | it |
Token ID | 340 |
Feature activation | -3.18e-02 |
Pos logit contributions | |
accelerator | +0.174 |
throttle | +0.173 |
iously | +0.171 |
Days | +0.170 |
ote | +0.168 |
Neg logit contributions | |
am | -0.068 |
have | -0.065 |
live | -0.063 |
wear | -0.062 |
wore | -0.058 |
Token | , |
Token ID | 11 |
Feature activation | -2.93e-02 |
Pos logit contributions | |
trigger | +0.087 |
throttle | +0.084 |
rus | +0.082 |
amus | +0.081 |
accelerator | +0.081 |
Neg logit contributions | |
am | -0.025 |
wear | -0.024 |
wore | -0.023 |
days | -0.021 |
packs | -0.018 |
Token | so |
Token ID | 523 |
Feature activation | -1.43e-02 |
Pos logit contributions | |
trigger | +0.065 |
amus | +0.061 |
beast | +0.061 |
rus | +0.061 |
throttle | +0.059 |
Neg logit contributions | |
wore | -0.038 |
wear | -0.036 |
am | -0.035 |
days | -0.031 |
have | -0.029 |
Token | he |
Token ID | 339 |
Feature activation | -4.25e-02 |
Pos logit contributions | |
amus | +0.032 |
trigger | +0.031 |
throttle | +0.031 |
angrily | +0.030 |
instructions | +0.030 |
Neg logit contributions | |
wore | -0.018 |
am | -0.017 |
wear | -0.016 |
days | -0.015 |
packs | -0.015 |
Token | started |
Token ID | 2067 |
Feature activation | -3.07e-02 |
Pos logit contributions | |
rier | +0.096 |
throttle | +0.095 |
trigger | +0.095 |
instructions | +0.091 |
angrily | +0.089 |
Neg logit contributions | |
wore | -0.063 |
lived | -0.044 |
wear | -0.044 |
am | -0.041 |
ouses | -0.038 |
Token |
|
Token ID | 198 |
Feature activation | -4.20e-02 |
Pos logit contributions | |
louder | +0.026 |
angrily | +0.026 |
trigger | +0.026 |
harder | +0.026 |
beast | +0.025 |
Neg logit contributions | |
days | -0.012 |
am | -0.011 |
wore | -0.011 |
packs | -0.010 |
ouses | -0.010 |
Token | Just |
Token ID | 5703 |
Feature activation | +1.54e-02 |
Pos logit contributions | |
trigger | +0.082 |
rier | +0.077 |
louder | +0.077 |
angrily | +0.077 |
iously | +0.076 |
Neg logit contributions | |
am | -0.068 |
days | -0.066 |
wore | -0.065 |
wear | -0.059 |
'm | -0.057 |
Token | then |
Token ID | 788 |
Feature activation | -1.17e-02 |
Pos logit contributions | |
wore | +0.028 |
am | +0.027 |
wear | +0.027 |
days | +0.026 |
packs | +0.025 |
Neg logit contributions | |
trigger | -0.025 |
angrily | -0.024 |
louder | -0.023 |
amus | -0.023 |
throttle | -0.023 |
Token | he |
Token ID | 339 |
Feature activation | -3.30e-02 |
Pos logit contributions | |
trigger | +0.026 |
amus | +0.025 |
louder | +0.025 |
angrily | +0.024 |
harder | +0.024 |
Neg logit contributions | |
am | -0.015 |
wore | -0.015 |
days | -0.014 |
packs | -0.013 |
wear | -0.013 |
Token | heard |
Token ID | 2982 |
Feature activation | -5.96e-02 |
Pos logit contributions | |
trigger | +0.068 |
angrily | +0.066 |
amus | +0.065 |
louder | +0.065 |
rier | +0.065 |
Neg logit contributions | |
wore | -0.048 |
am | -0.045 |
days | -0.043 |
packs | -0.042 |
wear | -0.040 |
Token | a |
Token ID | 257 |
Feature activation | -7.50e-02 |
Pos logit contributions | |
trigger | +0.152 |
rier | +0.143 |
rus | +0.137 |
iously | +0.136 |
amus | +0.136 |
Neg logit contributions | |
lived | -0.044 |
wore | -0.043 |
am | -0.043 |
wear | -0.042 |
live | -0.036 |
Token | voice |
Token ID | 3809 |
Feature activation | -4.72e-02 |
Pos logit contributions | |
amus | +0.121 |
trigger | +0.119 |
iously | +0.118 |
throttle | +0.113 |
harder | +0.112 |
Neg logit contributions | |
am | -0.141 |
days | -0.119 |
'm | -0.118 |
wear | -0.113 |
wore | -0.112 |
Token | . |
Token ID | 13 |
Feature activation | -5.66e-02 |
Pos logit contributions | |
trigger | +0.087 |
amus | +0.084 |
harder | +0.082 |
angrily | +0.081 |
throttle | +0.081 |
Neg logit contributions | |
days | -0.075 |
am | -0.075 |
wore | -0.073 |
wear | -0.071 |
packs | -0.068 |
Token | It |
Token ID | 632 |
Feature activation | -3.19e-02 |
Pos logit contributions | |
trigger | +0.111 |
louder | +0.109 |
harder | +0.109 |
amus | +0.105 |
angrily | +0.105 |
Neg logit contributions | |
am | -0.083 |
wore | -0.082 |
days | -0.077 |
wear | -0.072 |
packs | -0.071 |
Token | was |
Token ID | 373 |
Feature activation | -4.48e-02 |
Pos logit contributions | |
louder | +0.063 |
angrily | +0.062 |
harder | +0.062 |
trigger | +0.062 |
loudly | +0.058 |
Neg logit contributions | |
days | -0.047 |
am | -0.046 |
wore | -0.046 |
packs | -0.043 |
ouses | -0.042 |
Token | an |
Token ID | 281 |
Feature activation | -4.17e-02 |
Pos logit contributions | |
trigger | +0.075 |
louder | +0.075 |
angrily | +0.075 |
harder | +0.075 |
loudly | +0.069 |
Neg logit contributions | |
days | -0.077 |
am | -0.077 |
wore | -0.076 |
packs | -0.074 |
wear | -0.071 |
Token | , |
Token ID | 11 |
Feature activation | +8.95e-03 |
Pos logit contributions | |
days | +0.018 |
am | +0.017 |
packs | +0.017 |
wore | +0.017 |
ouses | +0.017 |
Neg logit contributions | |
louder | -0.020 |
angrily | -0.019 |
harder | -0.019 |
loudly | -0.018 |
trigger | -0.018 |
Token | Lily |
Token ID | 20037 |
Feature activation | -1.28e-02 |
Pos logit contributions | |
days | +0.014 |
am | +0.013 |
packs | +0.013 |
ouses | +0.013 |
wore | +0.013 |
Neg logit contributions | |
louder | -0.018 |
harder | -0.017 |
angrily | -0.017 |
trigger | -0.017 |
loudly | -0.016 |
Token | said |
Token ID | 531 |
Feature activation | -9.44e-03 |
Pos logit contributions | |
louder | +0.020 |
trigger | +0.019 |
angrily | +0.019 |
harder | +0.019 |
amus | +0.018 |
Neg logit contributions | |
wore | -0.024 |
days | -0.024 |
am | -0.024 |
packs | -0.023 |
ouses | -0.023 |
Token | , |
Token ID | 11 |
Feature activation | +2.03e-03 |
Pos logit contributions | |
louder | +0.018 |
angrily | +0.018 |
harder | +0.017 |
trigger | +0.017 |
loudly | +0.017 |
Neg logit contributions | |
days | -0.015 |
am | -0.015 |
wore | -0.014 |
packs | -0.014 |
ouses | -0.014 |
Token | " |
Token ID | 366 |
Feature activation | -2.66e-02 |
Pos logit contributions | |
days | +0.004 |
am | +0.004 |
wore | +0.004 |
packs | +0.004 |
ouses | +0.004 |
Neg logit contributions | |
louder | -0.003 |
angrily | -0.003 |
harder | -0.003 |
trigger | -0.003 |
beast | -0.003 |
Token | I |
Token ID | 40 |
Feature activation | +6.17e-02 |
Pos logit contributions | |
louder | +0.046 |
harder | +0.044 |
trigger | +0.043 |
angrily | +0.042 |
loudly | +0.040 |
Neg logit contributions | |
packs | -0.048 |
days | -0.048 |
ouses | -0.045 |
am | -0.044 |
wore | -0.043 |
Token | can |
Token ID | 460 |
Feature activation | +7.13e-03 |
Pos logit contributions | |
packs | +0.103 |
ouses | +0.097 |
owers | +0.093 |
days | +0.091 |
ained | +0.085 |
Neg logit contributions | |
harder | -0.112 |
louder | -0.109 |
angrily | -0.108 |
loudly | -0.102 |
beast | -0.093 |
Token | 't |
Token ID | 470 |
Feature activation | +1.60e-02 |
Pos logit contributions | |
packs | +0.013 |
days | +0.012 |
ouses | +0.012 |
wore | +0.012 |
am | +0.011 |
Neg logit contributions | |
louder | -0.012 |
harder | -0.011 |
angrily | -0.011 |
trigger | -0.011 |
loudly | -0.011 |
Token | wait |
Token ID | 4043 |
Feature activation | +2.50e-02 |
Pos logit contributions | |
packs | +0.030 |
ouses | +0.029 |
days | +0.029 |
wore | +0.028 |
am | +0.028 |
Neg logit contributions | |
louder | -0.026 |
harder | -0.025 |
angrily | -0.025 |
trigger | -0.024 |
loudly | -0.024 |
Token | to |
Token ID | 284 |
Feature activation | +1.16e-02 |
Pos logit contributions | |
days | +0.051 |
am | +0.049 |
wore | +0.049 |
packs | +0.048 |
ouses | +0.048 |
Neg logit contributions | |
louder | -0.037 |
harder | -0.036 |
angrily | -0.035 |
loudly | -0.033 |
trigger | -0.033 |
Token | see |
Token ID | 766 |
Feature activation | -1.28e-02 |
Pos logit contributions | |
days | +0.021 |
ouses | +0.020 |
packs | +0.020 |
am | +0.019 |
wore | +0.019 |
Neg logit contributions | |
louder | -0.019 |
harder | -0.019 |
angrily | -0.018 |
trigger | -0.018 |
loudly | -0.017 |
Token | . |
Token ID | 13 |
Feature activation | +2.96e-02 |
Pos logit contributions | |
days | +0.056 |
am | +0.051 |
ouses | +0.051 |
wore | +0.050 |
packs | +0.049 |
Neg logit contributions | |
louder | -0.041 |
harder | -0.040 |
loudly | -0.037 |
angrily | -0.036 |
trigger | -0.033 |
Token | She |
Token ID | 1375 |
Feature activation | +4.13e-02 |
Pos logit contributions | |
ouses | +0.060 |
days | +0.060 |
kin | +0.056 |
wore | +0.055 |
kins | +0.054 |
Neg logit contributions | |
harder | -0.038 |
louder | -0.034 |
Whoever | -0.034 |
angrily | -0.032 |
cautiously | -0.032 |
Token | had |
Token ID | 550 |
Feature activation | +2.13e-02 |
Pos logit contributions | |
packs | +0.066 |
days | +0.065 |
ouses | +0.063 |
am | +0.057 |
