Token | Jas |
Token ID | 21961 |
Feature activation | +2.74e+00 |
Pos logit contributions | |
their | +0.011 |
Their | +0.010 |
both | +0.009 |
Ben | +0.009 |
mouths | +0.008 |
Neg logit contributions | |
outage | -0.040 |
coat | -0.038 |
bush | -0.037 |
stump | -0.037 |
smanship | -0.035 |
Token | mine |
Token ID | 3810 |
Feature activation | +6.13e-01 |
Pos logit contributions | |
outage | +0.074 |
coat | +0.071 |
ock | +0.066 |
bush | +0.065 |
adows | +0.063 |
Neg logit contributions | |
their | -0.068 |
Their | -0.064 |
mouths | -0.063 |
our | -0.062 |
Ben | -0.061 |
Token | grabbed |
Token ID | 13176 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
outage | +0.020 |
coat | +0.019 |
bush | +0.018 |
stump | +0.017 |
adows | +0.017 |
Neg logit contributions | |
their | -0.012 |
Their | -0.012 |
our | -0.011 |
mouths | -0.011 |
Ben | -0.010 |
Token | some |
Token ID | 617 |
Feature activation | +4.41e+00 |
Pos logit contributions | |
outage | +0.048 |
coat | +0.047 |
bush | +0.044 |
stump | +0.043 |
ock | +0.043 |
Neg logit contributions | |
Their | -0.024 |
mouths | -0.022 |
their | -0.021 |
both | -0.020 |
our | -0.020 |
Token | tw |
Token ID | 665 |
Feature activation | +2.28e+00 |
Pos logit contributions | |
outage | +0.139 |
coat | +0.125 |
bush | +0.123 |
stump | +0.122 |
rito | +0.114 |
Neg logit contributions | |
their | -0.102 |
both | -0.093 |
at | -0.091 |
Their | -0.091 |
Ben | -0.088 |
Token | igs |
Token ID | 9235 |
Feature activation | +8.65e+00 |
Pos logit contributions | |
outage | +0.065 |
stump | +0.053 |
coat | +0.052 |
bush | +0.051 |
smanship | +0.049 |
Neg logit contributions | |
their | -0.061 |
both | -0.059 |
at | -0.059 |
our | -0.054 |
mouths | -0.053 |
Token | that |
Token ID | 326 |
Feature activation | +2.04e+00 |
Pos logit contributions | |
outage | +0.346 |
coat | +0.319 |
stump | +0.315 |
bush | +0.314 |
remedy | +0.303 |
Neg logit contributions | |
their | -0.127 |
both | -0.111 |
at | -0.108 |
Their | -0.101 |
Ben | -0.095 |
Token | she |
Token ID | 673 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
outage | +0.068 |
stump | +0.059 |
coat | +0.059 |
bush | +0.057 |
pleasures | +0.056 |
Neg logit contributions | |
their | -0.046 |
both | -0.042 |
at | -0.041 |
Ben | -0.040 |
Their | -0.039 |
Token | had |
Token ID | 550 |
Feature activation | -6.26e-01 |
Pos logit contributions | |
outage | +0.004 |
coat | +0.003 |
bush | +0.003 |
stump | +0.003 |
smanship | +0.003 |
Neg logit contributions | |
their | -0.002 |
both | -0.002 |
Their | -0.002 |
at | -0.002 |
Ben | -0.002 |
Token | found |
Token ID | 1043 |
Feature activation | +4.74e-01 |
Pos logit contributions | |
their | +0.012 |
both | +0.011 |
Their | +0.011 |
at | +0.010 |
Ben | +0.010 |
Neg logit contributions | |
outage | -0.022 |
coat | -0.020 |
bush | -0.020 |
stump | -0.020 |
smanship | -0.019 |
Token | and |
Token ID | 290 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
outage | +0.018 |
coat | +0.017 |
stump | +0.016 |
bush | +0.016 |
smanship | +0.016 |
Neg logit contributions | |
their | -0.008 |
both | -0.007 |
at | -0.007 |
Ben | -0.006 |
Their | -0.006 |
Token | home |
Token ID | 1363 |
Feature activation | +3.72e-01 |
Pos logit contributions | |
their | +0.010 |
Their | +0.009 |
both | +0.009 |
at | +0.009 |
Ben | +0.009 |
Neg logit contributions | |
outage | -0.013 |
coat | -0.012 |
bush | -0.012 |
stump | -0.012 |
smanship | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | -7.96e-01 |
Pos logit contributions | |
outage | +0.015 |
coat | +0.014 |
bush | +0.014 |
stump | +0.014 |
rito | +0.013 |
Neg logit contributions | |
their | -0.005 |
both | -0.004 |
at | -0.004 |
Their | -0.004 |
our | -0.004 |
Token | She |
Token ID | 1375 |
Feature activation | +4.71e-01 |
Pos logit contributions | |
their | +0.016 |
both | +0.014 |
at | +0.014 |
mouths | +0.014 |
faces | +0.014 |
Neg logit contributions | |
outage | -0.025 |
coat | -0.024 |
stump | -0.024 |
bush | -0.024 |
ock | -0.021 |
Token | gathered |
Token ID | 9272 |
Feature activation | +7.44e-01 |
Pos logit contributions | |
outage | +0.015 |
coat | +0.014 |
bush | +0.014 |
stump | +0.014 |
smanship | +0.013 |
Neg logit contributions | |
their | -0.010 |
Their | -0.009 |
both | -0.009 |
Ben | -0.008 |
at | -0.008 |
Token | tw |
Token ID | 665 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
outage | +0.027 |
coat | +0.025 |
bush | +0.025 |
stump | +0.025 |
smanship | +0.023 |
Neg logit contributions | |
their | -0.012 |
Their | -0.011 |
both | -0.011 |
Ben | -0.010 |
at | -0.010 |
Token | igs |
Token ID | 9235 |
Feature activation | +7.13e+00 |
Pos logit contributions | |
outage | +0.035 |
coat | +0.029 |
stump | +0.028 |
bush | +0.027 |
ock | +0.026 |
Neg logit contributions | |
their | -0.042 |
both | -0.040 |
at | -0.039 |
our | -0.037 |
Their | -0.037 |
Token | and |
Token ID | 290 |
Feature activation | -8.25e-01 |
Pos logit contributions | |
outage | +0.295 |
coat | +0.272 |
stump | +0.270 |
bush | +0.266 |
remedy | +0.259 |
Neg logit contributions | |
their | -0.101 |
both | -0.086 |
at | -0.081 |
Their | -0.075 |
Ben | -0.073 |
Token | leaves |
Token ID | 5667 |
Feature activation | +3.53e+00 |
Pos logit contributions | |
their | +0.020 |
both | +0.019 |
Ben | +0.017 |
mouths | +0.017 |
at | +0.017 |
Neg logit contributions | |
outage | -0.028 |
coat | -0.023 |
bush | -0.023 |
stump | -0.022 |
reetings | -0.022 |
Token | and |
Token ID | 290 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
outage | +0.151 |
coat | +0.136 |
stump | +0.134 |
remedy | +0.132 |
bush | +0.132 |
Neg logit contributions | |
their | -0.051 |
both | -0.041 |
at | -0.041 |
Their | -0.034 |
Ben | -0.032 |
Token | rocks |
Token ID | 12586 |
Feature activation | +2.06e+00 |
Pos logit contributions | |
their | +0.027 |
both | +0.025 |
Ben | +0.023 |
at | +0.023 |
Their | +0.022 |
Neg logit contributions | |
outage | -0.038 |
coat | -0.033 |
bush | -0.033 |
stump | -0.032 |
ock | -0.031 |
Token | , |
Token ID | 11 |
Feature activation | -2.52e-01 |
Pos logit contributions | |
outage | +0.088 |
coat | +0.079 |
stump | +0.079 |
bush | +0.078 |
remedy | +0.078 |
Neg logit contributions | |
their | -0.028 |
both | -0.024 |
at | -0.024 |
Their | -0.019 |
Ben | -0.018 |
Token | z |
Token ID | 1976 |
Feature activation | -2.20e+00 |
Pos logit contributions | |
their | +0.019 |
Their | +0.018 |
both | +0.017 |
Ben | +0.016 |
Tom | +0.016 |
Neg logit contributions | |
