Token | Why |
Token ID | 5195 |
Feature activation | +1.30e-01 |
Pos logit contributions | |
comm | +0.072 |
aback | +0.068 |
happened | +0.063 |
forgiven | +0.061 |
Birthday | +0.061 |
Neg logit contributions | |
often | -0.083 |
His | -0.074 |
nam | -0.069 |
ot | -0.068 |
ind | -0.067 |
Token | do |
Token ID | 466 |
Feature activation | +7.28e-02 |
Pos logit contributions | |
written | +0.004 |
aback | +0.004 |
comm | +0.004 |
Gu | +0.004 |
source | +0.004 |
Neg logit contributions | |
igs | -0.005 |
often | -0.005 |
ot | -0.005 |
solar | -0.005 |
lived | -0.004 |
Token | you |
Token ID | 345 |
Feature activation | +4.19e-01 |
Pos logit contributions | |
written | +0.002 |
aback | +0.002 |
comm | +0.002 |
Gu | +0.002 |
hered | +0.002 |
Neg logit contributions | |
often | -0.003 |
igs | -0.003 |
ot | -0.003 |
solar | -0.003 |
lived | -0.003 |
Token | want |
Token ID | 765 |
Feature activation | +4.69e-01 |
Pos logit contributions | |
aback | +0.013 |
written | +0.013 |
comm | +0.013 |
Gu | +0.013 |
hered | +0.012 |
Neg logit contributions | |
often | -0.017 |
igs | -0.017 |
ot | -0.015 |
lived | -0.015 |
solar | -0.015 |
Token | a |
Token ID | 257 |
Feature activation | +2.46e+00 |
Pos logit contributions | |
aback | +0.014 |
comm | +0.014 |
written | +0.014 |
Gu | +0.014 |
hered | +0.013 |
Neg logit contributions | |
often | -0.019 |
igs | -0.019 |
ot | -0.017 |
solar | -0.017 |
lived | -0.017 |
Token | bisc |
Token ID | 36228 |
Feature activation | +4.33e+00 |
Pos logit contributions | |
aback | +0.090 |
comm | +0.088 |
umbs | +0.082 |
written | +0.082 |
ctions | +0.082 |
Neg logit contributions | |
ot | -0.089 |
often | -0.080 |
tight | -0.078 |
igs | -0.078 |
oppy | -0.073 |
Token | uit |
Token ID | 5013 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
comm | +0.193 |
aback | +0.169 |
Gu | +0.165 |
payoff | +0.158 |
source | +0.155 |
Neg logit contributions | |
ot | -0.138 |
belt | -0.124 |
often | -0.118 |
ittens | -0.118 |
igs | -0.118 |
Token | ?" |
Token ID | 1701 |
Feature activation | +3.82e-01 |
Pos logit contributions | |
comm | +0.047 |
aback | +0.045 |
Gu | +0.045 |
written | +0.044 |
hered | +0.042 |
Neg logit contributions | |
often | -0.038 |
igs | -0.035 |
ot | -0.033 |
lived | -0.030 |
belt | -0.029 |
Token |
|
Token ID | 198 |
Feature activation | +1.52e-02 |
Pos logit contributions | |
written | +0.013 |
comm | +0.013 |
aback | +0.013 |
Gu | +0.012 |
hered | +0.012 |
Neg logit contributions | |
often | -0.014 |
igs | -0.014 |
ot | -0.013 |
solar | -0.012 |
lived | -0.012 |
Token |
|
Token ID | 198 |
Feature activation | -6.18e-01 |
Pos logit contributions | |
aback | +0.000 |
written | +0.000 |
Gu | +0.000 |
comm | +0.000 |
hered | +0.000 |
Neg logit contributions | |
igs | -0.001 |
often | -0.001 |
ot | -0.001 |
solar | -0.001 |
lived | -0.001 |
Token | The |
Token ID | 464 |
Feature activation | +3.53e-01 |
Pos logit contributions | |
igs | +0.022 |
often | +0.020 |
solar | +0.018 |
lived | +0.018 |
ot | +0.018 |
Neg logit contributions | |
Gu | -0.024 |
aback | -0.024 |
written | -0.023 |
comm | -0.023 |
Sur | -0.023 |
Token | They |
Token ID | 1119 |
Feature activation | -5.08e-01 |
Pos logit contributions | |
aback | +0.018 |
written | +0.018 |
comm | +0.018 |
Gu | +0.018 |
hered | +0.017 |
Neg logit contributions | |
often | -0.011 |
igs | -0.010 |
ot | -0.009 |
solar | -0.009 |
lived | -0.008 |
Token | write |
Token ID | 3551 |
Feature activation | +6.28e-01 |
Pos logit contributions | |
igs | +0.024 |
often | +0.022 |
ot | +0.021 |
ug | +0.021 |
gut | +0.020 |
Neg logit contributions | |
written | -0.014 |
aback | -0.012 |
comm | -0.012 |
Gu | -0.012 |
source | -0.012 |
Token | " |
Token ID | 366 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
comm | +0.023 |
aback | +0.023 |
Gu | +0.023 |
written | +0.022 |
source | +0.021 |
Neg logit contributions | |
often | -0.023 |
igs | -0.021 |
ot | -0.020 |
lived | -0.019 |
solar | -0.019 |
Token | Thank |
Token ID | 10449 |
Feature activation | +3.89e-01 |
Pos logit contributions | |
comm | +0.035 |
aback | +0.034 |
source | +0.031 |
written | +0.030 |
bisc | +0.029 |
Neg logit contributions | |
often | -0.059 |
ot | -0.056 |
igs | -0.055 |
lived | -0.053 |
solar | -0.052 |
Token | you |
Token ID | 345 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
aback | +0.012 |
written | +0.012 |
comm | +0.012 |
Gu | +0.012 |
source | +0.011 |
Neg logit contributions | |
often | -0.015 |
igs | -0.015 |
ot | -0.014 |
solar | -0.013 |
lived | -0.013 |
Token | " |
Token ID | 1 |
Feature activation | +4.20e+00 |
Pos logit contributions | |
igs | +0.054 |
often | +0.047 |
apy | +0.046 |
solar | +0.044 |
lived | +0.043 |
Neg logit contributions | |
written | -0.046 |
aback | -0.042 |
Birthday | -0.041 |
calling | -0.041 |
hered | -0.040 |
Token | and |
Token ID | 290 |
Feature activation | -6.49e-01 |
Pos logit contributions | |
comm | +0.188 |
aback | +0.177 |
ction | +0.175 |
ctions | +0.172 |
bisc | +0.172 |
Neg logit contributions | |
often | -0.122 |
ot | -0.113 |
every | -0.099 |
nicely | -0.094 |
tight | -0.087 |
Token | " |
Token ID | 366 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
igs | +0.027 |
often | +0.025 |
ug | +0.023 |
ind | +0.022 |
ot | +0.022 |
Neg logit contributions | |
written | -0.022 |
comm | -0.020 |
Gu | -0.020 |
aback | -0.020 |
saying | -0.019 |
Token | We |
Token ID | 1135 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
aback | +0.034 |
comm | +0.033 |
source | +0.030 |
written | +0.028 |
calling | +0.028 |
Neg logit contributions | |
often | -0.062 |
ot | -0.059 |
igs | -0.058 |
lived | -0.055 |
solar | -0.054 |
Token | miss |
Token ID | 2051 |
Feature activation | -8.11e-01 |
Pos logit contributions | |
written | +0.005 |
aback | +0.005 |
comm | +0.005 |
Gu | +0.005 |
source | +0.005 |
Neg logit contributions | |
often | -0.006 |
igs | -0.006 |
ot | -0.005 |
solar | -0.005 |
lived | -0.005 |
Token | you |
Token ID | 345 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
igs | +0.030 |
often | +0.028 |
lived | +0.025 |
solar | +0.025 |
gut | +0.024 |
Neg logit contributions | |
written | -0.029 |
aback | -0.027 |
comm | -0.026 |
Gu | -0.026 |
calling | -0.026 |
Token | " |
Token ID | 1 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
igs | +0.036 |
often | +0.033 |
solar | +0.031 |
gut | +0.030 |
lived | +0.029 |
Neg logit contributions | |
Gu | -0.030 |
written | -0.029 |
aback | -0.029 |
comm | -0.028 |
Sur | -0.028 |
Token | Where |
Token ID | 8496 |
Feature activation | +7.49e-01 |
Pos logit contributions | |
aback | +0.054 |
comm | +0.051 |
source | +0.049 |
written | +0.048 |
begs | +0.047 |
Neg logit contributions | |
often | -0.061 |
ot | -0.055 |
lived | -0.054 |
His | -0.052 |
apy | -0.051 |
Token | are |
Token ID | 389 |
Feature activation | +2.11e-01 |
Pos logit contributions | |
aback | +0.026 |
comm | +0.026 |
Gu | +0.026 |
written | +0.025 |
hered | +0.025 |
Neg logit contributions | |
often | -0.028 |
igs | -0.027 |
lived | -0.025 |
ot | -0.025 |
solar | -0.023 |
Token | we |
Token ID | 356 |
Feature activation | +9.60e-01 |
Pos logit contributions | |
written | +0.007 |
aback | +0.007 |
comm | +0.007 |
Gu | +0.007 |
hered | +0.006 |
Neg logit contributions | |
often | -0.008 |
igs | -0.008 |
ot | -0.007 |
solar | -0.007 |
lived | -0.007 |
Token | going |
Token ID | 1016 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
aback | +0.031 |
comm | +0.030 |
Gu | +0.029 |
written | +0.028 |
bisc | +0.028 |
Neg logit contributions | |
often | -0.041 |
igs | -0.037 |
lived | -0.036 |
ot | -0.035 |
solar | -0.035 |
Token | mom |
Token ID | 1995 |
Feature activation | +4.16e+00 |
Pos logit contributions | |
comm | +0.071 |
Gu | +0.068 |
aback | +0.068 |
written | +0.066 |
bisc | +0.065 |
Neg logit contributions | |
often | -0.052 |
igs | -0.047 |
ot | -0.041 |
solar | -0.039 |
lived | -0.039 |
Token | my |
Token ID | 1820 |
Feature activation | +2.75e+00 |
Pos logit contributions | |
comm | +0.231 |
aback | +0.223 |
bisc | +0.216 |
Gu | +0.212 |
Uh | +0.207 |
Neg logit contributions | |
often | -0.106 |
every | -0.068 |
own | -0.068 |
ot | -0.056 |
lived | -0.055 |
Token | ?" |
Token ID | 1701 |
Feature activation | +6.18e-02 |
Pos logit contributions | |
comm | +0.142 |
Gu | +0.137 |
aback | +0.136 |
bisc | +0.134 |
written | +0.128 |
Neg logit contributions | |
often | -0.070 |
igs | -0.051 |
ot | -0.048 |
lived | -0.047 |
every | -0.041 |
Token | asked |
Token ID | 1965 |
Feature activation | +1.97e-03 |
Pos logit contributions | |
written | +0.002 |
aback | +0.002 |
comm | +0.002 |
Gu | +0.002 |
source | +0.002 |
Neg logit contributions | |
igs | -0.002 |
often | -0.002 |
ot | -0.002 |
solar | -0.002 |
lived | -0.002 |
Token | Lucy |
Token ID | 22162 |
Feature activation | -6.71e-02 |
Pos logit contributions | |
written | +0.000 |
aback | +0.000 |
comm | +0.000 |
Gu | +0.000 |
hered | +0.000 |
Neg logit contributions | |
igs | -0.000 |
often | -0.000 |
solar | -0.000 |
ot | -0.000 |
lived | -0.000 |
Token | . |
Token ID | 13 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
igs | +0.002 |
often | +0.002 |
ot | +0.002 |
solar | +0.002 |
lived | +0.002 |
Neg logit contributions | |
written | -0.003 |
aback | -0.003 |
comm | -0.003 |
Gu | -0.003 |
source | -0.003 |
Token | " |
Token ID | 366 |
Feature activation | +2.87e+00 |
Pos logit contributions | |
written | +0.019 |
aback | +0.019 |
comm | +0.019 |
Gu | +0.019 |
hered | +0.018 |
Neg logit contributions | |
often | -0.014 |
igs | -0.013 |
ot | -0.012 |
solar | -0.011 |
lived | -0.011 |
Token | What |
Token ID | 2061 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
comm | +0.104 |
begs | +0.098 |
aback | +0.097 |
happened | +0.095 |
news | +0.094 |
Neg logit contributions | |
often | -0.090 |
His | -0.088 |
ind | -0.074 |
solar | -0.073 |
nicely | -0.072 |
Token | are |
Token ID | 389 |
Feature activation | -2.89e-01 |
Pos logit contributions | |
aback | +0.048 |
comm | +0.047 |
hered | +0.046 |
Gu | +0.045 |
source | +0.044 |
Neg logit contributions | |
often | -0.047 |
lived | -0.045 |
igs | -0.041 |
goals | -0.040 |
solar | -0.039 |
Token | you |
Token ID | 345 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
often | +0.013 |
igs | +0.013 |
ot | +0.012 |
solar | +0.012 |
gut | +0.012 |
Neg logit contributions | |
written | -0.008 |
comm | -0.007 |
Gu | -0.007 |
aback | -0.007 |
source | -0.006 |
Token | doing |
Token ID | 1804 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
aback | +0.060 |
bisc | +0.058 |
Gu | +0.056 |
umbs | +0.056 |
ives | +0.055 |
Neg logit contributions | |
often | -0.070 |
igs | -0.063 |
lived | -0.062 |
solar | -0.058 |
ot | -0.058 |
Token | sir |
Token ID | 15967 |
Feature activation | +4.11e+00 |
Pos logit contributions | |
Gu | +0.065 |
comm | +0.065 |
aback | +0.065 |
bisc | +0.065 |
umbs | +0.063 |
Neg logit contributions | |
often | -0.044 |
igs | -0.039 |
lived | -0.033 |
ot | -0.033 |
solar | -0.031 |
Token | ?" |
Token ID | 1701 |
Feature activation | +8.28e-01 |
Pos logit contributions | |
aback | +0.205 |
comm | +0.204 |
Gu | +0.202 |
Sur | +0.202 |
Uh | +0.200 |
Neg logit contributions | |
often | -0.097 |
ot | -0.065 |
lived | -0.062 |
nicely | -0.057 |
every | -0.056 |
Token |
|
Token ID | 198 |
Feature activation | -1.19e-02 |
Pos logit contributions | |
written | +0.029 |
aback | +0.029 |
comm | +0.029 |
Gu | +0.029 |
source | +0.028 |
Neg logit contributions | |
often | -0.029 |
igs | -0.027 |
ot | -0.026 |
lived | -0.025 |
solar | -0.024 |
Token |
|
Token ID | 198 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
igs | +0.000 |
often | +0.000 |
ot | +0.000 |
solar | +0.000 |
lived | +0.000 |
Neg logit contributions | |
written | -0.000 |
aback | -0.000 |
Gu | -0.000 |
comm | -0.000 |
hered | -0.000 |
Token | The |
Token ID | 464 |
Feature activation | -2.39e-01 |
Pos logit contributions | |
igs | +0.004 |
often | +0.004 |
solar | +0.003 |
ot | +0.003 |
lived | +0.003 |
Neg logit contributions | |
written | -0.005 |
aback | -0.005 |
Gu | -0.005 |
comm | -0.005 |
hered | -0.004 |
Token | man |
Token ID | 582 |
Feature activation | +8.14e-01 |
Pos logit contributions | |
igs | +0.009 |
often | +0.009 |
ot | +0.008 |
solar | +0.008 |
lived | +0.008 |
Neg logit contributions | |
comm | -0.008 |
written | -0.008 |
aback | -0.008 |
Gu | -0.007 |
source | -0.007 |
Token | , |
Token ID | 11 |
Feature activation | -2.54e-01 |
Pos logit contributions | |
igs | +0.046 |
often | +0.040 |
solar | +0.039 |
ind | +0.039 |
ot | +0.037 |
Neg logit contributions | |
written | -0.047 |
aback | -0.044 |
Gu | -0.041 |
comm | -0.040 |
cake | -0.040 |
Token | " |
Token ID | 366 |
Feature activation | +1.74e+00 |
Pos logit contributions | |
igs | +0.009 |
often | +0.008 |
ot | +0.008 |
solar | +0.007 |
lived | +0.007 |
Neg logit contributions | |
written | -0.010 |
aback | -0.009 |
comm | -0.009 |
Gu | -0.009 |
source | -0.009 |
Token | I |
Token ID | 40 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
comm | +0.059 |
aback | +0.055 |
bisc | +0.053 |
calling | +0.053 |
source | +0.053 |
Neg logit contributions | |
often | -0.065 |
ot | -0.059 |
His | -0.057 |
lived | -0.057 |
solar | -0.055 |
Token | demand |
Token ID | 3512 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
comm | +0.043 |
aback | +0.041 |
Gu | +0.041 |
written | +0.040 |
umbs | +0.040 |
Neg logit contributions | |
often | -0.046 |
lived | -0.041 |
ot | -0.039 |
igs | -0.039 |
solar | -0.037 |
Token | a |
Token ID | 257 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
igs | +0.005 |
often | +0.005 |
ot | +0.004 |
solar | +0.004 |
lived | +0.004 |
Neg logit contributions | |
written | -0.004 |
aback | -0.004 |
comm | -0.004 |
Gu | -0.003 |
source | -0.003 |
Token | bisc |
Token ID | 36228 |
Feature activation | +4.04e+00 |
Pos logit contributions | |
aback | +0.042 |
comm | +0.041 |
written | +0.040 |
Gu | +0.040 |
hered | +0.040 |
Neg logit contributions | |
often | -0.038 |
ot | -0.035 |
igs | -0.034 |
solar | -0.034 |
tight | -0.031 |
Token | uit |
Token ID | 5013 |
Feature activation | +4.13e-01 |
Pos logit contributions | |
comm | +0.178 |
aback | +0.156 |
Gu | +0.154 |
source | +0.146 |
faith | +0.141 |
Neg logit contributions | |
ot | -0.130 |
belt | -0.111 |
kin | -0.109 |
ig | -0.107 |
lived | -0.106 |
Token | !" |
Token ID | 2474 |
Feature activation | +8.60e-01 |
Pos logit contributions | |
aback | +0.014 |
written | +0.014 |
comm | +0.014 |
Gu | +0.014 |
hered | +0.013 |
Neg logit contributions | |
often | -0.015 |
igs | -0.015 |
ot | -0.014 |
solar | -0.013 |
lived | -0.013 |
Token |
|
Token ID | 198 |
Feature activation | +4.76e-01 |
Pos logit contributions | |
written | +0.039 |
comm | +0.038 |
Gu | +0.038 |
aback | +0.037 |
bisc | +0.037 |
Neg logit contributions | |
often | -0.022 |
igs | -0.020 |
ot | -0.019 |
lived | -0.017 |
solar | -0.017 |
Token |
|
Token ID | 198 |
Feature activation | -4.25e-01 |
Pos logit contributions | |
written | +0.015 |
comm | +0.015 |
aback | +0.015 |
Gu | +0.014 |
bisc | +0.014 |
Neg logit contributions | |
often | -0.019 |
igs | -0.018 |
ot | -0.017 |
solar | -0.016 |
lived | -0.016 |
Token | The |
Token ID | 464 |
Feature activation | +5.08e-01 |
Pos logit contributions | |
igs | +0.014 |
often | +0.013 |
solar | +0.012 |
lived | +0.011 |
ot | +0.011 |
Neg logit contributions | |
Gu | -0.017 |
written | -0.017 |
aback | -0.017 |
comm | -0.016 |
Sur | -0.016 |
Token | " |
Token ID | 366 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
igs | +0.008 |
often | +0.008 |
solar | +0.007 |
ot | +0.006 |
lived | +0.006 |
Neg logit contributions | |
aback | -0.008 |
Gu | -0.008 |
written | -0.008 |
comm | -0.007 |
hered | -0.007 |
Token | Maybe |
Token ID | 13300 |
Feature activation | +8.20e-01 |
Pos logit contributions | |
comm | +0.036 |
aback | +0.035 |
written | +0.034 |
calling | +0.032 |
source | +0.031 |
Neg logit contributions | |
often | -0.047 |
igs | -0.045 |
ot | -0.044 |
solar | -0.040 |
apy | -0.040 |
Token | it |
Token ID | 340 |
Feature activation | +1.94e+00 |
Pos logit contributions | |
aback | +0.034 |
comm | +0.033 |
hered | +0.032 |
written | +0.032 |
Gu | +0.031 |
Neg logit contributions | |
often | -0.027 |
igs | -0.026 |
ot | -0.022 |
lived | -0.022 |
solar | -0.020 |
Token | is |
Token ID | 318 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
aback | +0.080 |
comm | +0.079 |
written | +0.079 |
hered | +0.078 |
oph | +0.077 |
Neg logit contributions | |
often | -0.063 |
igs | -0.055 |
lived | -0.055 |
goals | -0.046 |
tight | -0.046 |
Token | a |
Token ID | 257 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
aback | +0.058 |
hered | +0.055 |
Gu | +0.054 |
comm | +0.053 |
ives | +0.052 |
Neg logit contributions | |
often | -0.049 |
igs | -0.045 |
lived | -0.040 |
ot | -0.039 |
tight | -0.037 |
Token | birthday |
Token ID | 10955 |
Feature activation | +3.88e+00 |
Pos logit contributions | |
aback | +0.063 |
hered | +0.056 |
written | +0.055 |
comm | +0.054 |
Gu | +0.054 |
Neg logit contributions | |
often | -0.063 |
igs | -0.054 |
solar | -0.054 |
ot | -0.054 |
lived | -0.050 |
Token | cake |
Token ID | 12187 |
Feature activation | +3.08e+00 |
Pos logit contributions | |
aback | +0.186 |
comm | +0.170 |
arre | +0.163 |
hered | +0.161 |
source | +0.161 |
Neg logit contributions | |
often | -0.123 |
ot | -0.102 |
throne | -0.094 |
lived | -0.094 |
nicely | -0.093 |
Token | !" |
Token ID | 2474 |
Feature activation | +4.07e-01 |
Pos logit contributions | |
aback | +0.163 |
comm | +0.149 |
Gu | +0.144 |
hered | +0.139 |
viously | +0.136 |
Neg logit contributions | |
often | -0.092 |
ot | -0.067 |
lived | -0.065 |
igs | -0.064 |
every | -0.064 |
Token |
|
Token ID | 198 |
Feature activation | -5.96e-01 |
Pos logit contributions | |
written | +0.013 |
aback | +0.013 |
comm | +0.013 |
Gu | +0.013 |
hered | +0.012 |
Neg logit contributions | |
often | -0.016 |
igs | -0.016 |
ot | -0.014 |
lived | -0.014 |
solar | -0.014 |
Token |
|
Token ID | 198 |
Feature activation | -6.37e-01 |
Pos logit contributions | |
often | +0.029 |
igs | +0.028 |
solar | +0.026 |
belt | +0.025 |
gut | +0.025 |
Neg logit contributions | |
written | -0.013 |
comm | -0.013 |
aback | -0.013 |
Gu | -0.012 |
source | -0.012 |
Token | They |
Token ID | 2990 |
Feature activation | -8.90e-01 |
Pos logit contributions | |
igs | +0.030 |
often | +0.030 |
solar | +0.028 |
lived | +0.027 |
gut | +0.027 |
Neg logit contributions | |
Gu | -0.015 |
Sur | -0.014 |
comm | -0.014 |
written | -0.014 |
aback | -0.013 |
Token | crying |
Token ID | 13774 |
Feature activation | -5.07e-01 |
Pos logit contributions | |
igs | +0.000 |
often | +0.000 |
ot | +0.000 |
solar | +0.000 |
lived | +0.000 |
Neg logit contributions | |
written | -0.000 |
aback | -0.000 |
comm | -0.000 |
Gu | -0.000 |
hered | -0.000 |
Token | and |
Token ID | 290 |
Feature activation | +3.48e-01 |
Pos logit contributions | |
igs | +0.020 |
often | +0.019 |
solar | +0.018 |
ot | +0.017 |
lived | +0.017 |
Neg logit contributions | |
written | -0.016 |
comm | -0.016 |
aback | -0.016 |
hered | -0.015 |
source | -0.015 |
Token | say |
Token ID | 910 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
written | +0.011 |
aback | +0.011 |
Gu | +0.011 |
comm | +0.010 |
hered | +0.010 |
Neg logit contributions | |
often | -0.014 |
igs | -0.014 |
ot | -0.012 |
solar | -0.012 |
lived | -0.012 |
Token | " |
Token ID | 366 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
igs | +0.044 |
ind | +0.040 |
often | +0.039 |
solar | +0.038 |
ig | +0.037 |
Neg logit contributions | |
written | -0.034 |
aback | -0.031 |
hered | -0.030 |
come | -0.030 |
Gu | -0.029 |
Token | sorry |
Token ID | 41599 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
written | +0.058 |
aback | +0.057 |
calling | +0.056 |
comm | +0.055 |
source | +0.054 |
Neg logit contributions | |
often | -0.048 |
ot | -0.044 |
igs | -0.039 |
apy | -0.039 |
lived | -0.038 |
Token | " |
Token ID | 1 |
Feature activation | +3.83e+00 |
Pos logit contributions | |
written | +0.054 |
comm | +0.053 |
aback | +0.052 |
Gu | +0.052 |
source | +0.050 |
Neg logit contributions | |
often | -0.022 |
igs | -0.021 |
ot | -0.020 |
lived | -0.017 |
ug | -0.017 |
Token | to |
Token ID | 284 |
Feature activation | -6.50e-01 |
Pos logit contributions | |
comm | +0.173 |
aback | +0.164 |
ctions | +0.163 |
Gu | +0.162 |
ction | +0.160 |
Neg logit contributions | |
often | -0.110 |
ot | -0.101 |
every | -0.085 |
nicely | -0.083 |
tight | -0.083 |
Token | each |
Token ID | 1123 |
Feature activation | +6.19e-01 |
Pos logit contributions | |
igs | +0.026 |
often | +0.025 |
solar | +0.024 |
lived | +0.023 |
belt | +0.023 |
Neg logit contributions | |
comm | -0.019 |
aback | -0.018 |
calling | -0.018 |
Gu | -0.018 |
written | -0.018 |
Token | other |
Token ID | 584 |
Feature activation | -2.52e-01 |
Pos logit contributions | |
aback | +0.032 |
written | +0.032 |
comm | +0.031 |
Gu | +0.031 |
hered | +0.030 |
Neg logit contributions | |
often | -0.013 |
igs | -0.012 |
ot | -0.010 |
lived | -0.009 |
solar | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
igs | +0.008 |
often | +0.007 |
solar | +0.007 |
lived | +0.006 |
ot | +0.006 |
Neg logit contributions | |
aback | -0.010 |
written | -0.010 |
comm | -0.010 |
Gu | -0.010 |
hered | -0.010 |
Token | They |
Token ID | 1119 |
Feature activation | -5.91e-01 |
Pos logit contributions | |
igs | +0.044 |
often | +0.039 |
ind | +0.036 |
ug | +0.035 |
ts | +0.035 |
Neg logit contributions | |
aback | -0.032 |
Gu | -0.032 |
How | -0.031 |
comm | -0.031 |
written | -0.031 |
Token | you |
Token ID | 345 |
Feature activation | +5.35e-01 |
Pos logit contributions | |
igs | +0.006 |
often | +0.006 |
ot | +0.006 |
solar | +0.005 |
lived | +0.005 |
Neg logit contributions | |
written | -0.004 |
aback | -0.004 |
comm | -0.004 |
Gu | -0.004 |
hered | -0.004 |
Token | want |
Token ID | 765 |
Feature activation | +8.52e-01 |
Pos logit contributions | |
aback | +0.017 |
written | +0.017 |
Gu | +0.017 |
comm | +0.017 |
bisc | +0.016 |
Neg logit contributions | |
often | -0.021 |
igs | -0.021 |
ot | -0.019 |
lived | -0.019 |
solar | -0.018 |
Token | to |
Token ID | 284 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
comm | +0.027 |
aback | +0.027 |
Gu | +0.027 |
written | +0.026 |
bisc | +0.025 |
Neg logit contributions | |
often | -0.034 |
igs | -0.032 |
ot | -0.029 |
lived | -0.029 |
solar | -0.028 |
Token | go |
Token ID | 467 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
written | +0.005 |
aback | +0.005 |
comm | +0.005 |
Gu | +0.005 |
source | +0.005 |
Neg logit contributions | |
often | -0.006 |
igs | -0.006 |
ot | -0.006 |
solar | -0.006 |
lived | -0.006 |
Token | this |
Token ID | 428 |
Feature activation | +7.54e-01 |
Pos logit contributions | |
comm | +0.051 |
Gu | +0.050 |
written | +0.050 |
aback | +0.049 |
bisc | +0.047 |
Neg logit contributions | |
often | -0.040 |
igs | -0.036 |
ot | -0.033 |
lived | -0.031 |
ug | -0.030 |
Token | morning |
Token ID | 3329 |
Feature activation | +3.83e+00 |
Pos logit contributions | |
aback | +0.027 |
written | +0.027 |