moderation | +0.054 |
Neg logit contributions | |
harder | -0.071 |
louder | -0.068 |
loudly | -0.065 |
carefully | -0.063 |
angrily | -0.062 |
Token | a |
Token ID | 257 |
Feature activation | +1.06e-02 |
Pos logit contributions | |
days | +0.048 |
ouses | +0.046 |
am | +0.046 |
packs | +0.045 |
wore | +0.043 |
Neg logit contributions | |
louder | -0.027 |
harder | -0.027 |
angrily | -0.024 |
loudly | -0.023 |
amus | -0.022 |
Token | lot |
Token ID | 1256 |
Feature activation | +4.26e-02 |
Pos logit contributions | |
days | +0.020 |
packs | +0.019 |
ouses | +0.019 |
am | +0.019 |
wore | +0.018 |
Neg logit contributions | |
louder | -0.017 |
harder | -0.016 |
angrily | -0.016 |
trigger | -0.016 |
loudly | -0.015 |
Token | of |
Token ID | 286 |
Feature activation | +4.92e-02 |
Pos logit contributions | |
days | +0.085 |
wore | +0.080 |
am | +0.080 |
packs | +0.079 |
ouses | +0.079 |
Neg logit contributions | |
harder | -0.066 |
louder | -0.065 |
angrily | -0.059 |
loudly | -0.057 |
instructions | -0.055 |
Token | fun |
Token ID | 1257 |
Feature activation | +3.61e-02 |
Pos logit contributions | |
days | +0.091 |
ouses | +0.085 |
packs | +0.083 |
am | +0.081 |
wore | +0.079 |
Neg logit contributions | |
harder | -0.081 |
louder | -0.081 |
instructions | -0.074 |
adult | -0.072 |
loudly | -0.071 |
Token | making |
Token ID | 1642 |
Feature activation | -3.41e-03 |
Pos logit contributions | |
days | +0.069 |
am | +0.067 |
ouses | +0.067 |
packs | +0.067 |
wore | +0.064 |
Neg logit contributions | |
louder | -0.054 |
harder | -0.052 |
loudly | -0.051 |
angrily | -0.048 |
instructions | -0.045 |
Token | pretty |
Token ID | 2495 |
Feature activation | +3.02e-02 |
Pos logit contributions | |
trigger | +0.007 |
angrily | +0.007 |
louder | +0.007 |
beast | +0.007 |
harder | +0.007 |
Neg logit contributions | |
days | -0.005 |
am | -0.005 |
wore | -0.005 |
packs | -0.005 |
ouses | -0.004 |
Token | pictures |
Token ID | 5986 |
Feature activation | +1.97e-02 |
Pos logit contributions | |
days | +0.060 |
am | +0.057 |
wore | +0.056 |
packs | +0.054 |
ouses | +0.053 |
Neg logit contributions | |
louder | -0.048 |
harder | -0.046 |
loudly | -0.043 |
angrily | -0.043 |
trigger | -0.041 |
Token | . |
Token ID | 13 |
Feature activation | +3.30e-02 |
Pos logit contributions | |
days | +0.040 |
am | +0.038 |
wore | +0.037 |
ouses | +0.037 |
packs | +0.037 |
Neg logit contributions | |
louder | -0.030 |
harder | -0.029 |
angrily | -0.027 |
loudly | -0.027 |
trigger | -0.024 |
Token | you |
Token ID | 345 |
Feature activation | +2.89e-02 |
Pos logit contributions | |
days | +0.014 |
am | +0.013 |
wore | +0.013 |
packs | +0.013 |
ouses | +0.013 |
Neg logit contributions | |
louder | -0.011 |
harder | -0.011 |
angrily | -0.011 |
trigger | -0.011 |
loudly | -0.010 |
Token | very |
Token ID | 845 |
Feature activation | +4.47e-02 |
Pos logit contributions | |
days | +0.059 |
am | +0.057 |
wore | +0.057 |
packs | +0.056 |
ouses | +0.056 |
Neg logit contributions | |
louder | -0.043 |
harder | -0.041 |
angrily | -0.041 |
trigger | -0.040 |
loudly | -0.038 |
Token | much |
Token ID | 881 |
Feature activation | +3.58e-02 |
Pos logit contributions | |
days | +0.074 |
am | +0.073 |
packs | +0.072 |
wore | +0.072 |
ouses | +0.069 |
Neg logit contributions | |
louder | -0.081 |
harder | -0.079 |
angrily | -0.079 |
loudly | -0.076 |
trigger | -0.073 |
Token | . |
Token ID | 13 |
Feature activation | +2.12e-02 |
Pos logit contributions | |
days | +0.060 |
am | +0.058 |
wore | +0.058 |
packs | +0.057 |
ouses | +0.056 |
Neg logit contributions | |
louder | -0.065 |
harder | -0.064 |
angrily | -0.064 |
trigger | -0.061 |
loudly | -0.060 |
Token | And |
Token ID | 843 |
Feature activation | +3.03e-02 |
Pos logit contributions | |
days | +0.042 |
packs | +0.041 |
ouses | +0.040 |
wore | +0.039 |
am | +0.038 |
Neg logit contributions | |
louder | -0.031 |
harder | -0.030 |
angrily | -0.028 |
trigger | -0.027 |
loudly | -0.026 |
Token | I |
Token ID | 314 |
Feature activation | +5.38e-02 |
Pos logit contributions | |
days | +0.054 |
packs | +0.053 |
ouses | +0.051 |
am | +0.051 |
wore | +0.050 |
Neg logit contributions | |
louder | -0.053 |
harder | -0.051 |
angrily | -0.049 |
loudly | -0.047 |
trigger | -0.046 |
Token | love |
Token ID | 1842 |
Feature activation | +7.11e-03 |
Pos logit contributions | |
packs | +0.076 |
ouses | +0.071 |
days | +0.065 |
wore | +0.062 |
owers | +0.059 |
Neg logit contributions | |
louder | -0.113 |
harder | -0.112 |
angrily | -0.105 |
loudly | -0.100 |
beast | -0.097 |
Token | your |
Token ID | 534 |
Feature activation | +5.80e-03 |
Pos logit contributions | |
days | +0.013 |
am | +0.013 |
wore | +0.012 |
packs | +0.012 |
ouses | +0.012 |
Neg logit contributions | |
louder | -0.012 |
angrily | -0.012 |
harder | -0.012 |
trigger | -0.011 |
loudly | -0.011 |
Token | pictures |
Token ID | 5986 |
Feature activation | +2.97e-02 |
Pos logit contributions | |
days | +0.010 |
am | +0.009 |
wore | +0.009 |
packs | +0.009 |
ouses | +0.009 |
Neg logit contributions | |
louder | -0.011 |
angrily | -0.011 |
harder | -0.010 |
trigger | -0.010 |
loudly | -0.010 |
Token | , |
Token ID | 11 |
Feature activation | -8.98e-03 |
Pos logit contributions | |
days | +0.058 |
am | +0.057 |
packs | +0.056 |
ouses | +0.056 |
wore | +0.055 |
Neg logit contributions | |
louder | -0.044 |
harder | -0.043 |
angrily | -0.040 |
loudly | -0.039 |
instructions | -0.035 |
Token | too |
Token ID | 1165 |
Feature activation | +3.06e-02 |
Pos logit contributions | |
trigger | +0.015 |
angrily | +0.015 |
louder | +0.015 |
harder | +0.015 |
beast | +0.014 |
Neg logit contributions | |
days | -0.016 |
wore | -0.015 |
am | -0.015 |
packs | -0.015 |
wear | -0.015 |
Token | to |
Token ID | 284 |
Feature activation | +2.62e-02 |
Pos logit contributions | |
days | +0.031 |
am | +0.030 |
wore | +0.030 |
packs | +0.030 |
ouses | +0.029 |
Neg logit contributions | |
louder | -0.028 |
trigger | -0.028 |
angrily | -0.028 |
harder | -0.027 |
beast | -0.026 |
Token | sit |
Token ID | 1650 |
Feature activation | +3.50e-02 |
Pos logit contributions | |
ouses | +0.037 |
days | +0.037 |
packs | +0.036 |
wore | +0.035 |
am | +0.034 |
Neg logit contributions | |
louder | -0.053 |
harder | -0.052 |
angrily | -0.052 |
loudly | -0.050 |
beast | -0.048 |
Token | at |
Token ID | 379 |
Feature activation | +1.76e-02 |
Pos logit contributions | |
days | +0.061 |
am | +0.060 |
wore | +0.059 |
packs | +0.058 |
ouses | +0.057 |
Neg logit contributions | |
louder | -0.061 |
angrily | -0.059 |
harder | -0.059 |
trigger | -0.058 |
loudly | -0.056 |
Token | . |
Token ID | 13 |
Feature activation | +6.72e-03 |
Pos logit contributions | |
days | +0.030 |
am | +0.029 |
wore | +0.029 |
packs | +0.029 |
ouses | +0.028 |
Neg logit contributions | |
louder | -0.031 |
angrily | -0.030 |
harder | -0.030 |
trigger | -0.029 |
loudly | -0.028 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +3.58e-02 |
Pos logit contributions | |
days | +0.011 |
packs | +0.011 |
ouses | +0.011 |
wore | +0.011 |
am | +0.011 |
Neg logit contributions | |
louder | -0.012 |
harder | -0.011 |
angrily | -0.011 |
Whoever | -0.011 |
amus | -0.010 |
Token | Once |
Token ID | 7454 |
Feature activation | +6.51e-02 |
Pos logit contributions | |
days | +0.060 |
ouses | +0.060 |
wore | +0.056 |
packs | +0.055 |
wear | +0.054 |
Neg logit contributions | |
harder | -0.060 |
angrily | -0.059 |
louder | -0.058 |
beast | -0.056 |
loudly | -0.055 |
Token | upon |
Token ID | 2402 |
Feature activation | +1.12e-02 |
Pos logit contributions | |
days | +0.099 |
ouses | +0.096 |
wore | +0.090 |
am | +0.090 |
packs | +0.083 |
Neg logit contributions | |
harder | -0.120 |
louder | -0.116 |
angrily | -0.114 |
loudly | -0.112 |
curiously | -0.108 |
Token | a |
Token ID | 257 |
Feature activation | +2.45e-02 |
Pos logit contributions | |
days | +0.023 |
am | +0.023 |
wore | +0.023 |
ouses | +0.022 |
packs | +0.022 |
Neg logit contributions | |
louder | -0.016 |
harder | -0.015 |
angrily | -0.015 |
trigger | -0.014 |
loudly | -0.014 |
Token | time |
Token ID | 640 |
Feature activation | +2.54e-02 |
Pos logit contributions | |
days | +0.036 |
am | +0.035 |
ouses | +0.035 |
wore | +0.034 |
packs | +0.034 |
Neg logit contributions | |
louder | -0.048 |
harder | -0.048 |
angrily | -0.048 |
loudly | -0.046 |
trigger | -0.044 |
Token | , |
Token ID | 11 |
Feature activation | +1.52e-02 |
Pos logit contributions | |
ouses | +0.050 |
days | +0.049 |
wore | +0.047 |
packs | +0.046 |
am | +0.046 |
Neg logit contributions | |
angrily | -0.037 |
harder | -0.036 |
louder | -0.036 |