outage | -0.029 |
coat | -0.027 |
stump | -0.027 |
bush | -0.027 |
remedy | -0.025 |
Token | ipped |
Token ID | 3949 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
Their | +0.055 |
their | +0.055 |
both | +0.048 |
faces | +0.047 |
our | +0.047 |
Neg logit contributions | |
coat | -0.057 |
outage | -0.054 |
iest | -0.052 |
row | -0.050 |
ock | -0.050 |
Token | around |
Token ID | 1088 |
Feature activation | +8.45e-01 |
Pos logit contributions | |
outage | +0.035 |
coat | +0.034 |
stump | +0.033 |
bush | +0.032 |
ock | +0.031 |
Neg logit contributions | |
Their | -0.018 |
their | -0.018 |
both | -0.016 |
mouths | -0.016 |
Ben | -0.016 |
Token | collecting |
Token ID | 13157 |
Feature activation | +4.24e-01 |
Pos logit contributions | |
outage | +0.030 |
stump | +0.029 |
coat | +0.028 |
bush | +0.028 |
ock | +0.027 |
Neg logit contributions | |
Their | -0.013 |
mouths | -0.012 |
their | -0.012 |
both | -0.011 |
our | -0.010 |
Token | tw |
Token ID | 665 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
outage | +0.012 |
coat | +0.011 |
bush | +0.011 |
stump | +0.011 |
ock | +0.010 |
Neg logit contributions | |
their | -0.010 |
Their | -0.010 |
both | -0.009 |
Ben | -0.009 |
Tom | -0.009 |
Token | igs |
Token ID | 9235 |
Feature activation | +7.07e+00 |
Pos logit contributions | |
outage | +0.028 |
coat | +0.023 |
stump | +0.022 |
bush | +0.022 |
remedy | +0.021 |
Neg logit contributions | |
their | -0.035 |
both | -0.034 |
at | -0.033 |
Their | -0.032 |
Ben | -0.032 |
Token | and |
Token ID | 290 |
Feature activation | -6.82e-01 |
Pos logit contributions | |
outage | +0.280 |
coat | +0.260 |
bush | +0.255 |
stump | +0.254 |
remedy | +0.245 |
Neg logit contributions | |
their | -0.104 |
both | -0.093 |
at | -0.089 |
Their | -0.084 |
Ben | -0.081 |
Token | leaves |
Token ID | 5667 |
Feature activation | +3.15e+00 |
Pos logit contributions | |
their | +0.016 |
both | +0.015 |
Ben | +0.014 |
at | +0.014 |
mouths | +0.014 |
Neg logit contributions | |
outage | -0.022 |
coat | -0.020 |
bush | -0.019 |
ock | -0.018 |
stump | -0.018 |
Token | , |
Token ID | 11 |
Feature activation | +5.70e-01 |
Pos logit contributions | |
outage | +0.131 |
coat | +0.120 |
bush | +0.118 |
stump | +0.117 |
remedy | +0.114 |
Neg logit contributions | |
their | -0.044 |
both | -0.038 |
at | -0.037 |
Their | -0.032 |
Ben | -0.031 |
Token | he |
Token ID | 339 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
outage | +0.020 |
coat | +0.019 |
bush | +0.018 |
stump | +0.018 |
smanship | +0.017 |
Neg logit contributions | |
their | -0.011 |
both | -0.010 |
Their | -0.010 |
at | -0.009 |
Ben | -0.009 |
Token | z |
Token ID | 1976 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
their | +0.022 |
both | +0.021 |
at | +0.020 |
Their | +0.020 |
Ben | +0.019 |
Neg logit contributions | |
outage | -0.035 |
coat | -0.032 |
bush | -0.031 |
stump | -0.031 |
smanship | -0.030 |
Token | . |
Token ID | 13 |
Feature activation | -6.32e-01 |
Pos logit contributions | |
outage | +0.043 |
coat | +0.039 |
bush | +0.039 |
stump | +0.039 |
smanship | +0.037 |
Neg logit contributions | |
their | -0.020 |
Their | -0.020 |
both | -0.019 |
Ben | -0.018 |
at | -0.018 |
Token | He |
Token ID | 679 |
Feature activation | -2.16e-01 |
Pos logit contributions | |
their | +0.012 |
both | +0.011 |
mouths | +0.011 |
our | +0.011 |
at | +0.011 |
Neg logit contributions | |
outage | -0.020 |
coat | -0.019 |
stump | -0.019 |
bush | -0.018 |
remedy | -0.017 |
Token | grabbed |
Token ID | 13176 |
Feature activation | +9.22e-01 |
Pos logit contributions | |
their | +0.005 |
Their | +0.004 |
both | +0.004 |
Ben | +0.004 |
Tom | +0.004 |
Neg logit contributions | |
outage | -0.007 |
coat | -0.006 |
stump | -0.006 |
bush | -0.006 |
smanship | -0.006 |
Token | different |
Token ID | 1180 |
Feature activation | +1.99e+00 |
Pos logit contributions | |
outage | +0.030 |
coat | +0.029 |
stump | +0.029 |
ock | +0.027 |
bush | +0.027 |
Neg logit contributions | |
Their | -0.015 |
their | -0.013 |
mouths | -0.013 |
our | -0.013 |
both | -0.012 |
Token | tw |
Token ID | 665 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
outage | +0.060 |
coat | +0.055 |
bush | +0.054 |
stump | +0.053 |
rito | +0.050 |
Neg logit contributions | |
their | -0.049 |
both | -0.045 |
Their | -0.044 |
at | -0.044 |
Ben | -0.042 |
Token | igs |
Token ID | 9235 |
Feature activation | +6.85e+00 |
Pos logit contributions | |
outage | +0.029 |
coat | +0.024 |
stump | +0.024 |
bush | +0.023 |
remedy | +0.022 |
Neg logit contributions | |
their | -0.032 |
both | -0.031 |
at | -0.030 |
our | -0.028 |
mouths | -0.028 |
Token | and |
Token ID | 290 |
Feature activation | -7.17e-01 |
Pos logit contributions | |
outage | +0.274 |
coat | +0.256 |
bush | +0.251 |
stump | +0.251 |
remedy | +0.240 |
Neg logit contributions | |
their | -0.097 |
both | -0.086 |
at | -0.082 |
Their | -0.078 |
Ben | -0.075 |
Token | branches |
Token ID | 13737 |
Feature activation | +2.88e+00 |
Pos logit contributions | |
their | +0.017 |
both | +0.016 |
Ben | +0.015 |
at | +0.015 |
mouths | +0.015 |
Neg logit contributions | |
outage | -0.023 |
coat | -0.021 |
bush | -0.020 |
stump | -0.019 |
smanship | -0.019 |
Token | , |
Token ID | 11 |
Feature activation | +3.28e-01 |
Pos logit contributions | |
outage | +0.117 |
coat | +0.108 |
bush | +0.107 |
stump | +0.106 |
remedy | +0.105 |
Neg logit contributions | |
their | -0.042 |
both | -0.036 |
at | -0.036 |
Their | -0.031 |
Tom | -0.030 |
Token | some |
Token ID | 617 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
outage | +0.012 |
coat | +0.011 |
bush | +0.010 |
stump | +0.010 |
smanship | +0.010 |
Neg logit contributions | |
their | -0.006 |
both | -0.006 |
at | -0.006 |
Their | -0.005 |
Ben | -0.005 |
Token | grass |
Token ID | 8701 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
outage | +0.053 |
coat | +0.047 |
bush | +0.046 |
stump | +0.045 |
smanship | +0.043 |
Neg logit contributions | |
their | -0.040 |
both | -0.036 |
at | -0.035 |
Ben | -0.033 |
Their | -0.033 |
Token | . |
Token ID | 13 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
outage | +0.022 |
coat | +0.020 |
bush | +0.020 |
stump | +0.020 |
ock | +0.018 |
Neg logit contributions | |
their | -0.012 |
Their | -0.011 |
both | -0.010 |
at | -0.010 |
Ben | -0.010 |
Token | He |
Token ID | 679 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
outage | +0.007 |
coat | +0.006 |
bush | +0.006 |
smanship | +0.006 |