Gu | +0.026 |
comm | +0.026 |
hered | +0.025 |
Neg logit contributions | |
often | -0.028 |
igs | -0.026 |
ot | -0.024 |
solar | -0.023 |
lived | -0.023 |
Token | John |
Token ID | 1757 |
Feature activation | +2.03e+00 |
Pos logit contributions | |
Gu | +0.213 |
comm | +0.208 |
aback | +0.206 |
ives | +0.203 |
eared | +0.199 |
Neg logit contributions | |
often | -0.073 |
lived | -0.046 |
ot | -0.046 |
igs | -0.040 |
every | -0.039 |
Token | ?" |
Token ID | 1701 |
Feature activation | +4.71e-01 |
Pos logit contributions | |
comm | +0.092 |
aback | +0.089 |
Gu | +0.088 |
written | +0.085 |
bisc | +0.085 |
Neg logit contributions | |
often | -0.060 |
lived | -0.048 |
igs | -0.047 |
ot | -0.047 |
solar | -0.039 |
Token | his |
Token ID | 465 |
Feature activation | -4.88e-01 |
Pos logit contributions | |
written | +0.016 |
aback | +0.016 |
comm | +0.016 |
Gu | +0.016 |
bisc | +0.015 |
Neg logit contributions | |
often | -0.017 |
igs | -0.016 |
ot | -0.015 |
lived | -0.015 |
solar | -0.014 |
Token | mom |
Token ID | 1995 |
Feature activation | +8.83e-01 |
Pos logit contributions | |
igs | +0.015 |
often | +0.014 |
solar | +0.013 |
ug | +0.012 |
ot | +0.012 |
Neg logit contributions | |
comm | -0.020 |
written | -0.020 |
aback | -0.020 |
source | -0.019 |
Gu | -0.019 |
Token | asked |
Token ID | 1965 |
Feature activation | +3.24e-01 |
Pos logit contributions | |
aback | +0.031 |
Gu | +0.030 |
comm | +0.029 |
written | +0.029 |
bisc | +0.029 |
Neg logit contributions | |
often | -0.033 |
igs | -0.030 |
ot | -0.029 |
lived | -0.027 |
ug | -0.026 |
Token | do |
Token ID | 466 |
Feature activation | +5.26e-01 |
Pos logit contributions | |
aback | +0.022 |
comm | +0.022 |
Gu | +0.021 |
written | +0.021 |
hered | +0.021 |
Neg logit contributions | |
often | -0.027 |
igs | -0.026 |
lived | -0.024 |
ot | -0.024 |
solar | -0.023 |
Token | I |
Token ID | 314 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
aback | +0.018 |
written | +0.018 |
comm | +0.017 |
Gu | +0.017 |
source | +0.016 |
Neg logit contributions | |
often | -0.020 |
igs | -0.020 |
ot | -0.018 |
lived | -0.017 |
solar | -0.017 |
Token | have |
Token ID | 423 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
oph | +0.072 |
aback | +0.070 |
Gu | +0.070 |
hered | +0.069 |
umbs | +0.069 |
Neg logit contributions | |
often | -0.050 |
ot | -0.043 |
lived | -0.043 |
igs | -0.042 |
exc | -0.039 |
Token | to |
Token ID | 284 |
Feature activation | -7.38e-01 |
Pos logit contributions | |
aback | +0.049 |
comm | +0.049 |
Gu | +0.048 |
bisc | +0.047 |
hered | +0.046 |
Neg logit contributions | |
often | -0.048 |
igs | -0.044 |
lived | -0.040 |
ot | -0.039 |
solar | -0.037 |
Token | do |
Token ID | 466 |
Feature activation | +6.61e-01 |
Pos logit contributions | |
igs | +0.029 |
often | +0.029 |
solar | +0.027 |
goals | +0.026 |
ug | +0.025 |
Neg logit contributions | |
written | -0.022 |
comm | -0.022 |
aback | -0.021 |
come | -0.021 |
source | -0.021 |
Token | mom |
Token ID | 1995 |
Feature activation | +3.81e+00 |
Pos logit contributions | |
comm | +0.026 |
aback | +0.026 |
written | +0.026 |
Gu | +0.026 |
bisc | +0.025 |
Neg logit contributions | |
often | -0.021 |
igs | -0.020 |
ot | -0.018 |
lived | -0.017 |
solar | -0.017 |
Token | my |
Token ID | 1820 |
Feature activation | +2.39e+00 |
Pos logit contributions | |
comm | +0.178 |
aback | +0.176 |
Sur | +0.166 |
bisc | +0.165 |
oph | +0.164 |
Neg logit contributions | |
often | -0.118 |
ot | -0.093 |
own | -0.088 |
nicely | -0.082 |
alone | -0.079 |
Token | ?". |
Token ID | 43634 |
Feature activation | +2.53e-01 |
Pos logit contributions | |
comm | +0.102 |
aback | +0.101 |
Gu | +0.100 |
bisc | +0.096 |
Sur | +0.095 |
Neg logit contributions | |
often | -0.076 |
ot | -0.065 |
igs | -0.063 |
lived | -0.055 |
nicely | -0.053 |
Token |
|
Token ID | 198 |
Feature activation | +6.85e-01 |
Pos logit contributions | |
written | +0.011 |
aback | +0.011 |
comm | +0.011 |
Gu | +0.011 |
source | +0.010 |
Neg logit contributions | |
often | -0.007 |
igs | -0.007 |
ot | -0.006 |
solar | -0.006 |
lived | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | -3.61e-01 |
Pos logit contributions | |
written | +0.023 |
aback | +0.023 |
comm | +0.023 |
Gu | +0.022 |
bisc | +0.022 |
Neg logit contributions | |
often | -0.026 |
igs | -0.024 |
ot | -0.023 |
lived | -0.022 |
solar | -0.022 |
Token | Her |
Token ID | 9360 |
Feature activation | +8.84e-02 |
Pos logit contributions | |
igs | +0.012 |
often | +0.011 |
solar | +0.010 |
ug | +0.010 |
ot | +0.009 |
Neg logit contributions | |
written | -0.014 |
Gu | -0.014 |
aback | -0.014 |
comm | -0.014 |
Sur | -0.013 |
Token | okay |
Token ID | 8788 |
Feature activation | +3.37e-01 |
Pos logit contributions | |
igs | +0.006 |
often | +0.005 |
ot | +0.005 |
solar | +0.005 |
lived | +0.005 |
Neg logit contributions | |
written | -0.005 |
aback | -0.005 |
comm | -0.005 |
Gu | -0.005 |
source | -0.005 |
Token | to |
Token ID | 284 |
Feature activation | -2.82e-01 |
Pos logit contributions | |
written | +0.011 |
aback | +0.011 |
comm | +0.011 |
Gu | +0.010 |
source | +0.010 |
Neg logit contributions | |
often | -0.013 |
igs | -0.013 |
ot | -0.012 |
lived | -0.012 |
solar | -0.012 |
Token | say |
Token ID | 910 |
Feature activation | -2.95e-01 |
Pos logit contributions | |
igs | +0.012 |
often | +0.011 |
solar | +0.010 |
ot | +0.010 |
apy | +0.010 |
Neg logit contributions | |
aback | -0.009 |
written | -0.009 |
comm | -0.009 |
Gu | -0.008 |
source | -0.008 |
Token | " |
Token ID | 366 |
Feature activation | +2.83e+00 |
Pos logit contributions | |
igs | +0.011 |
often | +0.010 |
solar | +0.009 |
ot | +0.009 |
lived | +0.009 |
Neg logit contributions | |
written | -0.011 |
aback | -0.010 |
comm | -0.010 |
Gu | -0.010 |
hered | -0.010 |
Token | sorry |
Token ID | 41599 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
comm | +0.088 |
bisc | +0.082 |
aback | +0.081 |
written | +0.079 |
begs | +0.078 |
Neg logit contributions | |
often | -0.113 |
ot | -0.106 |
ug | -0.098 |
igs | -0.096 |
ind | -0.092 |
Token | " |
Token ID | 1 |
Feature activation | +3.78e+00 |
Pos logit contributions | |
written | +0.052 |
comm | +0.052 |
aback | +0.051 |
Gu | +0.051 |
bisc | +0.049 |
Neg logit contributions | |
often | -0.042 |
igs | -0.040 |
ot | -0.039 |
lived | -0.036 |
ug | -0.035 |
Token | if |
Token ID | 611 |
Feature activation | +1.67e-01 |
Pos logit contributions | |
comm | +0.150 |
ctions | +0.144 |
ction | +0.143 |
Gu | +0.143 |
bisc | +0.143 |
Neg logit contributions | |
often | -0.119 |
ot | -0.112 |
every | -0.097 |
belt | -0.097 |
tight | -0.095 |
Token | you |
Token ID | 345 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
written | +0.006 |
aback | +0.006 |
comm | +0.006 |
Gu | +0.006 |
source | +0.006 |
Neg logit contributions | |
often | -0.006 |
igs | -0.006 |
ot | -0.005 |
solar | -0.005 |
lived | -0.005 |
Token | make |
Token ID | 787 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
written | +0.004 |
aback | +0.004 |
comm | +0.003 |
Gu | +0.003 |
hered | +0.003 |
Neg logit contributions | |
igs | -0.005 |
often | -0.005 |
ot | -0.004 |
solar | -0.004 |
lived | -0.004 |
Token | a |
Token ID | 257 |
Feature activation | +6.26e-04 |
Pos logit contributions | |
aback | +0.057 |
Gu | +0.057 |
written | +0.057 |
cake | +0.057 |
bisc | +0.057 |
Neg logit contributions | |
igs | -0.050 |
often | -0.049 |
ot | -0.044 |
goals | -0.043 |
tight | -0.040 |
Token | mistake |
Token ID | 7457 |
Feature activation | +2.87e-01 |
Pos logit contributions | |
written | +0.000 |
aback | +0.000 |
comm | +0.000 |
Gu | +0.000 |
source | +0.000 |
Neg logit contributions | |
igs | -0.000 |
often | -0.000 |
ot | -0.000 |
solar | -0.000 |
lived | -0.000 |
Token | , |
Token ID | 11 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
aback | +0.053 |
written | +0.052 |
Gu | +0.052 |
comm | +0.051 |
source | +0.050 |
Neg logit contributions | |
igs | -0.025 |
often | -0.024 |
ot | -0.021 |
lived | -0.019 |
ug | -0.017 |
Token | hey |
Token ID | 17207 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
written | +0.060 |
aback | +0.056 |
Gu | +0.055 |
comm | +0.054 |
cake | +0.053 |
Neg logit contributions | |
often | -0.047 |
igs | -0.046 |
ot | -0.044 |
lived | -0.042 |
gut | -0.041 |
Token | ! |
Token ID | 0 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
aback | +0.062 |
Gu | +0.060 |
written | +0.060 |
comm | +0.059 |
source | +0.058 |
Neg logit contributions | |
igs | -0.034 |
often | -0.032 |
ot | -0.029 |
lived | -0.028 |
ug | -0.025 |
Token | What |
Token ID | 1867 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
written | +0.036 |
aback | +0.034 |
comm | +0.033 |
source | +0.032 |
bisc | +0.030 |
Neg logit contributions | |
igs | -0.045 |
often | -0.044 |
ot | -0.044 |
lived | -0.043 |
solar | -0.042 |
Token | is |
Token ID | 318 |
Feature activation | +8.38e-02 |
Pos logit contributions | |
aback | +0.078 |
comm | +0.074 |
source | +0.073 |
Gu | +0.070 |
bisc | +0.070 |
Neg logit contributions | |
lived | -0.053 |
often | -0.051 |
ot | -0.045 |
igs | -0.045 |
solar | -0.043 |
Token | going |
Token ID | 1016 |
Feature activation | +3.78e+00 |
Pos logit contributions | |
written | +0.003 |
aback | +0.003 |
comm | +0.003 |
Gu | +0.003 |
source | +0.003 |
Neg logit contributions | |
often | -0.003 |
igs | -0.003 |
ot | -0.003 |
solar | -0.003 |
lived | -0.002 |
Token | on |
Token ID | 319 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
umbs | +0.180 |
oph | +0.179 |
aback | +0.170 |
Gu | +0.167 |
ives | +0.167 |
Neg logit contributions | |
often | -0.086 |
high | -0.082 |
ot | -0.079 |
alone | -0.076 |
igs | -0.070 |
Token | here |
Token ID | 994 |
Feature activation | +2.00e+00 |
Pos logit contributions | |
aback | +0.048 |
Gu | +0.047 |
written | +0.047 |
comm | +0.046 |
source | +0.043 |
Neg logit contributions | |
igs | -0.061 |
often | -0.059 |
ot | -0.054 |
lived | -0.051 |
ug | -0.051 |
Token | ?" |
Token ID | 1701 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
Gu | +0.101 |
aback | +0.099 |
comm | +0.098 |
written | +0.095 |
hered | +0.092 |
Neg logit contributions | |
often | -0.047 |
lived | -0.041 |
igs | -0.041 |
ot | -0.037 |
nicely | -0.032 |
Token | Mom |
Token ID | 11254 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
igs | +0.059 |
often | +0.056 |
belt | +0.055 |
ug | +0.051 |
solar | +0.050 |
Neg logit contributions | |
Gu | -0.042 |
comm | -0.041 |
written | -0.039 |
begs | -0.038 |
calling | -0.037 |
Token | my |
Token ID | 1820 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
aback | +0.049 |
bisc | +0.047 |
oph | +0.046 |
written | +0.046 |
hered | +0.046 |
Neg logit contributions | |
often | -0.078 |
igs | -0.072 |
ot | -0.068 |
ind | -0.065 |
ug | -0.063 |
Token | my |
Token ID | 1820 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
comm | +0.045 |
aback | +0.042 |
Gu | +0.042 |
bisc | +0.042 |
hered | +0.042 |
Neg logit contributions | |
often | -0.069 |
lived | -0.059 |
ot | -0.058 |
igs | -0.057 |
tight | -0.054 |
Token | saw |
Token ID | 2497 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
comm | +0.036 |
Gu | +0.035 |
aback | +0.035 |
written | +0.034 |
bisc | +0.033 |
Neg logit contributions | |
often | -0.048 |
lived | -0.043 |
igs | -0.043 |
ot | -0.041 |
solar | -0.038 |
Token | her |
Token ID | 607 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
comm | +0.085 |
Gu | +0.083 |
bisc | +0.080 |
hered | +0.080 |
aback | +0.079 |
Neg logit contributions | |
often | -0.037 |
lived | -0.033 |
igs | -0.032 |
ot | -0.030 |
every | -0.027 |
Token | and |
Token ID | 290 |
Feature activation | -8.43e-02 |
Pos logit contributions | |
Gu | +0.066 |
aback | +0.060 |
umbs | +0.057 |
comm | +0.057 |
Sur | +0.056 |
Neg logit contributions | |
often | -0.045 |
ot | -0.039 |
igs | -0.039 |
lived | -0.038 |
tight | -0.038 |
Token | said |
Token ID | 531 |
Feature activation | -5.77e-01 |
Pos logit contributions | |
igs | +0.004 |
often | +0.004 |
solar | +0.004 |
ot | +0.004 |
goals | +0.004 |
Neg logit contributions | |
written | -0.002 |
comm | -0.002 |
aback | -0.002 |
Gu | -0.002 |
source | -0.002 |
Token | " |
Token ID | 366 |
Feature activation | +3.75e+00 |
Pos logit contributions | |
igs | +0.019 |
often | +0.018 |
solar | +0.016 |
ind | +0.015 |
ot | +0.015 |
Neg logit contributions | |
written | -0.023 |
aback | -0.022 |
Gu | -0.022 |
comm | -0.022 |
hered | -0.021 |
Token | G |
Token ID | 38 |
Feature activation | -8.43e-01 |
Pos logit contributions | |
begs | +0.140 |
ives | +0.136 |
comm | +0.133 |
Birthday | +0.128 |
bisc | +0.127 |
Neg logit contributions | |
often | -0.118 |
ind | -0.106 |
ot | -0.104 |
every | -0.091 |
His | -0.089 |
Token | abby |
Token ID | 42457 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
often | +0.035 |
solar | +0.033 |
igs | +0.033 |
apy | +0.032 |
lived | +0.031 |
Neg logit contributions | |
written | -0.025 |
aback | -0.024 |
Gu | -0.023 |
oph | -0.023 |
cake | -0.022 |
Token | , |
Token ID | 11 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
igs | +0.045 |
often | +0.043 |
solar | +0.040 |
gut | +0.038 |
apy | +0.038 |
Neg logit contributions | |
written | -0.048 |
aback | -0.047 |
Birthday | -0.045 |
hered | -0.044 |
come | -0.044 |
Token | what |
Token ID | 644 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
aback | +0.042 |
comm | +0.042 |
hered | +0.041 |
written | +0.041 |
Gu | +0.041 |
Neg logit contributions | |
often | -0.034 |
igs | -0.031 |
ot | -0.029 |
lived | -0.029 |
solar | -0.027 |
Token | 's |
Token ID | 338 |
Feature activation | +6.90e-01 |
Pos logit contributions | |
aback | +0.054 |
comm | +0.053 |
hered | +0.050 |
Gu | +0.049 |
source | +0.048 |
Neg logit contributions | |
often | -0.054 |
lived | -0.052 |
igs | -0.047 |
solar | -0.046 |
goals | -0.045 |
Token | The |
Token ID | 383 |
Feature activation | -4.75e-01 |
Pos logit contributions | |
written | +0.028 |
aback | +0.027 |
comm | +0.027 |
Gu | +0.027 |
hered | +0.026 |
Neg logit contributions | |
often | -0.027 |
igs | -0.024 |
ot | -0.023 |
lived | -0.023 |
solar | -0.022 |
Token | flame |
Token ID | 16506 |
Feature activation | +9.65e-01 |
Pos logit contributions | |
igs | +0.016 |
often | +0.015 |
ot | +0.015 |
ug | +0.014 |
solar | +0.013 |
Neg logit contributions | |
comm | -0.018 |
source | -0.018 |
written | -0.017 |
Gu | -0.017 |
aback | -0.017 |
Token | said |
Token ID | 531 |
Feature activation | +2.77e-02 |
Pos logit contributions | |
aback | +0.034 |
Gu | +0.033 |
written | +0.033 |
comm | +0.032 |
hered | +0.031 |
Neg logit contributions | |
often | -0.037 |
igs | -0.034 |
lived | -0.032 |
ot | -0.031 |
solar | -0.030 |
Token | " |
Token ID | 366 |
Feature activation | +2.76e+00 |
Pos logit contributions | |
written | +0.001 |
aback | +0.001 |
comm | +0.001 |
Gu | +0.001 |
hered | +0.001 |
Neg logit contributions | |
igs | -0.001 |
often | -0.001 |
ot | -0.001 |
solar | -0.001 |
lived | -0.001 |
Token | bye |
Token ID | 16390 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
comm | +0.092 |
aback | +0.087 |
source | +0.082 |
begs | +0.082 |
calling | +0.081 |
Neg logit contributions | |
often | -0.111 |
ot | -0.102 |
lived | -0.094 |
ug | -0.086 |
His | -0.084 |
Token | " |
Token ID | 1 |
Feature activation | +3.74e+00 |
Pos logit contributions | |
comm | +0.062 |
aback | +0.061 |
written | +0.060 |
Gu | +0.058 |
bisc | +0.057 |
Neg logit contributions | |
often | -0.045 |
igs | -0.039 |
ot | -0.039 |
lived | -0.035 |
solar | -0.034 |
Token | too |
Token ID | 1165 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
comm | +0.158 |
Gu | +0.155 |
bisc | +0.152 |
ction | +0.152 |
ctions | +0.151 |
Neg logit contributions | |
often | -0.118 |
ot | -0.103 |
every | -0.091 |
tight | -0.085 |
lived | -0.083 |
Token | . |
Token ID | 13 |
Feature activation | +5.08e-01 |
Pos logit contributions | |
igs | +0.070 |
solar | +0.061 |
lived | +0.057 |
nam | +0.057 |
belt | +0.057 |
Neg logit contributions | |
written | -0.051 |
come | -0.048 |
calling | -0.048 |
saying | -0.046 |
alright | -0.046 |
Token | Amy |
Token ID | 14235 |
Feature activation | +2.03e-01 |
Pos logit contributions | |
written | +0.015 |
aback | +0.015 |
comm | +0.015 |
Gu | +0.015 |
source | +0.014 |
Neg logit contributions | |
often | -0.021 |
igs | -0.020 |
ot | -0.019 |
lived | -0.018 |
solar | -0.018 |
Token | went |
Token ID | 1816 |
Feature activation | +4.30e-01 |
Pos logit contributions | |
written | +0.006 |
aback | +0.006 |
comm | +0.006 |
Gu | +0.006 |
source | +0.006 |
Neg logit contributions | |
often | -0.008 |
igs | -0.008 |
ot | -0.007 |
solar | -0.007 |
lived | -0.007 |
Token | home |
Token ID | 1363 |
Feature activation | -5.12e-01 |
Pos logit contributions | |
written | +0.014 |
comm | +0.014 |
aback | +0.014 |
Gu | +0.013 |
source | +0.012 |
Neg logit contributions | |
often | -0.017 |
igs | -0.017 |
ot | -0.015 |
solar | -0.015 |
lived | -0.014 |
Token | me |
Token ID | 502 |
Feature activation | +5.15e-01 |
Pos logit contributions | |
often | +0.038 |
igs | +0.038 |
solar | +0.036 |
lived | +0.035 |
goals | +0.034 |
Neg logit contributions | |
written | -0.028 |
aback | -0.028 |
comm | -0.027 |
calling | -0.027 |
Gu | -0.026 |
Token | to |
Token ID | 284 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
comm | +0.016 |
written | +0.016 |
aback | +0.016 |
Gu | +0.016 |
hered | +0.015 |
Neg logit contributions | |
often | -0.020 |
igs | -0.020 |
ot | -0.018 |
solar | -0.017 |
lived | -0.017 |
Token | finish |
Token ID | 5461 |
Feature activation | -9.30e-01 |
Pos logit contributions | |
igs | +0.005 |
often | +0.005 |
solar | +0.004 |
ot | +0.004 |
lived | +0.004 |
Neg logit contributions | |
written | -0.003 |
aback | -0.003 |
comm | -0.003 |
Gu | -0.003 |
source | -0.003 |
Token | my |
Token ID | 616 |
Feature activation | -4.09e-01 |
Pos logit contributions | |
often | +0.031 |
igs | +0.031 |
solar | +0.030 |
lived | +0.029 |
ot | +0.029 |
Neg logit contributions | |
written | -0.033 |
aback | -0.031 |
comm | -0.031 |
calling | -0.031 |
source | -0.030 |
Token | bath |
Token ID | 7837 |
Feature activation | +4.24e-01 |
Pos logit contributions | |
often | +0.016 |
igs | +0.016 |
ot | +0.014 |
solar | +0.014 |
lived | +0.014 |
Neg logit contributions | |
comm | -0.013 |
written | -0.012 |
aback | -0.012 |
source | -0.012 |
Gu | -0.012 |
Token | " |
Token ID | 1 |
Feature activation | +3.74e+00 |
Pos logit contributions | |
written | +0.017 |
aback | +0.017 |
Gu | +0.017 |
comm | +0.017 |
hered | +0.016 |
Neg logit contributions | |
often | -0.013 |
igs | -0.013 |
ot | -0.011 |
lived | -0.011 |
solar | -0.011 |
Token | said |
Token ID | 531 |
Feature activation | +2.05e-02 |
Pos logit contributions | |
Gu | +0.146 |
comm | +0.141 |
ctions | +0.140 |
hered | +0.138 |
ction | +0.137 |
Neg logit contributions | |
often | -0.125 |
ot | -0.109 |
every | -0.101 |
tight | -0.100 |
belt | -0.095 |
Token | her |
Token ID | 607 |
Feature activation | -6.49e-01 |
Pos logit contributions | |
written | +0.001 |
aback | +0.001 |
comm | +0.001 |
Gu | +0.001 |
hered | +0.001 |
Neg logit contributions | |
igs | -0.001 |
often | -0.001 |
solar | -0.001 |
ot | -0.001 |
lived | -0.001 |
Token | mom |
Token ID | 1995 |
Feature activation | +6.01e-01 |
Pos logit contributions | |
igs | +0.020 |
often | +0.019 |
solar | +0.017 |
lived | +0.016 |
ug | +0.016 |
Neg logit contributions | |
written | -0.027 |
comm | -0.026 |
aback | -0.026 |
bisc | -0.025 |
source | -0.025 |
Token | . |
Token ID | 13 |
Feature activation | +7.76e-01 |
Pos logit contributions | |
aback | +0.016 |
Gu | +0.016 |
comm | +0.016 |
written | +0.016 |
hered | +0.015 |
Neg logit contributions | |
often | -0.027 |
igs | -0.026 |
ot | -0.024 |
lived | -0.023 |
solar | -0.023 |
Token |
|
Token ID | 198 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
written | +0.031 |
aback | +0.030 |
comm | +0.030 |
Gu | +0.030 |
bisc | +0.029 |
Neg logit contributions | |
often | -0.025 |
igs | -0.023 |
ot | -0.022 |
lived | -0.021 |
solar | -0.020 |
Token | my |
Token ID | 616 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
igs | +0.032 |
often | +0.031 |
solar | +0.029 |
ot | +0.028 |
ug | +0.028 |
Neg logit contributions | |
written | -0.020 |
comm | -0.019 |
Gu | -0.018 |
aback | -0.018 |
come | -0.017 |
Token | friend |
Token ID | 1545 |
Feature activation | +2.71e+00 |
Pos logit contributions | |
aback | +0.058 |
Gu | +0.054 |
hered | +0.053 |
comm | +0.052 |
written | +0.051 |
Neg logit contributions | |
often | -0.041 |
solar | -0.036 |
igs | -0.035 |
ot | -0.035 |
lived | -0.033 |
Token | send |
Token ID | 3758 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
aback | +0.112 |
comm | +0.110 |
Gu | +0.108 |
bisc | +0.102 |
ctions | +0.099 |
Neg logit contributions | |
often | -0.095 |
ot | -0.080 |
lived | -0.078 |
nicely | -0.070 |
own | -0.068 |
Token | me |
Token ID | 502 |
Feature activation | +6.26e-01 |
Pos logit contributions | |
Gu | +0.048 |
comm | +0.048 |
aback | +0.047 |
written | +0.045 |
hered | +0.045 |
Neg logit contributions | |
often | -0.038 |
igs | -0.036 |
ot | -0.035 |
lived | -0.031 |
solar | -0.030 |
Token | a |
Token ID | 257 |
Feature activation | +2.00e+00 |
Pos logit contributions | |
comm | +0.021 |
Gu | +0.021 |
written | +0.021 |
aback | +0.021 |
hered | +0.020 |
Neg logit contributions | |
often | -0.023 |
igs | -0.023 |
ot | -0.021 |
lived | -0.020 |
solar | -0.020 |
Token | birthday |
Token ID | 10955 |
Feature activation | +3.72e+00 |
Pos logit contributions | |
aback | +0.070 |
Gu | +0.067 |
comm | +0.064 |
hered | +0.063 |
umbs | +0.062 |
Neg logit contributions | |
often | -0.073 |
ot | -0.069 |
solar | -0.068 |
tight | -0.065 |
igs | -0.064 |
Token | card |
Token ID | 2657 |
Feature activation | +2.64e+00 |
Pos logit contributions | |
aback | +0.157 |
comm | +0.147 |
Gu | +0.144 |
hered | +0.135 |
viously | +0.133 |
Neg logit contributions | |
often | -0.129 |
ot | -0.115 |
collection | -0.103 |
nicely | -0.098 |
every | -0.098 |
Token | now |
Token ID | 783 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
comm | +0.120 |
aback | +0.120 |
Gu | +0.119 |
source | +0.107 |
hered | +0.107 |
Neg logit contributions | |
often | -0.079 |
ot | -0.063 |
lived | -0.062 |
igs | -0.060 |
nicely | -0.056 |
Token | ?" |
Token ID | 1701 |
Feature activation | +3.69e-01 |
Pos logit contributions | |
aback | +0.067 |
comm | +0.066 |
Gu | +0.065 |
bisc | +0.063 |
written | +0.063 |
Neg logit contributions | |
often | -0.037 |
igs | -0.031 |
lived | -0.031 |
ot | -0.028 |
solar | -0.025 |
Token | Her |
Token ID | 2332 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
written | +0.013 |
aback | +0.013 |
comm | +0.013 |
Gu | +0.013 |
source | +0.012 |
Neg logit contributions | |
often | -0.013 |
igs | -0.013 |
ot | -0.012 |
lived | -0.011 |
solar | -0.011 |
Token | mom |
Token ID | 1995 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
written | +0.008 |
aback | +0.008 |
comm | +0.007 |
Gu | +0.007 |
source | +0.007 |
Neg logit contributions | |
often | -0.004 |
igs | -0.004 |
ot | -0.003 |
solar | -0.003 |
lived | -0.003 |