loudly | -0.034 |
beast | -0.032 |
Token | there |
Token ID | 612 |
Feature activation | +3.34e-02 |
Pos logit contributions | |
ouses | +0.030 |
days | +0.027 |
packs | +0.026 |
wore | +0.025 |
am | +0.025 |
Neg logit contributions | |
harder | -0.024 |
louder | -0.024 |
angrily | -0.024 |
loudly | -0.023 |
trigger | -0.021 |
Token | Daisy |
Token ID | 40355 |
Feature activation | +1.58e-02 |
Pos logit contributions | |
days | +0.038 |
ouses | +0.037 |
packs | +0.036 |
am | +0.034 |
wore | +0.034 |
Neg logit contributions | |
harder | -0.029 |
louder | -0.029 |
loudly | -0.028 |
angrily | -0.028 |
cautiously | -0.025 |
Token | was |
Token ID | 373 |
Feature activation | +1.38e-02 |
Pos logit contributions | |
packs | +0.032 |
ouses | +0.030 |
days | +0.030 |
ippers | +0.027 |
ectar | +0.027 |
Neg logit contributions | |
loudly | -0.022 |
angrily | -0.021 |
harder | -0.020 |
quickly | -0.020 |
beast | -0.019 |
Token | three |
Token ID | 1115 |
Feature activation | +1.65e-02 |
Pos logit contributions | |
packs | +0.031 |
ouses | +0.031 |
days | +0.030 |
am | +0.029 |
wore | +0.028 |
Neg logit contributions | |
louder | -0.019 |
harder | -0.017 |
angrily | -0.017 |
loudly | -0.016 |
amus | -0.015 |
Token | years |
Token ID | 812 |
Feature activation | +3.52e-02 |
Pos logit contributions | |
days | +0.027 |
am | +0.027 |
wore | +0.026 |
packs | +0.026 |
ouses | +0.026 |
Neg logit contributions | |
louder | -0.030 |
angrily | -0.029 |
harder | -0.029 |
loudly | -0.028 |
trigger | -0.028 |
Token | old |
Token ID | 1468 |
Feature activation | +3.14e-02 |
Pos logit contributions | |
days | +0.075 |
am | +0.073 |
wore | +0.073 |
packs | +0.072 |
ouses | +0.071 |
Neg logit contributions | |
louder | -0.048 |
angrily | -0.046 |
harder | -0.046 |
trigger | -0.045 |
loudly | -0.042 |
Token | and |
Token ID | 290 |
Feature activation | +6.29e-02 |
Pos logit contributions | |
days | +0.058 |
wore | +0.057 |
am | +0.057 |
packs | +0.055 |
ouses | +0.054 |
Neg logit contributions | |
louder | -0.051 |
angrily | -0.050 |
trigger | -0.049 |
harder | -0.049 |
amus | -0.047 |
Token | loved |
Token ID | 6151 |
Feature activation | +1.66e-02 |
Pos logit contributions | |
packs | +0.148 |
ouses | +0.125 |
days | +0.122 |
aj | +0.114 |
aters | +0.113 |
Neg logit contributions | |
loudly | -0.096 |
louder | -0.090 |
angrily | -0.082 |
quickly | -0.080 |
harder | -0.076 |
Token | to |
Token ID | 284 |
Feature activation | +1.13e-02 |
Pos logit contributions | |
days | +0.036 |
am | +0.035 |
ouses | +0.035 |
packs | +0.034 |
wore | +0.034 |
Neg logit contributions | |
louder | -0.022 |
harder | -0.021 |
angrily | -0.020 |
loudly | -0.020 |
instructions | -0.018 |
Token | play |
Token ID | 711 |
Feature activation | -1.89e-03 |
Pos logit contributions | |
packs | +0.019 |
ouses | +0.018 |
days | +0.017 |
ained | +0.017 |
wore | +0.016 |
Neg logit contributions | |
louder | -0.018 |
loudly | -0.018 |
harder | -0.018 |
angrily | -0.017 |
defeat | -0.016 |
Token | all |
Token ID | 477 |
Feature activation | +5.47e-02 |
Pos logit contributions | |
louder | +0.003 |
harder | +0.003 |
angrily | +0.003 |
loudly | +0.003 |
trigger | +0.003 |
Neg logit contributions | |
days | -0.004 |
packs | -0.003 |
am | -0.003 |
wore | -0.003 |
ouses | -0.003 |
Token | day |
Token ID | 1110 |
Feature activation | +4.57e-02 |
Pos logit contributions | |
ouses | +0.102 |
aj | +0.092 |
packs | +0.086 |
days | +0.085 |
am | +0.081 |
Neg logit contributions | |
harder | -0.090 |
louder | -0.083 |
loudly | -0.082 |
way | -0.082 |
up | -0.076 |
Token | make |
Token ID | 787 |
Feature activation | -8.20e-03 |
Pos logit contributions | |
days | +0.034 |
am | +0.033 |
wore | +0.032 |
packs | +0.031 |
ouses | +0.031 |
Neg logit contributions | |
louder | -0.049 |
angrily | -0.048 |
harder | -0.048 |
trigger | -0.047 |
beast | -0.045 |
Token | it |
Token ID | 340 |
Feature activation | +1.07e-02 |
Pos logit contributions | |
trigger | +0.016 |
angrily | +0.015 |
beast | +0.015 |
louder | +0.015 |
throttle | +0.015 |
Neg logit contributions | |
am | -0.012 |
days | -0.012 |
packs | -0.012 |
wore | -0.011 |
wear | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | +1.24e-02 |
Pos logit contributions | |
days | +0.020 |
wore | +0.019 |
am | +0.019 |
packs | +0.019 |
ouses | +0.019 |
Neg logit contributions | |
louder | -0.017 |
harder | -0.017 |
angrily | -0.017 |
trigger | -0.016 |
loudly | -0.016 |
Token | She |
Token ID | 1375 |
Feature activation | +7.00e-03 |
Pos logit contributions | |
days | +0.019 |
am | +0.018 |
packs | +0.018 |
wore | +0.018 |
ouses | +0.017 |
Neg logit contributions | |
angrily | -0.024 |
louder | -0.024 |
harder | -0.024 |
loudly | -0.022 |
trigger | -0.022 |
Token | had |
Token ID | 550 |
Feature activation | +8.87e-03 |
Pos logit contributions | |
wore | +0.010 |
days | +0.009 |
am | +0.009 |
ouses | +0.008 |
packs | +0.008 |
Neg logit contributions | |
louder | -0.015 |
trigger | -0.015 |
angrily | -0.015 |
harder | -0.015 |
beast | -0.014 |
Token | all |
Token ID | 477 |
Feature activation | +4.03e-02 |
Pos logit contributions | |
days | +0.016 |
am | +0.016 |
wore | +0.016 |
packs | +0.015 |
ouses | +0.015 |
Neg logit contributions | |
louder | -0.015 |
trigger | -0.014 |
angrily | -0.014 |
harder | -0.014 |
beast | -0.013 |
Token | the |
Token ID | 262 |
Feature activation | +2.25e-02 |
Pos logit contributions | |
ouses | +0.063 |
days | +0.060 |
am | +0.055 |
wore | +0.055 |
packs | +0.053 |
Neg logit contributions | |
harder | -0.079 |
louder | -0.076 |
angrily | -0.072 |
instructions | -0.070 |
loudly | -0.069 |
Token | material |
Token ID | 2587 |
Feature activation | +3.15e-02 |
Pos logit contributions | |
days | +0.036 |
am | +0.035 |
wore | +0.035 |
packs | +0.034 |
ouses | +0.034 |
Neg logit contributions | |
louder | -0.042 |
angrily | -0.041 |
harder | -0.041 |
trigger | -0.040 |
loudly | -0.039 |
Token | she |
Token ID | 673 |
Feature activation | +3.66e-02 |
Pos logit contributions | |
days | +0.058 |
am | +0.055 |
wore | +0.055 |
packs | +0.054 |
ouses | +0.054 |
Neg logit contributions | |
louder | -0.052 |
harder | -0.051 |
angrily | -0.051 |
trigger | -0.049 |
loudly | -0.047 |
Token | needed |
Token ID | 2622 |
Feature activation | -7.48e-04 |
Pos logit contributions | |
packs | +0.052 |
days | +0.051 |
am | +0.048 |
ouses | +0.047 |
wore | +0.044 |
Neg logit contributions | |
angrily | -0.072 |
louder | -0.071 |
harder | -0.070 |
loudly | -0.069 |
trigger | -0.066 |
Token | , |
Token ID | 11 |
Feature activation | +3.61e-03 |
Pos logit contributions | |
louder | +0.001 |
trigger | +0.001 |
angrily | +0.001 |
harder | +0.001 |
amus | +0.001 |
Neg logit contributions | |
days | -0.001 |
am | -0.001 |
wore | -0.001 |
packs | -0.001 |
ouses | -0.001 |
Token | friends |
Token ID | 2460 |
Feature activation | +8.53e-03 |
Pos logit contributions | |
louder | +0.016 |
angrily | +0.016 |
harder | +0.016 |
trigger | +0.016 |
amus | +0.015 |
Neg logit contributions | |
days | -0.013 |
am | -0.013 |
wore | -0.013 |
packs | -0.013 |
ouses | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | -4.93e-04 |
Pos logit contributions | |
days | +0.017 |
packs | +0.016 |
wore | +0.016 |
ouses | +0.016 |
am | +0.015 |
Neg logit contributions | |
louder | -0.013 |
harder | -0.013 |
angrily | -0.012 |
loudly | -0.012 |
instructions | -0.011 |
Token | From |
Token ID | 3574 |
Feature activation | +2.08e-02 |
Pos logit contributions | |
harder | +0.001 |
louder | +0.001 |
angrily | +0.001 |
loudly | +0.001 |
trigger | +0.001 |
Neg logit contributions | |
days | -0.001 |
am | -0.001 |
packs | -0.001 |
wore | -0.001 |
ouses | -0.001 |
Token | that |
Token ID | 326 |
Feature activation | +1.04e-02 |
Pos logit contributions | |
wore | +0.043 |
am | +0.043 |
days | +0.043 |
packs | +0.041 |
ouses | +0.041 |
Neg logit contributions | |
louder | -0.029 |
angrily | -0.028 |
trigger | -0.028 |
harder | -0.027 |
amus | -0.025 |
Token | day |
Token ID | 1110 |
Feature activation | +2.62e-02 |
Pos logit contributions | |
days | +0.009 |
packs | +0.009 |
am | +0.009 |
ouses | +0.009 |
wore | +0.008 |
Neg logit contributions | |
louder | -0.027 |
harder | -0.027 |
angrily | -0.026 |
trigger | -0.026 |
loudly | -0.026 |
Token | on |
Token ID | 319 |
Feature activation | +4.42e-02 |
Pos logit contributions | |
days | +0.041 |
packs | +0.038 |
ouses | +0.038 |
am | +0.038 |
wore | +0.037 |
Neg logit contributions | |
louder | -0.052 |
harder | -0.051 |
angrily | -0.049 |
trigger | -0.048 |
loudly | -0.048 |
Token | , |
Token ID | 11 |
Feature activation | -6.33e-03 |