stump | +0.006 |
Neg logit contributions | |
their | -0.002 |
Their | -0.002 |
Tom | -0.002 |
Ben | -0.001 |
both | -0.001 |
Token | was |
Token ID | 373 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
outage | +0.036 |
coat | +0.035 |
stump | +0.034 |
bush | +0.032 |
ock | +0.031 |
Neg logit contributions | |
their | -0.029 |
Their | -0.028 |
both | -0.027 |
mouths | -0.027 |
our | -0.026 |
Token | a |
Token ID | 257 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
outage | +0.054 |
coat | +0.053 |
stump | +0.052 |
bush | +0.049 |
remedy | +0.047 |
Neg logit contributions | |
their | -0.029 |
Their | -0.028 |
mouths | -0.027 |
faces | -0.027 |
both | -0.025 |
Token | mis |
Token ID | 2984 |
Feature activation | +3.26e+00 |
Pos logit contributions | |
outage | +0.041 |
coat | +0.039 |
stump | +0.038 |
bush | +0.036 |
remedy | +0.035 |
Neg logit contributions | |
their | -0.027 |
Their | -0.026 |
mouths | -0.025 |
both | -0.025 |
cks | -0.025 |
Token | chie |
Token ID | 3043 |
Feature activation | +6.80e+00 |
Pos logit contributions | |
outage | +0.081 |
coat | +0.073 |
bush | +0.072 |
stump | +0.070 |
pleasures | +0.067 |
Neg logit contributions | |
both | -0.087 |
their | -0.085 |
at | -0.082 |
Their | -0.081 |
our | -0.077 |
Token | vous |
Token ID | 31222 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
outage | +0.090 |
coat | +0.071 |
stump | +0.065 |
bush | +0.064 |
ock | +0.055 |
Neg logit contributions | |
their | -0.277 |
both | -0.265 |
Their | -0.263 |
Ben | -0.262 |
mouths | -0.260 |
Token | little |
Token ID | 1310 |
Feature activation | +2.30e+00 |
Pos logit contributions | |
outage | +0.037 |
coat | +0.035 |
bush | +0.034 |
stump | +0.034 |
smanship | +0.032 |
Neg logit contributions | |
their | -0.021 |
Their | -0.019 |
both | -0.019 |
at | -0.018 |
Ben | -0.018 |
Token | baby |
Token ID | 5156 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
outage | +0.081 |
bush | +0.075 |
coat | +0.074 |
pleasures | +0.072 |
reetings | +0.072 |
Neg logit contributions | |
their | -0.045 |
at | -0.042 |
both | -0.041 |
Ben | -0.041 |
Tom | -0.038 |
Token | and |
Token ID | 290 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
outage | +0.057 |
coat | +0.054 |
bush | +0.053 |
stump | +0.052 |
smanship | +0.050 |
Neg logit contributions | |
their | -0.022 |
Their | -0.019 |
both | -0.019 |
at | -0.018 |
Ben | -0.018 |
Token | always |
Token ID | 1464 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
outage | +0.055 |
coat | +0.051 |
bush | +0.051 |
stump | +0.049 |
rito | +0.047 |
Neg logit contributions | |
their | -0.030 |
both | -0.027 |
Their | -0.026 |
Ben | -0.025 |
Tom | -0.025 |
Token | She |
Token ID | 1375 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
outage | +0.015 |
coat | +0.014 |
bush | +0.013 |
stump | +0.013 |
rito | +0.013 |
Neg logit contributions | |
their | -0.009 |
Their | -0.008 |
both | -0.008 |
Ben | -0.008 |
Tom | -0.008 |
Token | used |
Token ID | 973 |
Feature activation | +2.31e+00 |
Pos logit contributions | |
outage | +0.048 |
bush | +0.043 |
coat | +0.043 |
stump | +0.043 |
pleasures | +0.041 |
Neg logit contributions | |
their | -0.022 |
both | -0.020 |
Their | -0.019 |
at | -0.019 |
Ben | -0.019 |
Token | some |
Token ID | 617 |
Feature activation | +2.38e+00 |
Pos logit contributions | |
outage | +0.095 |
coat | +0.086 |
bush | +0.086 |
stump | +0.085 |
smanship | +0.083 |
Neg logit contributions | |
their | -0.035 |
both | -0.030 |
Their | -0.028 |
at | -0.028 |
Ben | -0.027 |
Token | big |
Token ID | 1263 |
Feature activation | +4.38e-01 |
Pos logit contributions | |
outage | +0.082 |
bush | +0.074 |
smanship | +0.070 |
reetings | +0.069 |
coat | +0.069 |
Neg logit contributions | |
their | -0.054 |
at | -0.049 |
both | -0.048 |
Their | -0.046 |
faces | -0.043 |
Token | tw |
Token ID | 665 |
Feature activation | +9.51e-01 |
Pos logit contributions | |
outage | +0.016 |
bush | +0.015 |
reetings | +0.014 |
coat | +0.014 |
ancer | +0.014 |
Neg logit contributions | |
their | -0.009 |
at | -0.008 |
mouths | -0.008 |
both | -0.008 |
hands | -0.008 |
Token | igs |
Token ID | 9235 |
Feature activation | +6.52e+00 |
Pos logit contributions | |
outage | +0.027 |
stump | +0.022 |
coat | +0.021 |
bush | +0.021 |
smanship | +0.021 |
Neg logit contributions | |
their | -0.025 |
both | -0.024 |
at | -0.024 |
mouths | -0.023 |
our | -0.023 |
Token | for |
Token ID | 329 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
outage | +0.255 |
coat | +0.236 |
stump | +0.232 |
bush | +0.232 |
remedy | +0.221 |
Neg logit contributions | |
their | -0.102 |
both | -0.090 |
at | -0.087 |
Their | -0.085 |
Ben | -0.080 |
Token | the |
Token ID | 262 |
Feature activation | +1.84e-01 |
Pos logit contributions | |
their | +0.002 |
Their | +0.002 |
at | +0.002 |
both | +0.002 |
mouths | +0.002 |
Neg logit contributions | |
outage | -0.004 |
coat | -0.004 |
stump | -0.004 |
bush | -0.004 |
ock | -0.004 |
Token | walls |
Token ID | 7714 |
Feature activation | +2.30e+00 |
Pos logit contributions | |
outage | +0.006 |
reetings | +0.005 |
stump | +0.005 |
bush | +0.005 |
smanship | +0.005 |
Neg logit contributions | |
their | -0.004 |
both | -0.004 |
mom | -0.004 |
at | -0.004 |
Ben | -0.004 |
Token | and |
Token ID | 290 |
Feature activation | -9.00e-01 |
Pos logit contributions | |
outage | +0.094 |
bush | +0.086 |
coat | +0.085 |
stump | +0.085 |
remedy | +0.084 |
Neg logit contributions | |
their | -0.033 |
both | -0.029 |
at | -0.029 |
Their | -0.025 |
Tom | -0.023 |
Token | a |
Token ID | 257 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
their | +0.018 |
both | +0.017 |
Ben | +0.016 |
at | +0.016 |
Their | +0.016 |
Neg logit contributions | |
outage | -0.032 |
coat | -0.029 |
bush | -0.028 |
stump | -0.028 |
smanship | -0.027 |
Token | small |
Token ID | 1402 |
Feature activation | +9.79e-01 |
Pos logit contributions | |
outage | +0.030 |
coat | +0.028 |
bush | +0.027 |
stump | +0.027 |
smanship | +0.025 |
Neg logit contributions | |
their | -0.021 |
Their | -0.020 |
both | -0.019 |
Ben | -0.019 |
at | -0.018 |
Token | nest |
Token ID | 16343 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
outage | +0.032 |
coat | +0.029 |
bush | +0.028 |
stump | +0.028 |
rito | +0.027 |
Neg logit contributions | |
their | -0.022 |
both | -0.019 |
at | -0.019 |
Their | -0.019 |
Ben | -0.019 |
Token | made |
Token ID | 925 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