Token | Daisy |
Token ID | 40355 |
Feature activation | +3.20e-01 |
Pos logit contributions | |
Gu | +0.043 |
written | +0.042 |
comm | +0.040 |
aback | +0.039 |
source | +0.039 |
Neg logit contributions | |
often | -0.039 |
igs | -0.036 |
ot | -0.035 |
lived | -0.034 |
apy | -0.032 |
Token | said |
Token ID | 531 |
Feature activation | -4.04e-01 |
Pos logit contributions | |
written | +0.011 |
aback | +0.011 |
comm | +0.011 |
Gu | +0.011 |
source | +0.010 |
Neg logit contributions | |
often | -0.012 |
igs | -0.011 |
ot | -0.010 |
solar | -0.010 |
lived | -0.010 |
Token | " |
Token ID | 366 |
Feature activation | +2.02e+00 |
Pos logit contributions | |
igs | +0.014 |
often | +0.013 |
solar | +0.012 |
lived | +0.011 |
ot | +0.011 |
Neg logit contributions | |
written | -0.015 |
aback | -0.015 |
comm | -0.014 |
hered | -0.014 |
Gu | -0.014 |
Token | Thank |
Token ID | 10449 |
Feature activation | +7.49e-01 |
Pos logit contributions | |
comm | +0.067 |
aback | +0.061 |
begs | +0.060 |
calling | +0.059 |
written | +0.059 |
Neg logit contributions | |
often | -0.085 |
ot | -0.076 |
igs | -0.069 |
lived | -0.068 |
belt | -0.066 |
Token | you |
Token ID | 345 |
Feature activation | -4.36e-01 |
Pos logit contributions | |
written | +0.026 |
aback | +0.026 |
comm | +0.026 |
Gu | +0.025 |
source | +0.025 |
Neg logit contributions | |
often | -0.028 |
igs | -0.027 |
ot | -0.025 |
lived | -0.024 |
ug | -0.023 |
Token | " |
Token ID | 1 |
Feature activation | +3.72e+00 |
Pos logit contributions | |
igs | +0.017 |
often | +0.016 |
solar | +0.015 |
lived | +0.014 |
ot | +0.014 |
Neg logit contributions | |
written | -0.015 |
aback | -0.014 |
comm | -0.014 |
Gu | -0.013 |
source | -0.013 |
Token | and |
Token ID | 290 |
Feature activation | -6.00e-01 |
Pos logit contributions | |
Gu | +0.152 |
comm | +0.150 |
ctions | +0.145 |
ograph | +0.144 |
ction | +0.143 |
Neg logit contributions | |
often | -0.117 |
ot | -0.106 |
every | -0.099 |
tight | -0.097 |
tightly | -0.094 |
Token | hugged |
Token ID | 41130 |
Feature activation | -9.02e-03 |
Pos logit contributions | |
igs | +0.024 |
often | +0.022 |
solar | +0.021 |
ot | +0.020 |
ug | +0.020 |
Neg logit contributions | |
written | -0.020 |
aback | -0.019 |
comm | -0.019 |
Gu | -0.018 |
hered | -0.018 |
Token | the |
Token ID | 262 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
igs | +0.000 |
often | +0.000 |
solar | +0.000 |
ot | +0.000 |
lived | +0.000 |
Neg logit contributions | |
aback | -0.000 |
written | -0.000 |
comm | -0.000 |
Gu | -0.000 |
hered | -0.000 |
Token | girl |
Token ID | 2576 |
Feature activation | -3.96e-01 |
Pos logit contributions | |
aback | +0.037 |
written | +0.037 |
comm | +0.037 |
oph | +0.034 |
umbs | +0.034 |
Neg logit contributions | |
often | -0.035 |
igs | -0.034 |
ot | -0.030 |
lived | -0.030 |
solar | -0.029 |
Token | . |
Token ID | 13 |
Feature activation | -2.04e-02 |
Pos logit contributions | |
igs | +0.014 |
often | +0.013 |
solar | +0.012 |
ot | +0.011 |
ug | +0.011 |
Neg logit contributions | |
written | -0.015 |
aback | -0.015 |
comm | -0.014 |
Gu | -0.014 |
hered | -0.014 |
Token | we |
Token ID | 356 |
Feature activation | -7.95e-01 |
Pos logit contributions | |
igs | +0.046 |
often | +0.043 |
ot | +0.041 |
solar | +0.041 |
gut | +0.039 |
Neg logit contributions | |
written | -0.028 |
Gu | -0.026 |
comm | -0.025 |
source | -0.025 |
come | -0.025 |
Token | have |
Token ID | 423 |
Feature activation | +6.89e-01 |
Pos logit contributions | |
igs | +0.033 |
often | +0.031 |
gut | +0.029 |
apy | +0.028 |
ot | +0.028 |
Neg logit contributions | |
written | -0.024 |
aback | -0.022 |
source | -0.022 |
come | -0.022 |
comm | -0.022 |
Token | a |
Token ID | 257 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
aback | +0.022 |
written | +0.022 |
comm | +0.021 |
Gu | +0.021 |
hered | +0.021 |
Neg logit contributions | |
often | -0.027 |
igs | -0.027 |
ot | -0.024 |
solar | -0.023 |
lived | -0.023 |
Token | perfectly |
Token ID | 7138 |
Feature activation | +5.32e-01 |
Pos logit contributions | |
aback | +0.048 |
written | +0.048 |
Gu | +0.046 |
comm | +0.044 |
eared | +0.044 |
Neg logit contributions | |
often | -0.050 |
igs | -0.046 |
solar | -0.043 |
ot | -0.042 |
tight | -0.040 |
Token | good |
Token ID | 922 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
aback | +0.021 |
comm | +0.021 |
written | +0.021 |
Gu | +0.020 |
hered | +0.019 |
Neg logit contributions | |
often | -0.017 |
igs | -0.017 |
ot | -0.015 |
solar | -0.014 |
lived | -0.014 |
Token | tea |
Token ID | 8887 |
Feature activation | +3.69e+00 |
Pos logit contributions | |
Gu | +0.051 |
written | +0.050 |
aback | +0.048 |
comm | +0.046 |
hered | +0.046 |
Neg logit contributions | |
often | -0.048 |
igs | -0.047 |
ot | -0.044 |
solar | -0.040 |
lived | -0.039 |
Token | set |
Token ID | 900 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
Gu | +0.161 |
aback | +0.156 |
comm | +0.139 |
Uh | +0.135 |
Come | +0.134 |
Neg logit contributions | |
often | -0.121 |
igs | -0.104 |
ot | -0.100 |
collection | -0.095 |
lived | -0.095 |
Token | ?" |
Token ID | 1701 |
Feature activation | +3.08e-01 |
Pos logit contributions | |
Gu | +0.057 |
comm | +0.056 |
aback | +0.054 |
written | +0.052 |
hered | +0.051 |
Neg logit contributions | |
often | -0.040 |
igs | -0.037 |
ot | -0.034 |
ug | -0.030 |
lived | -0.030 |
Token | he |
Token ID | 339 |
Feature activation | +1.91e-01 |
Pos logit contributions | |
written | +0.011 |
aback | +0.011 |
comm | +0.011 |
Gu | +0.011 |
source | +0.011 |
Neg logit contributions | |
often | -0.011 |
igs | -0.010 |
ot | -0.009 |
lived | -0.009 |
solar | -0.009 |
Token | asked |
Token ID | 1965 |
Feature activation | -7.17e-01 |
Pos logit contributions | |
written | +0.005 |
aback | +0.005 |
comm | +0.005 |
Gu | +0.005 |
hered | +0.005 |
Neg logit contributions | |
often | -0.008 |
igs | -0.008 |
ot | -0.007 |
solar | -0.007 |
lived | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | +3.08e-01 |
Pos logit contributions | |
igs | +0.027 |
solar | +0.025 |
often | +0.024 |
ug | +0.022 |
goals | +0.021 |
Neg logit contributions | |
aback | -0.027 |
written | -0.026 |
comm | -0.025 |
Gu | -0.024 |
hered | -0.024 |
Token | . |
Token ID | 13 |
Feature activation | +7.97e-01 |
Pos logit contributions | |
written | +0.021 |
Gu | +0.021 |
aback | +0.021 |
comm | +0.021 |
bisc | +0.020 |
Neg logit contributions | |
often | -0.015 |
igs | -0.014 |
ot | -0.013 |
gut | -0.011 |
solar | -0.011 |
Token | He |
Token ID | 679 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
written | +0.037 |
comm | +0.037 |
aback | +0.036 |
hered | +0.036 |
Gu | +0.036 |
Neg logit contributions | |
often | -0.019 |
igs | -0.018 |
ot | -0.016 |
lived | -0.015 |
solar | -0.015 |
Token | didn |
Token ID | 1422 |
Feature activation | +5.06e-01 |
Pos logit contributions | |
written | +0.004 |
aback | +0.004 |
comm | +0.004 |
Gu | +0.004 |
hered | +0.003 |
Neg logit contributions | |
igs | -0.004 |
often | -0.004 |
ot | -0.003 |
solar | -0.003 |
lived | -0.003 |
Token | 't |
Token ID | 470 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
written | +0.013 |
aback | +0.013 |
comm | +0.013 |
Gu | +0.013 |
bisc | +0.012 |
Neg logit contributions | |
often | -0.023 |
igs | -0.023 |
ot | -0.021 |
solar | -0.020 |
lived | -0.020 |
Token | want |
Token ID | 765 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
Gu | +0.052 |
oph | +0.051 |
comm | +0.051 |
written | +0.050 |
ingredients | +0.049 |
Neg logit contributions | |
often | -0.047 |
ot | -0.041 |
exc | -0.038 |
igs | -0.037 |
lived | -0.035 |
Token | Farmer |
Token ID | 37755 |
Feature activation | +3.69e+00 |
Pos logit contributions | |
comm | +0.039 |
Gu | +0.037 |
hered | +0.037 |
written | +0.037 |
aback | +0.036 |
Neg logit contributions | |
often | -0.040 |
igs | -0.037 |
ot | -0.035 |
solar | -0.032 |
gut | -0.031 |
Token | Dan |
Token ID | 6035 |
Feature activation | -8.03e-03 |
Pos logit contributions | |
Uh | +0.156 |
Gu | +0.153 |
umbs | +0.143 |
Ta | +0.142 |
arre | +0.142 |
Neg logit contributions | |
often | -0.112 |
ot | -0.086 |
toes | -0.086 |
lived | -0.084 |
gut | -0.080 |
Token | to |
Token ID | 284 |
Feature activation | +5.68e-01 |
Pos logit contributions | |
igs | +0.000 |
often | +0.000 |
solar | +0.000 |
ot | +0.000 |
lived | +0.000 |
Neg logit contributions | |
written | -0.000 |
aback | -0.000 |
comm | -0.000 |
Gu | -0.000 |
hered | -0.000 |
Token | be |
Token ID | 307 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
written | +0.019 |
aback | +0.019 |
Gu | +0.019 |
comm | +0.019 |
bisc | +0.017 |
Neg logit contributions | |
often | -0.022 |
igs | -0.021 |
ot | -0.019 |
lived | -0.018 |
gut | -0.018 |
Token | mad |
Token ID | 8805 |
Feature activation | +8.40e-01 |
Pos logit contributions | |
Gu | +0.040 |
cake | +0.039 |
written | +0.039 |
oph | +0.039 |
comm | +0.038 |
Neg logit contributions | |
often | -0.038 |
igs | -0.035 |
ot | -0.032 |
lived | -0.029 |
goals | -0.029 |
Token | . |
Token ID | 13 |
Feature activation | +8.65e-01 |
Pos logit contributions | |
Gu | +0.036 |
aback | +0.035 |
comm | +0.035 |
written | +0.035 |
bisc | +0.035 |
Neg logit contributions | |
often | -0.025 |
igs | -0.022 |
ot | -0.020 |
goals | -0.019 |
gut | -0.018 |
Token | . |
Token ID | 13 |
Feature activation | +6.86e-01 |
Pos logit contributions | |
written | +0.008 |
aback | +0.008 |
comm | +0.008 |
Gu | +0.008 |
source | +0.007 |
Neg logit contributions | |
often | -0.005 |
igs | -0.005 |
ot | -0.004 |
solar | -0.004 |
lived | -0.004 |
Token | Amy |
Token ID | 14235 |
Feature activation | +4.24e-01 |
Pos logit contributions | |
written | +0.019 |
aback | +0.019 |
Gu | +0.019 |
comm | +0.019 |
hered | +0.018 |
Neg logit contributions | |
often | -0.029 |
igs | -0.028 |
ot | -0.027 |
lived | -0.026 |
solar | -0.026 |
Token | said |
Token ID | 531 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
written | +0.012 |
aback | +0.012 |
Gu | +0.012 |
comm | +0.012 |
source | +0.011 |
Neg logit contributions | |
often | -0.018 |
igs | -0.017 |
ot | -0.016 |
lived | -0.016 |
solar | -0.016 |
Token | " |
Token ID | 366 |
Feature activation | +2.44e+00 |
Pos logit contributions | |
igs | +0.050 |
ind | +0.045 |
solar | +0.044 |
often | +0.042 |
agons | +0.040 |
Neg logit contributions | |
written | -0.036 |
aback | -0.034 |
come | -0.031 |
hered | -0.031 |
happened | -0.031 |
Token | bye |
Token ID | 16390 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
comm | +0.094 |
aback | +0.091 |
begs | +0.086 |
calling | +0.084 |
source | +0.081 |
Neg logit contributions | |
often | -0.088 |
ot | -0.079 |
lived | -0.072 |
belt | -0.065 |
His | -0.064 |
Token | " |
Token ID | 1 |
Feature activation | +3.67e+00 |
Pos logit contributions | |
comm | +0.061 |
aback | +0.060 |
written | +0.060 |
Gu | +0.057 |
bisc | +0.055 |
Neg logit contributions | |
often | -0.039 |
igs | -0.035 |
ot | -0.034 |
lived | -0.030 |
solar | -0.030 |
Token | to |
Token ID | 284 |
Feature activation | -2.62e-01 |
Pos logit contributions | |
comm | +0.164 |
ctions | +0.158 |
Gu | +0.157 |
ction | +0.157 |
aback | +0.153 |
Neg logit contributions | |
often | -0.111 |
ot | -0.094 |
every | -0.085 |
tight | -0.080 |
tightly | -0.075 |
Token | her |
Token ID | 607 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
igs | +0.010 |
often | +0.009 |
solar | +0.008 |
ot | +0.008 |
apy | +0.008 |
Neg logit contributions | |
written | -0.009 |
comm | -0.009 |
aback | -0.009 |
Gu | -0.008 |
calling | -0.008 |
Token | new |
Token ID | 649 |
Feature activation | -7.45e-01 |
Pos logit contributions | |
igs | +0.006 |
often | +0.006 |
ot | +0.005 |
solar | +0.005 |
lived | +0.005 |
Neg logit contributions | |
written | -0.007 |
comm | -0.007 |
aback | -0.007 |
Gu | -0.007 |
source | -0.007 |
Token | friend |
Token ID | 1545 |
Feature activation | +9.54e-01 |
Pos logit contributions | |
igs | +0.029 |
often | +0.028 |
ot | +0.026 |
apy | +0.026 |
ug | +0.026 |
Neg logit contributions | |
comm | -0.024 |
written | -0.023 |
aback | -0.023 |
source | -0.023 |
bisc | -0.022 |
Token | , |
Token ID | 11 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
comm | +0.043 |
aback | +0.043 |
Gu | +0.043 |
written | +0.042 |
source | +0.040 |
Neg logit contributions | |
often | -0.026 |
igs | -0.022 |
ot | -0.021 |
lived | -0.021 |
solar | -0.019 |
Token | She |
Token ID | 1375 |
Feature activation | -4.03e-01 |
Pos logit contributions | |
written | +0.017 |
aback | +0.017 |
comm | +0.016 |
Gu | +0.016 |
hered | +0.016 |
Neg logit contributions | |
often | -0.012 |
igs | -0.011 |
ot | -0.010 |
solar | -0.009 |
lived | -0.009 |
Token | said |
Token ID | 531 |
Feature activation | -4.73e-01 |
Pos logit contributions | |
igs | +0.019 |
often | +0.018 |
solar | +0.017 |
ot | +0.016 |
ug | +0.016 |
Neg logit contributions | |
written | -0.011 |
comm | -0.010 |
aback | -0.010 |
Gu | -0.009 |
bisc | -0.009 |
Token | " |
Token ID | 366 |
Feature activation | +2.25e+00 |
Pos logit contributions | |
igs | +0.017 |
often | +0.015 |
solar | +0.014 |
ind | +0.014 |
ot | +0.013 |
Neg logit contributions | |
written | -0.018 |
aback | -0.018 |
comm | -0.017 |
Gu | -0.017 |
hered | -0.016 |
Token | Thank |
Token ID | 10449 |
Feature activation | +8.44e-01 |
Pos logit contributions | |
comm | +0.083 |
aback | +0.079 |
begs | +0.078 |
calling | +0.073 |
source | +0.072 |
Neg logit contributions | |
often | -0.082 |
ot | -0.077 |
ind | -0.066 |
lived | -0.065 |
His | -0.063 |
Token | you |
Token ID | 345 |
Feature activation | -2.51e-01 |
Pos logit contributions | |
written | +0.031 |
comm | +0.031 |
aback | +0.031 |
source | +0.030 |
Gu | +0.029 |
Neg logit contributions | |
often | -0.030 |
igs | -0.029 |
ot | -0.027 |
lived | -0.025 |
solar | -0.024 |
Token | " |
Token ID | 1 |
Feature activation | +3.67e+00 |
Pos logit contributions | |
igs | +0.009 |
often | +0.008 |
solar | +0.008 |
lived | +0.007 |
ot | +0.007 |
Neg logit contributions | |
written | -0.009 |
aback | -0.009 |
comm | -0.009 |
Gu | -0.009 |
source | -0.008 |
Token | in |
Token ID | 287 |
Feature activation | +6.29e-01 |
Pos logit contributions | |
ctions | +0.165 |
ograph | +0.164 |
comm | +0.163 |
Gu | +0.163 |
ction | +0.161 |
Neg logit contributions | |
often | -0.106 |
ot | -0.086 |
every | -0.085 |
tight | -0.079 |
nicely | -0.074 |
Token | a |
Token ID | 257 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
Gu | +0.025 |
comm | +0.024 |
aback | +0.024 |
written | +0.024 |
bisc | +0.023 |
Neg logit contributions | |
often | -0.020 |
igs | -0.019 |
ot | -0.019 |
lived | -0.017 |
solar | -0.017 |
Token | tiny |
Token ID | 7009 |
Feature activation | -4.81e-02 |
Pos logit contributions | |
written | +0.009 |
aback | +0.009 |
comm | +0.009 |
Gu | +0.009 |
hered | +0.008 |
Neg logit contributions | |
often | -0.007 |
igs | -0.007 |
ot | -0.006 |
solar | -0.006 |
lived | -0.006 |
Token | voice |
Token ID | 3809 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
igs | +0.002 |
often | +0.002 |
ot | +0.002 |
solar | +0.002 |
lived | +0.001 |
Neg logit contributions | |
aback | -0.002 |
written | -0.002 |
comm | -0.002 |
Gu | -0.002 |
hered | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
Gu | +0.072 |
comm | +0.070 |
aback | +0.070 |
source | +0.067 |
written | +0.067 |
Neg logit contributions | |
often | -0.029 |
ot | -0.024 |
igs | -0.021 |
lived | -0.019 |
ug | -0.018 |
Token | Tim |
Token ID | 5045 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
igs | +0.008 |
often | +0.007 |
ot | +0.007 |
solar | +0.006 |
gut | +0.006 |
Neg logit contributions | |
aback | -0.010 |
written | -0.010 |
Gu | -0.010 |
comm | -0.009 |
bisc | -0.009 |
Token | enjoyed |
Token ID | 8359 |
Feature activation | -3.94e-01 |
Pos logit contributions | |
igs | +0.048 |
gut | +0.043 |
apy | +0.042 |
solar | +0.042 |
often | +0.041 |
Neg logit contributions | |
written | -0.034 |
Gu | -0.031 |
comm | -0.031 |
aback | -0.031 |
hered | -0.030 |
Token | hitting |
Token ID | 9008 |
Feature activation | -2.04e-01 |
Pos logit contributions | |
often | +0.015 |
igs | +0.015 |
ot | +0.014 |
solar | +0.014 |
lived | +0.013 |
Neg logit contributions | |
written | -0.013 |
Gu | -0.012 |
comm | -0.012 |
aback | -0.012 |
hered | -0.012 |
Token | the |
Token ID | 262 |
Feature activation | +8.28e-01 |
Pos logit contributions | |
often | +0.006 |
igs | +0.006 |
ot | +0.005 |
solar | +0.005 |
lived | +0.005 |
Neg logit contributions | |
written | -0.009 |
aback | -0.009 |
comm | -0.009 |
Gu | -0.008 |
source | -0.008 |
Token | ball |
Token ID | 2613 |
Feature activation | -2.02e+00 |
Pos logit contributions | |
aback | +0.035 |
written | +0.034 |
Gu | +0.034 |
comm | +0.033 |
hered | +0.031 |
Neg logit contributions | |
igs | -0.025 |
often | -0.024 |
ot | -0.021 |
goals | -0.021 |
solar | -0.021 |
Token | very |
Token ID | 845 |
Feature activation | -4.70e+00 |
Pos logit contributions | |
igs | +0.090 |
gut | +0.089 |
ind | +0.088 |
solar | +0.086 |
oppy | +0.081 |
Neg logit contributions | |
written | -0.050 |
aback | -0.048 |
right | -0.047 |
source | -0.047 |
come | -0.045 |
Token | hard |
Token ID | 1327 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
solar | +0.206 |
ocol | +0.194 |
lived | +0.187 |
Acc | +0.185 |
childhood | +0.182 |
Neg logit contributions | |
sure | -0.088 |
right | -0.086 |
so | -0.084 |
too | -0.083 |
t | -0.081 |
Token | . |
Token ID | 13 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
igs | +0.060 |
gut | +0.057 |
solar | +0.056 |
ot | +0.055 |
apy | +0.055 |
Neg logit contributions | |
written | -0.049 |
aback | -0.043 |
comm | -0.042 |
source | -0.041 |
saying | -0.039 |
Token |
|
Token ID | 198 |
Feature activation | +6.68e-01 |
Pos logit contributions | |
written | +0.004 |
aback | +0.004 |
comm | +0.004 |
Gu | +0.004 |
source | +0.004 |
Neg logit contributions | |
often | -0.005 |
igs | -0.005 |
ot | -0.004 |
solar | -0.004 |
lived | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | -7.23e-01 |
Pos logit contributions | |
written | +0.022 |
aback | +0.022 |
comm | +0.022 |
Gu | +0.021 |
hered | +0.020 |
Neg logit contributions | |
often | -0.026 |
igs | -0.025 |
ot | -0.023 |
lived | -0.023 |
solar | -0.022 |
Token | One |
Token ID | 3198 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
igs | +0.025 |
gut | +0.023 |
solar | +0.022 |
often | +0.021 |
ot | +0.020 |
Neg logit contributions | |
Gu | -0.027 |
written | -0.026 |
bisc | -0.025 |
comm | -0.025 |
source | -0.025 |
Token | a |
Token ID | 257 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
aback | +0.052 |
comm | +0.050 |
written | +0.048 |
begs | +0.048 |
Gu | +0.047 |
Neg logit contributions | |
often | -0.046 |
igs | -0.042 |
lived | -0.041 |
ot | -0.040 |
solar | -0.038 |
Token | delicate |
Token ID | 19217 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
igs | +0.064 |
often | +0.059 |
ug | +0.055 |
goals | +0.054 |
belt | +0.053 |
Neg logit contributions | |
Gu | -0.041 |
comm | -0.041 |
bisc | -0.039 |
written | -0.038 |
source | -0.037 |
Token | bird |
Token ID | 6512 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
igs | +0.060 |
often | +0.057 |
apy | +0.052 |
solar | +0.052 |
goals | +0.051 |
Neg logit contributions | |
written | -0.038 |
comm | -0.038 |
source | -0.036 |
bisc | -0.036 |
Gu | -0.034 |
Token | named |
Token ID | 3706 |
Feature activation | +2.53e-01 |
Pos logit contributions | |
igs | +0.058 |
gut | +0.052 |
goals | +0.052 |
apy | +0.050 |
belt | +0.049 |
Neg logit contributions | |
written | -0.058 |
calling | -0.057 |
source | -0.057 |
appeared | -0.054 |
comm | -0.054 |
Token | Fl |
Token ID | 1610 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
written | +0.009 |
aback | +0.009 |
comm | +0.009 |
Gu | +0.009 |
hered | +0.009 |
Neg logit contributions | |
often | -0.009 |
igs | -0.008 |
ot | -0.008 |
solar | -0.007 |
lived | -0.007 |
Token | appy |
Token ID | 7774 |
Feature activation | -4.64e+00 |
Pos logit contributions | |
often | +0.036 |
igs | +0.035 |
solar | +0.031 |
nam | +0.031 |
ships | +0.030 |
Neg logit contributions | |
hered | -0.035 |
written | -0.033 |
bisc | -0.033 |
source | -0.032 |
Gu | -0.032 |
Token | . |
Token ID | 13 |
Feature activation | -2.17e+00 |
Pos logit contributions | |
igs | +0.274 |
belt | +0.260 |
apy | +0.259 |
gut | +0.253 |
nam | +0.243 |
Neg logit contributions | |
's | -0.050 |
appeared | -0.045 |
once | -0.043 |
m | -0.040 |
come | -0.033 |
Token | She |
Token ID | 1375 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
igs | +0.099 |
gut | +0.092 |
belt | +0.089 |
ot | +0.087 |
ind | +0.087 |
Neg logit contributions | |
How | -0.057 |
Gu | -0.056 |
aback | -0.053 |
bisc | -0.053 |
Would | -0.050 |
Token | liked |
Token ID | 8288 |
Feature activation | +5.07e-01 |
Pos logit contributions | |
igs | +0.051 |
gut | +0.047 |
goals | +0.044 |
belt | +0.043 |
toes | +0.042 |
Neg logit contributions | |
written | -0.072 |
happened | -0.069 |
appeared | -0.069 |
Gu | -0.065 |
baked | -0.065 |
Token | to |
Token ID | 284 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
aback | +0.015 |
written | +0.014 |
comm | +0.014 |
Gu | +0.014 |
hered | +0.013 |
Neg logit contributions | |
often | -0.022 |
igs | -0.021 |
ot | -0.019 |
solar | -0.019 |
lived | -0.019 |
Token | fly |
Token ID | 6129 |
Feature activation | -5.99e-01 |
Pos logit contributions | |
igs | +0.048 |
often | +0.047 |
belt | +0.046 |
bers | +0.045 |
goals | +0.044 |
Neg logit contributions | |
come | -0.027 |
written | -0.027 |
source | -0.026 |
comm | -0.026 |
Gu | -0.025 |
Token | had |
Token ID | 550 |
Feature activation | +8.24e-01 |
Pos logit contributions | |
igs | +0.060 |
gut | +0.052 |
apy | +0.050 |
aro | +0.050 |
ug | +0.049 |
Neg logit contributions | |
written | -0.048 |
happened | -0.043 |
Gu | -0.042 |
baked | -0.042 |
comm | -0.042 |
Token | a |
Token ID | 257 |
Feature activation | -8.27e-01 |
Pos logit contributions | |
aback | +0.031 |
comm | +0.028 |
written | +0.027 |
Gu | +0.027 |
hered | +0.027 |
Neg logit contributions | |
often | -0.031 |
igs | -0.028 |
lived | -0.027 |
ot | -0.027 |
solar | -0.026 |
Token | toy |
Token ID | 13373 |
Feature activation | -2.87e+00 |
Pos logit contributions | |
igs | +0.029 |
often | +0.027 |
ug | +0.026 |
ot | +0.024 |
aro | +0.024 |
Neg logit contributions | |
comm | -0.030 |
written | -0.030 |
bisc | -0.029 |
Gu | -0.029 |
source | -0.029 |
Token | he |
Token ID | 339 |
Feature activation | -1.82e+00 |
Pos logit contributions | |
igs | +0.129 |
often | +0.111 |
ts | +0.108 |
ot | +0.107 |
lo | +0.107 |
Neg logit contributions | |
written | -0.079 |
bisc | -0.073 |
source | -0.072 |
saying | -0.072 |
appeared | -0.069 |
Token | loved |
Token ID | 6151 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
igs | +0.065 |
lights | +0.055 |
apy | +0.055 |
gut | +0.053 |
aro | +0.053 |
Neg logit contributions | |
written | -0.077 |
Gu | -0.068 |
baked | -0.066 |
meant | -0.063 |
come | -0.063 |
Token | very |
Token ID | 845 |
Feature activation | -4.55e+00 |
Pos logit contributions | |
igs | +0.091 |
apy | +0.084 |
oppy | +0.083 |
ug | +0.082 |