Pos logit contributions | |
days | +0.083 |
ouses | +0.079 |
packs | +0.077 |
wore | +0.075 |
am | +0.075 |
Neg logit contributions | |
harder | -0.072 |
louder | -0.071 |
angrily | -0.070 |
loudly | -0.067 |
beast | -0.066 |
Token | Lily |
Token ID | 20037 |
Feature activation | -1.32e-02 |
Pos logit contributions | |
louder | +0.012 |
harder | +0.012 |
angrily | +0.012 |
loudly | +0.011 |
trigger | +0.011 |
Neg logit contributions | |
days | -0.010 |
packs | -0.010 |
am | -0.010 |
ouses | -0.010 |
wore | -0.009 |
Token | and |
Token ID | 290 |
Feature activation | -3.17e-03 |
Pos logit contributions | |
harder | +0.020 |
louder | +0.020 |
angrily | +0.019 |
loudly | +0.019 |
beast | +0.019 |
Neg logit contributions | |
days | -0.026 |
packs | -0.025 |
ouses | -0.024 |
am | -0.023 |
wear | -0.022 |
Token | her |
Token ID | 607 |
Feature activation | -2.80e-02 |
Pos logit contributions | |
louder | +0.007 |
angrily | +0.006 |
trigger | +0.006 |
harder | +0.006 |
throttle | +0.006 |
Neg logit contributions | |
wore | -0.004 |
days | -0.004 |
am | -0.004 |
packs | -0.004 |
wear | -0.004 |
Token | animal |
Token ID | 5044 |
Feature activation | -8.19e-03 |
Pos logit contributions | |
angrily | +0.052 |
louder | +0.050 |
harder | +0.049 |
trigger | +0.049 |
throttle | +0.047 |
Neg logit contributions | |
am | -0.047 |
wore | -0.046 |
days | -0.044 |
packs | -0.043 |
wear | -0.043 |
Token | red |
Token ID | 2266 |
Feature activation | -6.36e-03 |
Pos logit contributions | |
days | +0.000 |
wore | +0.000 |
packs | +0.000 |
am | +0.000 |
wear | +0.000 |
Neg logit contributions | |
angrily | -0.000 |
louder | -0.000 |
harder | -0.000 |
trigger | -0.000 |
loudly | -0.000 |
Token | car |
Token ID | 1097 |
Feature activation | +5.43e-03 |
Pos logit contributions | |
angrily | +0.009 |
louder | +0.009 |
harder | +0.008 |
loudly | +0.008 |
trigger | +0.008 |
Neg logit contributions | |
am | -0.013 |
days | -0.013 |
packs | -0.013 |
wore | -0.013 |
wear | -0.013 |
Token | ? |
Token ID | 30 |
Feature activation | -6.04e-03 |
Pos logit contributions | |
days | +0.007 |
am | +0.007 |
wore | +0.007 |
packs | +0.006 |
ouses | +0.006 |
Neg logit contributions | |
louder | -0.012 |
angrily | -0.012 |
harder | -0.012 |
trigger | -0.012 |
beast | -0.011 |
Token | Where |
Token ID | 6350 |
Feature activation | +1.99e-02 |
Pos logit contributions | |
louder | +0.011 |
angrily | +0.011 |
harder | +0.011 |
trigger | +0.011 |
loudly | +0.010 |
Neg logit contributions | |
days | -0.010 |
am | -0.010 |
wore | -0.009 |
packs | -0.009 |
ouses | -0.009 |
Token | is |
Token ID | 318 |
Feature activation | -2.69e-02 |
Pos logit contributions | |
days | +0.027 |
ouses | +0.026 |
packs | +0.025 |
wore | +0.025 |
am | +0.025 |
Neg logit contributions | |
louder | -0.041 |
harder | -0.041 |
angrily | -0.041 |
trigger | -0.039 |
beast | -0.039 |
Token | it |
Token ID | 340 |
Feature activation | +6.10e-03 |
Pos logit contributions | |
louder | +0.048 |
angrily | +0.048 |
harder | +0.046 |
trigger | +0.046 |
loudly | +0.044 |
Neg logit contributions | |
wore | -0.045 |
days | -0.044 |
am | -0.044 |
packs | -0.043 |
wear | -0.042 |
Token | ?" |
Token ID | 1701 |
Feature activation | -3.02e-04 |
Pos logit contributions | |
days | +0.008 |
ouses | +0.008 |
packs | +0.008 |
am | +0.007 |
wore | +0.007 |
Neg logit contributions | |
louder | -0.013 |
harder | -0.013 |
angrily | -0.013 |
loudly | -0.012 |
trigger | -0.012 |
Token | Lily |
Token ID | 20037 |
Feature activation | -9.45e-03 |
Pos logit contributions | |
louder | +0.001 |
angrily | +0.001 |
harder | +0.001 |
trigger | +0.001 |
loudly | +0.001 |
Neg logit contributions | |
days | -0.000 |
packs | -0.000 |
am | -0.000 |
wore | -0.000 |
ouses | -0.000 |
Token | pretended |
Token ID | 36766 |
Feature activation | -3.96e-02 |
Pos logit contributions | |
trigger | +0.020 |
louder | +0.020 |
harder | +0.019 |
throttle | +0.019 |
beast | +0.019 |
Neg logit contributions | |
wore | -0.014 |
am | -0.013 |
days | -0.012 |
wear | -0.012 |
packs | -0.012 |
Token | she |
Token ID | 673 |
Feature activation | +1.18e-02 |
Pos logit contributions | |
trigger | +0.078 |
louder | +0.073 |
amus | +0.072 |
angrily | +0.071 |
throttle | +0.070 |
Neg logit contributions | |
wore | -0.063 |
am | -0.060 |
days | -0.059 |
wear | -0.058 |
packs | -0.057 |
Token | did |
Token ID | 750 |
Feature activation | -3.02e-02 |
Pos logit contributions | |
days | +0.017 |
am | +0.016 |
packs | +0.016 |
ouses | +0.016 |
wore | +0.016 |
Neg logit contributions | |
louder | -0.024 |
angrily | -0.024 |
harder | -0.023 |
trigger | -0.023 |
loudly | -0.022 |
Token | now |
Token ID | 783 |
Feature activation | +1.81e-02 |
Pos logit contributions | |
louder | +0.002 |
trigger | +0.002 |
angrily | +0.002 |
harder | +0.002 |
beast | +0.002 |
Neg logit contributions | |
days | -0.002 |
am | -0.002 |
wore | -0.002 |
packs | -0.002 |
ouses | -0.002 |
Token | ! |
Token ID | 0 |
Feature activation | -6.14e-03 |
Pos logit contributions | |
am | +0.025 |
days | +0.025 |
wore | +0.024 |
packs | +0.024 |
wear | +0.023 |
Neg logit contributions | |
louder | -0.037 |
trigger | -0.037 |
angrily | -0.036 |
amus | -0.035 |
harder | -0.035 |
Token | It |
Token ID | 632 |
Feature activation | +1.38e-02 |
Pos logit contributions | |
louder | +0.012 |
angrily | +0.011 |
harder | +0.011 |
trigger | +0.011 |
loudly | +0.011 |
Neg logit contributions | |
days | -0.010 |
packs | -0.009 |
am | -0.009 |
wore | -0.009 |
ouses | -0.009 |
Token | looks |
Token ID | 3073 |
Feature activation | -4.16e-03 |
Pos logit contributions | |
am | +0.020 |
days | +0.019 |
wore | +0.019 |
packs | +0.018 |
ouses | +0.017 |
Neg logit contributions | |
louder | -0.028 |
trigger | -0.028 |
angrily | -0.028 |
harder | -0.027 |
throttle | -0.026 |
Token | y |
Token ID | 331 |
Feature activation | +1.30e-02 |
Pos logit contributions | |
louder | +0.008 |
angrily | +0.008 |
trigger | +0.008 |
harder | +0.008 |
beast | +0.007 |
Neg logit contributions | |
days | -0.006 |
am | -0.006 |
wore | -0.006 |
packs | -0.006 |
ouses | -0.006 |
Token | ummy |
Token ID | 13513 |
Feature activation | +3.30e-02 |
Pos logit contributions | |
days | +0.023 |
am | +0.022 |
wore | +0.022 |
packs | +0.021 |
ouses | +0.021 |
Neg logit contributions | |
louder | -0.022 |
angrily | -0.022 |
harder | -0.022 |
trigger | -0.021 |
loudly | -0.021 |
Token | and |
Token ID | 290 |
Feature activation | +5.65e-02 |
Pos logit contributions | |
days | +0.065 |
am | +0.062 |
wore | +0.061 |
ouses | +0.061 |
packs | +0.060 |
Neg logit contributions | |
louder | -0.051 |
harder | -0.050 |
angrily | -0.050 |
trigger | -0.047 |
loudly | -0.046 |
Token | fun |
Token ID | 1257 |
Feature activation | +2.45e-02 |
Pos logit contributions | |
days | +0.119 |
packs | +0.115 |
ouses | +0.109 |
am | +0.101 |
wore | +0.097 |
Neg logit contributions | |
louder | -0.091 |
harder | -0.090 |
angrily | -0.081 |
loudly | -0.079 |
trigger | -0.074 |
Token | . |
Token ID | 13 |
Feature activation | +1.02e-02 |
Pos logit contributions | |
days | +0.047 |
am | +0.045 |
wore | +0.045 |
ouses | +0.044 |
packs | +0.044 |
Neg logit contributions | |
louder | -0.039 |
harder | -0.038 |
angrily | -0.038 |
trigger | -0.036 |
loudly | -0.035 |
Token | Please |
Token ID | 4222 |
Feature activation | +1.46e-02 |
Pos logit contributions | |
days | +0.018 |
packs | +0.017 |
am | +0.017 |
wore | +0.017 |
ouses | +0.017 |
Neg logit contributions | |
louder | -0.018 |
angrily | -0.018 |
harder | -0.017 |
trigger | -0.017 |
loudly | -0.017 |
Token | , |
Token ID | 11 |
Feature activation | -1.09e-02 |
Pos logit contributions | |
days | +0.025 |
packs | +0.025 |
ouses | +0.024 |
wore | +0.024 |
am | +0.023 |
Neg logit contributions | |
louder | -0.026 |
harder | -0.025 |
angrily | -0.025 |
trigger | -0.025 |
loudly | -0.023 |
Token | she |
Token ID | 673 |
Feature activation | +3.43e-02 |
Pos logit contributions | |
days | +0.015 |
ouses | +0.014 |
packs | +0.013 |
am | +0.013 |
wore | +0.012 |
Neg logit contributions | |
louder | -0.016 |
harder | -0.016 |
angrily | -0.016 |
loudly | -0.015 |
beast | -0.015 |
Token | touched |
Token ID | 12615 |
Feature activation | +6.37e-03 |
Pos logit contributions | |
days | +0.057 |
packs | +0.056 |
ouses | +0.054 |
am | +0.049 |
wore | +0.046 |
Neg logit contributions | |
angrily | -0.062 |
louder | -0.062 |
harder | -0.061 |
beast | -0.060 |
loudly | -0.058 |
Token | and |
Token ID | 290 |
Feature activation | +1.93e-02 |
Pos logit contributions | |
days | +0.011 |
am | +0.011 |
wore | +0.011 |
packs | +0.010 |
ouses | +0.010 |