outage | +0.050 |
coat | +0.046 |
stump | +0.045 |
bush | +0.044 |
remedy | +0.044 |
Neg logit contributions | |
their | -0.021 |
at | -0.018 |
both | -0.018 |
Their | -0.017 |
Tom | -0.016 |
Token | of |
Token ID | 286 |
Feature activation | +7.33e-01 |
Pos logit contributions | |
outage | +0.067 |
coat | +0.061 |
bush | +0.061 |
stump | +0.060 |
ock | +0.058 |
Neg logit contributions | |
their | -0.031 |
Their | -0.031 |
both | -0.029 |
mouths | -0.028 |
Ben | -0.028 |
Token | tw |
Token ID | 665 |
Feature activation | +8.91e-01 |
Pos logit contributions | |
outage | +0.023 |
coat | +0.022 |
bush | +0.021 |
stump | +0.020 |
smanship | +0.019 |
Neg logit contributions | |
their | -0.018 |
both | -0.016 |
Their | -0.015 |
Ben | -0.015 |
at | -0.015 |
Token | igs |
Token ID | 9235 |
Feature activation | +6.49e+00 |
Pos logit contributions | |
outage | +0.026 |
coat | +0.022 |
stump | +0.021 |
remedy | +0.021 |
bush | +0.020 |
Neg logit contributions | |
their | -0.023 |
both | -0.023 |
at | -0.022 |
our | -0.021 |
mouths | -0.020 |
Token | . |
Token ID | 13 |
Feature activation | -7.30e-01 |
Pos logit contributions | |
outage | +0.272 |
coat | +0.251 |
stump | +0.248 |
bush | +0.248 |
remedy | +0.245 |
Neg logit contributions | |
their | -0.085 |
both | -0.074 |
at | -0.071 |
Their | -0.055 |
our | -0.054 |
Token | The |
Token ID | 383 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
their | +0.014 |
both | +0.012 |
at | +0.012 |
mouths | +0.012 |
faces | +0.012 |
Neg logit contributions | |
outage | -0.024 |
coat | -0.023 |
stump | -0.022 |
bush | -0.022 |
ock | -0.020 |
Token | bird |
Token ID | 6512 |
Feature activation | -8.80e-01 |
Pos logit contributions | |
outage | +0.041 |
coat | +0.038 |
bush | +0.036 |
stump | +0.036 |
smanship | +0.035 |
Neg logit contributions | |
their | -0.023 |
both | -0.022 |
at | -0.021 |
Ben | -0.021 |
Their | -0.020 |
Token | ie |
Token ID | 494 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
their | +0.017 |
both | +0.016 |
Their | +0.016 |
at | +0.015 |
Ben | +0.015 |
Neg logit contributions | |
outage | -0.030 |
coat | -0.028 |
bush | -0.027 |
stump | -0.027 |
smanship | -0.025 |
Token | loved |
Token ID | 6151 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
outage | +0.005 |
coat | +0.005 |
bush | +0.005 |
stump | +0.004 |
smanship | +0.004 |
Neg logit contributions | |
their | -0.002 |
both | -0.002 |
Their | -0.002 |
at | -0.002 |
Ben | -0.002 |
Token | reached |
Token ID | 4251 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
their | +0.035 |
Their | +0.033 |
both | +0.031 |
Ben | +0.030 |
mouths | +0.030 |
Neg logit contributions | |
outage | -0.054 |
coat | -0.051 |
bush | -0.050 |
stump | -0.049 |
remedy | -0.046 |
Token | out |
Token ID | 503 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
outage | +0.050 |
stump | +0.048 |
coat | +0.047 |
bush | +0.047 |
rito | +0.044 |
Neg logit contributions | |
Their | -0.025 |
their | -0.024 |
mouths | -0.023 |
both | -0.023 |
faces | -0.022 |
Token | for |
Token ID | 329 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
their | +0.028 |
Their | +0.028 |
mouths | +0.026 |
both | +0.026 |
Ben | +0.026 |
Neg logit contributions | |
outage | -0.057 |
stump | -0.053 |
bush | -0.053 |
coat | -0.053 |
remedy | -0.049 |
Token | some |
Token ID | 617 |
Feature activation | +2.32e+00 |
Pos logit contributions | |
outage | +0.005 |
stump | +0.005 |
coat | +0.005 |
bush | +0.005 |
remedy | +0.005 |
Neg logit contributions | |
Their | -0.002 |
their | -0.002 |
mouths | -0.002 |
at | -0.002 |
both | -0.002 |
Token | tw |
Token ID | 665 |
Feature activation | +5.40e-01 |
Pos logit contributions | |
outage | +0.078 |
coat | +0.070 |
bush | +0.069 |
stump | +0.066 |
rito | +0.063 |
Neg logit contributions | |
their | -0.051 |
at | -0.048 |
both | -0.047 |
Ben | -0.043 |
mouths | -0.043 |
Token | igs |
Token ID | 9235 |
Feature activation | +6.46e+00 |
Pos logit contributions | |
outage | +0.016 |
stump | +0.013 |
coat | +0.013 |
bush | +0.013 |
smanship | +0.013 |
Neg logit contributions | |
their | -0.013 |
at | -0.013 |
both | -0.013 |
our | -0.012 |
mouths | -0.011 |
Token | and |
Token ID | 290 |
Feature activation | -9.38e-01 |
Pos logit contributions | |
outage | +0.263 |
coat | +0.243 |
bush | +0.239 |
stump | +0.239 |
remedy | +0.231 |
Neg logit contributions | |
their | -0.090 |
both | -0.079 |
at | -0.077 |
Their | -0.069 |
Ben | -0.067 |
Token | made |
Token ID | 925 |
Feature activation | +2.84e+00 |
Pos logit contributions | |
their | +0.020 |
both | +0.019 |
Ben | +0.017 |
at | +0.017 |
Their | +0.017 |
Neg logit contributions | |
outage | -0.033 |
coat | -0.029 |
bush | -0.028 |
smanship | -0.027 |
stump | -0.027 |
Token | the |
Token ID | 262 |
Feature activation | +2.06e+00 |
Pos logit contributions | |
outage | +0.097 |
coat | +0.092 |
stump | +0.091 |
bush | +0.091 |
ock | +0.088 |
Neg logit contributions | |
Their | -0.045 |
their | -0.042 |
mouths | -0.040 |
both | -0.039 |
at | -0.038 |
Token | bed |
Token ID | 3996 |
Feature activation | +3.75e-01 |
Pos logit contributions | |
outage | +0.065 |
coat | +0.058 |
bush | +0.056 |
stump | +0.054 |
ock | +0.052 |
Neg logit contributions | |
their | -0.046 |
both | -0.045 |
at | -0.042 |
Ben | -0.042 |
mouths | -0.041 |
Token | stronger |
Token ID | 7387 |
Feature activation | -6.42e-01 |
Pos logit contributions | |
outage | +0.013 |
coat | +0.012 |
stump | +0.011 |
bush | +0.011 |
rito | +0.011 |
Neg logit contributions | |
their | -0.008 |
both | -0.007 |
at | -0.007 |
Their | -0.006 |
Ben | -0.006 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.74e+00 |
Pos logit contributions | |
outage | +0.005 |
coat | +0.005 |
bush | +0.005 |
stump | +0.005 |
smanship | +0.004 |
Neg logit contributions | |
their | -0.002 |
both | -0.002 |
Their | -0.002 |
at | -0.001 |
mouths | -0.001 |
Token | Peter |
Token ID | 19727 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
outage | +0.060 |
coat | +0.056 |
stump | +0.055 |
bush | +0.055 |
smanship | +0.051 |
Neg logit contributions | |
their | -0.032 |
Their | -0.029 |
both | -0.029 |
at | -0.027 |
mouths | -0.027 |
Token | was |
Token ID | 373 |
Feature activation | +8.11e-01 |
Pos logit contributions | |
their | +0.002 |
both | +0.002 |
Their | +0.002 |
at | +0.002 |
Ben | +0.002 |
Neg logit contributions | |
outage | -0.004 |
coat | -0.004 |
bush | -0.004 |
stump | -0.004 |
smanship | -0.004 |
Token | a |