ot | +0.082 |
Neg logit contributions | |
written | -0.025 |
saying | -0.019 |
coming | -0.018 |
calling | -0.018 |
comm | -0.017 |
Token | much |
Token ID | 881 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
stack | +0.230 |
prope | +0.223 |
solar | +0.219 |
mast | +0.215 |
gut | +0.210 |
Neg logit contributions | |
news | -0.065 |
t | -0.049 |
written | -0.045 |
cake | -0.042 |
supposed | -0.042 |
Token | . |
Token ID | 13 |
Feature activation | -7.06e-01 |
Pos logit contributions | |
igs | +0.074 |
apy | +0.069 |
ot | +0.066 |
solar | +0.063 |
lived | +0.063 |
Neg logit contributions | |
written | -0.052 |
aback | -0.048 |
comm | -0.047 |
such | -0.045 |
saying | -0.044 |
Token | One |
Token ID | 1881 |
Feature activation | -7.33e-01 |
Pos logit contributions | |
igs | +0.024 |
often | +0.022 |
ind | +0.020 |
gut | +0.020 |
ot | +0.020 |
Neg logit contributions | |
aback | -0.027 |
Gu | -0.027 |
written | -0.027 |
bisc | -0.025 |
source | -0.025 |
Token | day |
Token ID | 1110 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
igs | +0.029 |
often | +0.026 |
solar | +0.024 |
gut | +0.023 |
goals | +0.023 |
Neg logit contributions | |
written | -0.025 |
Gu | -0.024 |
bisc | -0.024 |
source | -0.024 |
comm | -0.024 |
Token | , |
Token ID | 11 |
Feature activation | -7.18e-01 |
Pos logit contributions | |
igs | +0.044 |
often | +0.044 |
solar | +0.043 |
ind | +0.041 |
gut | +0.040 |
Neg logit contributions | |
hered | -0.039 |
written | -0.038 |
happened | -0.038 |
aback | -0.037 |
appeared | -0.037 |
Token | pillar |
Token ID | 41643 |
Feature activation | -2.44e+00 |
Pos logit contributions | |
often | +0.024 |
igs | +0.024 |
ot | +0.023 |
solar | +0.022 |
gut | +0.022 |
Neg logit contributions | |
written | -0.009 |
aback | -0.009 |
comm | -0.009 |
Gu | -0.008 |
hered | -0.008 |
Token | loved |
Token ID | 6151 |
Feature activation | -7.14e-01 |
Pos logit contributions | |
igs | +0.121 |
ug | +0.113 |
belt | +0.113 |
nam | +0.112 |
apy | +0.111 |
Neg logit contributions | |
written | -0.054 |
happened | -0.048 |
appeared | -0.047 |
meant | -0.045 |
comm | -0.044 |
Token | to |
Token ID | 284 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
igs | +0.037 |
often | +0.035 |
belt | +0.035 |
ot | +0.035 |
ug | +0.035 |
Neg logit contributions | |
written | -0.013 |
comm | -0.012 |
Gu | -0.012 |
aback | -0.012 |
source | -0.011 |
Token | move |
Token ID | 1445 |
Feature activation | -1.95e+00 |
Pos logit contributions | |
igs | +0.076 |
ug | +0.074 |
belt | +0.074 |
bers | +0.074 |
ind | +0.073 |
Neg logit contributions | |
come | -0.049 |
bisc | -0.042 |
smell | -0.041 |
taste | -0.040 |
source | -0.039 |
Token | around |
Token ID | 1088 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
igs | +0.086 |
belt | +0.081 |
oppy | +0.078 |
gut | +0.077 |
apy | +0.077 |
Neg logit contributions | |
aback | -0.056 |
written | -0.051 |
such | -0.047 |
comm | -0.043 |
news | -0.042 |
Token | very |
Token ID | 845 |
Feature activation | -4.55e+00 |
Pos logit contributions | |
belt | +0.091 |
igs | +0.087 |
apy | +0.084 |
ot | +0.083 |
oppy | +0.079 |
Neg logit contributions | |
coming | -0.033 |
written | -0.033 |
such | -0.032 |
aback | -0.032 |
calling | -0.031 |
Token | quickly |
Token ID | 2952 |
Feature activation | -2.34e+00 |
Pos logit contributions | |
belt | +0.208 |
lived | +0.205 |
agons | +0.198 |
Acc | +0.196 |
isher | +0.193 |
Neg logit contributions | |
out | -0.071 |
so | -0.066 |
sure | -0.064 |
right | -0.062 |
to | -0.059 |
Token | . |
Token ID | 13 |
Feature activation | -8.59e-01 |
Pos logit contributions | |
igs | +0.097 |
apy | +0.089 |
oppy | +0.088 |
ot | +0.087 |
ind | +0.086 |
Neg logit contributions | |
written | -0.069 |
calling | -0.063 |
saying | -0.062 |
comm | -0.061 |
aback | -0.061 |
Token | One |
Token ID | 1881 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
igs | +0.034 |
often | +0.030 |
ot | +0.029 |
gut | +0.029 |
ind | +0.029 |
Neg logit contributions | |
Gu | -0.029 |
aback | -0.028 |
written | -0.027 |
How | -0.026 |
source | -0.026 |
Token | day |
Token ID | 1110 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
igs | +0.044 |
often | +0.038 |
belt | +0.036 |
solar | +0.036 |
gut | +0.036 |
Neg logit contributions | |
written | -0.031 |
source | -0.030 |
Gu | -0.030 |
bisc | -0.030 |
comm | -0.030 |
Token | , |
Token ID | 11 |
Feature activation | -6.75e-01 |
Pos logit contributions | |
igs | +0.045 |
often | +0.043 |
ind | +0.042 |
solar | +0.041 |
belt | +0.041 |
Neg logit contributions | |
written | -0.035 |
happened | -0.034 |
hered | -0.034 |
aback | -0.033 |
appeared | -0.033 |
Token | and |
Token ID | 290 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
igs | +0.014 |
often | +0.013 |
ot | +0.012 |
solar | +0.012 |
apy | +0.011 |
Neg logit contributions | |
written | -0.016 |
aback | -0.016 |
comm | -0.015 |
hered | -0.015 |
Gu | -0.015 |
Token | could |
Token ID | 714 |
Feature activation | -4.75e-01 |
Pos logit contributions | |
igs | +0.064 |
ig | +0.053 |
ind | +0.052 |
solar | +0.051 |
gut | +0.051 |
Neg logit contributions | |
written | -0.069 |
Gu | -0.061 |
aback | -0.060 |
come | -0.059 |
funn | -0.057 |
Token | kick |
Token ID | 4829 |
Feature activation | -1.89e-01 |
Pos logit contributions | |
igs | +0.019 |
often | +0.017 |
solar | +0.017 |
ug | +0.016 |
ot | +0.016 |
Neg logit contributions | |
written | -0.015 |
comm | -0.015 |
aback | -0.014 |
Gu | -0.014 |
source | -0.014 |
Token | the |
Token ID | 262 |
Feature activation | +9.90e-02 |
Pos logit contributions | |
igs | +0.006 |
often | +0.006 |
ot | +0.006 |
solar | +0.005 |
lived | +0.005 |
Neg logit contributions | |
written | -0.007 |
aback | -0.007 |
comm | -0.007 |
Gu | -0.007 |
hered | -0.007 |
Token | ball |
Token ID | 2613 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
written | +0.004 |
aback | +0.004 |
comm | +0.004 |
Gu | +0.004 |
source | +0.004 |
Neg logit contributions | |
often | -0.003 |
igs | -0.003 |
ot | -0.003 |
solar | -0.003 |
lived | -0.003 |
Token | very |
Token ID | 845 |
Feature activation | -4.51e+00 |
Pos logit contributions | |
igs | +0.068 |
gut | +0.064 |
solar | +0.062 |
apy | +0.059 |
lived | +0.059 |
Neg logit contributions | |
written | -0.049 |
aback | -0.048 |
hered | -0.047 |
source | -0.045 |
come | -0.045 |
Token | far |
Token ID | 1290 |
Feature activation | -9.62e-01 |
Pos logit contributions | |
solar | +0.193 |
lived | +0.192 |
ig | +0.192 |
chim | +0.185 |
Acc | +0.180 |
Neg logit contributions | |
right | -0.101 |
so | -0.087 |
written | -0.086 |
sure | -0.085 |
too | -0.085 |
Token | . |
Token ID | 13 |
Feature activation | -6.42e-01 |
Pos logit contributions | |
igs | +0.040 |
apy | +0.036 |
often | +0.035 |
solar | +0.034 |
lived | +0.033 |
Neg logit contributions | |
aback | -0.032 |
written | -0.031 |
comm | -0.029 |
source | -0.029 |
hered | -0.028 |
Token | She |
Token ID | 1375 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
igs | +0.021 |
often | +0.018 |
gut | +0.017 |
ot | +0.017 |
ug | +0.017 |
Neg logit contributions | |
Gu | -0.026 |
written | -0.025 |
aback | -0.025 |
comm | -0.024 |
source | -0.024 |
Token | wanted |
Token ID | 2227 |
Feature activation | +6.08e-01 |
Pos logit contributions | |
igs | +0.057 |
gut | +0.050 |
ind | +0.048 |
apy | +0.048 |
solar | +0.048 |
Neg logit contributions | |
written | -0.042 |
comm | -0.037 |
Gu | -0.037 |
aback | -0.037 |
hered | -0.036 |
Token | to |
Token ID | 284 |
Feature activation | +3.20e-01 |
Pos logit contributions | |
aback | +0.018 |
comm | +0.018 |
written | +0.018 |
Gu | +0.018 |
bisc | +0.017 |
Neg logit contributions | |
often | -0.026 |
igs | -0.024 |
ot | -0.023 |
solar | -0.022 |
goals | -0.021 |
Token | to |
Token ID | 284 |
Feature activation | -2.58e+00 |
Pos logit contributions | |
igs | +0.049 |
gut | +0.045 |
oppy | +0.045 |
often | +0.045 |
apy | +0.044 |
Neg logit contributions | |
written | -0.015 |
Gu | -0.012 |
comm | -0.011 |
calling | -0.011 |
come | -0.011 |
Token | go |
Token ID | 467 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
igs | +0.122 |
bers | +0.120 |
goals | +0.120 |
gut | +0.120 |
oppy | +0.119 |
Neg logit contributions | |
come | -0.075 |
say | -0.054 |
smell | -0.051 |
surprise | -0.051 |
calling | -0.051 |
Token | around |
Token ID | 1088 |
Feature activation | -1.89e+00 |
Pos logit contributions | |
igs | +0.055 |
gut | +0.054 |
apy | +0.053 |
goals | +0.053 |
oppy | +0.052 |
Neg logit contributions | |
come | -0.025 |
calling | -0.025 |
source | -0.025 |
written | -0.024 |
aback | -0.022 |
Token | the |
Token ID | 262 |
Feature activation | -7.21e-01 |
Pos logit contributions | |
igs | +0.086 |
oppy | +0.084 |
apy | +0.084 |
ot | +0.084 |
belt | +0.082 |
Neg logit contributions | |
calling | -0.046 |
coming | -0.045 |
source | -0.045 |
written | -0.044 |
saying | -0.042 |
Token | track |
Token ID | 2610 |
Feature activation | -1.86e+00 |
Pos logit contributions | |
igs | +0.028 |
often | +0.026 |
apy | +0.025 |
gut | +0.023 |
ot | +0.023 |
Neg logit contributions | |
Gu | -0.024 |
source | -0.023 |
written | -0.023 |
comm | -0.023 |
aback | -0.022 |
Token | very |
Token ID | 845 |
Feature activation | -4.51e+00 |
Pos logit contributions | |
igs | +0.079 |
gut | +0.069 |
apy | +0.067 |
oppy | +0.066 |
ind | +0.065 |
Neg logit contributions | |
written | -0.062 |
source | -0.055 |
come | -0.053 |
calling | -0.052 |
aback | -0.050 |
Token | fast |
Token ID | 3049 |
Feature activation | -2.16e+00 |
Pos logit contributions | |
ocol | +0.235 |
microsc | +0.195 |
solar | +0.194 |
Acc | +0.192 |
charged | +0.188 |
Neg logit contributions | |
so | -0.076 |
sure | -0.064 |
out | -0.060 |
once | -0.059 |
t | -0.059 |
Token | . |
Token ID | 13 |
Feature activation | -5.09e-01 |
Pos logit contributions | |
igs | +0.102 |
apy | +0.094 |
oppy | +0.089 |
gut | +0.086 |
aro | +0.086 |
Neg logit contributions | |
written | -0.060 |
aback | -0.054 |
comm | -0.052 |
source | -0.050 |
such | -0.050 |
Token | One |
Token ID | 1881 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
igs | +0.018 |
often | +0.017 |
ot | +0.015 |
gut | +0.015 |
ind | +0.015 |
Neg logit contributions | |
Gu | -0.019 |
written | -0.019 |
aback | -0.019 |
source | -0.018 |
comm | -0.018 |
Token | day |
Token ID | 1110 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
igs | +0.067 |
often | +0.054 |
nam | +0.053 |
gut | +0.053 |
aro | +0.053 |
Neg logit contributions | |
written | -0.038 |
source | -0.038 |
come | -0.037 |
bisc | -0.036 |
Gu | -0.036 |
Token | , |
Token ID | 11 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
igs | +0.064 |
often | +0.063 |
ind | +0.062 |
solar | +0.059 |
gut | +0.058 |
Neg logit contributions | |
happened | -0.044 |
written | -0.042 |
hered | -0.042 |
appeared | -0.042 |
come | -0.039 |
Token | liked |
Token ID | 8288 |
Feature activation | +4.24e-01 |
Pos logit contributions | |
igs | +0.049 |
gut | +0.041 |
goals | +0.041 |
ug | +0.041 |
aro | +0.038 |
Neg logit contributions | |
written | -0.042 |
happened | -0.040 |
Gu | -0.039 |
comm | -0.038 |
appeared | -0.038 |
Token | playing |
Token ID | 2712 |
Feature activation | +4.80e-01 |
Pos logit contributions | |
aback | +0.012 |
written | +0.012 |
comm | +0.011 |
Gu | +0.011 |
hered | +0.011 |
Neg logit contributions | |
often | -0.019 |
igs | -0.018 |
ot | -0.017 |
solar | -0.016 |
lived | -0.016 |
Token | in |
Token ID | 287 |
Feature activation | -4.66e-01 |
Pos logit contributions | |
written | +0.016 |
aback | +0.016 |
comm | +0.016 |
Gu | +0.016 |
source | +0.015 |
Neg logit contributions | |
often | -0.018 |
igs | -0.018 |
ot | -0.016 |
lived | -0.016 |
solar | -0.016 |
Token | the |
Token ID | 262 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
igs | +0.016 |
often | +0.016 |
gut | +0.014 |
ot | +0.014 |
ug | +0.014 |
Neg logit contributions | |
Gu | -0.017 |
written | -0.017 |
comm | -0.016 |
aback | -0.016 |
source | -0.016 |
Token | sun |
Token ID | 4252 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
igs | +0.005 |
often | +0.005 |
ot | +0.005 |
solar | +0.004 |
lived | +0.004 |
Neg logit contributions | |
written | -0.004 |
comm | -0.004 |
Gu | -0.004 |
aback | -0.004 |
source | -0.004 |
Token | very |
Token ID | 845 |
Feature activation | -4.49e+00 |
Pos logit contributions | |
aback | +0.051 |
Gu | +0.050 |
comm | +0.050 |
written | +0.047 |
Sur | +0.045 |
Neg logit contributions | |
often | -0.028 |
igs | -0.024 |
ot | -0.021 |
lived | -0.020 |
solar | -0.019 |
Token | much |
Token ID | 881 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
charged | +0.187 |
rum | +0.182 |
hetic | +0.180 |
solar | +0.177 |
vered | +0.175 |
Neg logit contributions | |
out | -0.095 |
cake | -0.095 |
so | -0.093 |
up | -0.085 |
right | -0.083 |
Token | . |
Token ID | 13 |
Feature activation | -8.81e-01 |
Pos logit contributions | |
igs | +0.088 |
apy | +0.081 |
aro | +0.075 |
ot | +0.075 |
ug | +0.073 |
Neg logit contributions | |
written | -0.056 |
aback | -0.050 |
source | -0.046 |
such | -0.045 |
calling | -0.045 |
Token | One |
Token ID | 1881 |
Feature activation | -6.90e-01 |
Pos logit contributions | |
igs | +0.033 |
often | +0.030 |
ot | +0.029 |
ts | +0.028 |
ug | +0.027 |
Neg logit contributions | |
written | -0.030 |
aback | -0.030 |
Gu | -0.029 |
source | -0.028 |
comm | -0.027 |
Token | day |
Token ID | 1110 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
igs | +0.027 |
often | +0.023 |
solar | +0.022 |
gut | +0.021 |
goals | +0.021 |
Neg logit contributions | |
written | -0.024 |
Gu | -0.023 |
source | -0.023 |
bisc | -0.023 |
comm | -0.023 |
Token | , |
Token ID | 11 |
Feature activation | -7.60e-01 |
Pos logit contributions | |
igs | +0.035 |
often | +0.035 |
solar | +0.032 |
goals | +0.031 |
ot | +0.031 |
Neg logit contributions | |
aback | -0.037 |
written | -0.037 |
hered | -0.036 |
appeared | -0.034 |
comm | -0.034 |
Token | shiny |
Token ID | 22441 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
igs | +0.020 |
often | +0.019 |
ot | +0.018 |
ug | +0.017 |
apy | +0.016 |
Neg logit contributions | |
written | -0.025 |
comm | -0.025 |
Gu | -0.024 |
source | -0.024 |
bisc | -0.024 |
Token | shield |
Token ID | 7614 |
Feature activation | -5.23e-01 |
Pos logit contributions | |
often | +0.039 |
igs | +0.038 |
apy | +0.037 |
ot | +0.036 |
aro | +0.036 |
Neg logit contributions | |
written | -0.062 |
source | -0.059 |
bisc | -0.058 |
comm | -0.056 |
aback | -0.056 |
Token | that |
Token ID | 326 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
igs | +0.020 |
often | +0.018 |
ot | +0.017 |
solar | +0.017 |
apy | +0.016 |
Neg logit contributions | |
written | -0.019 |
aback | -0.017 |
comm | -0.017 |
source | -0.017 |
hered | -0.016 |
Token | he |
Token ID | 339 |
Feature activation | -1.97e+00 |
Pos logit contributions | |
igs | +0.057 |
ind | +0.051 |
ug | +0.049 |
goals | +0.048 |
gut | +0.047 |
Neg logit contributions | |
written | -0.058 |
happened | -0.051 |
come | -0.051 |
Gu | -0.051 |
appeared | -0.051 |
Token | loved |
Token ID | 6151 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
igs | +0.070 |
apy | +0.066 |
gut | +0.065 |
goals | +0.065 |
lights | +0.064 |
Neg logit contributions | |
written | -0.069 |
baked | -0.063 |
prevented | -0.061 |
Gu | -0.060 |
appeared | -0.060 |
Token | very |
Token ID | 845 |
Feature activation | -4.48e+00 |
Pos logit contributions | |
igs | +0.079 |
apy | +0.075 |
ot | +0.073 |
oppy | +0.072 |
gut | +0.071 |
Neg logit contributions | |
written | -0.022 |
come | -0.015 |
coming | -0.015 |
saying | -0.015 |
comm | -0.014 |
Token | much |
Token ID | 881 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
stack | +0.204 |
belt | +0.203 |
solar | +0.202 |
mast | +0.201 |
gut | +0.199 |
Neg logit contributions | |
sure | -0.058 |
news | -0.053 |
written | -0.049 |
umbs | -0.046 |
ata | -0.045 |
Token | . |
Token ID | 13 |
Feature activation | -8.71e-01 |
Pos logit contributions | |
igs | +0.072 |
apy | +0.067 |
ot | +0.066 |
solar | +0.061 |
lived | +0.060 |
Neg logit contributions | |
written | -0.053 |
aback | -0.047 |
comm | -0.046 |
such | -0.045 |
saying | -0.043 |
Token | He |
Token ID | 679 |
Feature activation | -2.34e+00 |
Pos logit contributions | |
igs | +0.029 |
often | +0.026 |
ot | +0.025 |
ind | +0.025 |
apy | +0.025 |
Neg logit contributions | |
Gu | -0.034 |
aback | -0.033 |
written | -0.033 |
source | -0.032 |
How | -0.031 |
Token | would |
Token ID | 561 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
igs | +0.101 |
apy | +0.098 |
gut | +0.097 |
lights | +0.093 |
lo | +0.093 |
Neg logit contributions | |
written | -0.068 |
baked | -0.062 |
appeared | -0.060 |
come | -0.056 |
revealed | -0.056 |
Token | always |
Token ID | 1464 |
Feature activation | -2.17e-01 |
Pos logit contributions | |
igs | +0.065 |
apy | +0.061 |
lo | +0.060 |
ug | +0.060 |
bers | +0.058 |
Neg logit contributions | |
come | -0.046 |
written | -0.045 |
source | -0.039 |
calling | -0.039 |
comm | -0.038 |
Token | had |
Token ID | 550 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
igs | +0.049 |
gut | +0.041 |
apy | +0.041 |
aro | +0.040 |
ug | +0.040 |
Neg logit contributions | |
written | -0.045 |
Gu | -0.041 |
comm | -0.041 |
aback | -0.040 |
happened | -0.040 |
Token | a |
Token ID | 257 |
Feature activation | -7.14e-01 |
Pos logit contributions | |
aback | +0.043 |
comm | +0.039 |
oph | +0.038 |
Gu | +0.038 |
hered | +0.038 |
Neg logit contributions | |
often | -0.038 |
igs | -0.033 |
lived | -0.033 |
ot | -0.032 |
solar | -0.031 |
Token | toy |
Token ID | 13373 |
Feature activation | -2.91e+00 |
Pos logit contributions | |
igs | +0.025 |
often | +0.023 |
ug | +0.021 |
ot | +0.021 |
aro | +0.020 |
Neg logit contributions | |
comm | -0.026 |
written | -0.026 |
bisc | -0.026 |
Gu | -0.025 |
source | -0.025 |
Token | he |
Token ID | 339 |
Feature activation | -1.71e+00 |
Pos logit contributions | |
igs | +0.131 |
often | +0.112 |
ot | +0.111 |
ts | +0.111 |
lo | +0.109 |
Neg logit contributions | |
written | -0.078 |
source | -0.073 |
saying | -0.072 |
bisc | -0.072 |
appeared | -0.070 |
Token | loved |
Token ID | 6151 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
igs | +0.060 |
lights | +0.050 |
apy | +0.050 |
ug | +0.049 |
gut | +0.049 |
Neg logit contributions | |
written | -0.073 |
Gu | -0.065 |
baked | -0.062 |
aback | -0.060 |
bisc | -0.060 |
Token | very |
Token ID | 845 |
Feature activation | -4.46e+00 |
Pos logit contributions | |
igs | +0.088 |
apy | +0.081 |
oppy | +0.080 |
ot | +0.079 |
ug | +0.079 |
Neg logit contributions | |
written | -0.025 |
saying | -0.019 |
coming | -0.017 |
calling | -0.017 |
comm | -0.017 |
Token | much |
Token ID | 881 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
stack | +0.218 |
solar | +0.212 |
prope | +0.211 |
gut | +0.210 |
mast | +0.208 |
Neg logit contributions | |
news | -0.065 |
written | -0.053 |
cake | -0.051 |
supposed | -0.049 |
t | -0.048 |
Token | . |
Token ID | 13 |
Feature activation | -7.24e-01 |
Pos logit contributions | |
igs | +0.057 |
apy | +0.051 |
ot | +0.050 |
solar | +0.048 |
lived | +0.047 |
Neg logit contributions | |
written | -0.047 |
aback | -0.043 |
comm | -0.042 |
source | -0.040 |
saying | -0.039 |
Token | The |
Token ID | 383 |
Feature activation | -2.34e-01 |
Pos logit contributions | |
igs | +0.025 |
often | +0.023 |
ind | +0.021 |
ot | +0.021 |
gut | +0.021 |
Neg logit contributions | |
Gu | -0.028 |
aback | -0.028 |
written | -0.027 |
bisc | -0.026 |
source | -0.026 |
Token | toy |
Token ID | 13373 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
igs | +0.008 |
often | +0.008 |
ot | +0.007 |
ug | +0.007 |
solar | +0.006 |
Neg logit contributions | |
written | -0.009 |
Gu | -0.009 |
comm | -0.009 |
aback | -0.009 |
source | -0.008 |
Token | was |
Token ID | 373 |
Feature activation | -9.83e-01 |
Pos logit contributions | |
igs | +0.089 |
often | +0.077 |
ot | +0.077 |
gut | +0.076 |
ind | +0.073 |
Neg logit contributions | |
written | -0.041 |
appeared | -0.037 |
happened | -0.034 |
comm | -0.033 |
hered | -0.032 |
Token | loved |
Token ID | 6151 |
Feature activation | -3.86e-02 |
Pos logit contributions | |
igs | +0.052 |
gut | +0.043 |
goals | +0.043 |
aro | +0.043 |
ug | +0.043 |
Neg logit contributions | |
written | -0.047 |
Gu | -0.045 |
happened | -0.045 |
comm | -0.045 |
baked | -0.043 |
Token | to |
Token ID | 284 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
igs | +0.002 |
often | +0.002 |
ot | +0.002 |
solar | +0.002 |
lived | +0.002 |
Neg logit contributions | |
written | -0.001 |
comm | -0.001 |
aback | -0.001 |
Gu | -0.001 |
source | -0.001 |
Token | ride |
Token ID | 6594 |
Feature activation | -8.05e-01 |
Pos logit contributions | |
igs | +0.053 |
often | +0.051 |
ug | +0.050 |
ind | +0.050 |
gut | +0.049 |
Neg logit contributions | |
come | -0.037 |
bisc | -0.036 |
written | -0.033 |
Gu | -0.033 |
smell | -0.031 |
Token | his |
Token ID | 465 |
Feature activation | -5.97e-01 |
Pos logit contributions | |
igs | +0.023 |
often | +0.021 |
solar | +0.020 |
ot | +0.020 |
gut | +0.020 |
Neg logit contributions | |
written | -0.035 |
aback | -0.032 |
comm | -0.032 |
hered | -0.031 |
source | -0.031 |
Token | bike |
Token ID | 7161 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
often | +0.017 |
igs | +0.017 |
ot | +0.016 |
lived | +0.015 |
ug | +0.015 |
Neg logit contributions | |
comm | -0.024 |
written | -0.024 |
source | -0.023 |
bisc | -0.023 |
Gu | -0.023 |
Token | very |
Token ID | 845 |
Feature activation | -4.42e+00 |
Pos logit contributions | |
igs | +0.064 |
apy | +0.061 |
gut | +0.059 |
ot | +0.057 |
solar | +0.057 |
Neg logit contributions | |
written | -0.042 |
source | -0.038 |
aback | -0.036 |
come | -0.034 |
hered | -0.034 |
Token | fast |
Token ID | 3049 |
Feature activation | -1.90e+00 |
Pos logit contributions | |
ocol | +0.212 |
lived | +0.197 |
downs | +0.194 |
solar | +0.193 |
Acc | +0.190 |
Neg logit contributions | |
so | -0.072 |
right | -0.070 |
t | -0.069 |
sure | -0.064 |
out | -0.063 |
Token | . |
Token ID | 13 |
Feature activation | -6.77e-01 |
Pos logit contributions | |
igs | +0.086 |
apy | +0.079 |
oppy | +0.074 |
ot | +0.073 |
aro | +0.072 |
Neg logit contributions | |
written | -0.058 |
aback | -0.054 |
hered | -0.049 |
comm | -0.049 |
source | -0.049 |
Token | One |
Token ID | 1881 |
Feature activation | -9.65e-01 |
Pos logit contributions | |
igs | +0.020 |
often | +0.017 |
ot | +0.016 |
gut | +0.016 |
solar | +0.016 |
Neg logit contributions | |
Gu | -0.029 |
aback | -0.028 |
written | -0.028 |
bisc | -0.027 |
source | -0.027 |
Token | day |
Token ID | 1110 |
Feature activation | -7.89e-01 |
Pos logit contributions | |
igs | +0.040 |
often | +0.035 |
solar | +0.033 |
gut | +0.032 |
goals | +0.032 |
Neg logit contributions | |
written | -0.031 |
Gu | -0.030 |
bisc | -0.029 |
source | -0.029 |
comm | -0.029 |
Token | , |
Token ID | 11 |
Feature activation | -4.42e-01 |
Pos logit contributions | |
igs | +0.027 |
often | +0.027 |
solar | +0.025 |
goals | +0.024 |
gut | +0.023 |
Neg logit contributions | |
written | -0.029 |
hered | -0.028 |