Neg logit contributions | |
louder | -0.011 |
angrily | -0.011 |
harder | -0.011 |
trigger | -0.011 |
loudly | -0.010 |
Token | put |
Token ID | 1234 |
Feature activation | +1.88e-02 |
Pos logit contributions | |
days | +0.030 |
am | +0.029 |
packs | +0.029 |
wore | +0.028 |
ouses | +0.028 |
Neg logit contributions | |
louder | -0.037 |
angrily | -0.036 |
harder | -0.036 |
trigger | -0.035 |
loudly | -0.034 |
Token | in |
Token ID | 287 |
Feature activation | +3.58e-02 |
Pos logit contributions | |
days | +0.031 |
am | +0.030 |
wore | +0.030 |
packs | +0.029 |
ouses | +0.029 |
Neg logit contributions | |
louder | -0.034 |
angrily | -0.033 |
harder | -0.033 |
trigger | -0.033 |
loudly | -0.031 |
Token | her |
Token ID | 607 |
Feature activation | +2.35e-02 |
Pos logit contributions | |
days | +0.053 |
am | +0.051 |
wore | +0.050 |
packs | +0.049 |
ouses | +0.049 |
Neg logit contributions | |
louder | -0.073 |
angrily | -0.071 |
harder | -0.071 |
trigger | -0.069 |
loudly | -0.067 |
Token | mouth |
Token ID | 5422 |
Feature activation | +7.93e-03 |
Pos logit contributions | |
days | +0.041 |
am | +0.039 |
packs | +0.039 |
wore | +0.039 |
ouses | +0.038 |
Neg logit contributions | |
louder | -0.040 |
harder | -0.040 |
angrily | -0.039 |
trigger | -0.038 |
beast | -0.037 |
Token | . |
Token ID | 13 |
Feature activation | +1.70e-03 |
Pos logit contributions | |
days | +0.011 |
wore | +0.011 |
am | +0.011 |
packs | +0.011 |
ouses | +0.010 |
Neg logit contributions | |
trigger | -0.016 |
beast | -0.016 |
louder | -0.016 |
amus | -0.015 |
throttle | -0.015 |
Token | She |
Token ID | 1375 |
Feature activation | +9.81e-03 |
Pos logit contributions | |
days | +0.003 |
packs | +0.002 |
am | +0.002 |
wore | +0.002 |
ouses | +0.002 |
Neg logit contributions | |
louder | -0.003 |
harder | -0.003 |
angrily | -0.003 |
loudly | -0.003 |
trigger | -0.003 |
Token | continued |
Token ID | 3767 |
Feature activation | +8.23e-03 |
Pos logit contributions | |
days | +0.016 |
packs | +0.016 |
am | +0.015 |
ouses | +0.015 |
wore | +0.015 |
Neg logit contributions | |
louder | -0.018 |
harder | -0.018 |
angrily | -0.018 |
loudly | -0.017 |
trigger | -0.017 |
Token | to |
Token ID | 284 |
Feature activation | +2.61e-02 |
Pos logit contributions | |
days | +0.017 |
am | +0.016 |
ouses | +0.016 |
packs | +0.016 |
wore | +0.015 |
Neg logit contributions | |
louder | -0.012 |
harder | -0.012 |
angrily | -0.012 |
loudly | -0.011 |
trigger | -0.011 |
Token | and |
Token ID | 290 |
Feature activation | +1.80e-02 |
Pos logit contributions | |
days | +0.020 |
ouses | +0.019 |
wore | +0.019 |
am | +0.019 |
packs | +0.019 |
Neg logit contributions | |
louder | -0.021 |
harder | -0.021 |
angrily | -0.020 |
loudly | -0.019 |
trigger | -0.019 |
Token | has |
Token ID | 468 |
Feature activation | -8.57e-03 |
Pos logit contributions | |
days | +0.030 |
am | +0.029 |
wore | +0.029 |
packs | +0.029 |
ouses | +0.028 |
Neg logit contributions | |
louder | -0.033 |
angrily | -0.032 |
harder | -0.032 |
trigger | -0.031 |
loudly | -0.030 |
Token | some |
Token ID | 617 |
Feature activation | +1.07e-02 |
Pos logit contributions | |
louder | +0.015 |
angrily | +0.015 |
trigger | +0.014 |
harder | +0.014 |
beast | +0.014 |
Neg logit contributions | |
days | -0.015 |
am | -0.015 |
wore | -0.014 |
packs | -0.014 |
ouses | -0.014 |
Token | water |
Token ID | 1660 |
Feature activation | +7.61e-03 |
Pos logit contributions | |
days | +0.020 |
am | +0.018 |
ouses | +0.018 |
wore | +0.018 |
packs | +0.018 |
Neg logit contributions | |
louder | -0.018 |
harder | -0.018 |
angrily | -0.017 |
trigger | -0.017 |
loudly | -0.016 |
Token | ," |
Token ID | 553 |
Feature activation | +5.81e-03 |
Pos logit contributions | |
days | +0.013 |
am | +0.012 |
wore | +0.012 |
packs | +0.012 |
ouses | +0.012 |
Neg logit contributions | |
louder | -0.014 |
angrily | -0.013 |
harder | -0.013 |
trigger | -0.013 |
loudly | -0.013 |
Token | Ben |
Token ID | 3932 |
Feature activation | -3.61e-02 |
Pos logit contributions | |
am | +0.008 |
wore | +0.008 |
days | +0.008 |
packs | +0.008 |
wear | +0.008 |
Neg logit contributions | |
louder | -0.011 |
angrily | -0.011 |
trigger | -0.011 |
harder | -0.011 |
beast | -0.011 |
Token | said |
Token ID | 531 |
Feature activation | -2.22e-02 |
Pos logit contributions | |
trigger | +0.091 |
throttle | +0.087 |
beast | +0.086 |
amus | +0.085 |
louder | +0.085 |
Neg logit contributions | |
wore | -0.042 |
am | -0.034 |
days | -0.034 |
wear | -0.033 |
packs | -0.032 |
Token | . |
Token ID | 13 |
Feature activation | -1.92e-02 |
Pos logit contributions | |
amus | +0.052 |
beast | +0.052 |
trigger | +0.051 |
throttle | +0.051 |
accelerator | +0.048 |
Neg logit contributions | |
days | -0.026 |
wore | -0.023 |
am | -0.023 |
packs | -0.023 |
ouses | -0.022 |
Token | He |
Token ID | 679 |
Feature activation | -1.22e-02 |
Pos logit contributions | |
trigger | +0.040 |
louder | +0.040 |
beast | +0.039 |
angrily | +0.039 |
throttle | +0.039 |
Neg logit contributions | |
am | -0.026 |
wore | -0.025 |
packs | -0.023 |
days | -0.023 |
ouses | -0.023 |
Token | hoped |
Token ID | 10719 |
Feature activation | -1.24e-02 |
Pos logit contributions | |
trigger | +0.027 |
louder | +0.026 |
amus | +0.026 |
harder | +0.025 |
throttle | +0.025 |
Neg logit contributions | |
wore | -0.018 |
am | -0.015 |
days | -0.014 |
wear | -0.014 |
packs | -0.014 |
Token | the |
Token ID | 262 |
Feature activation | -1.56e-02 |
Pos logit contributions | |
trigger | +0.025 |
angrily | +0.024 |
amus | +0.023 |
throttle | +0.023 |
rus | +0.022 |
Neg logit contributions | |
am | -0.019 |
wore | -0.018 |
days | -0.018 |
packs | -0.018 |
wear | -0.018 |
Token | . |
Token ID | 13 |
Feature activation | -2.75e-02 |
Pos logit contributions | |
days | +0.015 |
am | +0.015 |
wore | +0.015 |
packs | +0.015 |
ouses | +0.014 |
Neg logit contributions | |
louder | -0.016 |
trigger | -0.016 |
angrily | -0.016 |
harder | -0.016 |
amus | -0.016 |
Token | The |
Token ID | 383 |
Feature activation | -3.00e-02 |
Pos logit contributions | |
louder | +0.064 |
trigger | +0.064 |
harder | +0.062 |
angrily | +0.060 |
throttle | +0.060 |
Neg logit contributions | |
wore | -0.030 |
am | -0.029 |
days | -0.026 |
wear | -0.024 |
ouses | -0.024 |
Token | fancy |
Token ID | 14996 |
Feature activation | -3.10e-02 |
Pos logit contributions | |
angrily | +0.051 |
louder | +0.046 |
harder | +0.046 |
iously | +0.044 |
loudly | +0.043 |
Neg logit contributions | |
wore | -0.054 |
am | -0.054 |
days | -0.051 |
wear | -0.048 |
lived | -0.046 |
Token | elephant |
Token ID | 20950 |
Feature activation | -3.22e-02 |
Pos logit contributions | |
louder | +0.048 |
harder | +0.048 |
angrily | +0.046 |
trigger | +0.041 |
tighter | +0.039 |
Neg logit contributions | |
wore | -0.063 |
am | -0.062 |
days | -0.060 |
packs | -0.059 |
wear | -0.057 |
Token | used |
Token ID | 973 |
Feature activation | -2.79e-02 |
Pos logit contributions | |
trigger | +0.084 |
louder | +0.080 |
rier | +0.079 |
amus | +0.077 |
throttle | +0.077 |
Neg logit contributions | |
wore | -0.042 |
lived | -0.031 |
am | -0.030 |
wear | -0.028 |
days | -0.027 |
Token | his |
Token ID | 465 |
Feature activation | -2.23e-02 |
Pos logit contributions | |
louder | +0.052 |
trigger | +0.052 |
angrily | +0.051 |
beast | +0.051 |
ote | +0.049 |
Neg logit contributions | |
wore | -0.043 |
packs | -0.042 |
am | -0.041 |
wear | -0.040 |
days | -0.038 |
Token | trunk |
Token ID | 21427 |
Feature activation | -1.90e-03 |
Pos logit contributions | |
louder | +0.033 |
angrily | +0.033 |
harder | +0.032 |
trigger | +0.032 |
loudly | +0.030 |
Neg logit contributions | |
days | -0.044 |
am | -0.043 |
wore | -0.043 |
packs | -0.042 |
ouses | -0.042 |
Token | to |
Token ID | 284 |
Feature activation | +2.03e-03 |
Pos logit contributions | |
louder | +0.004 |
trigger | +0.004 |
beast | +0.004 |
amus | +0.003 |
angrily | +0.003 |
Neg logit contributions | |
packs | -0.003 |
wore | -0.003 |
am | -0.003 |
days | -0.003 |
ouses | -0.003 |
Token | help |
Token ID | 1037 |
Feature activation | -4.38e-02 |
Pos logit contributions | |
am | +0.003 |
days | +0.003 |
wore | +0.003 |
wear | +0.003 |
packs | +0.003 |
Neg logit contributions | |
louder | -0.004 |
angrily | -0.004 |
trigger | -0.004 |
harder | -0.004 |
beast | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | -4.54e-02 |
Pos logit contributions | |
throttle | +0.094 |
louder | +0.094 |
trigger | +0.094 |
rus | +0.091 |
ote | +0.091 |
Neg logit contributions | |
wear | -0.052 |
am | -0.050 |
wore | -0.047 |
live | -0.043 |
days | -0.043 |
Token | bird |
Token ID | 6512 |