Token ID | 257 |
Feature activation | +5.10e-01 |
Pos logit contributions | |
outage | +0.025 |
coat | +0.025 |
stump | +0.023 |
bush | +0.023 |
remedy | +0.021 |
Neg logit contributions | |
their | -0.016 |
mouths | -0.015 |
Their | -0.015 |
faces | -0.015 |
our | -0.014 |
Token | mis |
Token ID | 2984 |
Feature activation | +2.85e+00 |
Pos logit contributions | |
outage | +0.015 |
coat | +0.015 |
stump | +0.014 |
bush | +0.014 |
remedy | +0.013 |
Neg logit contributions | |
their | -0.011 |
Their | -0.011 |
mouths | -0.010 |
faces | -0.010 |
cks | -0.009 |
Token | chie |
Token ID | 3043 |
Feature activation | +6.45e+00 |
Pos logit contributions | |
outage | +0.075 |
coat | +0.069 |
bush | +0.067 |
stump | +0.065 |
pleasures | +0.064 |
Neg logit contributions | |
both | -0.071 |
their | -0.066 |
at | -0.066 |
Their | -0.063 |
ra | -0.062 |
Token | vous |
Token ID | 31222 |
Feature activation | +6.76e-01 |
Pos logit contributions | |
outage | +0.091 |
coat | +0.074 |
bush | +0.069 |
stump | +0.068 |
ock | +0.057 |
Neg logit contributions | |
their | -0.255 |
Their | -0.244 |
both | -0.243 |
Ben | -0.240 |
mouths | -0.236 |
Token | 3 |
Token ID | 513 |
Feature activation | +3.70e+00 |
Pos logit contributions | |
outage | +0.021 |
coat | +0.020 |
stump | +0.019 |
bush | +0.019 |
ock | +0.018 |
Neg logit contributions | |
their | -0.015 |
Their | -0.014 |
both | -0.014 |
at | -0.013 |
Ben | -0.013 |
Token | year |
Token ID | 614 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
outage | +0.080 |
coat | +0.070 |
iest | +0.066 |
stump | +0.066 |
bush | +0.065 |
Neg logit contributions | |
Their | -0.111 |
their | -0.110 |
Ben | -0.107 |
mouths | -0.105 |
our | -0.105 |
Token | old |
Token ID | 1468 |
Feature activation | +3.61e+00 |
Pos logit contributions | |
outage | +0.036 |
coat | +0.032 |
bush | +0.031 |
stump | +0.031 |
ock | +0.028 |
Neg logit contributions | |
their | -0.045 |
Their | -0.042 |
both | -0.042 |
Ben | -0.041 |
mouths | -0.040 |
Token | who |
Token ID | 508 |
Feature activation | -5.93e-01 |
Pos logit contributions | |
outage | +0.123 |
coat | +0.115 |
stump | +0.112 |
bush | +0.110 |
smanship | +0.106 |
Neg logit contributions | |
their | -0.066 |
Their | -0.063 |
both | -0.060 |
mouths | -0.057 |
our | -0.057 |
Token | nest |
Token ID | 16343 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
Their | +0.019 |
Ben | +0.019 |
their | +0.018 |
Tom | +0.018 |
both | +0.017 |
Neg logit contributions | |
outage | -0.013 |
stump | -0.013 |
bush | -0.012 |
coat | -0.012 |
remedy | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | -5.17e-01 |
Pos logit contributions | |
outage | +0.047 |
coat | +0.044 |
bush | +0.042 |
stump | +0.042 |
pleasures | +0.042 |
Neg logit contributions | |
their | -0.015 |
both | -0.013 |
at | -0.013 |
Their | -0.011 |
our | -0.010 |
Token | She |
Token ID | 1375 |
Feature activation | +4.84e-01 |
Pos logit contributions | |
their | +0.010 |
both | +0.009 |
at | +0.009 |
our | +0.009 |
mouths | +0.009 |
Neg logit contributions | |
outage | -0.016 |
coat | -0.016 |
bush | -0.015 |
stump | -0.015 |
rito | -0.013 |
Token | collected |
Token ID | 7723 |
Feature activation | +8.55e-01 |
Pos logit contributions | |
outage | +0.016 |
coat | +0.015 |
bush | +0.015 |
stump | +0.015 |
smanship | +0.014 |
Neg logit contributions | |
their | -0.010 |
both | -0.009 |
Their | -0.009 |
at | -0.009 |
Ben | -0.008 |
Token | tw |
Token ID | 665 |
Feature activation | +9.94e-01 |
Pos logit contributions | |
outage | +0.029 |
coat | +0.028 |
bush | +0.027 |
stump | +0.027 |
rito | +0.025 |
Neg logit contributions | |
their | -0.015 |
Their | -0.014 |
both | -0.014 |
Ben | -0.013 |
at | -0.013 |
Token | igs |
Token ID | 9235 |
Feature activation | +6.40e+00 |
Pos logit contributions | |
outage | +0.024 |
coat | +0.020 |
stump | +0.019 |
bush | +0.019 |
smanship | +0.017 |
Neg logit contributions | |
their | -0.031 |
both | -0.030 |
at | -0.029 |
Their | -0.029 |
our | -0.028 |
Token | and |
Token ID | 290 |
Feature activation | -9.40e-01 |
Pos logit contributions | |
outage | +0.260 |
coat | +0.241 |
stump | +0.237 |
bush | +0.235 |
remedy | +0.226 |
Neg logit contributions | |
their | -0.091 |
both | -0.079 |
at | -0.075 |
Their | -0.073 |
Ben | -0.069 |
Token | leaves |
Token ID | 5667 |
Feature activation | +3.27e+00 |
Pos logit contributions | |
their | +0.023 |
both | +0.021 |
Ben | +0.019 |
at | +0.019 |
Their | +0.019 |
Neg logit contributions | |
outage | -0.031 |
coat | -0.027 |
bush | -0.026 |
smanship | -0.025 |
stump | -0.025 |
Token | , |
Token ID | 11 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
outage | +0.137 |
coat | +0.125 |
stump | +0.122 |
bush | +0.121 |
pleasures | +0.119 |
Neg logit contributions | |
their | -0.047 |
both | -0.040 |
at | -0.039 |
Their | -0.035 |
Ben | -0.032 |
Token | and |
Token ID | 290 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
outage | +0.004 |
coat | +0.004 |
bush | +0.004 |
stump | +0.004 |
smanship | +0.004 |
Neg logit contributions | |
their | -0.002 |
both | -0.002 |
Their | -0.002 |
at | -0.002 |
Ben | -0.002 |
Token | the |
Token ID | 262 |
Feature activation | +4.67e-01 |
Pos logit contributions | |
their | +0.023 |
both | +0.021 |
Their | +0.020 |
at | +0.020 |
Ben | +0.020 |
Neg logit contributions | |
outage | -0.037 |
coat | -0.034 |
bush | -0.033 |
stump | -0.032 |
smanship | -0.031 |
Token | He |
Token ID | 679 |
Feature activation | +8.33e-02 |
Pos logit contributions | |
outage | +0.002 |
coat | +0.002 |
bush | +0.002 |
stump | +0.002 |
smanship | +0.002 |
Neg logit contributions | |
their | -0.001 |
Their | -0.001 |
both | -0.001 |
Tom | -0.001 |
Ben | -0.001 |
Token | carefully |
Token ID | 7773 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
outage | +0.003 |
coat | +0.003 |
bush | +0.003 |
stump | +0.003 |
pleasures | +0.003 |
Neg logit contributions | |
their | -0.002 |
both | -0.001 |
Their | -0.001 |
at | -0.001 |
Ben | -0.001 |
Token | put |
Token ID | 1234 |
Feature activation | +2.48e+00 |
Pos logit contributions | |
outage | +0.039 |
coat | +0.035 |
bush | +0.035 |
stump | +0.034 |
smanship | +0.032 |
Neg logit contributions | |
their | -0.024 |
both | -0.022 |
Their | -0.022 |
at | -0.022 |
Ben | -0.021 |
Token | the |
Token ID | 262 |
Feature activation | +2.60e+00 |
Pos logit contributions | |
outage | +0.099 |
coat | +0.094 |
stump | +0.092 |
bush | +0.092 |
rito | +0.088 |
Neg logit contributions | |