aback | -0.028 |
Gu | -0.027 |
bisc | -0.027 |
Token | !" |
Token ID | 2474 |
Feature activation | -2.10e-01 |
Pos logit contributions | |
aback | +0.029 |
Gu | +0.028 |
comm | +0.028 |
written | +0.028 |
source | +0.026 |
Neg logit contributions | |
often | -0.026 |
igs | -0.025 |
ot | -0.023 |
lived | -0.022 |
solar | -0.022 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
igs | +0.008 |
often | +0.008 |
solar | +0.007 |
ot | +0.007 |
gut | +0.007 |
Neg logit contributions | |
written | -0.007 |
aback | -0.007 |
comm | -0.006 |
Gu | -0.006 |
bisc | -0.006 |
Token | Sam |
Token ID | 16305 |
Feature activation | -7.76e-01 |
Pos logit contributions | |
comm | +0.054 |
written | +0.053 |
aback | +0.052 |
Birthday | +0.050 |
Gu | +0.050 |
Neg logit contributions | |
often | -0.046 |
lived | -0.045 |
igs | -0.044 |
ot | -0.040 |
solar | -0.040 |
Token | liked |
Token ID | 8288 |
Feature activation | -6.16e-01 |
Pos logit contributions | |
igs | +0.046 |
often | +0.043 |
apy | +0.041 |
solar | +0.041 |
gut | +0.040 |
Neg logit contributions | |
aback | -0.011 |
written | -0.011 |
comm | -0.010 |
Gu | -0.009 |
bisc | -0.008 |
Token | hockey |
Token ID | 12217 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
igs | +0.032 |
often | +0.030 |
lived | +0.028 |
ot | +0.028 |
solar | +0.028 |
Neg logit contributions | |
written | -0.012 |
comm | -0.012 |
Gu | -0.012 |
aback | -0.011 |
source | -0.011 |
Token | very |
Token ID | 845 |
Feature activation | -4.42e+00 |
Pos logit contributions | |
igs | +0.071 |
solar | +0.066 |
apy | +0.062 |
ind | +0.061 |
gut | +0.060 |
Neg logit contributions | |
written | -0.048 |
comm | -0.047 |
hered | -0.046 |
come | -0.045 |
aback | -0.045 |
Token | much |
Token ID | 881 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
gut | +0.251 |
solar | +0.212 |
igs | +0.212 |
instincts | +0.211 |
charged | +0.207 |
Neg logit contributions | |
m | -0.048 |
Happy | -0.047 |
time | -0.044 |
once | -0.044 |
come | -0.042 |
Token | . |
Token ID | 13 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
igs | +0.066 |
solar | +0.059 |
ot | +0.057 |
often | +0.057 |
gut | +0.057 |
Neg logit contributions | |
written | -0.047 |
comm | -0.044 |
saying | -0.044 |
calling | -0.042 |
news | -0.042 |
Token | He |
Token ID | 679 |
Feature activation | -2.37e+00 |
Pos logit contributions | |
igs | +0.052 |
gut | +0.043 |
often | +0.043 |
ind | +0.041 |
ts | +0.041 |
Neg logit contributions | |
Gu | -0.051 |
written | -0.049 |
aback | -0.047 |
How | -0.046 |
cake | -0.045 |
Token | had |
Token ID | 550 |
Feature activation | +3.42e-02 |
Pos logit contributions | |
igs | +0.113 |
gut | +0.108 |
icker | +0.101 |
apy | +0.100 |
lights | +0.098 |
Neg logit contributions | |
written | -0.059 |
come | -0.053 |
been | -0.050 |
baked | -0.050 |
happened | -0.050 |
Token | a |
Token ID | 257 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
written | +0.001 |
aback | +0.001 |
comm | +0.001 |
Gu | +0.001 |
source | +0.001 |
Neg logit contributions | |
igs | -0.001 |
often | -0.001 |
ot | -0.001 |
solar | -0.001 |
lived | -0.001 |
Token | toy |
Token ID | 13373 |
Feature activation | -2.95e+00 |
Pos logit contributions | |
igs | +0.036 |
often | +0.033 |
ug | +0.032 |
aro | +0.030 |
lo | +0.030 |
Neg logit contributions | |
comm | -0.035 |
bisc | -0.034 |
written | -0.034 |
source | -0.033 |
Gu | -0.033 |
Token | fork |
Token ID | 15563 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
igs | +0.131 |
often | +0.113 |
ot | +0.111 |
ts | +0.110 |
lo | +0.109 |
Neg logit contributions | |
written | -0.079 |
source | -0.074 |
bisc | -0.073 |
saying | -0.073 |
appeared | -0.071 |
Token | that |
Token ID | 326 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
igs | +0.073 |
gut | +0.062 |
often | +0.061 |
ot | +0.061 |
solar | +0.061 |
Neg logit contributions | |
written | -0.051 |
appeared | -0.041 |
source | -0.041 |
cake | -0.039 |
come | -0.039 |
Token | he |
Token ID | 339 |
Feature activation | -2.21e+00 |
Pos logit contributions | |
igs | +0.065 |
ug | +0.058 |
ind | +0.057 |
goals | +0.054 |
gut | +0.053 |
Neg logit contributions | |
written | -0.060 |
happened | -0.055 |
come | -0.053 |
Gu | -0.052 |
baked | -0.052 |
Token | loved |
Token ID | 6151 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
igs | +0.080 |
lights | +0.073 |
ug | +0.071 |
gut | +0.070 |
aro | +0.069 |
Neg logit contributions | |
written | -0.084 |
baked | -0.078 |
Gu | -0.073 |
happened | -0.072 |
prevented | -0.071 |
Token | very |
Token ID | 845 |
Feature activation | -4.42e+00 |
Pos logit contributions | |
igs | +0.086 |
apy | +0.080 |
ug | +0.079 |
ot | +0.078 |
gut | +0.078 |
Neg logit contributions | |
written | -0.028 |
saying | -0.021 |
coming | -0.020 |
such | -0.020 |
come | -0.019 |
Token | much |
Token ID | 881 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
stack | +0.233 |
prope | +0.215 |
mast | +0.211 |
belt | +0.209 |
gut | +0.208 |
Neg logit contributions | |
news | -0.050 |
sure | -0.044 |
written | -0.040 |
t | -0.033 |
supposed | -0.033 |
Token | . |
Token ID | 13 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
igs | +0.051 |
apy | +0.045 |
ot | +0.045 |
often | +0.042 |
solar | +0.042 |
Neg logit contributions | |
written | -0.044 |
aback | -0.041 |
comm | -0.040 |
source | -0.037 |
such | -0.037 |
Token | Tim |
Token ID | 5045 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
igs | +0.037 |
often | +0.033 |
ind | +0.032 |
ot | +0.032 |
gut | +0.032 |
Neg logit contributions | |
Gu | -0.037 |
aback | -0.036 |
written | -0.035 |
How | -0.034 |
bisc | -0.034 |
Token | 's |
Token ID | 338 |
Feature activation | -4.76e-01 |
Pos logit contributions | |
igs | +0.065 |
apy | +0.061 |
aro | +0.060 |
gut | +0.058 |
ug | +0.055 |
Neg logit contributions | |
written | -0.046 |
baked | -0.042 |
Gu | -0.041 |
my | -0.041 |
meant | -0.041 |
Token | fork |
Token ID | 15563 |
Feature activation | -1.89e+00 |
Pos logit contributions | |
igs | +0.015 |
often | +0.014 |
ug | +0.013 |
ot | +0.013 |
solar | +0.012 |
Neg logit contributions | |
written | -0.019 |
comm | -0.019 |
aback | -0.019 |
source | -0.019 |
Gu | -0.018 |
Token | toy |
Token ID | 13373 |
Feature activation | -2.96e+00 |
Pos logit contributions | |
igs | +0.032 |
often | +0.030 |
ug | +0.028 |
ot | +0.027 |
aro | +0.027 |
Neg logit contributions | |
comm | -0.032 |
written | -0.032 |
bisc | -0.032 |
Gu | -0.031 |
source | -0.031 |
Token | car |
Token ID | 1097 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
igs | +0.132 |
often | +0.115 |
ot | +0.112 |
lo | +0.111 |
ts | +0.111 |
Neg logit contributions | |
written | -0.079 |
source | -0.074 |
bisc | -0.074 |
saying | -0.074 |
appeared | -0.073 |
Token | that |
Token ID | 326 |
Feature activation | -2.04e+00 |
Pos logit contributions | |
igs | +0.081 |
gut | +0.071 |
apy | +0.069 |
goals | +0.067 |
solar | +0.066 |
Neg logit contributions | |
written | -0.049 |
come | -0.039 |
source | -0.038 |
calling | -0.038 |
hered | -0.037 |
Token | he |
Token ID | 339 |
Feature activation | -2.24e+00 |
Pos logit contributions | |
igs | +0.088 |
ind | +0.077 |
goals | +0.075 |
ug | +0.074 |
gut | +0.072 |
Neg logit contributions | |
written | -0.066 |
happened | -0.063 |
come | -0.061 |
Gu | -0.059 |
meant | -0.058 |
Token | loved |
Token ID | 6151 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
igs | +0.084 |
gut | +0.072 |
rocky | +0.070 |
lights | +0.070 |
apy | +0.069 |
Neg logit contributions | |
written | -0.082 |
baked | -0.075 |
Gu | -0.075 |
prevented | -0.072 |
happened | -0.070 |
Token | very |
Token ID | 845 |
Feature activation | -4.41e+00 |
Pos logit contributions | |
igs | +0.090 |
oppy | +0.086 |
apy | +0.083 |
ot | +0.082 |
gut | +0.081 |
Neg logit contributions | |
written | -0.024 |
saying | -0.018 |
coming | -0.017 |
calling | -0.016 |
come | -0.016 |
Token | much |
Token ID | 881 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
stack | +0.218 |
gut | +0.213 |
mast | +0.206 |
solar | +0.203 |
prope | +0.199 |
Neg logit contributions | |
news | -0.053 |
written | -0.050 |
sure | -0.045 |
supposed | -0.045 |
umbs | -0.042 |
Token | . |
Token ID | 13 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
igs | +0.065 |
apy | +0.059 |
ot | +0.058 |
solar | +0.054 |
lived | +0.053 |
Neg logit contributions | |
written | -0.049 |
aback | -0.043 |
comm | -0.043 |
such | -0.040 |
calling | -0.040 |
Token | It |
Token ID | 632 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
igs | +0.044 |
often | +0.040 |
ind | +0.039 |
ot | +0.037 |
gut | +0.037 |
Neg logit contributions | |
Gu | -0.040 |
aback | -0.038 |
How | -0.037 |
written | -0.037 |
bisc | -0.036 |
Token | was |
Token ID | 373 |
Feature activation | -6.22e-01 |
Pos logit contributions | |
igs | +0.071 |
gut | +0.062 |
goals | +0.061 |
ug | +0.060 |
toes | +0.058 |
Neg logit contributions | |
Gu | -0.024 |
written | -0.023 |
come | -0.021 |
meant | -0.021 |
appeared | -0.020 |
Token | his |
Token ID | 465 |
Feature activation | -8.70e-01 |
Pos logit contributions | |
igs | +0.025 |
often | +0.023 |
ot | +0.022 |
gut | +0.022 |
solar | +0.022 |
Neg logit contributions | |
written | -0.021 |
source | -0.019 |
Gu | -0.018 |
aback | -0.018 |
comm | -0.018 |
Token | toy |
Token ID | 13373 |
Feature activation | -2.26e+00 |
Pos logit contributions | |
igs | +0.004 |
often | +0.004 |
ot | +0.003 |
solar | +0.003 |
ug | +0.003 |
Neg logit contributions | |
written | -0.005 |
comm | -0.005 |
aback | -0.005 |
Gu | -0.005 |
source | -0.004 |
Token | bunny |
Token ID | 44915 |
Feature activation | -1.93e+00 |
Pos logit contributions | |
igs | +0.097 |
often | +0.087 |
goals | +0.082 |
ot | +0.081 |
ts | +0.081 |
Neg logit contributions | |
written | -0.064 |
bisc | -0.061 |
appeared | -0.059 |
saying | -0.059 |
source | -0.058 |
Token | that |
Token ID | 326 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
igs | +0.073 |
lo | +0.069 |
goals | +0.066 |
gut | +0.065 |
lights | +0.064 |
Neg logit contributions | |
written | -0.063 |
bisc | -0.060 |
appeared | -0.058 |
hered | -0.056 |
calling | -0.055 |
Token | she |
Token ID | 673 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
igs | +0.081 |
ug | +0.076 |
goals | +0.073 |
ind | +0.071 |
gut | +0.069 |
Neg logit contributions | |
Gu | -0.045 |
written | -0.044 |
appeared | -0.043 |
happened | -0.042 |
aback | -0.042 |
Token | loved |
Token ID | 6151 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
igs | +0.063 |
lights | +0.056 |
ug | +0.054 |
gut | +0.053 |
goals | +0.053 |
Neg logit contributions | |
written | -0.068 |
Gu | -0.066 |
baked | -0.064 |
comm | -0.063 |
appeared | -0.062 |
Token | very |
Token ID | 845 |
Feature activation | -4.40e+00 |
Pos logit contributions | |
igs | +0.074 |
ug | +0.068 |
apy | +0.068 |
belt | +0.067 |
ot | +0.067 |
Neg logit contributions | |
written | -0.021 |
comm | -0.016 |
saying | -0.016 |
calling | -0.015 |
such | -0.015 |
Token | much |
Token ID | 881 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
mast | +0.223 |
gut | +0.219 |
belt | +0.219 |
prope | +0.213 |
stack | +0.212 |
Neg logit contributions | |
umbs | -0.060 |
news | -0.047 |
cake | -0.046 |
ata | -0.043 |
sure | -0.043 |
Token | . |
Token ID | 13 |
Feature activation | -8.34e-01 |
Pos logit contributions | |
igs | +0.054 |
apy | +0.048 |
ot | +0.048 |
ug | +0.045 |
belt | +0.045 |
Neg logit contributions | |
written | -0.044 |
aback | -0.041 |
comm | -0.040 |
calling | -0.037 |
saying | -0.037 |
Token | The |
Token ID | 383 |
Feature activation | -7.61e-02 |
Pos logit contributions | |
igs | +0.030 |
ug | +0.026 |
often | +0.025 |
gut | +0.024 |
ot | +0.024 |
Neg logit contributions | |
Gu | -0.032 |
aback | -0.030 |
written | -0.030 |
How | -0.029 |
bisc | -0.029 |
Token | bunny |
Token ID | 44915 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
igs | +0.003 |
often | +0.003 |
ot | +0.002 |
solar | +0.002 |
ug | +0.002 |
Neg logit contributions | |
written | -0.003 |
aback | -0.003 |
comm | -0.003 |
Gu | -0.003 |
source | -0.003 |
Token | belonged |
Token ID | 19611 |
Feature activation | -3.41e-01 |
Pos logit contributions | |
igs | +0.086 |
ug | +0.079 |
gut | +0.078 |
lo | +0.078 |
goals | +0.075 |
Neg logit contributions | |
appeared | -0.037 |
written | -0.036 |
revealed | -0.032 |
comm | -0.032 |
bisc | -0.031 |
Token | a |
Token ID | 257 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
aback | +0.051 |
comm | +0.049 |
written | +0.047 |
Gu | +0.047 |
begs | +0.047 |
Neg logit contributions | |
often | -0.045 |
igs | -0.041 |
lived | -0.040 |
ot | -0.039 |
solar | -0.037 |
Token | small |
Token ID | 1402 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
igs | +0.074 |
often | +0.067 |
ug | +0.063 |
belt | +0.063 |
goals | +0.062 |
Neg logit contributions | |
Gu | -0.045 |
comm | -0.045 |
bisc | -0.043 |
written | -0.042 |
source | -0.040 |
Token | bird |
Token ID | 6512 |
Feature activation | -1.78e+00 |
Pos logit contributions | |
igs | +0.072 |
often | +0.068 |
apy | +0.063 |
belt | +0.062 |
gut | +0.062 |
Neg logit contributions | |
comm | -0.031 |
written | -0.030 |
bisc | -0.029 |
source | -0.028 |
Gu | -0.028 |
Token | called |
Token ID | 1444 |
Feature activation | +1.75e-02 |
Pos logit contributions | |
igs | +0.062 |
gut | +0.056 |
goals | +0.056 |
belt | +0.054 |
apy | +0.052 |
Neg logit contributions | |
written | -0.062 |
calling | -0.061 |
source | -0.060 |
appeared | -0.059 |
comm | -0.058 |
Token | Fl |
Token ID | 1610 |
Feature activation | -9.85e-01 |
Pos logit contributions | |
written | +0.001 |
aback | +0.001 |
comm | +0.001 |
Gu | +0.001 |
hered | +0.001 |
Neg logit contributions | |
often | -0.001 |
igs | -0.001 |
ot | -0.001 |
solar | -0.001 |
lived | -0.001 |
Token | appy |
Token ID | 7774 |
Feature activation | -4.39e+00 |
Pos logit contributions | |
often | +0.035 |
igs | +0.033 |
solar | +0.030 |
nam | +0.029 |
goals | +0.029 |
Neg logit contributions | |
hered | -0.034 |
written | -0.032 |
source | -0.032 |
bisc | -0.032 |
Gu | -0.032 |
Token | . |
Token ID | 13 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
igs | +0.255 |
belt | +0.240 |
apy | +0.236 |
gut | +0.231 |
nam | +0.226 |
Neg logit contributions | |
appeared | -0.050 |
once | -0.049 |
's | -0.048 |
written | -0.041 |
coming | -0.040 |
Token | Fl |
Token ID | 1610 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
igs | +0.096 |
gut | +0.088 |
ot | +0.086 |
ind | +0.086 |
belt | +0.084 |
Neg logit contributions | |
How | -0.061 |
Gu | -0.061 |
aback | -0.057 |
bisc | -0.055 |
Would | -0.054 |
Token | appy |
Token ID | 7774 |
Feature activation | -3.27e+00 |
Pos logit contributions | |
often | +0.028 |
igs | +0.025 |
nam | +0.022 |
belt | +0.021 |
gut | +0.021 |
Neg logit contributions | |
hered | -0.044 |
aback | -0.043 |
written | -0.043 |
Gu | -0.042 |
comm | -0.041 |
Token | was |
Token ID | 373 |
Feature activation | +1.30e-02 |
Pos logit contributions | |
igs | +0.140 |
gut | +0.132 |
nam | +0.127 |
belt | +0.126 |
apy | +0.122 |
Neg logit contributions | |
written | -0.098 |
happened | -0.097 |
appeared | -0.095 |
's | -0.092 |
meant | -0.091 |
Token | always |
Token ID | 1464 |
Feature activation | +5.02e-01 |
Pos logit contributions | |
written | +0.001 |
aback | +0.001 |
comm | +0.001 |
Gu | +0.001 |
source | +0.000 |
Neg logit contributions | |
igs | -0.000 |
often | -0.000 |
ot | -0.000 |
solar | -0.000 |
lived | -0.000 |
Token | She |
Token ID | 1375 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
igs | +0.014 |
often | +0.012 |
ug | +0.011 |
solar | +0.011 |
ot | +0.011 |
Neg logit contributions | |
aback | -0.011 |
written | -0.011 |
Gu | -0.010 |
comm | -0.010 |
source | -0.010 |
Token | ran |
Token ID | 4966 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
igs | +0.067 |
gut | +0.063 |
apy | +0.061 |
solar | +0.060 |
goals | +0.060 |
Neg logit contributions | |
written | -0.035 |
Gu | -0.032 |
comm | -0.032 |
appeared | -0.030 |
come | -0.030 |
Token | up |
Token ID | 510 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
written | +0.004 |
aback | +0.004 |
comm | +0.004 |
Gu | +0.004 |
source | +0.004 |
Neg logit contributions | |
often | -0.006 |
igs | -0.006 |
ot | -0.005 |
solar | -0.005 |
lived | -0.005 |
Token | the |
Token ID | 262 |
Feature activation | -6.98e-01 |
Pos logit contributions | |
written | +0.005 |
aback | +0.005 |
comm | +0.005 |
Gu | +0.005 |
source | +0.005 |
Neg logit contributions | |
often | -0.007 |
igs | -0.007 |
ot | -0.006 |
solar | -0.006 |
lived | -0.006 |
Token | stairs |
Token ID | 16046 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
igs | +0.019 |
often | +0.018 |
ot | +0.017 |
lived | +0.016 |
apy | +0.016 |
Neg logit contributions | |
source | -0.031 |
comm | -0.030 |
written | -0.030 |
aback | -0.029 |
Gu | -0.028 |
Token | very |
Token ID | 845 |
Feature activation | -4.39e+00 |
Pos logit contributions | |
igs | +0.049 |
solar | +0.044 |
lived | +0.044 |
often | +0.044 |
ot | +0.043 |
Neg logit contributions | |
aback | -0.025 |
written | -0.024 |
source | -0.023 |
hered | -0.021 |
calling | -0.021 |
Token | quickly |
Token ID | 2952 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
ocol | +0.219 |
lived | +0.202 |
solar | +0.198 |
rum | +0.188 |
microsc | +0.187 |
Neg logit contributions | |
right | -0.082 |
up | -0.081 |
source | -0.080 |
late | -0.073 |
so | -0.071 |
Token | , |
Token ID | 11 |
Feature activation | +6.24e-01 |
Pos logit contributions | |
igs | +0.062 |
often | +0.057 |
apy | +0.056 |
ot | +0.056 |
solar | +0.055 |
Neg logit contributions | |
written | -0.036 |
aback | -0.033 |
source | -0.032 |
calling | -0.032 |
comm | -0.032 |
Token | but |
Token ID | 475 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
written | +0.017 |
aback | +0.017 |
Gu | +0.017 |
comm | +0.016 |
bisc | +0.016 |
Neg logit contributions | |
often | -0.028 |
igs | -0.027 |
ot | -0.024 |
solar | -0.024 |
lived | -0.024 |
Token | her |
Token ID | 607 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
igs | +0.049 |
solar | +0.045 |
ot | +0.042 |
often | +0.042 |
ug | +0.041 |
Neg logit contributions | |
written | -0.033 |
aback | -0.029 |
source | -0.028 |
calling | -0.028 |
comm | -0.027 |
Token | mom |
Token ID | 1995 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
igs | +0.039 |
often | +0.037 |
ot | +0.036 |
ug | +0.035 |
aro | +0.034 |
Neg logit contributions | |
comm | -0.043 |
source | -0.042 |
written | -0.040 |
surprise | -0.038 |
Birthday | -0.038 |
Token | blue |
Token ID | 4171 |
Feature activation | -8.31e-01 |
Pos logit contributions | |
igs | +0.030 |
often | +0.028 |
ug | +0.027 |
ot | +0.025 |
aro | +0.025 |
Neg logit contributions | |
comm | -0.031 |
written | -0.031 |
bisc | -0.030 |
source | -0.030 |
Gu | -0.029 |
Token | sweater |
Token ID | 35685 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
igs | +0.033 |
often | +0.032 |
ug | +0.028 |
ot | +0.028 |
solar | +0.028 |
Neg logit contributions | |
written | -0.026 |
bisc | -0.026 |
source | -0.025 |
comm | -0.025 |
hered | -0.024 |
Token | that |
Token ID | 326 |
Feature activation | -1.89e+00 |
Pos logit contributions | |
igs | +0.072 |
goals | +0.061 |
gut | +0.061 |
ot | +0.060 |
solar | +0.059 |
Neg logit contributions | |
written | -0.047 |
cake | -0.040 |
source | -0.040 |
bisc | -0.037 |
hered | -0.037 |
Token | he |
Token ID | 339 |
Feature activation | -2.37e+00 |
Pos logit contributions | |
igs | +0.074 |
goals | +0.064 |
ug | +0.064 |
ind | +0.063 |
gut | +0.062 |
Neg logit contributions | |
written | -0.067 |
come | -0.061 |
happened | -0.061 |
bisc | -0.060 |
Gu | -0.059 |
Token | loved |
Token ID | 6151 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
igs | +0.086 |
ug | +0.076 |
goals | +0.075 |
gut | +0.075 |
lights | +0.073 |
Neg logit contributions | |
written | -0.086 |
baked | -0.081 |
Gu | -0.079 |
come | -0.076 |
appeared | -0.075 |
Token | very |
Token ID | 845 |
Feature activation | -4.39e+00 |
Pos logit contributions | |
igs | +0.091 |
gut | +0.083 |
oppy | +0.083 |
apy | +0.082 |
ubby | +0.082 |
Neg logit contributions | |
written | -0.026 |
saying | -0.021 |
come | -0.020 |
coming | -0.020 |
such | -0.019 |
Token | much |
Token ID | 881 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
stack | +0.220 |
gut | +0.214 |
mast | +0.207 |
prope | +0.206 |
solar | +0.205 |
Neg logit contributions | |
news | -0.051 |
sure | -0.046 |
written | -0.043 |
supposed | -0.041 |
umbs | -0.040 |
Token | . |
Token ID | 13 |
Feature activation | -8.81e-01 |
Pos logit contributions | |
igs | +0.072 |
apy | +0.065 |
ot | +0.063 |
solar | +0.060 |
lived | +0.059 |
Neg logit contributions | |
written | -0.052 |
aback | -0.045 |
comm | -0.044 |
such | -0.043 |
saying | -0.042 |
Token | Tim |
Token ID | 5045 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
igs | +0.032 |
often | +0.030 |
ind | +0.028 |
gut | +0.028 |
ot | +0.028 |
Neg logit contributions | |
Gu | -0.032 |
aback | -0.031 |
written | -0.030 |
bisc | -0.029 |
How | -0.029 |
Token | wore |
Token ID | 12408 |
Feature activation | -5.97e-01 |
Pos logit contributions | |
igs | +0.057 |
apy | +0.053 |
gut | +0.052 |
aro | +0.051 |
solar | +0.049 |
Neg logit contributions | |
written | -0.046 |
Gu | -0.042 |
baked | -0.042 |
my | -0.041 |
meant | -0.041 |
Token | his |
Token ID | 465 |
Feature activation | -8.47e-01 |
Pos logit contributions | |
igs | +0.023 |
often | +0.023 |
ot | +0.021 |
solar | +0.021 |
ug | +0.021 |
Neg logit contributions | |
written | -0.020 |
aback | -0.018 |
Gu | -0.018 |
source | -0.017 |
comm | -0.017 |
Token | L |
Token ID | 43 |
Feature activation | -2.80e-02 |
Pos logit contributions | |
igs | +0.050 |
often | +0.045 |
solar | +0.044 |
gut | +0.042 |
toes | +0.042 |
Neg logit contributions | |
Gu | -0.040 |
Sur | -0.038 |
written | -0.037 |
comm | -0.036 |
aback | -0.035 |
Token | ily |
Token ID | 813 |
Feature activation | +3.97e-02 |
Pos logit contributions | |
often | +0.001 |
igs | +0.001 |
solar | +0.001 |
ot | +0.001 |
lived | +0.001 |
Neg logit contributions | |
written | -0.001 |
aback | -0.001 |
comm | -0.001 |
Gu | -0.001 |
hered | -0.001 |
Token | learned |
Token ID | 4499 |
Feature activation | -5.31e-01 |
Pos logit contributions | |
written | +0.001 |
aback | +0.001 |
comm | +0.001 |
Gu | +0.001 |
hered | +0.001 |
Neg logit contributions | |
igs | -0.002 |
often | -0.002 |
ot | -0.001 |
solar | -0.001 |
lived | -0.001 |
Token | to |
Token ID | 284 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
igs | +0.022 |
often | +0.021 |
solar | +0.020 |
ot | +0.019 |
ug | +0.019 |
Neg logit contributions | |
written | -0.017 |
comm | -0.016 |
aback | -0.016 |
source | -0.015 |
Gu | -0.015 |
Token | sail |
Token ID | 14936 |
Feature activation | -4.62e-01 |
Pos logit contributions | |
igs | +0.045 |
solar | +0.042 |
apy | +0.040 |
often | +0.040 |
ships | +0.039 |
Neg logit contributions | |
comm | -0.027 |
written | -0.027 |
aback | -0.027 |
come | -0.027 |
calling | -0.026 |
Token | very |
Token ID | 845 |
Feature activation | -4.37e+00 |
Pos logit contributions | |
igs | +0.018 |