Feature activation | -2.41e-02 |
Pos logit contributions | |
angrily | +0.080 |
harder | +0.075 |
louder | +0.074 |
cautiously | +0.071 |
accelerator | +0.070 |
Neg logit contributions | |
am | -0.075 |
wore | -0.074 |
days | -0.070 |
wear | -0.067 |
live | -0.066 |
Token | him |
Token ID | 683 |
Feature activation | -1.56e-02 |
Pos logit contributions | |
trigger | +0.024 |
beast | +0.022 |
throttle | +0.021 |
angrily | +0.021 |
louder | +0.021 |
Neg logit contributions | |
am | -0.015 |
wear | -0.015 |
wore | -0.015 |
days | -0.015 |
packs | -0.013 |
Token | that |
Token ID | 326 |
Feature activation | +2.91e-03 |
Pos logit contributions | |
louder | +0.024 |
angrily | +0.023 |
trigger | +0.023 |
harder | +0.023 |
beast | +0.022 |
Neg logit contributions | |
days | -0.030 |
am | -0.030 |
wore | -0.030 |
packs | -0.029 |
ouses | -0.029 |
Token | she |
Token ID | 673 |
Feature activation | +1.25e-02 |
Pos logit contributions | |
days | +0.004 |
am | +0.004 |
wore | +0.004 |
packs | +0.004 |
ouses | +0.004 |
Neg logit contributions | |
louder | -0.006 |
harder | -0.006 |
angrily | -0.006 |
trigger | -0.005 |
loudly | -0.005 |
Token | would |
Token ID | 561 |
Feature activation | +9.17e-04 |
Pos logit contributions | |
days | +0.016 |
am | +0.015 |
wore | +0.015 |
packs | +0.014 |
ouses | +0.014 |
Neg logit contributions | |
louder | -0.028 |
angrily | -0.028 |
trigger | -0.027 |
harder | -0.027 |
beast | -0.026 |
Token | be |
Token ID | 307 |
Feature activation | +5.06e-03 |
Pos logit contributions | |
days | +0.001 |
am | +0.001 |
wore | +0.001 |
packs | +0.001 |
wear | +0.001 |
Neg logit contributions | |
louder | -0.002 |
angrily | -0.002 |
harder | -0.002 |
trigger | -0.002 |
beast | -0.002 |
Token | careful |
Token ID | 8161 |
Feature activation | -1.98e-03 |
Pos logit contributions | |
days | +0.011 |
am | +0.010 |
packs | +0.010 |
ouses | +0.010 |
wore | +0.010 |
Neg logit contributions | |
louder | -0.008 |
harder | -0.007 |
angrily | -0.007 |
loudly | -0.007 |
amus | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | +1.96e-02 |
Pos logit contributions | |
trigger | +0.004 |
angrily | +0.003 |
louder | +0.003 |
beast | +0.003 |
amus | +0.003 |
Neg logit contributions | |
days | -0.003 |
wore | -0.003 |
am | -0.003 |
packs | -0.003 |
ouses | -0.003 |
Token | But |
Token ID | 887 |
Feature activation | +3.22e-02 |
Pos logit contributions | |
days | +0.031 |
am | +0.031 |
wore | +0.030 |
ouses | +0.030 |
packs | +0.029 |
Neg logit contributions | |
angrily | -0.035 |
louder | -0.035 |
harder | -0.035 |
loudly | -0.033 |
throttle | -0.032 |
Token | when |
Token ID | 618 |
Feature activation | +2.84e-02 |
Pos logit contributions | |
days | +0.047 |
am | +0.045 |
wore | +0.045 |
packs | +0.044 |
ouses | +0.043 |
Neg logit contributions | |
louder | -0.066 |
angrily | -0.064 |
harder | -0.064 |
trigger | -0.064 |
beast | -0.061 |
Token | Sarah |
Token ID | 10490 |
Feature activation | -2.46e-02 |
Pos logit contributions | |
days | +0.039 |
ouses | +0.039 |
wore | +0.037 |
am | +0.037 |
packs | +0.037 |
Neg logit contributions | |
louder | -0.061 |
harder | -0.060 |
angrily | -0.057 |
loudly | -0.056 |
trigger | -0.054 |
Token | got |
Token ID | 1392 |
Feature activation | -3.43e-03 |
Pos logit contributions | |
louder | +0.052 |
trigger | +0.051 |
angrily | +0.049 |
harder | +0.049 |
amus | +0.048 |
Neg logit contributions | |
wore | -0.036 |
am | -0.034 |
days | -0.034 |
wear | -0.032 |
packs | -0.032 |
Token | to |
Token ID | 284 |
Feature activation | +1.18e-02 |
Pos logit contributions | |
days | +0.005 |
am | +0.005 |
wore | +0.005 |
ouses | +0.005 |
packs | +0.005 |
Neg logit contributions | |
louder | -0.003 |
harder | -0.003 |
angrily | -0.003 |
trigger | -0.003 |
loudly | -0.003 |
Token | say |
Token ID | 910 |
Feature activation | -1.25e-02 |
Pos logit contributions | |
days | +0.025 |
am | +0.025 |
wore | +0.024 |
packs | +0.024 |
ouses | +0.024 |
Neg logit contributions | |
louder | -0.016 |
angrily | -0.015 |
harder | -0.015 |
trigger | -0.015 |
loudly | -0.014 |
Token | hello |
Token ID | 23748 |
Feature activation | -2.03e-02 |
Pos logit contributions | |
trigger | +0.021 |
angrily | +0.021 |
harder | +0.020 |
beast | +0.020 |
louder | +0.020 |
Neg logit contributions | |
am | -0.022 |
wore | -0.021 |
days | -0.021 |
wear | -0.020 |
ouses | -0.020 |
Token | to |
Token ID | 284 |
Feature activation | +2.30e-03 |
Pos logit contributions | |
trigger | +0.038 |
louder | +0.037 |
angrily | +0.037 |
beast | +0.036 |
harder | +0.036 |
Neg logit contributions | |
days | -0.033 |
am | -0.032 |
packs | -0.032 |
wore | -0.031 |
ouses | -0.030 |
Token | the |
Token ID | 262 |
Feature activation | -1.96e-03 |
Pos logit contributions | |
days | +0.004 |
am | +0.004 |
wore | +0.004 |
packs | +0.004 |
wear | +0.004 |
Neg logit contributions | |
louder | -0.004 |
angrily | -0.004 |
trigger | -0.004 |
harder | -0.004 |
throttle | -0.003 |
Token | spider |
Token ID | 19230 |
Feature activation | -9.71e-04 |
Pos logit contributions | |
angrily | +0.003 |
iously | +0.003 |
louder | +0.003 |
amus | +0.003 |
trigger | +0.003 |
Neg logit contributions | |
am | -0.003 |
days | -0.003 |
wore | -0.003 |
packs | -0.003 |
wear | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | +4.28e-03 |
Pos logit contributions | |
louder | +0.002 |
trigger | +0.002 |
angrily | +0.002 |
harder | +0.002 |
throttle | +0.002 |
Neg logit contributions | |
days | -0.002 |
am | -0.001 |
wore | -0.001 |
packs | -0.001 |
ouses | -0.001 |
Token | It |
Token ID | 632 |
Feature activation | +1.18e-02 |
Pos logit contributions | |
days | +0.008 |
packs | +0.007 |
ouses | +0.007 |
wore | +0.007 |
am | +0.007 |
Neg logit contributions | |
louder | -0.008 |
angrily | -0.007 |
harder | -0.007 |
loudly | -0.007 |
trigger | -0.007 |
Token | is |
Token ID | 318 |
Feature activation | +1.83e-03 |
Pos logit contributions | |
days | +0.016 |
am | +0.016 |
packs | +0.015 |
wore | +0.015 |
ouses | +0.015 |
Neg logit contributions | |
louder | -0.025 |
angrily | -0.024 |
harder | -0.024 |
trigger | -0.024 |
loudly | -0.023 |
Token | polite |
Token ID | 23507 |
Feature activation | -1.45e-03 |
Pos logit contributions | |
days | +0.004 |
am | +0.003 |
ouses | +0.003 |
packs | +0.003 |
wore | +0.003 |
Neg logit contributions | |
louder | -0.003 |
harder | -0.003 |
angrily | -0.003 |
loudly | -0.003 |
trigger | -0.003 |
Token | to |
Token ID | 284 |
Feature activation | +5.91e-03 |
Pos logit contributions | |
louder | +0.002 |
harder | +0.002 |
angrily | +0.002 |
trigger | +0.002 |
loudly | +0.002 |
Neg logit contributions | |
days | -0.003 |
am | -0.003 |
wore | -0.003 |
packs | -0.003 |
ouses | -0.003 |
Token | ay |
Token ID | 323 |
Feature activation | +2.12e-02 |
Pos logit contributions | |
days | +0.002 |
wore | +0.002 |
am | +0.002 |
packs | +0.002 |
ouses | +0.002 |
Neg logit contributions | |
louder | -0.002 |
angrily | -0.002 |
harder | -0.002 |
trigger | -0.002 |
loudly | -0.002 |
Token | ons |
Token ID | 684 |
Feature activation | +9.90e-03 |
Pos logit contributions | |
days | +0.032 |
am | +0.031 |
wore | +0.030 |
packs | +0.029 |
ouses | +0.029 |
Neg logit contributions | |
louder | -0.043 |
angrily | -0.042 |
harder | -0.042 |
trigger | -0.041 |
loudly | -0.039 |
Token | are |
Token ID | 389 |
Feature activation | -1.21e-02 |
Pos logit contributions | |
days | +0.009 |
am | +0.009 |
wore | +0.009 |
packs | +0.008 |
ouses | +0.008 |
Neg logit contributions | |
louder | -0.025 |
angrily | -0.025 |
harder | -0.025 |
trigger | -0.024 |
loudly | -0.024 |
Token | too |
Token ID | 1165 |
Feature activation | +6.04e-03 |
Pos logit contributions | |
louder | +0.019 |
angrily | +0.018 |
trigger | +0.018 |
harder | +0.018 |
beast | +0.017 |
Neg logit contributions | |
am | -0.023 |
wore | -0.023 |
days | -0.023 |
packs | -0.022 |
wear | -0.021 |
Token | hot |
Token ID | 3024 |
Feature activation | +1.68e-02 |
Pos logit contributions | |
am | +0.010 |
wore | +0.010 |
days | +0.010 |
packs | +0.010 |
ouses | +0.010 |
Neg logit contributions | |
louder | -0.010 |
trigger | -0.010 |
angrily | -0.010 |
amus | -0.010 |
harder | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | +1.31e-03 |
Pos logit contributions | |
days | +0.031 |
am | +0.031 |
wore | +0.031 |
packs | +0.030 |
ouses | +0.029 |
Neg logit contributions | |
louder | -0.027 |
angrily | -0.026 |
trigger | -0.026 |
harder | -0.025 |
amus | -0.025 |
Token | They |
Token ID | 1119 |
Feature activation | +2.50e-02 |
Pos logit contributions | |
days | +0.002 |
packs | +0.002 |
ouses | +0.002 |
wore | +0.002 |