their | -0.031 |
Their | -0.029 |
both | -0.027 |
Ben | -0.025 |
at | -0.025 |
Token | tw |
Token ID | 665 |
Feature activation | +9.96e-01 |
Pos logit contributions | |
outage | +0.085 |
coat | +0.078 |
bush | +0.074 |
ock | +0.072 |
reetings | +0.072 |
Neg logit contributions | |
both | -0.056 |
their | -0.056 |
at | -0.052 |
our | -0.051 |
mom | -0.051 |
Token | igs |
Token ID | 9235 |
Feature activation | +6.39e+00 |
Pos logit contributions | |
outage | +0.031 |
coat | +0.028 |
stump | +0.026 |
smanship | +0.026 |
remedy | +0.025 |
Neg logit contributions | |
both | -0.021 |
at | -0.021 |
their | -0.021 |
ra | -0.020 |
our | -0.019 |
Token | and |
Token ID | 290 |
Feature activation | -7.56e-01 |
Pos logit contributions | |
outage | +0.260 |
coat | +0.240 |
bush | +0.236 |
stump | +0.236 |
remedy | +0.226 |
Neg logit contributions | |
their | -0.091 |
both | -0.080 |
at | -0.077 |
Their | -0.071 |
Ben | -0.068 |
Token | grass |
Token ID | 8701 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
their | +0.019 |
both | +0.017 |
Ben | +0.016 |
at | +0.016 |
mouths | +0.016 |
Neg logit contributions | |
outage | -0.024 |
coat | -0.022 |
bush | -0.021 |
stump | -0.020 |
smanship | -0.020 |
Token | and |
Token ID | 290 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
outage | +0.042 |
coat | +0.039 |
bush | +0.038 |
stump | +0.038 |
smanship | +0.036 |
Neg logit contributions | |
their | -0.019 |
Their | -0.017 |
both | -0.017 |
Ben | -0.016 |
at | -0.016 |
Token | leaves |
Token ID | 5667 |
Feature activation | +2.68e+00 |
Pos logit contributions | |
their | +0.023 |
both | +0.021 |
Their | +0.020 |
Ben | +0.020 |
at | +0.020 |
Neg logit contributions | |
outage | -0.036 |
coat | -0.033 |
bush | -0.032 |
stump | -0.032 |
smanship | -0.030 |
Token | together |
Token ID | 1978 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
outage | +0.106 |
coat | +0.098 |
bush | +0.097 |
stump | +0.096 |
smanship | +0.092 |
Neg logit contributions | |
their | -0.041 |
both | -0.036 |
at | -0.034 |
Their | -0.033 |
Ben | -0.032 |
Token | ! |
Token ID | 0 |
Feature activation | +3.78e-02 |
Pos logit contributions | |
outage | +0.072 |
coat | +0.067 |
stump | +0.065 |
bush | +0.065 |
pleasures | +0.064 |
Neg logit contributions | |
their | -0.026 |
at | -0.024 |
both | -0.023 |
Tom | -0.020 |
Ben | -0.019 |
Token | He |
Token ID | 679 |
Feature activation | -3.14e-01 |
Pos logit contributions | |
outage | +0.001 |
stump | +0.001 |
bush | +0.001 |
coat | +0.001 |
remedy | +0.001 |
Neg logit contributions | |
their | -0.001 |
faces | -0.001 |
mouths | -0.001 |
our | -0.001 |
both | -0.001 |
Token | gathered |
Token ID | 9272 |
Feature activation | +8.21e-01 |
Pos logit contributions | |
their | +0.006 |
both | +0.006 |
at | +0.005 |
Their | +0.005 |
Ben | +0.005 |
Neg logit contributions | |
outage | -0.011 |
coat | -0.010 |
bush | -0.010 |
stump | -0.010 |
smanship | -0.009 |
Token | some |
Token ID | 617 |
Feature activation | +2.94e+00 |
Pos logit contributions | |
outage | +0.031 |
coat | +0.029 |
bush | +0.029 |
stump | +0.029 |
smanship | +0.027 |
Neg logit contributions | |
their | -0.013 |
both | -0.011 |
Their | -0.011 |
at | -0.011 |
Ben | -0.011 |
Token | tw |
Token ID | 665 |
Feature activation | +9.31e-01 |
Pos logit contributions | |
outage | +0.100 |
coat | +0.090 |
bush | +0.084 |
stump | +0.082 |
ancer | +0.082 |
Neg logit contributions | |
their | -0.069 |
at | -0.064 |
both | -0.062 |
our | -0.056 |
mouths | -0.054 |
Token | igs |
Token ID | 9235 |
Feature activation | +6.36e+00 |
Pos logit contributions | |
outage | +0.026 |
coat | +0.022 |
stump | +0.021 |
bush | +0.020 |
smanship | +0.020 |
Neg logit contributions | |
their | -0.026 |
both | -0.025 |
at | -0.025 |
our | -0.024 |
mouths | -0.023 |
Token | and |
Token ID | 290 |
Feature activation | -5.40e-01 |
Pos logit contributions | |
outage | +0.263 |
coat | +0.244 |
stump | +0.240 |
bush | +0.238 |
remedy | +0.230 |
Neg logit contributions | |
their | -0.089 |
both | -0.077 |
at | -0.074 |
Their | -0.068 |
Ben | -0.064 |
Token | leaves |
Token ID | 5667 |
Feature activation | +3.13e+00 |
Pos logit contributions | |
their | +0.013 |
both | +0.012 |
at | +0.010 |
Ben | +0.010 |
mouths | +0.010 |
Neg logit contributions | |
outage | -0.019 |
coat | -0.017 |
bush | -0.016 |
reetings | -0.015 |
smanship | -0.015 |
Token | , |
Token ID | 11 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
outage | +0.131 |
coat | +0.119 |
stump | +0.117 |
bush | +0.116 |
remedy | +0.114 |
Neg logit contributions | |
their | -0.047 |
both | -0.039 |
at | -0.039 |
Their | -0.033 |
Tom | -0.031 |
Token | and |
Token ID | 290 |
Feature activation | -8.28e-01 |
Pos logit contributions | |
outage | +0.008 |
coat | +0.007 |
bush | +0.007 |
stump | +0.007 |
smanship | +0.007 |
Neg logit contributions | |
their | -0.003 |
both | -0.003 |
at | -0.003 |
Ben | -0.002 |
Their | -0.002 |
Token | organized |
Token ID | 8389 |
Feature activation | +9.84e-02 |
Pos logit contributions | |
their | +0.017 |
both | +0.016 |
at | +0.015 |
Ben | +0.014 |
Tom | +0.014 |
Neg logit contributions | |
outage | -0.029 |
coat | -0.026 |
bush | -0.026 |
stump | -0.025 |
smanship | -0.024 |
Token | would |
Token ID | 561 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
outage | +0.026 |
coat | +0.025 |
bush | +0.024 |
stump | +0.024 |
smanship | +0.022 |
Neg logit contributions | |
their | -0.018 |
Their | -0.017 |
both | -0.016 |
Ben | -0.016 |
our | -0.016 |
Token | pick |
Token ID | 2298 |
Feature activation | +1.85e+00 |
Pos logit contributions | |
outage | +0.003 |
coat | +0.003 |
bush | +0.003 |
stump | +0.003 |
smanship | +0.003 |
Neg logit contributions | |
their | -0.002 |
both | -0.002 |
Their | -0.002 |
at | -0.002 |
Ben | -0.002 |
Token | up |
Token ID | 510 |
Feature activation | -9.89e-01 |
Pos logit contributions | |
outage | +0.063 |
coat | +0.059 |
bush | +0.059 |
stump | +0.058 |
ock | +0.055 |
Neg logit contributions | |
their | -0.034 |
Their | -0.032 |
both | -0.031 |
Ben | -0.029 |
at | -0.029 |
Token | some |
Token ID | 617 |
Feature activation | +3.11e+00 |
Pos logit contributions | |
Their | +0.015 |
their | +0.015 |
both | +0.014 |
Ben | +0.013 |
mouths | +0.013 |
Neg logit contributions | |
outage | -0.034 |
coat | -0.033 |
bush | -0.033 |
stump | -0.032 |
ock | -0.030 |
Token | tw |
Token ID | 665 |
Feature activation | +8.50e-01 |
Pos logit contributions | |
outage | +0.104 |