often | +0.017 |
solar | +0.016 |
ot | +0.015 |
ug | +0.015 |
Neg logit contributions | |
aback | -0.015 |
written | -0.015 |
comm | -0.014 |
source | -0.014 |
Gu | -0.014 |
Token | well |
Token ID | 880 |
Feature activation | -2.04e+00 |
Pos logit contributions | |
ig | +0.176 |
chim | +0.167 |
solar | +0.164 |
throne | +0.162 |
ships | +0.155 |
Neg logit contributions | |
written | -0.106 |
right | -0.100 |
sure | -0.099 |
late | -0.098 |
aback | -0.097 |
Token | . |
Token ID | 13 |
Feature activation | -9.37e-01 |
Pos logit contributions | |
igs | +0.087 |
solar | +0.079 |
apy | +0.077 |
often | +0.075 |
ot | +0.074 |
Neg logit contributions | |
written | -0.060 |
aback | -0.057 |
comm | -0.051 |
hered | -0.051 |
source | -0.050 |
Token | The |
Token ID | 383 |
Feature activation | -9.70e-01 |
Pos logit contributions | |
igs | +0.042 |
often | +0.039 |
ts | +0.035 |
aro | +0.035 |
ind | +0.035 |
Neg logit contributions | |
aback | -0.027 |
written | -0.027 |
Gu | -0.026 |
comm | -0.024 |
How | -0.024 |
Token | boat |
Token ID | 8848 |
Feature activation | -2.95e-01 |
Pos logit contributions | |
igs | +0.035 |
often | +0.034 |
ot | +0.030 |
apy | +0.029 |
ug | +0.029 |
Neg logit contributions | |
written | -0.034 |
comm | -0.034 |
source | -0.034 |
bisc | -0.032 |
Gu | -0.032 |
Token | was |
Token ID | 373 |
Feature activation | -2.13e-01 |
Pos logit contributions | |
igs | +0.012 |
often | +0.011 |
ot | +0.011 |
solar | +0.010 |
apy | +0.010 |
Neg logit contributions | |
written | -0.009 |
aback | -0.009 |
comm | -0.009 |
Gu | -0.009 |
source | -0.008 |
Token | toy |
Token ID | 13373 |
Feature activation | -2.82e+00 |
Pos logit contributions | |
igs | +0.018 |
often | +0.018 |
ug | +0.016 |
ot | +0.015 |
lived | +0.015 |
Neg logit contributions | |
comm | -0.021 |
written | -0.021 |
Gu | -0.020 |
bisc | -0.020 |
source | -0.020 |
Token | car |
Token ID | 1097 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
igs | +0.124 |
often | +0.106 |
ts | +0.104 |
lo | +0.103 |
ot | +0.103 |
Neg logit contributions | |
written | -0.078 |
bisc | -0.073 |
source | -0.073 |
saying | -0.072 |
appeared | -0.070 |
Token | that |
Token ID | 326 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
igs | +0.074 |
gut | +0.065 |
apy | +0.061 |
goals | +0.061 |
solar | +0.061 |
Neg logit contributions | |
written | -0.049 |
source | -0.039 |
come | -0.038 |
calling | -0.038 |
saying | -0.038 |
Token | he |
Token ID | 339 |
Feature activation | -2.49e+00 |
Pos logit contributions | |
igs | +0.074 |
ind | +0.066 |
ug | +0.063 |
gut | +0.062 |
goals | +0.061 |
Neg logit contributions | |
written | -0.063 |
happened | -0.058 |
come | -0.056 |
meant | -0.056 |
Gu | -0.055 |
Token | loved |
Token ID | 6151 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
igs | +0.096 |
gut | +0.085 |
lights | +0.083 |
rocky | +0.082 |
apy | +0.081 |
Neg logit contributions | |
written | -0.087 |
baked | -0.082 |
prevented | -0.079 |
Gu | -0.077 |
happened | -0.076 |
Token | very |
Token ID | 845 |
Feature activation | -4.37e+00 |
Pos logit contributions | |
igs | +0.112 |
oppy | +0.105 |
apy | +0.102 |
ubby | +0.101 |
gut | +0.099 |
Neg logit contributions | |
written | -0.027 |
coming | -0.021 |
saying | -0.020 |
come | -0.019 |
telling | -0.018 |
Token | much |
Token ID | 881 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
stack | +0.217 |
gut | +0.207 |
solar | +0.205 |
mast | +0.201 |
prope | +0.199 |
Neg logit contributions | |
news | -0.062 |
written | -0.053 |
cake | -0.051 |
umbs | -0.049 |
sure | -0.049 |
Token | . |
Token ID | 13 |
Feature activation | -6.92e-01 |
Pos logit contributions | |
igs | +0.065 |
apy | +0.058 |
ot | +0.056 |
solar | +0.054 |
lived | +0.053 |
Neg logit contributions | |
written | -0.051 |
aback | -0.045 |
comm | -0.044 |
such | -0.043 |
cake | -0.042 |
Token | It |
Token ID | 632 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
igs | +0.023 |
often | +0.022 |
ot | +0.020 |
ind | +0.020 |
gut | +0.019 |
Neg logit contributions | |
Gu | -0.027 |
aback | -0.027 |
written | -0.026 |
bisc | -0.025 |
comm | -0.025 |
Token | was |
Token ID | 373 |
Feature activation | -6.05e-01 |
Pos logit contributions | |
igs | +0.085 |
gut | +0.077 |
goals | +0.073 |
ug | +0.071 |
ind | +0.071 |
Neg logit contributions | |
written | -0.025 |
Gu | -0.024 |
meant | -0.023 |
come | -0.023 |
appeared | -0.021 |
Token | red |
Token ID | 2266 |
Feature activation | -5.43e-01 |
Pos logit contributions | |
igs | +0.025 |
often | +0.023 |
gut | +0.022 |
solar | +0.022 |
ot | +0.022 |
Neg logit contributions | |
written | -0.019 |
source | -0.017 |
Gu | -0.017 |
aback | -0.017 |
comm | -0.017 |
Token | , |
Token ID | 11 |
Feature activation | +3.25e-01 |
Pos logit contributions | |
igs | +0.045 |
often | +0.043 |
nam | +0.041 |
solar | +0.041 |
goals | +0.040 |
Neg logit contributions | |
written | -0.033 |
aback | -0.033 |
hered | -0.032 |
comm | -0.032 |
appeared | -0.031 |
Token | how |
Token ID | 703 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
written | +0.011 |
aback | +0.011 |
comm | +0.011 |
Gu | +0.010 |
hered | +0.010 |
Neg logit contributions | |
often | -0.013 |
igs | -0.012 |
ot | -0.011 |
solar | -0.011 |
lived | -0.011 |
Token | do |
Token ID | 466 |
Feature activation | -8.92e-01 |
Pos logit contributions | |
igs | +0.070 |
often | +0.063 |
solar | +0.063 |
ind | +0.062 |
aro | +0.059 |
Neg logit contributions | |
come | -0.047 |
written | -0.047 |
happened | -0.043 |
news | -0.042 |
aback | -0.042 |
Token | you |
Token ID | 345 |
Feature activation | -5.05e-01 |
Pos logit contributions | |
often | +0.040 |
igs | +0.040 |
solar | +0.039 |
ot | +0.038 |
gut | +0.036 |
Neg logit contributions | |
Gu | -0.021 |
written | -0.020 |
comm | -0.020 |
come | -0.019 |
aback | -0.019 |
Token | zip |
Token ID | 19974 |
Feature activation | -1.78e+00 |
Pos logit contributions | |
igs | +0.021 |
often | +0.020 |
solar | +0.019 |
ot | +0.018 |
apy | +0.018 |
Neg logit contributions | |
aback | -0.015 |
written | -0.015 |
comm | -0.014 |
hered | -0.014 |
source | -0.014 |
Token | so |
Token ID | 523 |
Feature activation | -4.36e+00 |
Pos logit contributions | |
igs | +0.080 |
often | +0.080 |
solar | +0.074 |
ot | +0.073 |
apy | +0.073 |
Neg logit contributions | |
aback | -0.046 |
written | -0.041 |
source | -0.039 |
come | -0.037 |
such | -0.036 |
Token | fast |
Token ID | 3049 |
Feature activation | -6.19e-01 |
Pos logit contributions | |
ocol | +0.198 |
solar | +0.197 |
alk | +0.187 |
mo | +0.186 |
alks | +0.186 |
Neg logit contributions | |
come | -0.087 |
right | -0.086 |
It | -0.082 |
won | -0.077 |
sure | -0.076 |
Token | ?" |
Token ID | 1701 |
Feature activation | -7.50e-01 |
Pos logit contributions | |
igs | +0.024 |
often | +0.024 |
ot | +0.022 |
solar | +0.022 |
lived | +0.021 |
Neg logit contributions | |
written | -0.020 |
aback | -0.019 |
comm | -0.019 |
Gu | -0.018 |
hered | -0.018 |
Token |
|
Token ID | 198 |
Feature activation | -4.26e-01 |
Pos logit contributions | |
igs | +0.032 |
often | +0.030 |
solar | +0.029 |
ind | +0.028 |
goals | +0.028 |
Neg logit contributions | |
comm | -0.023 |
Gu | -0.022 |
aback | -0.022 |
written | -0.022 |
bisc | -0.020 |
Token |
|
Token ID | 198 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
igs | +0.020 |
often | +0.020 |
solar | +0.018 |
ot | +0.018 |
goals | +0.018 |
Neg logit contributions | |
aback | -0.010 |
Gu | -0.010 |
written | -0.010 |
comm | -0.009 |
source | -0.009 |
Token | B |
Token ID | 33 |
Feature activation | -9.04e-01 |
Pos logit contributions | |
igs | +0.085 |
goals | +0.080 |
solar | +0.079 |
ig | +0.078 |
ug | +0.077 |
Neg logit contributions | |
Gu | -0.047 |
Sur | -0.044 |
hered | -0.037 |
comm | -0.036 |
aback | -0.035 |
Token | laughed |
Token ID | 13818 |
Feature activation | +5.78e-01 |
Pos logit contributions | |
igs | +0.037 |
often | +0.034 |
gut | +0.033 |
belt | +0.031 |
solar | +0.031 |
Neg logit contributions | |
written | -0.022 |
comm | -0.020 |
aback | -0.019 |
announced | -0.018 |
hered | -0.017 |
Token | and |
Token ID | 290 |
Feature activation | +3.02e-01 |
Pos logit contributions | |
Gu | +0.019 |
aback | +0.019 |
comm | +0.019 |
written | +0.019 |
source | +0.018 |
Neg logit contributions | |
often | -0.022 |
igs | -0.021 |
ot | -0.019 |
lived | -0.019 |
solar | -0.019 |
Token | smiled |
Token ID | 13541 |
Feature activation | -2.58e-02 |
Pos logit contributions | |
aback | +0.009 |
written | +0.009 |
Gu | +0.008 |
comm | +0.008 |
source | +0.008 |
Neg logit contributions | |
often | -0.013 |
igs | -0.013 |
ot | -0.012 |
lived | -0.011 |
solar | -0.011 |
Token | at |
Token ID | 379 |
Feature activation | -3.68e-01 |
Pos logit contributions | |
igs | +0.001 |
often | +0.001 |
ot | +0.001 |
solar | +0.001 |
lived | +0.001 |
Neg logit contributions | |
written | -0.001 |
aback | -0.001 |
comm | -0.001 |
Gu | -0.001 |
source | -0.001 |
Token | the |
Token ID | 262 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
igs | +0.016 |
often | +0.015 |
solar | +0.015 |
ot | +0.014 |
ug | +0.014 |
Neg logit contributions | |
written | -0.010 |
aback | -0.010 |
comm | -0.010 |
Gu | -0.009 |
source | -0.009 |
Token | funny |
Token ID | 8258 |
Feature activation | +2.45e+00 |
Pos logit contributions | |
aback | +0.075 |
Gu | +0.069 |
oph | +0.066 |
hered | +0.064 |
andra | +0.064 |
Neg logit contributions | |
often | -0.062 |
solar | -0.057 |
tight | -0.055 |
ot | -0.055 |
dusty | -0.053 |
Token | dog |
Token ID | 3290 |
Feature activation | +3.02e-01 |
Pos logit contributions | |
aback | +0.096 |
Gu | +0.093 |
alright | +0.085 |
written | +0.084 |
Michelle | +0.082 |
Neg logit contributions | |
ot | -0.084 |
often | -0.079 |
lived | -0.075 |
ships | -0.071 |
solar | -0.071 |
Token | . |
Token ID | 13 |
Feature activation | +3.92e-01 |
Pos logit contributions | |
written | +0.014 |
aback | +0.014 |
comm | +0.014 |
Gu | +0.014 |
source | +0.013 |
Neg logit contributions | |
often | -0.008 |
igs | -0.008 |
ot | -0.006 |
solar | -0.006 |
lived | -0.006 |
Token | After |
Token ID | 2293 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
aback | +0.013 |
written | +0.013 |
comm | +0.013 |
Gu | +0.013 |
hered | +0.012 |
Neg logit contributions | |
often | -0.015 |
igs | -0.014 |
ot | -0.013 |
solar | -0.013 |
lived | -0.013 |
Token | the |
Token ID | 262 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
igs | +0.004 |
often | +0.004 |
ot | +0.003 |
solar | +0.003 |
lived | +0.003 |
Neg logit contributions | |
written | -0.003 |
comm | -0.003 |
aback | -0.003 |
Gu | -0.003 |
hered | -0.003 |
Token | video |
Token ID | 2008 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
aback | +0.076 |
Gu | +0.069 |
oph | +0.068 |
andra | +0.066 |
written | +0.066 |
Neg logit contributions | |
often | -0.062 |
ot | -0.058 |
solar | -0.057 |
tight | -0.056 |
rainy | -0.056 |
Token | tomorrow |
Token ID | 9439 |
Feature activation | +2.03e+00 |
Pos logit contributions | |
aback | +0.017 |
written | +0.017 |
comm | +0.017 |
Gu | +0.016 |
hered | +0.016 |
Neg logit contributions | |
often | -0.013 |
igs | -0.013 |
ot | -0.012 |
solar | -0.011 |
lived | -0.011 |
Token | ?" |
Token ID | 1701 |
Feature activation | +4.22e-01 |
Pos logit contributions | |
aback | +0.108 |
comm | +0.106 |
Gu | +0.101 |
written | +0.100 |
hered | +0.097 |
Neg logit contributions | |
often | -0.049 |
ot | -0.036 |
igs | -0.036 |
lived | -0.034 |
solar | -0.029 |
Token |
|
Token ID | 198 |
Feature activation | -6.67e-01 |
Pos logit contributions | |
written | +0.014 |
aback | +0.014 |
comm | +0.013 |
Gu | +0.013 |
source | +0.013 |
Neg logit contributions | |
often | -0.017 |
igs | -0.016 |
ot | -0.015 |
lived | -0.014 |
solar | -0.014 |
Token |
|
Token ID | 198 |
Feature activation | -5.22e-01 |
Pos logit contributions | |
igs | +0.034 |
often | +0.033 |
solar | +0.031 |
belt | +0.030 |
ug | +0.029 |
Neg logit contributions | |
written | -0.013 |
comm | -0.013 |
Gu | -0.013 |
aback | -0.013 |
bisc | -0.012 |
Token | Her |
Token ID | 9360 |
Feature activation | +8.65e-02 |
Pos logit contributions | |
igs | +0.022 |
often | +0.021 |
solar | +0.020 |
ug | +0.019 |
ships | +0.019 |
Neg logit contributions | |
Gu | -0.015 |
written | -0.015 |
Sur | -0.015 |
comm | -0.014 |
bisc | -0.014 |
Token | mom |
Token ID | 1995 |
Feature activation | +2.15e+00 |
Pos logit contributions | |
written | +0.004 |
aback | +0.004 |
comm | +0.004 |
Gu | +0.004 |
source | +0.004 |
Neg logit contributions | |
often | -0.002 |
igs | -0.002 |
ot | -0.002 |
solar | -0.002 |
lived | -0.002 |
Token | smiled |
Token ID | 13541 |
Feature activation | +6.68e-01 |
Pos logit contributions | |
source | +0.095 |
Gu | +0.094 |
ctions | +0.094 |
aback | +0.093 |
umbs | +0.091 |
Neg logit contributions | |
often | -0.055 |
lived | -0.053 |
ot | -0.051 |
tight | -0.044 |
loved | -0.040 |
Token | and |
Token ID | 290 |
Feature activation | +1.96e+00 |
Pos logit contributions | |
Gu | +0.023 |
comm | +0.023 |
aback | +0.023 |
written | +0.023 |
bisc | +0.022 |
Neg logit contributions | |
often | -0.025 |
igs | -0.023 |
ot | -0.022 |
lived | -0.020 |
solar | -0.020 |
Token | hugged |
Token ID | 41130 |
Feature activation | +7.04e-01 |
Pos logit contributions | |
source | +0.068 |
ctions | +0.068 |
umbs | +0.067 |
aback | +0.067 |
arre | +0.064 |
Neg logit contributions | |
lived | -0.067 |
often | -0.066 |
ot | -0.063 |
igs | -0.060 |
tight | -0.058 |
Token | her |
Token ID | 607 |
Feature activation | -3.77e-02 |
Pos logit contributions | |
written | +0.029 |
comm | +0.029 |
aback | +0.029 |
Gu | +0.029 |
source | +0.028 |
Neg logit contributions | |
often | -0.022 |
igs | -0.020 |
ot | -0.019 |
lived | -0.017 |
goals | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | -3.95e-01 |
Pos logit contributions | |
igs | +0.001 |
often | +0.001 |
solar | +0.001 |
ot | +0.001 |
lived | +0.001 |
Neg logit contributions | |
written | -0.002 |
aback | -0.002 |
comm | -0.002 |
Gu | -0.002 |
source | -0.002 |
Token | day |
Token ID | 1110 |
Feature activation | -8.06e-01 |
Pos logit contributions | |
igs | +0.018 |
often | +0.016 |
solar | +0.015 |
gut | +0.014 |
goals | +0.014 |
Neg logit contributions | |
written | -0.019 |
Gu | -0.019 |
comm | -0.019 |
aback | -0.019 |
bisc | -0.018 |
Token | , |
Token ID | 11 |
Feature activation | +3.50e-02 |
Pos logit contributions | |
igs | +0.028 |
often | +0.028 |
solar | +0.025 |
gut | +0.025 |
goals | +0.024 |
Neg logit contributions | |
hered | -0.029 |
written | -0.029 |
aback | -0.028 |
Gu | -0.027 |
happened | -0.027 |
Token | they |
Token ID | 484 |
Feature activation | +2.86e-01 |
Pos logit contributions | |
written | +0.001 |
aback | +0.001 |
Gu | +0.001 |
comm | +0.001 |
hered | +0.001 |
Neg logit contributions | |
igs | -0.001 |
often | -0.001 |
solar | -0.001 |
ot | -0.001 |
lived | -0.001 |
Token | saw |
Token ID | 2497 |
Feature activation | +5.64e-01 |
Pos logit contributions | |
aback | +0.010 |
written | +0.010 |
comm | +0.010 |
Gu | +0.010 |
source | +0.009 |
Neg logit contributions | |
often | -0.011 |
igs | -0.010 |
ot | -0.009 |
lived | -0.009 |
solar | -0.009 |
Token | a |
Token ID | 257 |
Feature activation | +3.46e-01 |
Pos logit contributions | |
aback | +0.018 |
written | +0.018 |
Gu | +0.017 |
comm | +0.017 |
hered | +0.017 |
Neg logit contributions | |
often | -0.022 |
igs | -0.022 |
ot | -0.020 |
lived | -0.020 |
solar | -0.019 |
Token | lady |
Token ID | 10846 |
Feature activation | +2.16e+00 |
Pos logit contributions | |
aback | +0.015 |
written | +0.015 |
comm | +0.014 |
Gu | +0.014 |
hered | +0.014 |
Neg logit contributions | |
often | -0.010 |
igs | -0.010 |
ot | -0.009 |
solar | -0.008 |
lived | -0.008 |
Token | wearing |
Token ID | 5762 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
aback | +0.097 |
Gu | +0.089 |
comm | +0.089 |
oph | +0.087 |
bisc | +0.084 |
Neg logit contributions | |
often | -0.072 |
lived | -0.056 |
ot | -0.056 |
ind | -0.053 |
igs | -0.052 |
Token | a |
Token ID | 257 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
aback | +0.064 |
comm | +0.061 |
Gu | +0.061 |
ives | +0.059 |
begs | +0.058 |
Neg logit contributions | |
often | -0.053 |
lived | -0.049 |
igs | -0.048 |
ot | -0.047 |
nam | -0.044 |
Token | veil |
Token ID | 30615 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
aback | +0.080 |
Gu | +0.075 |
comm | +0.073 |
written | +0.072 |
hered | +0.071 |
Neg logit contributions | |
often | -0.041 |
igs | -0.038 |
ot | -0.034 |
solar | -0.031 |
tight | -0.031 |
Token | . |
Token ID | 13 |
Feature activation | +5.44e-01 |
Pos logit contributions | |
aback | +0.043 |
Gu | +0.043 |
comm | +0.042 |
written | +0.039 |
Sur | +0.039 |
Neg logit contributions | |
often | -0.033 |
igs | -0.028 |
lived | -0.027 |
ot | -0.026 |
solar | -0.025 |
Token | Lily |
Token ID | 20037 |
Feature activation | -2.43e-01 |
Pos logit contributions | |
written | +0.023 |
aback | +0.023 |
comm | +0.023 |
Gu | +0.022 |
hered | +0.022 |
Neg logit contributions | |
often | -0.016 |
igs | -0.015 |
ot | -0.013 |
lived | -0.013 |
solar | -0.013 |
Token | stir |
Token ID | 11240 |
Feature activation | -2.84e-01 |
Pos logit contributions | |
igs | +0.056 |
often | +0.055 |
solar | +0.054 |
gut | +0.053 |
goals | +0.052 |
Neg logit contributions | |
written | -0.031 |
bisc | -0.028 |
come | -0.028 |
aback | -0.028 |
source | -0.027 |
Token | things |
Token ID | 1243 |
Feature activation | -9.88e-02 |
Pos logit contributions | |
often | +0.010 |
igs | +0.009 |
solar | +0.009 |
ot | +0.008 |
lived | +0.008 |
Neg logit contributions | |
aback | -0.010 |
written | -0.010 |
comm | -0.010 |
Gu | -0.010 |
source | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
igs | +0.003 |
often | +0.003 |
solar | +0.003 |
ot | +0.003 |
lived | +0.003 |
Neg logit contributions | |
written | -0.004 |
aback | -0.004 |
comm | -0.004 |
Gu | -0.004 |
source | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
comm | +0.066 |
hered | +0.065 |
written | +0.065 |
aback | +0.064 |
source | +0.062 |
Neg logit contributions | |
often | -0.045 |
igs | -0.036 |
apy | -0.036 |
lived | -0.036 |
ot | -0.035 |
Token |
|
Token ID | 198 |
Feature activation | +6.28e-01 |
Pos logit contributions | |
comm | +0.064 |
written | +0.062 |
aback | +0.062 |
hered | +0.059 |
bisc | +0.059 |
Neg logit contributions | |
often | -0.052 |
igs | -0.043 |
ot | -0.043 |
lived | -0.041 |
apy | -0.037 |
Token | " |
Token ID | 1 |
Feature activation | +2.30e+00 |
Pos logit contributions | |
aback | +0.029 |
comm | +0.028 |
written | +0.028 |
Gu | +0.027 |
source | +0.027 |
Neg logit contributions | |
often | -0.017 |
igs | -0.015 |
ot | -0.014 |
lived | -0.013 |
solar | -0.012 |
Token | Let |
Token ID | 5756 |
Feature activation | +1.94e+00 |
Pos logit contributions | |
aback | +0.098 |
comm | +0.093 |
begs | +0.088 |
calling | +0.084 |
source | +0.083 |
Neg logit contributions | |
often | -0.069 |
ot | -0.060 |
lived | -0.059 |
His | -0.058 |
tops | -0.057 |
Token | 's |
Token ID | 338 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
written | +0.076 |
aback | +0.071 |
Gu | +0.071 |
source | +0.069 |
eared | +0.068 |
Neg logit contributions | |
often | -0.068 |
ot | -0.061 |
lived | -0.060 |
tight | -0.055 |
igs | -0.054 |
Token | crack |
Token ID | 8469 |
Feature activation | +2.05e-02 |
Pos logit contributions | |
igs | +0.007 |
often | +0.007 |
ot | +0.006 |
solar | +0.006 |
lived | +0.006 |
Neg logit contributions | |
written | -0.005 |
aback | -0.005 |
comm | -0.005 |
Gu | -0.004 |
source | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
written | +0.001 |
aback | +0.001 |
comm | +0.001 |
Gu | +0.001 |
source | +0.001 |
Neg logit contributions | |
often | -0.001 |
igs | -0.001 |
ot | -0.001 |
solar | -0.001 |
lived | -0.001 |
Token | eggs |
Token ID | 9653 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
aback | +0.052 |
hered | +0.049 |
written | +0.049 |
Gu | +0.049 |
comm | +0.048 |
Neg logit contributions | |
igs | -0.043 |
often | -0.042 |
chim | -0.038 |
ot | -0.037 |
solar | -0.037 |
Token | upon |
Token ID | 2402 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
igs | +0.076 |
solar | +0.070 |
often | +0.070 |
gut | +0.067 |
belt | +0.067 |
Neg logit contributions | |
written | -0.035 |
aback | -0.034 |
source | -0.031 |
m | -0.030 |
happened | -0.030 |
Token | a |
Token ID | 257 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
aback | +0.050 |
comm | +0.047 |
hered | +0.046 |
written | +0.046 |
Gu | +0.045 |
Neg logit contributions | |
often | -0.047 |
lived | -0.042 |
igs | -0.041 |
ot | -0.040 |
apy | -0.037 |
Token | time |
Token ID | 640 |
Feature activation | +6.27e-02 |
Pos logit contributions | |
written | +0.041 |
aback | +0.041 |
Gu | +0.040 |
comm | +0.039 |
source | +0.037 |
Neg logit contributions | |
often | -0.052 |
igs | -0.047 |
ot | -0.045 |
lived | -0.042 |
solar | -0.042 |
Token | , |
Token ID | 11 |
Feature activation | -2.02e-01 |
Pos logit contributions | |
written | +0.003 |
aback | +0.003 |
comm | +0.003 |
Gu | +0.003 |
hered | +0.003 |
Neg logit contributions | |
igs | -0.002 |
often | -0.002 |
ot | -0.001 |
solar | -0.001 |
lived | -0.001 |
Token | there |
Token ID | 612 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
igs | +0.010 |
often | +0.010 |
solar | +0.009 |
ot | +0.009 |
gut | +0.009 |
Neg logit contributions | |
written | -0.004 |
aback | -0.004 |
Gu | -0.004 |
comm | -0.004 |
source | -0.004 |
Token | were |
Token ID | 547 |
Feature activation | +2.13e+00 |
Pos logit contributions | |
written | +0.004 |
aback | +0.004 |
comm | +0.004 |
Gu | +0.004 |
source | +0.004 |
Neg logit contributions | |
often | -0.006 |
igs | -0.006 |
ot | -0.005 |
solar | -0.005 |
lived | -0.005 |
Token | two |
Token ID | 734 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
aback | +0.082 |
written | +0.078 |
comm | +0.076 |
begs | +0.075 |
source | +0.074 |
Neg logit contributions | |
often | -0.075 |
igs | -0.069 |
ot | -0.066 |
many | -0.065 |
lived | -0.063 |
Token | friends |
Token ID | 2460 |
Feature activation | -9.59e-01 |
Pos logit contributions | |
igs | +0.041 |
often | +0.040 |
belt | +0.039 |
solar | +0.039 |
ot | +0.038 |
Neg logit contributions | |
comm | -0.038 |
written | -0.034 |
calling | -0.034 |
bisc | -0.033 |
alright | -0.033 |
Token | , |
Token ID | 11 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
igs | +0.031 |
solar | +0.027 |
goals | +0.027 |
often | +0.027 |
belt | +0.027 |
Neg logit contributions | |
calling | -0.038 |
written | -0.036 |
comm | -0.036 |
aback | -0.036 |
hered | -0.035 |
Token | Max |
Token ID | 5436 |
Feature activation | +6.47e-01 |
Pos logit contributions | |
written | +0.004 |
aback | +0.004 |
comm | +0.004 |
Gu | +0.004 |
hered | +0.003 |
Neg logit contributions | |
igs | -0.005 |
often | -0.005 |
ot | -0.004 |
solar | -0.004 |
lived | -0.004 |
Token | and |
Token ID | 290 |
Feature activation | -4.75e-01 |
Pos logit contributions | |
aback | +0.022 |
Gu | +0.022 |
written | +0.022 |
comm | +0.022 |
source | +0.021 |
Neg logit contributions | |
often | -0.025 |
igs | -0.023 |
ot | -0.022 |