am | +0.002 |
Neg logit contributions | |
louder | -0.002 |
angrily | -0.002 |
trigger | -0.002 |
harder | -0.002 |
loudly | -0.002 |
Token | are |
Token ID | 389 |
Feature activation | +1.51e-03 |
Pos logit contributions | |
days | +0.029 |
am | +0.027 |
wore | +0.027 |
packs | +0.027 |
ouses | +0.026 |
Neg logit contributions | |
louder | -0.058 |
angrily | -0.057 |
harder | -0.057 |
trigger | -0.056 |
loudly | -0.054 |
Token | not |
Token ID | 407 |
Feature activation | -2.20e-03 |
Pos logit contributions | |
days | +0.003 |
am | +0.003 |
wore | +0.003 |
packs | +0.003 |
ouses | +0.003 |
Neg logit contributions | |
louder | -0.002 |
angrily | -0.002 |
trigger | -0.002 |
harder | -0.002 |
beast | -0.002 |
Token | good |
Token ID | 922 |
Feature activation | +1.03e-02 |
Pos logit contributions | |
louder | +0.004 |
angrily | +0.004 |
trigger | +0.004 |
harder | +0.004 |
beast | +0.004 |
Neg logit contributions | |
days | -0.004 |
wore | -0.004 |
am | -0.004 |
packs | -0.004 |
ouses | -0.004 |
Token | to |
Token ID | 284 |
Feature activation | +4.97e-03 |
Pos logit contributions | |
days | +0.018 |
am | +0.017 |
wore | +0.017 |
packs | +0.017 |
ouses | +0.016 |
Neg logit contributions | |
louder | -0.018 |
angrily | -0.018 |
harder | -0.017 |
trigger | -0.017 |
beast | -0.017 |
Token | |
Token ID | 220 |
Feature activation | +3.99e-02 |
Pos logit contributions | |
louder | +0.011 |
harder | +0.011 |
angrily | +0.011 |
trigger | +0.011 |
loudly | +0.010 |
Neg logit contributions | |
days | -0.009 |
am | -0.008 |
ouses | -0.008 |
wore | -0.008 |
packs | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | +3.79e-03 |
Pos logit contributions | |
days | +0.057 |
wore | +0.056 |
am | +0.053 |
ouses | +0.053 |
packs | +0.052 |
Neg logit contributions | |
louder | -0.080 |
angrily | -0.079 |
harder | -0.079 |
trigger | -0.075 |
loudly | -0.074 |
Token |
|
Token ID | 198 |
Feature activation | -2.72e-02 |
Pos logit contributions | |
days | +0.005 |
packs | +0.005 |
wore | +0.005 |
am | +0.005 |
ouses | +0.005 |
Neg logit contributions | |
louder | -0.008 |
angrily | -0.008 |
harder | -0.008 |
trigger | -0.007 |
loudly | -0.007 |
Token | The |
Token ID | 464 |
Feature activation | -9.51e-03 |
Pos logit contributions | |
louder | +0.052 |
angrily | +0.051 |
harder | +0.051 |
trigger | +0.051 |
beast | +0.049 |
Neg logit contributions | |
days | -0.043 |
wore | -0.042 |
am | -0.042 |
ouses | -0.039 |
packs | -0.039 |
Token | older |
Token ID | 4697 |
Feature activation | -3.03e-03 |
Pos logit contributions | |
angrily | +0.021 |
iously | +0.019 |
harder | +0.019 |
loudly | +0.019 |
amus | +0.019 |
Neg logit contributions | |
wore | -0.013 |
days | -0.013 |
am | -0.012 |
wear | -0.012 |
ouses | -0.011 |
Token | brother |
Token ID | 3956 |
Feature activation | -4.30e-02 |
Pos logit contributions | |
angrily | +0.006 |
louder | +0.006 |
harder | +0.006 |
trigger | +0.006 |
amus | +0.005 |
Neg logit contributions | |
days | -0.005 |
wore | -0.005 |
am | -0.005 |
packs | -0.005 |
ouses | -0.004 |
Token | said |
Token ID | 531 |
Feature activation | -3.14e-02 |
Pos logit contributions | |
trigger | +0.097 |
louder | +0.095 |
harder | +0.091 |
amus | +0.090 |
rier | +0.090 |
Neg logit contributions | |
wore | -0.062 |
am | -0.054 |
days | -0.053 |
wear | -0.050 |
packs | -0.050 |
Token | to |
Token ID | 284 |
Feature activation | -1.18e-02 |
Pos logit contributions | |
amus | +0.072 |
trigger | +0.071 |
beast | +0.069 |
louder | +0.069 |
throttle | +0.068 |
Neg logit contributions | |
am | -0.037 |
wore | -0.035 |
days | -0.034 |
wear | -0.030 |
ouses | -0.030 |
Token | his |
Token ID | 465 |
Feature activation | -2.86e-02 |
Pos logit contributions | |
angrily | +0.023 |
trigger | +0.023 |
louder | +0.022 |
harder | +0.022 |
throttle | +0.022 |
Neg logit contributions | |
am | -0.018 |
days | -0.017 |
wear | -0.017 |
wore | -0.017 |
packs | -0.015 |
Token | younger |
Token ID | 7099 |
Feature activation | -1.54e-02 |
Pos logit contributions | |
trigger | +0.068 |
angrily | +0.067 |
amus | +0.064 |
rus | +0.064 |
rier | +0.063 |
Neg logit contributions | |
days | -0.028 |
am | -0.027 |
wore | -0.026 |
packs | -0.025 |
wear | -0.024 |
Token | brother |
Token ID | 3956 |
Feature activation | -4.17e-02 |
Pos logit contributions | |
angrily | +0.032 |
trigger | +0.032 |
louder | +0.032 |
harder | +0.032 |
amus | +0.031 |
Neg logit contributions | |
days | -0.021 |
packs | -0.020 |
wore | -0.019 |
am | -0.019 |
ouses | -0.018 |
Token | want |
Token ID | 765 |
Feature activation | -3.15e-02 |
Pos logit contributions | |
packs | +0.067 |
days | +0.067 |
ouses | +0.067 |
wore | +0.060 |
am | +0.056 |
Neg logit contributions | |
angrily | -0.089 |
louder | -0.087 |
harder | -0.087 |
loudly | -0.083 |
beast | -0.080 |
Token | one |
Token ID | 530 |
Feature activation | +2.29e-03 |
Pos logit contributions | |
trigger | +0.058 |
angrily | +0.057 |
louder | +0.055 |
amus | +0.053 |
loudly | +0.052 |
Neg logit contributions | |
am | -0.051 |
wore | -0.051 |
days | -0.050 |
wear | -0.049 |
packs | -0.047 |
Token | !" |
Token ID | 2474 |
Feature activation | -1.07e-02 |
Pos logit contributions | |
days | +0.004 |
am | +0.004 |
wore | +0.004 |
packs | +0.004 |
wear | +0.004 |
Neg logit contributions | |
louder | -0.004 |
trigger | -0.004 |
angrily | -0.004 |
amus | -0.004 |
harder | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | +1.08e-03 |
Pos logit contributions | |
louder | +0.025 |
trigger | +0.025 |
harder | +0.024 |
angrily | +0.024 |
beast | +0.024 |
Neg logit contributions | |
days | -0.012 |
am | -0.012 |
wore | -0.012 |
ouses | -0.011 |
packs | -0.011 |
Token |
|
Token ID | 198 |
Feature activation | -1.27e-02 |
Pos logit contributions | |
days | +0.001 |
am | +0.001 |
wore | +0.001 |
ouses | +0.001 |
packs | +0.001 |
Neg logit contributions | |
louder | -0.003 |
trigger | -0.003 |
harder | -0.003 |
angrily | -0.003 |
beast | -0.003 |
Token | Jack |
Token ID | 14295 |
Feature activation | -4.19e-02 |
Pos logit contributions | |
trigger | +0.025 |
louder | +0.023 |
harder | +0.023 |
beast | +0.022 |
amus | +0.022 |
Neg logit contributions | |
days | -0.021 |
am | -0.020 |
wore | -0.019 |
ouses | -0.019 |
packs | -0.018 |
Token | said |
Token ID | 531 |
Feature activation | -2.79e-02 |
Pos logit contributions | |
trigger | +0.099 |
throttle | +0.092 |
rier | +0.091 |
louder | +0.090 |
beast | +0.089 |
Neg logit contributions | |
wore | -0.060 |
am | -0.047 |
days | -0.047 |
wear | -0.046 |
lived | -0.043 |
Token | , |
Token ID | 11 |
Feature activation | -1.17e-02 |
Pos logit contributions | |
amus | +0.064 |
trigger | +0.064 |
beast | +0.063 |
throttle | +0.063 |
harder | +0.060 |
Neg logit contributions | |
am | -0.032 |
wore | -0.030 |
days | -0.030 |
ouses | -0.027 |
wear | -0.027 |
Token | " |
Token ID | 366 |
Feature activation | -3.71e-02 |
Pos logit contributions | |
trigger | +0.026 |
throttle | +0.025 |
beast | +0.025 |
amus | +0.025 |
harder | +0.023 |
Neg logit contributions | |
wore | -0.015 |
am | -0.014 |
days | -0.014 |
wear | -0.012 |
'm | -0.012 |
Token | You |
Token ID | 1639 |
Feature activation | +2.70e-02 |
Pos logit contributions | |
louder | +0.071 |
angrily | +0.071 |
trigger | +0.070 |
harder | +0.070 |
beast | +0.067 |
Neg logit contributions | |
days | -0.057 |
am | -0.056 |
wore | -0.055 |
ouses | -0.051 |
wear | -0.051 |
Token | can |
Token ID | 460 |
Feature activation | -1.98e-03 |
Pos logit contributions | |
am | +0.033 |
wore | +0.032 |
days | +0.031 |
wear | +0.029 |
packs | +0.027 |
Neg logit contributions | |
louder | -0.063 |
angrily | -0.062 |
harder | -0.061 |
trigger | -0.060 |
loudly | -0.058 |
Token | , |
Token ID | 11 |
Feature activation | -4.47e-02 |
Pos logit contributions | |
trigger | +0.104 |
louder | +0.104 |
harder | +0.102 |
angrily | +0.100 |
instructions | +0.098 |
Neg logit contributions | |
am | -0.051 |
wore | -0.051 |
wear | -0.051 |
days | -0.050 |
packs | -0.049 |
Token | mom |
Token ID | 1995 |
Feature activation | -1.71e-02 |
Pos logit contributions | |
angrily | +0.088 |
louder | +0.084 |
harder | +0.084 |
trigger | +0.082 |
loudly | +0.080 |
Neg logit contributions | |
am | -0.072 |
days | -0.067 |
wore | -0.067 |
wear | -0.064 |
packs | -0.062 |
Token | , |
Token ID | 11 |
Feature activation | -2.40e-02 |
Pos logit contributions | |
trigger | +0.035 |
louder | +0.035 |
angrily | +0.035 |
harder | +0.034 |
amus | +0.033 |
Neg logit contributions | |
days | -0.025 |
wore | -0.024 |
am | -0.024 |
packs | -0.024 |
wear | -0.022 |
Token | look |
Token ID | 804 |