coat | +0.096 |
stump | +0.092 |
bush | +0.092 |
rito | +0.087 |
Neg logit contributions | |
their | -0.068 |
at | -0.063 |
both | -0.061 |
Their | -0.057 |
our | -0.056 |
Token | igs |
Token ID | 9235 |
Feature activation | +6.35e+00 |
Pos logit contributions | |
outage | +0.026 |
coat | +0.023 |
stump | +0.022 |
bush | +0.021 |
smanship | +0.020 |
Neg logit contributions | |
their | -0.021 |
both | -0.019 |
at | -0.019 |
our | -0.018 |
mouths | -0.018 |
Token | and |
Token ID | 290 |
Feature activation | -3.77e-01 |
Pos logit contributions | |
outage | +0.254 |
coat | +0.237 |
stump | +0.232 |
bush | +0.231 |
rito | +0.222 |
Neg logit contributions | |
their | -0.091 |
both | -0.079 |
at | -0.076 |
Their | -0.074 |
Ben | -0.071 |
Token | leaves |
Token ID | 5667 |
Feature activation | +3.38e+00 |
Pos logit contributions | |
their | +0.009 |
both | +0.008 |
Their | +0.008 |
Ben | +0.008 |
at | +0.007 |
Neg logit contributions | |
outage | -0.012 |
coat | -0.011 |
bush | -0.011 |
stump | -0.011 |
rito | -0.010 |
Token | , |
Token ID | 11 |
Feature activation | +4.26e-01 |
Pos logit contributions | |
outage | +0.137 |
coat | +0.126 |
stump | +0.124 |
bush | +0.122 |
remedy | +0.119 |
Neg logit contributions | |
their | -0.052 |
both | -0.043 |
at | -0.042 |
Their | -0.039 |
Ben | -0.038 |
Token | and |
Token ID | 290 |
Feature activation | -4.37e-01 |
Pos logit contributions | |
outage | +0.015 |
coat | +0.014 |
bush | +0.014 |
stump | +0.014 |
rito | +0.013 |
Neg logit contributions | |
their | -0.008 |
both | -0.007 |
Their | -0.007 |
at | -0.007 |
Ben | -0.007 |
Token | carefully |
Token ID | 7773 |
Feature activation | +5.31e-01 |
Pos logit contributions | |
their | +0.009 |
both | +0.009 |
Their | +0.009 |
at | +0.008 |
Ben | +0.008 |
Neg logit contributions | |
outage | -0.014 |
coat | -0.013 |
bush | -0.013 |
stump | -0.013 |
smanship | -0.012 |
Token | , |
Token ID | 11 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
Their | +0.004 |
faces | +0.004 |
cks | +0.004 |
ast | +0.004 |
mouths | +0.004 |
Neg logit contributions | |
outage | -0.005 |
bush | -0.005 |
stump | -0.005 |
smanship | -0.004 |
boat | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | +3.31e-01 |
Pos logit contributions | |
outage | +0.004 |
bush | +0.004 |
stump | +0.004 |
colder | +0.003 |
boat | +0.003 |
Neg logit contributions | |
Their | -0.002 |
faces | -0.002 |
mouths | -0.002 |
ast | -0.002 |
cks | -0.002 |
Token | birds |
Token ID | 10087 |
Feature activation | -8.72e-01 |
Pos logit contributions | |
outage | +0.010 |
coat | +0.009 |
bush | +0.008 |
stump | +0.008 |
rito | +0.008 |
Neg logit contributions | |
their | -0.008 |
both | -0.008 |
at | -0.008 |
Their | -0.008 |
Ben | -0.008 |
Token | brought |
Token ID | 3181 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
their | +0.017 |
Their | +0.016 |
both | +0.015 |
Ben | +0.015 |
Tom | +0.015 |
Neg logit contributions | |
outage | -0.029 |
coat | -0.027 |
bush | -0.026 |
stump | -0.026 |
ock | -0.025 |
Token | tw |
Token ID | 665 |
Feature activation | +9.03e-01 |
Pos logit contributions | |
outage | +0.004 |
coat | +0.004 |
stump | +0.004 |
bush | +0.004 |
wood | +0.003 |
Neg logit contributions | |
Their | -0.001 |
ast | -0.001 |
Ben | -0.001 |
mouths | -0.001 |
their | -0.001 |
Token | igs |
Token ID | 9235 |
Feature activation | +6.31e+00 |
Pos logit contributions | |
outage | +0.024 |
coat | +0.020 |
stump | +0.019 |
bush | +0.018 |
smanship | +0.017 |
Neg logit contributions | |
their | -0.027 |
both | -0.026 |
at | -0.025 |
our | -0.024 |
mouths | -0.024 |
Token | and |
Token ID | 290 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
outage | +0.248 |
coat | +0.231 |
stump | +0.226 |
bush | +0.226 |
smanship | +0.215 |
Neg logit contributions | |
their | -0.095 |
both | -0.083 |
Their | -0.080 |
at | -0.079 |
Ben | -0.074 |
Token | leaves |
Token ID | 5667 |
Feature activation | +2.78e+00 |
Pos logit contributions | |
their | +0.031 |
both | +0.028 |
Their | +0.026 |
Ben | +0.026 |
mouths | +0.026 |
Neg logit contributions | |
outage | -0.037 |
coat | -0.034 |
bush | -0.032 |
stump | -0.031 |
smanship | -0.031 |
Token | , |
Token ID | 11 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
outage | +0.108 |
coat | +0.100 |
stump | +0.098 |
bush | +0.098 |
smanship | +0.094 |
Neg logit contributions | |
their | -0.044 |
both | -0.038 |
at | -0.037 |
Their | -0.037 |
Ben | -0.033 |
Token | and |
Token ID | 290 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
their | +0.002 |
both | +0.002 |
Their | +0.002 |
at | +0.002 |
Ben | +0.002 |
Neg logit contributions | |
outage | -0.005 |
coat | -0.005 |
bush | -0.005 |
stump | -0.005 |
smanship | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
their | +0.022 |
Their | +0.020 |
both | +0.020 |
at | +0.019 |
Ben | +0.019 |
Neg logit contributions | |
outage | -0.044 |
coat | -0.041 |
bush | -0.040 |
stump | -0.040 |
smanship | -0.037 |
Token | small |
Token ID | 1402 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
their | +0.012 |
both | +0.011 |
Ben | +0.010 |
at | +0.010 |
mom | +0.010 |
Neg logit contributions | |
outage | -0.029 |
coat | -0.026 |
bush | -0.026 |
pleasures | -0.026 |
ock | -0.025 |
Token | boy |
Token ID | 2933 |
Feature activation | +7.76e-01 |
Pos logit contributions | |
outage | +0.044 |
adows | +0.040 |
coat | +0.040 |
reetings | +0.040 |
bush | +0.040 |
Neg logit contributions | |
their | -0.023 |
at | -0.022 |
Ben | -0.021 |
Tom | -0.021 |
mom | -0.021 |
Token | with |
Token ID | 351 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
outage | +0.024 |
stump | +0.023 |
coat | +0.022 |
bush | +0.021 |
remedy | +0.020 |
Neg logit contributions | |
their | -0.016 |
Their | -0.016 |
mouths | -0.015 |
our | -0.014 |
both | -0.014 |
Token | a |
Token ID | 257 |
Feature activation | -5.72e-01 |
Pos logit contributions | |
their | +0.021 |
Their | +0.020 |
both | +0.018 |
at | +0.018 |
Ben | +0.018 |
Neg logit contributions | |
outage | -0.047 |
coat | -0.044 |
stump | -0.044 |
bush | -0.042 |
remedy | -0.041 |
Token | mis |
Token ID | 2984 |
Feature activation | +2.25e+00 |
Pos logit contributions | |
their | +0.011 |
both | +0.010 |
Their | +0.010 |
at | +0.009 |
Ben | +0.009 |
Neg logit contributions | |
outage | -0.020 |
coat | -0.018 |
bush | -0.018 |
stump | -0.018 |
ock | -0.017 |
Token | chie |
Token ID | 3043 |
Feature activation | +6.31e+00 |
Pos logit contributions | |