lived | -0.021 |
solar | -0.020 |
Token | One |
Token ID | 1881 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
igs | +0.031 |
often | +0.027 |
ot | +0.026 |
ind | +0.026 |
gut | +0.026 |
Neg logit contributions | |
Gu | -0.031 |
written | -0.031 |
source | -0.029 |
aback | -0.029 |
comm | -0.029 |
Token | day |
Token ID | 1110 |
Feature activation | -7.58e-01 |
Pos logit contributions | |
igs | +0.046 |
often | +0.039 |
solar | +0.037 |
belt | +0.037 |
gut | +0.037 |
Neg logit contributions | |
source | -0.033 |
written | -0.033 |
comm | -0.031 |
Gu | -0.031 |
news | -0.031 |
Token | , |
Token ID | 11 |
Feature activation | -5.62e-01 |
Pos logit contributions | |
igs | +0.028 |
often | +0.027 |
ind | +0.025 |
solar | +0.024 |
ot | +0.023 |
Neg logit contributions | |
written | -0.029 |
aback | -0.027 |
Gu | -0.026 |
hered | -0.026 |
happened | -0.026 |
Token | a |
Token ID | 257 |
Feature activation | -2.18e-01 |
Pos logit contributions | |
igs | +0.027 |
often | +0.026 |
ot | +0.024 |
solar | +0.024 |
ind | +0.024 |
Neg logit contributions | |
written | -0.014 |
source | -0.013 |
Gu | -0.013 |
comm | -0.013 |
aback | -0.013 |
Token | little |
Token ID | 1310 |
Feature activation | +6.42e-01 |
Pos logit contributions | |
igs | +0.008 |
often | +0.008 |
ot | +0.007 |
solar | +0.007 |
lived | +0.007 |
Neg logit contributions | |
written | -0.008 |
comm | -0.008 |
aback | -0.008 |
Gu | -0.008 |
source | -0.007 |
Token | boy |
Token ID | 2933 |
Feature activation | +3.14e-01 |
Pos logit contributions | |
written | +0.019 |
aback | +0.019 |
comm | +0.018 |
Gu | +0.018 |
hered | +0.017 |
Neg logit contributions | |
often | -0.026 |
igs | -0.026 |
ot | -0.024 |
solar | -0.023 |
lived | -0.023 |
Token | touched |
Token ID | 12615 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
aback | +0.013 |
written | +0.013 |
comm | +0.013 |
Gu | +0.013 |
source | +0.012 |
Neg logit contributions | |
often | -0.009 |
igs | -0.009 |
ot | -0.008 |
lived | -0.008 |
solar | -0.008 |
Token | the |
Token ID | 262 |
Feature activation | +2.02e-01 |
Pos logit contributions | |
igs | +0.005 |
often | +0.005 |
solar | +0.004 |
ot | +0.004 |
gut | +0.004 |
Neg logit contributions | |
written | -0.007 |
aback | -0.007 |
comm | -0.006 |
Gu | -0.006 |
source | -0.006 |
Token | tree |
Token ID | 5509 |
Feature activation | -7.51e-01 |
Pos logit contributions | |
written | +0.009 |
aback | +0.009 |
comm | +0.009 |
Gu | +0.009 |
hered | +0.009 |
Neg logit contributions | |
often | -0.005 |
igs | -0.005 |
ot | -0.004 |
solar | -0.004 |
lived | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | -4.96e-01 |
Pos logit contributions | |
igs | +0.034 |
often | +0.032 |
solar | +0.031 |
gut | +0.030 |
ot | +0.030 |
Neg logit contributions | |
written | -0.021 |
aback | -0.019 |
source | -0.019 |
comm | -0.018 |
calling | -0.018 |
Token | Suddenly |
Token ID | 24975 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
igs | +0.017 |
often | +0.016 |
ot | +0.014 |
solar | +0.014 |
ind | +0.014 |
Neg logit contributions | |
aback | -0.020 |
Gu | -0.020 |
written | -0.020 |
comm | -0.019 |
source | -0.019 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
written | +0.011 |
aback | +0.011 |
comm | +0.011 |
Gu | +0.010 |
hered | +0.010 |
Neg logit contributions | |
often | -0.011 |
igs | -0.011 |
ot | -0.010 |
solar | -0.009 |
lived | -0.009 |
Token | L |
Token ID | 43 |
Feature activation | +6.17e-01 |
Pos logit contributions | |
comm | +0.032 |
written | +0.032 |
aback | +0.031 |
Gu | +0.029 |
Birthday | +0.028 |
Neg logit contributions | |
often | -0.040 |
igs | -0.039 |
lived | -0.037 |
solar | -0.036 |
ot | -0.035 |
Token | ily |
Token ID | 813 |
Feature activation | -7.79e-01 |
Pos logit contributions | |
aback | +0.022 |
comm | +0.022 |
written | +0.022 |
Gu | +0.021 |
hered | +0.020 |
Neg logit contributions | |
igs | -0.023 |
often | -0.023 |
ot | -0.021 |
lived | -0.020 |
ug | -0.019 |
Token | and |
Token ID | 290 |
Feature activation | +4.47e-01 |
Pos logit contributions | |
igs | +0.034 |
often | +0.032 |
ot | +0.030 |
apy | +0.030 |
ug | +0.029 |
Neg logit contributions | |
written | -0.023 |
aback | -0.022 |
Gu | -0.021 |
comm | -0.021 |
bisc | -0.020 |
Token | Sam |
Token ID | 3409 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
written | +0.019 |
aback | +0.018 |
comm | +0.018 |
Gu | +0.018 |
source | +0.017 |
Neg logit contributions | |
often | -0.014 |
igs | -0.013 |
ot | -0.012 |
lived | -0.012 |
solar | -0.011 |
Token | were |
Token ID | 547 |
Feature activation | +1.92e-01 |
Pos logit contributions | |
igs | +0.063 |
often | +0.056 |
ug | +0.054 |
belt | +0.054 |
gut | +0.054 |
Neg logit contributions | |
written | -0.033 |
aback | -0.033 |
comm | -0.030 |
come | -0.030 |
hered | -0.030 |
Token | friends |
Token ID | 2460 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
written | +0.007 |
aback | +0.006 |
comm | +0.006 |
Gu | +0.006 |
hered | +0.006 |
Neg logit contributions | |
often | -0.007 |
igs | -0.007 |
ot | -0.006 |
solar | -0.006 |
lived | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
igs | +0.053 |
solar | +0.047 |
apy | +0.044 |
ot | +0.044 |
lived | +0.043 |
Neg logit contributions | |
written | -0.044 |
calling | -0.041 |
aback | -0.041 |
source | -0.041 |
comm | -0.040 |
Token | They |
Token ID | 1119 |
Feature activation | -2.06e+00 |
Pos logit contributions | |
igs | +0.006 |
often | +0.006 |
gut | +0.005 |
solar | +0.005 |
ot | +0.005 |
Neg logit contributions | |
written | -0.009 |
aback | -0.009 |
Gu | -0.009 |
comm | -0.009 |
bisc | -0.009 |
Token | liked |
Token ID | 8288 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
igs | +0.096 |
gut | +0.082 |
instincts | +0.074 |
belt | +0.074 |
ug | +0.073 |
Neg logit contributions | |
written | -0.075 |
come | -0.071 |
baked | -0.067 |
appeared | -0.064 |
announced | -0.060 |
Token | to |
Token ID | 284 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
written | +0.006 |
aback | +0.006 |
comm | +0.006 |
Gu | +0.005 |
hered | +0.005 |
Neg logit contributions | |
often | -0.010 |
igs | -0.010 |
ot | -0.009 |
solar | -0.009 |
lived | -0.009 |
Token |
|
Token ID | 198 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
written | +0.033 |
comm | +0.033 |
aback | +0.032 |
Gu | +0.032 |
hered | +0.031 |
Neg logit contributions | |
often | -0.029 |
igs | -0.027 |
ot | -0.026 |
lived | -0.025 |
solar | -0.024 |
Token |
|
Token ID | 198 |
Feature activation | -9.70e-02 |
Pos logit contributions | |
written | +0.006 |
aback | +0.006 |
comm | +0.006 |
Gu | +0.006 |
hered | +0.005 |
Neg logit contributions | |
often | -0.008 |
igs | -0.008 |
ot | -0.007 |
solar | -0.007 |
lived | -0.007 |
Token | The |
Token ID | 464 |
Feature activation | +5.69e-01 |
Pos logit contributions | |
igs | +0.004 |
often | +0.003 |
solar | +0.003 |
ot | +0.003 |
lived | +0.003 |
Neg logit contributions | |
written | -0.003 |
aback | -0.003 |
Gu | -0.003 |
comm | -0.003 |
hered | -0.003 |
Token | balloon |
Token ID | 21190 |
Feature activation | +5.03e-01 |
Pos logit contributions | |
aback | +0.021 |
written | +0.020 |
Gu | +0.020 |
comm | +0.020 |
hered | +0.019 |
Neg logit contributions | |
often | -0.020 |
igs | -0.019 |
ot | -0.018 |
solar | -0.017 |
lived | -0.017 |
Token | was |
Token ID | 373 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
aback | +0.017 |
written | +0.017 |
Gu | +0.017 |
comm | +0.017 |
hered | +0.016 |
Neg logit contributions | |
often | -0.019 |
igs | -0.018 |
ot | -0.016 |
lived | -0.016 |
solar | -0.016 |
Token | filled |
Token ID | 5901 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
Gu | +0.042 |
comm | +0.039 |
aback | +0.038 |
bisc | +0.038 |
begs | +0.037 |
Neg logit contributions | |
often | -0.052 |
igs | -0.047 |
ot | -0.044 |
tight | -0.043 |
lived | -0.042 |
Token | with |
Token ID | 351 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
Gu | +0.036 |
comm | +0.036 |
written | +0.035 |
aback | +0.035 |
bisc | +0.034 |
Neg logit contributions | |
often | -0.038 |
igs | -0.034 |
ot | -0.033 |
lived | -0.031 |
solar | -0.030 |
Token | love |
Token ID | 1842 |
Feature activation | +5.56e-01 |
Pos logit contributions | |
Gu | +0.038 |
written | +0.035 |
aback | +0.035 |
comm | +0.035 |
hered | +0.034 |
Neg logit contributions | |
often | -0.038 |
igs | -0.036 |
ot | -0.034 |
solar | -0.033 |
lived | -0.033 |
Token | , |
Token ID | 11 |
Feature activation | +1.93e+00 |
Pos logit contributions | |
Gu | +0.019 |
aback | +0.019 |
comm | +0.019 |
written | +0.019 |
source | +0.018 |
Neg logit contributions | |
often | -0.021 |
igs | -0.020 |
ot | -0.018 |
lived | -0.017 |
solar | -0.017 |
Token | and |
Token ID | 290 |
Feature activation | +5.75e-01 |
Pos logit contributions | |
Gu | +0.073 |
hered | +0.067 |
aback | +0.066 |
comm | +0.065 |
written | +0.063 |
Neg logit contributions | |
often | -0.076 |
igs | -0.064 |
ot | -0.061 |
tight | -0.057 |
lived | -0.057 |
Token | when |
Token ID | 618 |
Feature activation | +6.32e-02 |
Pos logit contributions | |
aback | +0.022 |
Gu | +0.022 |
written | +0.022 |
comm | +0.022 |
hered | +0.021 |
Neg logit contributions | |
often | -0.019 |
igs | -0.018 |
ot | -0.016 |
lived | -0.016 |
solar | -0.016 |
Token | again |
Token ID | 757 |
Feature activation | +2.68e-01 |
Pos logit contributions | |
bisc | +0.042 |
Gu | +0.042 |
comm | +0.041 |
written | +0.040 |
aback | +0.039 |
Neg logit contributions | |
often | -0.049 |
igs | -0.040 |
ot | -0.039 |
goals | -0.039 |
gut | -0.038 |
Token | and |
Token ID | 290 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
written | +0.011 |
aback | +0.011 |
comm | +0.011 |
Gu | +0.011 |
hered | +0.011 |
Neg logit contributions | |
often | -0.008 |
igs | -0.008 |
ot | -0.007 |
solar | -0.006 |
lived | -0.006 |
Token | always |
Token ID | 1464 |
Feature activation | -8.78e-02 |
Pos logit contributions | |
igs | +0.004 |
often | +0.003 |
ot | +0.003 |
solar | +0.003 |
ug | +0.003 |
Neg logit contributions | |
written | -0.004 |
aback | -0.004 |
comm | -0.004 |
Gu | -0.004 |
source | -0.004 |
Token | said |
Token ID | 531 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
igs | +0.004 |
often | +0.004 |
ot | +0.003 |
solar | +0.003 |
ug | +0.003 |
Neg logit contributions | |
written | -0.003 |
aback | -0.003 |
comm | -0.003 |
Gu | -0.003 |
hered | -0.002 |
Token | please |
Token ID | 3387 |
Feature activation | -9.06e-01 |
Pos logit contributions | |
igs | +0.048 |
often | +0.044 |
ind | +0.043 |
solar | +0.043 |
ot | +0.042 |
Neg logit contributions | |
written | -0.033 |
aback | -0.032 |
come | -0.030 |
Gu | -0.029 |
alright | -0.029 |
Token | and |
Token ID | 290 |
Feature activation | -1.64e-01 |
Pos logit contributions | |
igs | +0.041 |
apy | +0.036 |
often | +0.035 |
solar | +0.035 |
ug | +0.034 |
Neg logit contributions | |
written | -0.026 |
aback | -0.025 |
come | -0.024 |
calling | -0.024 |
source | -0.024 |
Token | thank |
Token ID | 5875 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
igs | +0.006 |
often | +0.006 |
ot | +0.005 |
solar | +0.005 |
ug | +0.005 |
Neg logit contributions | |
written | -0.006 |
aback | -0.006 |
comm | -0.006 |
Gu | -0.006 |
source | -0.005 |
Token | you |
Token ID | 345 |
Feature activation | -6.03e-01 |
Pos logit contributions | |
written | +0.006 |
aback | +0.006 |
comm | +0.006 |
Gu | +0.006 |
source | +0.005 |
Neg logit contributions | |
often | -0.006 |
igs | -0.006 |
ot | -0.005 |
solar | -0.005 |
lived | -0.005 |
Token | to |
Token ID | 284 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
igs | +0.026 |
often | +0.024 |
solar | +0.023 |
apy | +0.023 |
lived | +0.023 |
Neg logit contributions | |
written | -0.018 |
aback | -0.017 |
comm | -0.016 |
Gu | -0.016 |
calling | -0.016 |
Token | everyone |
Token ID | 2506 |
Feature activation | -7.39e-01 |
Pos logit contributions | |
igs | +0.053 |
apy | +0.050 |
belt | +0.047 |
ot | +0.045 |
often | +0.044 |
Neg logit contributions | |
come | -0.047 |
calling | -0.047 |
such | -0.045 |
saying | -0.045 |
written | -0.044 |
Token | . |
Token ID | 13 |
Feature activation | -5.88e-01 |
Pos logit contributions | |
igs | +0.026 |
often | +0.023 |
solar | +0.022 |
ot | +0.021 |
apy | +0.020 |
Neg logit contributions | |
written | -0.029 |
aback | -0.027 |
comm | -0.026 |
Gu | -0.026 |
calling | -0.026 |
Token | in |
Token ID | 287 |
Feature activation | -5.62e-01 |
Pos logit contributions | |
igs | +0.011 |
often | +0.011 |
solar | +0.010 |
ot | +0.010 |
lived | +0.010 |
Neg logit contributions | |
written | -0.010 |
comm | -0.010 |
aback | -0.010 |
Gu | -0.009 |
source | -0.009 |
Token | a |
Token ID | 257 |
Feature activation | +3.03e-01 |
Pos logit contributions | |
igs | +0.019 |
often | +0.019 |
solar | +0.016 |
lived | +0.016 |
ot | +0.016 |
Neg logit contributions | |
aback | -0.021 |
written | -0.021 |
comm | -0.020 |
Gu | -0.020 |
hered | -0.020 |
Token | harsh |
Token ID | 11859 |
Feature activation | +5.58e-01 |
Pos logit contributions | |
written | +0.012 |
aback | +0.012 |
comm | +0.012 |
Gu | +0.012 |
hered | +0.011 |
Neg logit contributions | |
often | -0.009 |
igs | -0.009 |
ot | -0.008 |
solar | -0.008 |
lived | -0.008 |
Token | voice |
Token ID | 3809 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
written | +0.020 |
Gu | +0.019 |
aback | +0.019 |
comm | +0.018 |
bisc | +0.017 |
Neg logit contributions | |
often | -0.021 |
igs | -0.020 |
ot | -0.019 |
lived | -0.018 |
solar | -0.018 |
Token | and |
Token ID | 290 |
Feature activation | -4.77e-01 |
Pos logit contributions | |
Gu | +0.050 |
aback | +0.048 |
comm | +0.048 |
written | +0.048 |
source | +0.047 |
Neg logit contributions | |
often | -0.027 |
igs | -0.023 |
ot | -0.022 |
lived | -0.022 |
ug | -0.020 |
Token | the |
Token ID | 262 |
Feature activation | +2.45e-01 |
Pos logit contributions | |
igs | +0.019 |
often | +0.017 |
solar | +0.016 |
ot | +0.016 |
goals | +0.015 |
Neg logit contributions | |
written | -0.016 |
comm | -0.016 |
aback | -0.016 |
Gu | -0.015 |
source | -0.014 |
Token | little |
Token ID | 1310 |
Feature activation | +8.89e-01 |
Pos logit contributions | |
written | +0.010 |
aback | +0.010 |
Gu | +0.009 |
comm | +0.009 |
hered | +0.009 |
Neg logit contributions | |
often | -0.008 |
igs | -0.008 |
ot | -0.007 |
solar | -0.007 |
lived | -0.007 |
Token | boy |
Token ID | 2933 |
Feature activation | -3.47e-01 |
Pos logit contributions | |
written | +0.031 |
aback | +0.029 |
Gu | +0.029 |
comm | +0.029 |
hered | +0.028 |
Neg logit contributions | |
often | -0.032 |
igs | -0.031 |
ot | -0.029 |
lived | -0.028 |
solar | -0.028 |
Token | knew |
Token ID | 2993 |
Feature activation | -8.57e-01 |
Pos logit contributions | |
igs | +0.015 |
often | +0.014 |
solar | +0.013 |
ot | +0.013 |
gut | +0.012 |
Neg logit contributions | |
written | -0.010 |
comm | -0.010 |
aback | -0.010 |
Gu | -0.010 |
hered | -0.009 |
Token | he |
Token ID | 339 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
igs | +0.030 |
solar | +0.029 |
ot | +0.028 |
often | +0.028 |
apy | +0.025 |
Neg logit contributions | |
written | -0.032 |
aback | -0.029 |
calling | -0.029 |
comm | -0.029 |
saying | -0.028 |
Token | would |
Token ID | 561 |
Feature activation | +3.35e-01 |
Pos logit contributions | |
written | +0.005 |
aback | +0.005 |
comm | +0.005 |
Gu | +0.005 |
hered | +0.005 |
Neg logit contributions | |
igs | -0.005 |
often | -0.005 |
ot | -0.004 |
solar | -0.004 |
lived | -0.004 |
Token | and |
Token ID | 290 |
Feature activation | +3.32e-01 |
Pos logit contributions | |
igs | +0.006 |
often | +0.005 |
ot | +0.005 |
solar | +0.005 |
lived | +0.005 |
Neg logit contributions | |
written | -0.003 |
aback | -0.003 |
comm | -0.003 |
Gu | -0.003 |
source | -0.003 |
Token | saw |
Token ID | 2497 |
Feature activation | -1.73e-01 |
Pos logit contributions | |
written | +0.010 |
aback | +0.010 |
comm | +0.010 |
Gu | +0.010 |
hered | +0.009 |
Neg logit contributions | |
often | -0.014 |
igs | -0.013 |
ot | -0.012 |
solar | -0.012 |
lived | -0.012 |
Token | a |
Token ID | 257 |
Feature activation | +3.77e-01 |
Pos logit contributions | |
igs | +0.007 |
often | +0.007 |
ot | +0.006 |
solar | +0.006 |
ug | +0.006 |
Neg logit contributions | |
written | -0.006 |
aback | -0.005 |
comm | -0.005 |
Gu | -0.005 |
source | -0.005 |
Token | big |
Token ID | 1263 |
Feature activation | +3.68e-02 |
Pos logit contributions | |
aback | +0.015 |
written | +0.015 |
comm | +0.015 |
Gu | +0.015 |
hered | +0.014 |
Neg logit contributions | |
often | -0.011 |
igs | -0.011 |
ot | -0.010 |
solar | -0.010 |
lived | -0.009 |
Token | , |
Token ID | 11 |
Feature activation | +4.51e-01 |
Pos logit contributions | |
written | +0.001 |
aback | +0.001 |
comm | +0.001 |
Gu | +0.001 |
source | +0.001 |
Neg logit contributions | |
often | -0.001 |
igs | -0.001 |
ot | -0.001 |
solar | -0.001 |
lived | -0.001 |
Token | dark |
Token ID | 3223 |
Feature activation | -4.65e-01 |
Pos logit contributions | |
aback | +0.020 |
written | +0.020 |
comm | +0.020 |
Gu | +0.020 |
hered | +0.019 |
Neg logit contributions | |
often | -0.012 |
igs | -0.012 |
ot | -0.010 |
solar | -0.010 |
lived | -0.009 |
Token | cave |
Token ID | 11527 |
Feature activation | -3.67e-01 |
Pos logit contributions | |
igs | +0.014 |
often | +0.014 |
ot | +0.012 |
ug | +0.011 |
goals | +0.011 |
Neg logit contributions | |
written | -0.019 |
comm | -0.019 |
aback | -0.018 |
Gu | -0.018 |
source | -0.018 |
Token | inside |
Token ID | 2641 |
Feature activation | -3.47e-01 |
Pos logit contributions | |
igs | +0.012 |
often | +0.012 |
ot | +0.011 |
solar | +0.010 |
gut | +0.010 |
Neg logit contributions | |
written | -0.015 |
comm | -0.014 |
aback | -0.014 |
source | -0.013 |
Gu | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | +5.78e-01 |
Pos logit contributions | |
igs | +0.011 |
often | +0.010 |
ot | +0.009 |
solar | +0.009 |
gut | +0.009 |
Neg logit contributions | |
written | -0.014 |
aback | -0.014 |
comm | -0.014 |
Gu | -0.013 |
source | -0.013 |
Token |
|
Token ID | 198 |
Feature activation | +9.21e-02 |
Pos logit contributions | |
written | +0.021 |
aback | +0.021 |
comm | +0.021 |
Gu | +0.020 |
hered | +0.020 |
Neg logit contributions | |
often | -0.020 |
igs | -0.019 |
lived | -0.018 |
ot | -0.017 |
solar | -0.017 |
Token |
|
Token ID | 198 |
Feature activation | -6.24e-01 |
Pos logit contributions | |
written | +0.003 |
aback | +0.003 |
comm | +0.003 |
Gu | +0.003 |
source | +0.002 |
Neg logit contributions | |
igs | -0.004 |
often | -0.004 |
ot | -0.004 |
solar | -0.003 |
lived | -0.003 |
Token | and |
Token ID | 290 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
igs | +0.012 |
often | +0.012 |
solar | +0.010 |
ot | +0.010 |
lived | +0.010 |
Neg logit contributions | |
written | -0.010 |
aback | -0.010 |
comm | -0.010 |
hered | -0.009 |
Gu | -0.009 |
Token | shook |
Token ID | 14682 |
Feature activation | -4.20e-01 |
Pos logit contributions | |
written | +0.004 |
aback | +0.004 |
comm | +0.004 |
Gu | +0.004 |
source | +0.004 |
Neg logit contributions | |
often | -0.004 |
igs | -0.004 |
ot | -0.004 |
solar | -0.004 |
lived | -0.004 |
Token | his |
Token ID | 465 |
Feature activation | -3.14e-01 |
Pos logit contributions | |
igs | +0.011 |
often | +0.010 |
solar | +0.009 |
ot | +0.008 |
ug | +0.008 |
Neg logit contributions | |
written | -0.020 |
aback | -0.020 |
comm | -0.019 |
source | -0.019 |
Gu | -0.018 |
Token | head |
Token ID | 1182 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
often | +0.010 |
igs | +0.010 |
solar | +0.008 |
ot | +0.008 |
lived | +0.008 |
Neg logit contributions | |
written | -0.013 |
comm | -0.013 |
aback | -0.012 |
source | -0.012 |
bisc | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | +6.53e-02 |
Pos logit contributions | |
igs | +0.043 |
often | +0.036 |
solar | +0.036 |
ot | +0.033 |
lived | +0.033 |
Neg logit contributions | |
written | -0.046 |
aback | -0.042 |
source | -0.041 |
hered | -0.041 |
comm | -0.039 |
Token |
|
Token ID | 198 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
written | +0.002 |
aback | +0.002 |
comm | +0.002 |
Gu | +0.002 |
source | +0.002 |
Neg logit contributions | |
igs | -0.002 |
often | -0.002 |
ot | -0.002 |
solar | -0.002 |
lived | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
igs | +0.060 |
often | +0.058 |
solar | +0.056 |
toes | +0.054 |
gut | +0.054 |
Neg logit contributions | |
aback | -0.018 |
Gu | -0.018 |
written | -0.018 |
comm | -0.017 |
source | -0.015 |
Token | " |
Token ID | 1 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
igs | +0.047 |
solar | +0.045 |
often | +0.044 |
toes | +0.043 |
tops | +0.040 |
Neg logit contributions | |
Gu | -0.038 |
Sur | -0.037 |
written | -0.036 |
aback | -0.035 |
comm | -0.034 |
Token | Wow |
Token ID | 22017 |
Feature activation | +3.28e-01 |
Pos logit contributions | |
aback | +0.040 |
written | +0.038 |
source | +0.037 |
calling | +0.037 |
comm | +0.037 |
Neg logit contributions | |
often | -0.049 |
His | -0.044 |
igs | -0.044 |
lived | -0.044 |
ot | -0.043 |
Token | , |
Token ID | 11 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
written | +0.015 |
aback | +0.015 |
comm | +0.015 |
Gu | +0.015 |
source | +0.014 |
Neg logit contributions | |
often | -0.008 |
igs | -0.008 |
ot | -0.007 |
lived | -0.007 |
solar | -0.007 |
Token | he |
Token ID | 339 |
Feature activation | +2.99e+00 |
Pos logit contributions | |
written | +0.051 |
aback | +0.051 |
Gu | +0.049 |
source | +0.049 |
comm | +0.049 |
Neg logit contributions | |
often | -0.036 |
igs | -0.033 |
lived | -0.031 |
ot | -0.030 |
solar | -0.028 |
Token | . |
Token ID | 13 |
Feature activation | -3.27e-01 |
Pos logit contributions | |
aback | +0.014 |
written | +0.014 |
comm | +0.013 |
Gu | +0.013 |
source | +0.013 |
Neg logit contributions | |
often | -0.011 |
igs | -0.011 |
ot | -0.009 |
solar | -0.009 |
lived | -0.009 |
Token | The |
Token ID | 383 |
Feature activation | -3.01e-02 |
Pos logit contributions | |
igs | +0.011 |
often | +0.011 |
ot | +0.009 |
solar | +0.009 |
gut | +0.009 |
Neg logit contributions | |
aback | -0.013 |
written | -0.012 |
Gu | -0.012 |
comm | -0.012 |
hered | -0.011 |
Token | pond |
Token ID | 16723 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
igs | +0.001 |
often | +0.001 |
ot | +0.001 |
solar | +0.001 |
lived | +0.001 |
Neg logit contributions | |
comm | -0.001 |
written | -0.001 |
aback | -0.001 |
Gu | -0.001 |
source | -0.001 |
Token | and |
Token ID | 290 |
Feature activation | -5.18e-01 |
Pos logit contributions | |
written | +0.004 |
aback | +0.004 |
comm | +0.003 |
Gu | +0.003 |
source | +0.003 |
Neg logit contributions | |
igs | -0.004 |
often | -0.004 |
ot | -0.004 |
solar | -0.004 |
lived | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | +5.63e-01 |
Pos logit contributions | |
igs | +0.018 |
often | +0.017 |
ot | +0.015 |
solar | +0.015 |
ug | +0.014 |
Neg logit contributions | |
comm | -0.019 |
written | -0.019 |
aback | -0.019 |
source | -0.018 |
Gu | -0.018 |
Token | animals |
Token ID | 4695 |
Feature activation | -7.06e-01 |
Pos logit contributions | |
written | +0.022 |
aback | +0.022 |
Gu | +0.021 |