Feature activation | -2.42e-02 |
Pos logit contributions | |
louder | +0.045 |
angrily | +0.045 |
harder | +0.044 |
trigger | +0.043 |
loudly | +0.041 |
Neg logit contributions | |
days | -0.039 |
am | -0.039 |
wore | -0.038 |
packs | -0.037 |
ouses | -0.035 |
Token | !" |
Token ID | 2474 |
Feature activation | -2.22e-02 |
Pos logit contributions | |
trigger | +0.044 |
louder | +0.043 |
harder | +0.042 |
amus | +0.042 |
angrily | +0.042 |
Neg logit contributions | |
am | -0.039 |
wore | -0.038 |
days | -0.038 |
packs | -0.037 |
wear | -0.036 |
Token | Tim |
Token ID | 5045 |
Feature activation | -5.94e-02 |
Pos logit contributions | |
louder | +0.042 |
harder | +0.042 |
amus | +0.041 |
trigger | +0.041 |
throttle | +0.040 |
Neg logit contributions | |
am | -0.034 |
wore | -0.033 |
days | -0.032 |
wear | -0.031 |
packs | -0.030 |
Token | said |
Token ID | 531 |
Feature activation | -3.51e-02 |
Pos logit contributions | |
trigger | +0.148 |
rier | +0.140 |
amus | +0.130 |
beast | +0.129 |
louder | +0.127 |
Neg logit contributions | |
wore | -0.079 |
packs | -0.063 |
days | -0.061 |
wear | -0.059 |
am | -0.058 |
Token | , |
Token ID | 11 |
Feature activation | -2.27e-02 |
Pos logit contributions | |
amus | +0.089 |
beast | +0.088 |
trigger | +0.087 |
throttle | +0.085 |
zee | +0.082 |
Neg logit contributions | |
days | -0.033 |
wore | -0.032 |
am | -0.030 |
wear | -0.029 |
packs | -0.029 |
Token | pointing |
Token ID | 10609 |
Feature activation | -3.90e-02 |
Pos logit contributions | |
trigger | +0.048 |
amus | +0.047 |
throttle | +0.046 |
zee | +0.046 |
beast | +0.045 |
Neg logit contributions | |
wore | -0.031 |
wear | -0.026 |
days | -0.026 |
am | -0.024 |
packs | -0.022 |
Token | at |
Token ID | 379 |
Feature activation | -3.64e-02 |
Pos logit contributions | |
trigger | +0.084 |
beast | +0.079 |
rus | +0.079 |
amus | +0.078 |
accelerator | +0.076 |
Neg logit contributions | |
packs | -0.051 |
wore | -0.048 |
am | -0.048 |
wear | -0.043 |
ouses | -0.040 |
Token | the |
Token ID | 262 |
Feature activation | -2.69e-02 |
Pos logit contributions | |
angrily | +0.093 |
ote | +0.090 |
rus | +0.089 |
iously | +0.089 |
louder | +0.089 |
Neg logit contributions | |
am | -0.025 |
packs | -0.024 |
wore | -0.024 |
wear | -0.024 |
days | -0.018 |
Token | Lily |
Token ID | 20037 |
Feature activation | -4.20e-02 |
Pos logit contributions | |
louder | +0.019 |
harder | +0.018 |
trigger | +0.018 |
angrily | +0.018 |
amus | +0.018 |
Neg logit contributions | |
am | -0.011 |
wore | -0.011 |
days | -0.011 |
packs | -0.010 |
wear | -0.010 |
Token | said |
Token ID | 531 |
Feature activation | -2.70e-02 |
Pos logit contributions | |
trigger | +0.104 |
rier | +0.100 |
amus | +0.099 |
throttle | +0.097 |
beast | +0.096 |
Neg logit contributions | |
wore | -0.051 |
am | -0.041 |
wear | -0.037 |
packs | -0.036 |
days | -0.035 |
Token | . |
Token ID | 13 |
Feature activation | +5.04e-03 |
Pos logit contributions | |
beast | +0.073 |
amus | +0.072 |
throttle | +0.070 |
trigger | +0.069 |
zee | +0.067 |
Neg logit contributions | |
days | -0.020 |
wore | -0.019 |
packs | -0.018 |
am | -0.017 |
wear | -0.017 |
Token |
|
Token ID | 198 |
Feature activation | +7.80e-03 |
Pos logit contributions | |
am | +0.004 |
wore | +0.004 |
packs | +0.003 |
days | +0.003 |
ouses | +0.003 |
Neg logit contributions | |
trigger | -0.013 |
louder | -0.013 |
amus | -0.013 |
beast | -0.013 |
harder | -0.013 |
Token |
|
Token ID | 198 |
Feature activation | -1.37e-02 |
Pos logit contributions | |
days | +0.009 |
am | +0.008 |
wore | +0.008 |
packs | +0.008 |
ouses | +0.008 |
Neg logit contributions | |
louder | -0.019 |
angrily | -0.018 |
harder | -0.018 |
trigger | -0.018 |
beast | -0.017 |
Token | " |
Token ID | 1 |
Feature activation | -4.03e-02 |
Pos logit contributions | |
trigger | +0.026 |
angrily | +0.026 |
louder | +0.026 |
harder | +0.025 |
beast | +0.025 |
Neg logit contributions | |
am | -0.021 |
wore | -0.020 |
days | -0.020 |
packs | -0.019 |
ouses | -0.019 |
Token | Bad |
Token ID | 22069 |
Feature activation | -4.90e-02 |
Pos logit contributions | |
angrily | +0.075 |
harder | +0.075 |
louder | +0.075 |
trigger | +0.072 |
beast | +0.072 |
Neg logit contributions | |
am | -0.063 |
days | -0.061 |
wore | -0.060 |
packs | -0.055 |
ouses | -0.055 |
Token | dog |
Token ID | 3290 |
Feature activation | -3.84e-02 |
Pos logit contributions | |
louder | +0.079 |
angrily | +0.078 |
harder | +0.077 |
throttle | +0.072 |
amus | +0.072 |
Neg logit contributions | |
am | -0.093 |
wore | -0.087 |
wear | -0.084 |
days | -0.084 |
packs | -0.083 |
Token | ! |
Token ID | 0 |
Feature activation | -4.41e-02 |
Pos logit contributions | |
louder | +0.077 |
harder | +0.075 |
trigger | +0.074 |
amus | +0.074 |
throttle | +0.074 |
Neg logit contributions | |
am | -0.060 |
wore | -0.054 |
wear | -0.050 |
days | -0.050 |
packs | -0.048 |
Token | Go |
Token ID | 1514 |
Feature activation | -2.23e-02 |
Pos logit contributions | |
louder | +0.089 |
harder | +0.089 |
angrily | +0.081 |
amus | +0.080 |
trigger | +0.079 |
Neg logit contributions | |
am | -0.068 |
days | -0.065 |
wore | -0.063 |
packs | -0.059 |
wear | -0.058 |
Token | away |
Token ID | 1497 |
Feature activation | -1.08e-02 |
Pos logit contributions | |
louder | +0.028 |
angrily | +0.027 |
trigger | +0.026 |
harder | +0.026 |
amus | +0.025 |
Neg logit contributions | |
am | -0.051 |
days | -0.050 |
wore | -0.049 |
packs | -0.048 |
wear | -0.047 |
Token | the |
Token ID | 262 |
Feature activation | -3.13e-02 |
Pos logit contributions | |
ote | +0.121 |
iously | +0.115 |
beast | +0.115 |
rus | +0.113 |
der | +0.112 |
Neg logit contributions | |
am | -0.046 |
wear | -0.046 |
wore | -0.045 |
have | -0.043 |
packs | -0.043 |
Token | ball |
Token ID | 2613 |
Feature activation | -4.32e-02 |
Pos logit contributions | |
iously | +0.061 |
angrily | +0.061 |
amus | +0.060 |
louder | +0.060 |
harder | +0.057 |
Neg logit contributions | |
am | -0.050 |
wore | -0.044 |
wear | -0.043 |
days | -0.042 |
packs | -0.041 |
Token | and |
Token ID | 290 |
Feature activation | -1.92e-02 |
Pos logit contributions | |
beast | +0.098 |
ote | +0.097 |
amus | +0.091 |
iously | +0.090 |
zee | +0.089 |
Neg logit contributions | |
packs | -0.048 |
days | -0.043 |
am | -0.043 |
wear | -0.041 |
wore | -0.039 |
Token | would |
Token ID | 561 |
Feature activation | -2.53e-02 |
Pos logit contributions | |
louder | +0.038 |
amus | +0.037 |
trigger | +0.037 |
angrily | +0.037 |
harder | +0.036 |
Neg logit contributions | |
wore | -0.030 |
am | -0.027 |
packs | -0.027 |
wear | -0.027 |
days | -0.027 |
Token | not |
Token ID | 407 |
Feature activation | -1.70e-02 |
Pos logit contributions | |
louder | +0.047 |
trigger | +0.047 |
beast | +0.046 |
throttle | +0.046 |
harder | +0.046 |
Neg logit contributions | |
am | -0.040 |
wear | -0.040 |
wore | -0.040 |
days | -0.039 |
packs | -0.034 |
Token | give |
Token ID | 1577 |
Feature activation | -6.27e-02 |
Pos logit contributions | |
louder | +0.036 |
angrily | +0.035 |
harder | +0.035 |
trigger | +0.035 |
beast | +0.034 |
Neg logit contributions | |
days | -0.024 |
am | -0.024 |
wore | -0.023 |
wear | -0.022 |
packs | -0.021 |
Token | it |
Token ID | 340 |
Feature activation | -2.39e-02 |
Pos logit contributions | |
ote | +0.131 |
der | +0.129 |
beast | +0.126 |
iously | +0.125 |
louder | +0.123 |
Neg logit contributions | |
packs | -0.074 |
am | -0.073 |
wear | -0.072 |
wore | -0.071 |
have | -0.066 |
Token | back |
Token ID | 736 |
Feature activation | +2.57e-03 |
Pos logit contributions | |
beast | +0.044 |
angrily | +0.042 |
trigger | +0.041 |
rus | +0.041 |
iously | +0.040 |
Neg logit contributions | |
packs | -0.039 |
am | -0.038 |
wear | -0.037 |
days | -0.036 |
wore | -0.036 |
Token | . |
Token ID | 13 |
Feature activation | -2.39e-02 |
Pos logit contributions | |
packs | +0.004 |
days | +0.004 |
am | +0.004 |
wore | +0.004 |
wear | +0.003 |
Neg logit contributions | |
trigger | -0.005 |
louder | -0.005 |
angrily | -0.005 |
beast | -0.005 |
harder | -0.005 |
Token |
|
Token ID | 198 |
Feature activation | -6.34e-03 |
Pos logit contributions | |
louder | +0.054 |
harder | +0.053 |
trigger | +0.053 |
angrily | +0.052 |
beast | +0.051 |
Neg logit contributions | |
am | -0.029 |
days | -0.028 |
wore | -0.028 |
packs | -0.026 |
ouses | -0.026 |
Token |
|
Token ID | 198 |
Feature activation | -3.05e-02 |
Pos logit contributions | |
louder | +0.014 |
angrily | +0.014 |
harder | +0.014 |
trigger | +0.014 |
loudly | +0.013 |
Neg logit contributions | |
days | -0.008 |
wore | -0.007 |
am | -0.007 |
packs | -0.007 |
ouses | -0.007 |