comm | +0.020 |
hered | +0.020 |
Neg logit contributions | |
often | -0.019 |
igs | -0.019 |
ot | -0.017 |
lived | -0.016 |
solar | -0.016 |
Token | stayed |
Token ID | 9658 |
Feature activation | +9.40e-01 |
Pos logit contributions | |
igs | +0.028 |
often | +0.026 |
ot | +0.024 |
solar | +0.024 |
gut | +0.024 |
Neg logit contributions | |
written | -0.023 |
aback | -0.022 |
comm | -0.021 |
hered | -0.021 |
source | -0.020 |
Token | happy |
Token ID | 3772 |
Feature activation | +8.26e-01 |
Pos logit contributions | |
Gu | +0.036 |
comm | +0.035 |
written | +0.035 |
aback | +0.035 |
cake | +0.035 |
Neg logit contributions | |
often | -0.034 |
igs | -0.032 |
ot | -0.028 |
solar | -0.028 |
lived | -0.027 |
Token | forever |
Token ID | 8097 |
Feature activation | -3.62e-01 |
Pos logit contributions | |
Gu | +0.032 |
aback | +0.031 |
comm | +0.030 |
written | +0.030 |
bisc | +0.029 |
Neg logit contributions | |
often | -0.030 |
igs | -0.027 |
lived | -0.025 |
ot | -0.025 |
solar | -0.024 |
Token | . |
Token ID | 13 |
Feature activation | +9.95e-02 |
Pos logit contributions | |
igs | +0.012 |
often | +0.011 |
solar | +0.010 |
ot | +0.010 |
lived | +0.009 |
Neg logit contributions | |
written | -0.015 |
aback | -0.014 |
comm | -0.014 |
hered | -0.014 |
source | -0.014 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
written | +0.004 |
aback | +0.004 |
comm | +0.004 |
Gu | +0.003 |
hered | +0.003 |
Neg logit contributions | |
igs | -0.003 |
often | -0.003 |
ot | -0.003 |
solar | -0.003 |
lived | -0.003 |
Token | Mr |
Token ID | 1770 |
Feature activation | -2.65e-01 |
Pos logit contributions | |
igs | +0.009 |
often | +0.008 |
ot | +0.008 |
solar | +0.007 |
ug | +0.007 |
Neg logit contributions | |
written | -0.008 |
aback | -0.008 |
comm | -0.008 |
Gu | -0.008 |
hered | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
igs | +0.008 |
often | +0.007 |
ot | +0.006 |
solar | +0.006 |
apy | +0.006 |
Neg logit contributions | |
written | -0.011 |
aback | -0.011 |
comm | -0.011 |
Gu | -0.011 |
hered | -0.011 |
Token | Bear |
Token ID | 14732 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
igs | +0.060 |
often | +0.055 |
ot | +0.053 |
ug | +0.052 |
goals | +0.051 |
Neg logit contributions | |
aback | -0.033 |
Gu | -0.033 |
source | -0.032 |
hered | -0.031 |
written | -0.030 |
Token | and |
Token ID | 290 |
Feature activation | -9.01e-01 |
Pos logit contributions | |
igs | +0.047 |
often | +0.041 |
solar | +0.040 |
ot | +0.040 |
ug | +0.040 |
Neg logit contributions | |
written | -0.032 |
aback | -0.029 |
source | -0.028 |
comm | -0.028 |
hered | -0.028 |
Token | he |
Token ID | 339 |
Feature activation | -2.72e+00 |
Pos logit contributions | |
igs | +0.037 |
ug | +0.033 |
often | +0.031 |
ot | +0.031 |
ind | +0.031 |
Neg logit contributions | |
written | -0.029 |
comm | -0.027 |
bisc | -0.026 |
aback | -0.026 |
Gu | -0.026 |
Token | would |
Token ID | 561 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
igs | +0.125 |
ug | +0.107 |
ubby | +0.099 |
agons | +0.098 |
gut | +0.097 |
Neg logit contributions | |
written | -0.089 |
come | -0.080 |
baked | -0.079 |
meant | -0.079 |
appeared | -0.078 |
Token | always |
Token ID | 1464 |
Feature activation | -2.50e-01 |
Pos logit contributions | |
igs | +0.065 |
ug | +0.058 |
apy | +0.055 |
bers | +0.054 |
belt | +0.054 |
Neg logit contributions | |
come | -0.046 |
written | -0.044 |
calling | -0.042 |
comm | -0.041 |
source | -0.040 |
Token | comfort |
Token ID | 4467 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
igs | +0.010 |
often | +0.010 |
ot | +0.009 |
solar | +0.009 |
ug | +0.009 |
Neg logit contributions | |
written | -0.008 |
aback | -0.007 |
comm | -0.007 |
Gu | -0.007 |
source | -0.007 |
Token | her |
Token ID | 607 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
igs | +0.005 |
often | +0.005 |
ot | +0.004 |
solar | +0.004 |
lived | +0.004 |
Neg logit contributions | |
aback | -0.004 |
written | -0.004 |
comm | -0.004 |
Gu | -0.004 |
hered | -0.004 |
Token | when |
Token ID | 618 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
igs | +0.058 |
apy | +0.049 |
ug | +0.048 |
ot | +0.048 |
often | +0.046 |
Neg logit contributions | |
written | -0.042 |
aback | -0.040 |
source | -0.040 |
Birthday | -0.037 |
such | -0.037 |
Token | she |
Token ID | 673 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
igs | +0.053 |
ug | +0.047 |
ot | +0.047 |
solar | +0.046 |
often | +0.044 |
Neg logit contributions | |
written | -0.048 |
Gu | -0.046 |
comm | -0.045 |
come | -0.044 |
calling | -0.044 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
igs | +0.062 |
often | +0.055 |
ts | +0.052 |
ug | +0.051 |
belt | +0.050 |
Neg logit contributions | |
Gu | -0.035 |
How | -0.033 |
written | -0.033 |
aback | -0.032 |
comm | -0.031 |
Token | Once |
Token ID | 7454 |
Feature activation | -1.86e+00 |
Pos logit contributions | |
comm | +0.045 |
written | +0.044 |
aback | +0.044 |
Gu | +0.042 |
Birthday | +0.041 |
Neg logit contributions | |
often | -0.044 |
lived | -0.042 |
igs | -0.042 |
solar | -0.039 |
ot | -0.038 |
Token | upon |
Token ID | 2402 |
Feature activation | +9.57e-01 |
Pos logit contributions | |
igs | +0.092 |
solar | +0.087 |
often | +0.086 |
gut | +0.085 |
belt | +0.083 |
Neg logit contributions | |
written | -0.035 |
happened | -0.033 |
m | -0.032 |
aback | -0.031 |
source | -0.030 |
Token | a |
Token ID | 257 |
Feature activation | -2.05e-02 |
Pos logit contributions | |
aback | +0.033 |
comm | +0.031 |
written | +0.031 |
hered | +0.030 |
Gu | +0.030 |
Neg logit contributions | |
often | -0.037 |
igs | -0.035 |
lived | -0.033 |
ot | -0.032 |
solar | -0.031 |
Token | time |
Token ID | 640 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
igs | +0.001 |
often | +0.001 |
ot | +0.001 |
solar | +0.001 |
lived | +0.001 |
Neg logit contributions | |
written | -0.000 |
aback | -0.000 |
comm | -0.000 |
Gu | -0.000 |
hered | -0.000 |
Token | , |
Token ID | 11 |
Feature activation | -2.42e-01 |
Pos logit contributions | |
written | +0.006 |
aback | +0.006 |
comm | +0.006 |
Gu | +0.006 |
hered | +0.006 |
Neg logit contributions | |
often | -0.003 |
igs | -0.003 |
ot | -0.003 |
solar | -0.003 |
lived | -0.003 |
Token | there |
Token ID | 612 |
Feature activation | +2.78e-01 |
Pos logit contributions | |
igs | +0.011 |
often | +0.011 |
solar | +0.010 |
ot | +0.010 |
gut | +0.010 |
Neg logit contributions | |
written | -0.006 |
aback | -0.006 |
Gu | -0.006 |
comm | -0.006 |
source | -0.005 |
Token | was |
Token ID | 373 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
written | +0.009 |
aback | +0.009 |
comm | +0.009 |
Gu | +0.009 |
hered | +0.008 |
Neg logit contributions | |
often | -0.011 |
igs | -0.011 |
ot | -0.010 |
lived | -0.010 |
solar | -0.009 |
Token | a |
Token ID | 257 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
aback | +0.041 |
comm | +0.039 |
written | +0.038 |
Gu | +0.037 |
source | +0.036 |
Neg logit contributions | |
often | -0.040 |
igs | -0.039 |
lived | -0.036 |
ot | -0.036 |
solar | -0.034 |
Token | little |
Token ID | 1310 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
igs | +0.077 |
often | +0.070 |
belt | +0.066 |
aro | +0.065 |
ug | +0.065 |
Neg logit contributions | |
Gu | -0.045 |
comm | -0.043 |
bisc | -0.042 |
written | -0.041 |
source | -0.039 |
Token | do |
Token ID | 466 |
Feature activation | -2.81e-01 |
Pos logit contributions | |
often | +0.081 |
igs | +0.081 |
gut | +0.073 |
belt | +0.073 |
goals | +0.073 |
Neg logit contributions | |
bisc | -0.022 |
comm | -0.021 |
Gu | -0.019 |
hered | -0.019 |
written | -0.018 |
Token | the |
Token ID | 262 |
Feature activation | +7.22e-02 |
Pos logit contributions | |
igs | +0.001 |
often | +0.001 |
ot | +0.001 |
lived | +0.001 |
solar | +0.001 |
Neg logit contributions | |
aback | -0.001 |
written | -0.001 |
comm | -0.001 |
Gu | -0.001 |
source | -0.001 |
Token | sky |
Token ID | 6766 |
Feature activation | +5.12e-01 |
Pos logit contributions | |
written | +0.002 |
aback | +0.002 |
comm | +0.002 |
Gu | +0.002 |
source | +0.002 |
Neg logit contributions | |
often | -0.003 |
igs | -0.003 |
ot | -0.003 |
solar | -0.003 |
lived | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
Gu | +0.019 |
aback | +0.019 |
written | +0.019 |
comm | +0.018 |
hered | +0.017 |
Neg logit contributions | |
often | -0.018 |
igs | -0.017 |
ot | -0.016 |
solar | -0.015 |
lived | -0.015 |
Token | It |
Token ID | 632 |
Feature activation | -5.32e-03 |
Pos logit contributions | |
igs | +0.037 |
often | +0.033 |
ind | +0.031 |
solar | +0.030 |
ot | +0.029 |
Neg logit contributions | |
written | -0.037 |
aback | -0.037 |
Gu | -0.036 |
comm | -0.035 |
source | -0.034 |
Token | flew |
Token ID | 13112 |
Feature activation | +2.88e-01 |
Pos logit contributions | |
igs | +0.000 |
often | +0.000 |
ot | +0.000 |
solar | +0.000 |
gut | +0.000 |
Neg logit contributions | |
written | -0.000 |
aback | -0.000 |
comm | -0.000 |
Gu | -0.000 |
source | -0.000 |
Token | very |
Token ID | 845 |
Feature activation | -2.86e+00 |
Pos logit contributions | |
written | +0.011 |
aback | +0.011 |
comm | +0.011 |
Gu | +0.011 |
hered | +0.010 |
Neg logit contributions | |
often | -0.010 |
igs | -0.010 |
ot | -0.009 |
solar | -0.008 |
lived | -0.008 |
Token | high |
Token ID | 1029 |
Feature activation | -5.34e-01 |
Pos logit contributions | |
lived | +0.116 |
solar | +0.112 |
ig | +0.109 |
belt | +0.106 |
ocol | +0.106 |
Neg logit contributions | |
right | -0.077 |
closer | -0.075 |
source | -0.074 |
higher | -0.074 |
comm | -0.070 |
Token | and |
Token ID | 290 |
Feature activation | -1.12e-01 |
Pos logit contributions | |
igs | +0.023 |
often | +0.022 |
ot | +0.022 |
solar | +0.021 |
lived | +0.021 |
Neg logit contributions | |
written | -0.015 |
aback | -0.014 |
comm | -0.014 |
source | -0.013 |
Gu | -0.013 |
Token | then |
Token ID | 788 |
Feature activation | -4.75e-01 |
Pos logit contributions | |
igs | +0.004 |
often | +0.004 |
ot | +0.003 |
solar | +0.003 |
gut | +0.003 |
Neg logit contributions | |
written | -0.004 |
aback | -0.004 |
comm | -0.004 |
Gu | -0.004 |
source | -0.004 |
Token | quickly |
Token ID | 2952 |
Feature activation | -3.39e-01 |
Pos logit contributions | |
igs | +0.016 |
often | +0.015 |
solar | +0.013 |
ot | +0.013 |
ind | +0.013 |
Neg logit contributions | |
written | -0.019 |
comm | -0.018 |
aback | -0.018 |
Gu | -0.018 |
source | -0.017 |
Token | came |
Token ID | 1625 |
Feature activation | +3.71e-01 |
Pos logit contributions | |
often | +0.013 |
igs | +0.013 |
solar | +0.011 |
ot | +0.011 |
gut | +0.011 |
Neg logit contributions | |
written | -0.012 |
comm | -0.011 |
aback | -0.011 |
Gu | -0.011 |
hered | -0.011 |
Token | to |
Token ID | 284 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
igs | +0.021 |
often | +0.020 |
ot | +0.019 |
lived | +0.019 |
ug | +0.019 |
Neg logit contributions | |
written | -0.010 |
Gu | -0.010 |
comm | -0.009 |
aback | -0.009 |
source | -0.008 |
Token | play |
Token ID | 711 |
Feature activation | +1.30e-01 |
Pos logit contributions | |
igs | +0.063 |
ind | +0.060 |
often | +0.059 |
ug | +0.058 |
goals | +0.058 |
Neg logit contributions | |
come | -0.043 |
bisc | -0.040 |
written | -0.038 |
Gu | -0.036 |
surprise | -0.036 |
Token | games |
Token ID | 1830 |
Feature activation | -4.08e-01 |
Pos logit contributions | |
written | +0.004 |
aback | +0.004 |
comm | +0.004 |
Gu | +0.004 |
hered | +0.004 |
Neg logit contributions | |
often | -0.005 |
igs | -0.005 |
ot | -0.005 |
solar | -0.005 |
lived | -0.005 |
Token | and |
Token ID | 290 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
igs | +0.019 |
often | +0.017 |
ot | +0.017 |
gut | +0.017 |
solar | +0.017 |
Neg logit contributions | |
written | -0.011 |
aback | -0.010 |
comm | -0.010 |
hered | -0.009 |
Gu | -0.009 |
Token | explore |
Token ID | 7301 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
igs | +0.005 |
often | +0.005 |
ot | +0.005 |
solar | +0.004 |
ug | +0.004 |
Neg logit contributions | |
written | -0.004 |
comm | -0.004 |
Gu | -0.004 |
aback | -0.004 |
source | -0.004 |
Token | outside |
Token ID | 2354 |
Feature activation | -2.47e+00 |
Pos logit contributions | |
belt | +0.074 |
ot | +0.070 |
igs | +0.070 |
oppy | +0.068 |
gut | +0.068 |
Neg logit contributions | |
such | -0.046 |
come | -0.044 |
written | -0.044 |
calling | -0.043 |
comm | -0.043 |
Token | . |
Token ID | 13 |
Feature activation | -8.51e-01 |
Pos logit contributions | |
igs | +0.130 |
oppy | +0.117 |
belt | +0.114 |
gut | +0.111 |
ience | +0.110 |
Neg logit contributions | |
such | -0.058 |
coming | -0.054 |
come | -0.053 |
How | -0.050 |
out | -0.049 |
Token | One |
Token ID | 1881 |
Feature activation | -7.10e-01 |
Pos logit contributions | |
igs | +0.026 |
often | +0.022 |
ot | +0.022 |
ug | +0.021 |
gut | +0.021 |
Neg logit contributions | |
Gu | -0.035 |
written | -0.034 |
aback | -0.034 |
bisc | -0.033 |
source | -0.033 |
Token | day |
Token ID | 1110 |
Feature activation | -6.61e-01 |
Pos logit contributions | |
igs | +0.027 |
often | +0.024 |
solar | +0.022 |
gut | +0.022 |
goals | +0.022 |
Neg logit contributions | |
written | -0.025 |
Gu | -0.024 |
bisc | -0.024 |
comm | -0.023 |
source | -0.023 |
Token | , |
Token ID | 11 |
Feature activation | -4.01e-01 |
Pos logit contributions | |
often | +0.022 |
igs | +0.022 |
solar | +0.020 |
gut | +0.019 |
ind | +0.019 |
Neg logit contributions | |
written | -0.025 |
aback | -0.025 |
hered | -0.024 |
Gu | -0.024 |
comm | -0.023 |
Token | Tim |
Token ID | 5045 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
igs | +0.014 |
often | +0.014 |
solar | +0.013 |
goals | +0.012 |
ot | +0.012 |
Neg logit contributions | |
written | -0.014 |
Gu | -0.014 |
aback | -0.014 |
comm | -0.014 |
source | -0.013 |
Token | yard |
Token ID | 12699 |
Feature activation | -9.78e-01 |
Pos logit contributions | |
igs | +0.056 |
ug | +0.056 |
often | +0.054 |
aro | +0.053 |
apy | +0.049 |
Neg logit contributions | |
bisc | -0.040 |
source | -0.037 |
ingredients | -0.037 |
comm | -0.037 |
written | -0.037 |
Token | with |
Token ID | 351 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
igs | +0.035 |
often | +0.030 |
solar | +0.029 |
gut | +0.029 |
ot | +0.028 |
Neg logit contributions | |
written | -0.037 |
comm | -0.034 |
source | -0.034 |
aback | -0.034 |
calling | -0.034 |
Token | many |
Token ID | 867 |
Feature activation | -2.18e+00 |
Pos logit contributions | |
igs | +0.076 |
belt | +0.075 |
oppy | +0.073 |
gut | +0.072 |
ug | +0.072 |
Neg logit contributions | |
written | -0.047 |
ingredients | -0.045 |
come | -0.044 |
treats | -0.044 |
surprise | -0.043 |
Token | branches |
Token ID | 13737 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
ot | +0.091 |
oppy | +0.089 |
belt | +0.087 |
ug | +0.087 |
solar | +0.084 |
Neg logit contributions | |
ingredients | -0.063 |
comm | -0.062 |
treats | -0.062 |
written | -0.058 |
news | -0.055 |
Token | . |
Token ID | 13 |
Feature activation | -2.38e-02 |
Pos logit contributions | |
igs | +0.042 |
solar | +0.040 |
often | +0.039 |
gut | +0.038 |
ind | +0.036 |
Neg logit contributions | |
written | -0.039 |
source | -0.035 |
calling | -0.034 |
aback | -0.034 |
come | -0.033 |
Token | They |
Token ID | 1119 |
Feature activation | -2.45e+00 |
Pos logit contributions | |
igs | +0.001 |
often | +0.001 |
ot | +0.000 |
solar | +0.000 |
gut | +0.000 |
Neg logit contributions | |
written | -0.001 |
aback | -0.001 |
Gu | -0.001 |
comm | -0.001 |
source | -0.001 |
Token | wanted |
Token ID | 2227 |
Feature activation | +6.11e-01 |
Pos logit contributions | |
igs | +0.132 |
gut | +0.128 |
instincts | +0.118 |
ind | +0.118 |
ug | +0.113 |
Neg logit contributions | |
written | -0.061 |
baked | -0.055 |
come | -0.052 |
seen | -0.051 |
appeared | -0.051 |
Token | to |
Token ID | 284 |
Feature activation | -8.38e-03 |
Pos logit contributions | |
aback | +0.019 |
comm | +0.019 |
written | +0.018 |
Gu | +0.018 |
hered | +0.018 |
Neg logit contributions | |
often | -0.026 |
igs | -0.025 |
ot | -0.022 |
solar | -0.022 |
lived | -0.022 |
Token | climb |
Token ID | 12080 |
Feature activation | -5.36e-01 |
Pos logit contributions | |
igs | +0.000 |
often | +0.000 |
ot | +0.000 |
solar | +0.000 |
lived | +0.000 |
Neg logit contributions | |
written | -0.000 |
aback | -0.000 |
comm | -0.000 |
Gu | -0.000 |
source | -0.000 |
Token | the |
Token ID | 262 |
Feature activation | -6.71e-01 |
Pos logit contributions | |
often | +0.019 |
igs | +0.019 |
ot | +0.018 |
solar | +0.017 |
gut | +0.017 |
Neg logit contributions | |
aback | -0.018 |
written | -0.018 |
source | -0.017 |
Gu | -0.017 |
comm | -0.017 |
Token | tree |
Token ID | 5509 |
Feature activation | +6.45e-03 |
Pos logit contributions | |
igs | +0.020 |
often | +0.020 |
ot | +0.019 |
ug | +0.018 |
apy | +0.018 |
Neg logit contributions | |
source | -0.027 |
comm | -0.026 |
written | -0.026 |
aback | -0.026 |
Gu | -0.025 |
Token | enjoyed |
Token ID | 8359 |
Feature activation | -7.79e-01 |
Pos logit contributions | |
igs | +0.064 |
ug | +0.056 |
solar | +0.054 |
ot | +0.054 |
gut | +0.053 |
Neg logit contributions | |
written | -0.039 |
comm | -0.037 |
aback | -0.035 |
come | -0.034 |
announced | -0.034 |
Token | his |
Token ID | 465 |
Feature activation | -5.08e-02 |
Pos logit contributions | |
igs | +0.024 |
often | +0.022 |
ot | +0.021 |
solar | +0.021 |
ug | +0.021 |
Neg logit contributions | |
written | -0.031 |
comm | -0.029 |
Gu | -0.029 |
saying | -0.029 |
aback | -0.029 |
Token | toast |
Token ID | 27805 |
Feature activation | +5.50e-01 |
Pos logit contributions | |
often | +0.002 |
igs | +0.002 |
ot | +0.002 |
solar | +0.002 |
lived | +0.002 |
Neg logit contributions | |
written | -0.002 |
aback | -0.002 |
comm | -0.002 |
Gu | -0.002 |
bisc | -0.002 |
Token | with |
Token ID | 351 |
Feature activation | -4.02e-01 |
Pos logit contributions | |
aback | +0.021 |
Gu | +0.021 |
written | +0.021 |
comm | +0.021 |
source | +0.019 |
Neg logit contributions | |
often | -0.019 |
igs | -0.018 |
ot | -0.016 |
lived | -0.015 |
solar | -0.015 |
Token | jam |
Token ID | 16853 |
Feature activation | +3.10e-01 |
Pos logit contributions | |
igs | +0.013 |
often | +0.012 |
solar | +0.011 |
ot | +0.011 |
ug | +0.010 |
Neg logit contributions | |
written | -0.016 |
aback | -0.016 |
comm | -0.016 |
source | -0.015 |
bisc | -0.015 |
Token | very |
Token ID | 845 |
Feature activation | -3.26e+00 |
Pos logit contributions | |
written | +0.013 |
aback | +0.013 |
comm | +0.013 |
Gu | +0.012 |
source | +0.012 |
Neg logit contributions | |
often | -0.009 |
igs | -0.009 |
ot | -0.008 |
solar | -0.008 |
lived | -0.008 |
Token | much |
Token ID | 881 |
Feature activation | -3.14e-01 |
Pos logit contributions | |
solar | +0.133 |
igs | +0.126 |
ships | +0.122 |
agons | +0.118 |
hedge | +0.118 |
Neg logit contributions | |
sure | -0.087 |
cake | -0.084 |
once | -0.081 |
written | -0.078 |
come | -0.077 |
Token | . |
Token ID | 13 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
igs | +0.010 |
often | +0.009 |
ot | +0.008 |
solar | +0.008 |
lived | +0.008 |
Neg logit contributions | |
written | -0.013 |
aback | -0.013 |
comm | -0.013 |
bisc | -0.012 |
Gu | -0.012 |
Token | The |
Token ID | 383 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
igs | +0.056 |
often | +0.051 |
ts | +0.049 |
ug | +0.048 |
gut | +0.048 |
Neg logit contributions | |
aback | -0.025 |
written | -0.024 |
Gu | -0.024 |
comm | -0.023 |
How | -0.023 |
Token | end |
Token ID | 886 |
Feature activation | -5.03e-01 |
Pos logit contributions | |
igs | +0.004 |
often | +0.004 |
ot | +0.003 |
solar | +0.003 |
lived | +0.003 |
Neg logit contributions | |
written | -0.006 |
comm | -0.006 |
aback | -0.006 |
Gu | -0.006 |
source | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | +6.54e-01 |
Pos logit contributions | |
igs | +0.017 |
often | +0.016 |
solar | +0.014 |
ot | +0.014 |
ug | +0.014 |
Neg logit contributions | |
written | -0.020 |
aback | -0.020 |
comm | -0.019 |
source | -0.018 |
bisc | -0.018 |
Token | a |
Token ID | 257 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
aback | +0.048 |
comm | +0.046 |
hered | +0.045 |
written | +0.045 |
Gu | +0.044 |
Neg logit contributions | |
often | -0.047 |
igs | -0.043 |
lived | -0.042 |
ot | -0.040 |
solar | -0.038 |
Token | time |
Token ID | 640 |
Feature activation | -4.35e-02 |
Pos logit contributions | |
written | +0.034 |
aback | +0.034 |
Gu | +0.033 |
comm | +0.032 |
source | +0.030 |
Neg logit contributions | |
often | -0.046 |
igs | -0.042 |
ot | -0.040 |
lived | -0.038 |
solar | -0.038 |
Token | there |
Token ID | 612 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
igs | +0.001 |
often | +0.001 |
ot | +0.001 |
solar | +0.001 |
lived | +0.001 |
Neg logit contributions | |
written | -0.002 |
aback | -0.002 |
comm | -0.002 |
Gu | -0.002 |
hered | -0.002 |
Token | was |
Token ID | 373 |
Feature activation | +8.39e-01 |
Pos logit contributions | |
igs | +0.004 |
often | +0.004 |
ot | +0.004 |
solar | +0.004 |
gut | +0.004 |
Neg logit contributions | |
written | -0.003 |
aback | -0.003 |
comm | -0.003 |
Gu | -0.003 |
hered | -0.003 |
Token | an |
Token ID | 281 |
Feature activation | -2.48e+00 |
Pos logit contributions | |
aback | +0.028 |
comm | +0.027 |
written | +0.027 |
Gu | +0.027 |
hered | +0.025 |
Neg logit contributions | |
often | -0.032 |
igs | -0.031 |
lived | -0.029 |
ot | -0.029 |
solar | -0.028 |
Token | ant |
Token ID | 1885 |
Feature activation | -3.34e+00 |
Pos logit contributions | |
apy | +0.096 |
igs | +0.094 |
belt | +0.085 |
often | +0.085 |
oppy | +0.081 |
Neg logit contributions | |
comm | -0.079 |
written | -0.075 |
news | -0.074 |
calling | -0.073 |
saying | -0.071 |
Token | called |
Token ID | 1444 |
Feature activation | -7.73e-01 |
Pos logit contributions | |
igs | +0.151 |
apy | +0.143 |
belt | +0.137 |
goals | +0.136 |
gut | +0.133 |
Neg logit contributions | |
calling | -0.084 |
telling | -0.080 |
saying | -0.077 |
written | -0.075 |
source | -0.073 |
Token | Jack |
Token ID | 3619 |
Feature activation | -2.38e+00 |
Pos logit contributions | |
igs | +0.035 |
often | +0.035 |
ot | +0.032 |
solar | +0.032 |
lived | +0.031 |
Neg logit contributions | |
aback | -0.020 |
written | -0.020 |
comm | -0.019 |
Gu | -0.018 |
source | -0.018 |
Token | . |
Token ID | 13 |
Feature activation | -7.01e-01 |
Pos logit contributions | |
igs | +0.121 |
apy | +0.121 |
belt | +0.112 |
gut | +0.108 |
aro | +0.104 |
Neg logit contributions | |
written | -0.065 |
calling | -0.050 |
saying | -0.049 |
come | -0.049 |
seen | -0.047 |
Token | Jack |
Token ID | 3619 |
Feature activation | -2.79e+00 |
Pos logit contributions | |
igs | +0.035 |
often | +0.032 |
ot | +0.031 |
ug | +0.031 |
aro | +0.030 |
Neg logit contributions | |
aback | -0.017 |
written | -0.017 |
Gu | -0.016 |
comm | -0.015 |
source | -0.015 |
Token | was |
Token ID | 373 |
Feature activation | -2.28e-01 |
Pos logit contributions | |
igs | +0.128 |
gut | +0.119 |
lights | +0.116 |
nam | +0.115 |
ug | +0.113 |
Neg logit contributions | |
written | -0.082 |
happened | -0.078 |
meant | -0.077 |
appeared | -0.073 |
's | -0.071 |