outage | +0.060 |
bush | +0.054 |
coat | +0.054 |
pleasures | +0.051 |
stump | +0.051 |
Neg logit contributions | |
both | -0.055 |
at | -0.053 |
their | -0.051 |
ra | -0.049 |
Their | -0.048 |
Token | vous |
Token ID | 31222 |
Feature activation | -4.60e-01 |
Pos logit contributions | |
outage | +0.093 |
coat | +0.078 |
bush | +0.073 |
stump | +0.072 |
smanship | +0.061 |
Neg logit contributions | |
their | -0.243 |
Their | -0.233 |
both | -0.232 |
at | -0.228 |
Ben | -0.225 |
Token | tw |
Token ID | 665 |
Feature activation | +7.71e-01 |
Pos logit contributions | |
their | +0.008 |
at | +0.007 |
Ben | +0.007 |
Tom | +0.007 |
Their | +0.007 |
Neg logit contributions | |
outage | -0.017 |
bush | -0.015 |
coat | -0.015 |
stump | -0.015 |
smanship | -0.014 |
Token | inkle |
Token ID | 19894 |
Feature activation | +5.53e-01 |
Pos logit contributions | |
outage | +0.025 |
stump | +0.022 |
coat | +0.022 |
bush | +0.022 |
smanship | +0.021 |
Neg logit contributions | |
their | -0.015 |
at | -0.015 |
both | -0.015 |
Ben | -0.013 |
Their | -0.013 |
Token | in |
Token ID | 287 |
Feature activation | -2.64e-01 |
Pos logit contributions | |
outage | +0.022 |
coat | +0.020 |
bush | +0.020 |
stump | +0.020 |
smanship | +0.019 |
Neg logit contributions | |
their | -0.008 |
Their | -0.007 |
both | -0.007 |
Ben | -0.006 |
Tom | -0.006 |
Token | his |
Token ID | 465 |
Feature activation | +2.68e-01 |
Pos logit contributions | |
Their | +0.004 |
both | +0.004 |
mouths | +0.004 |
at | +0.004 |
faces | +0.004 |
Neg logit contributions | |
stump | -0.008 |
outage | -0.008 |
coat | -0.007 |
remedy | -0.007 |
kinds | -0.007 |
Token | and |
Token ID | 290 |
Feature activation | -7.30e-01 |
Pos logit contributions | |
outage | +0.034 |
coat | +0.031 |
stump | +0.030 |
bush | +0.030 |
rito | +0.028 |
Neg logit contributions | |
their | -0.030 |
both | -0.028 |
Their | -0.027 |
at | -0.027 |
Ben | -0.026 |
Token | snapped |
Token ID | 20821 |
Feature activation | +7.92e-01 |
Pos logit contributions | |
their | +0.013 |
Their | +0.012 |
both | +0.012 |
at | +0.011 |
Ben | +0.011 |
Neg logit contributions | |
outage | -0.025 |
coat | -0.024 |
bush | -0.023 |
stump | -0.023 |
smanship | -0.021 |
Token | off |
Token ID | 572 |
Feature activation | -7.24e-01 |
Pos logit contributions | |
outage | +0.024 |
coat | +0.024 |
bush | +0.023 |
stump | +0.023 |
rito | +0.022 |
Neg logit contributions | |
Their | -0.013 |
mouths | -0.011 |
their | -0.011 |
ast | -0.011 |
eg | -0.010 |
Token | some |
Token ID | 617 |
Feature activation | +2.01e+00 |
Pos logit contributions | |
Their | +0.010 |
their | +0.009 |
both | +0.009 |
mouths | +0.009 |
Ben | +0.009 |
Neg logit contributions | |
outage | -0.026 |
coat | -0.025 |
stump | -0.024 |
bush | -0.024 |
rito | -0.022 |
Token | tw |
Token ID | 665 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
outage | +0.060 |
coat | +0.055 |
bush | +0.054 |
stump | +0.054 |
smanship | +0.050 |
Neg logit contributions | |
their | -0.047 |
Their | -0.044 |
both | -0.043 |
at | -0.042 |
Ben | -0.042 |
Token | igs |
Token ID | 9235 |
Feature activation | +6.30e+00 |
Pos logit contributions | |
outage | +0.005 |
coat | +0.004 |
stump | +0.004 |
bush | +0.004 |
remedy | +0.004 |
Neg logit contributions | |
their | -0.005 |
both | -0.004 |
at | -0.004 |
Their | -0.004 |
our | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | -8.46e-01 |
Pos logit contributions | |
outage | +0.245 |
coat | +0.229 |
bush | +0.224 |
stump | +0.224 |
smanship | +0.213 |
Neg logit contributions | |
their | -0.093 |
both | -0.082 |
Their | -0.079 |
at | -0.078 |
Ben | -0.074 |
Token | He |
Token ID | 679 |
Feature activation | -5.49e-01 |
Pos logit contributions | |
their | +0.015 |
both | +0.013 |
faces | +0.013 |
at | +0.013 |
mouths | +0.013 |
Neg logit contributions | |
outage | -0.028 |
coat | -0.026 |
bush | -0.026 |
stump | -0.026 |
remedy | -0.023 |
Token | held |
Token ID | 2714 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
their | +0.011 |
Their | +0.011 |
both | +0.010 |
our | +0.010 |
Ben | +0.009 |
Neg logit contributions | |
outage | -0.017 |
coat | -0.017 |
bush | -0.016 |
stump | -0.016 |
remedy | -0.015 |
Token | them |
Token ID | 606 |
Feature activation | +2.32e+00 |
Pos logit contributions | |
coat | +0.058 |
outage | +0.057 |
bush | +0.056 |
stump | +0.056 |
rito | +0.055 |
Neg logit contributions | |
Their | -0.027 |
their | -0.025 |
mouths | -0.023 |
faces | -0.022 |
our | -0.022 |
Token | up |
Token ID | 510 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
outage | +0.075 |
coat | +0.072 |
bush | +0.070 |
stump | +0.070 |
smanship | +0.065 |
Neg logit contributions | |
their | -0.043 |
Their | -0.043 |
Ben | -0.039 |
Tom | -0.038 |
mouths | -0.038 |
Token | was |
Token ID | 373 |
Feature activation | -3.36e-01 |
Pos logit contributions | |
outage | +0.040 |
coat | +0.037 |
bush | +0.036 |
stump | +0.036 |
smanship | +0.034 |
Neg logit contributions | |
their | -0.020 |
Their | -0.018 |
both | -0.018 |
at | -0.017 |
Ben | -0.017 |
Token | a |
Token ID | 257 |
Feature activation | -2.79e-01 |
Pos logit contributions | |
their | +0.006 |
Their | +0.006 |
both | +0.005 |
at | +0.005 |
mouths | +0.005 |
Neg logit contributions | |
outage | -0.012 |
coat | -0.011 |
stump | -0.011 |
bush | -0.010 |
rito | -0.010 |
Token | box |
Token ID | 3091 |
Feature activation | +2.00e+00 |
Pos logit contributions | |
their | +0.006 |
Their | +0.006 |
both | +0.006 |
at | +0.006 |
Ben | +0.006 |
Neg logit contributions | |
outage | -0.008 |
coat | -0.008 |
stump | -0.008 |
bush | -0.007 |
remedy | -0.007 |
Token | of |
Token ID | 286 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
outage | +0.074 |
coat | +0.069 |
bush | +0.068 |
stump | +0.067 |
smanship | +0.063 |
Neg logit contributions | |
their | -0.033 |
both | -0.030 |
Their | -0.029 |
at | -0.028 |
Ben | -0.028 |
Token | ch |
Token ID | 442 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
outage | +0.057 |
coat | +0.053 |
bush | +0.053 |
stump | +0.051 |
rated | +0.049 |
Neg logit contributions | |
their | -0.034 |
both | -0.029 |
Their | -0.028 |
our | -0.027 |
Ben | -0.027 |
Token | ocol |
Token ID | 4668 |
Feature activation | +6.30e+00 |
Pos logit contributions | |
their | +0.043 |
both | +0.040 |
Their | +0.040 |
at | +0.039 |
Ben | +0.039 |
Neg logit contributions | |
outage | -0.050 |
coat | -0.046 |
bush | -0.045 |
stump | -0.044 |
smanship | -0.041 |
Token | ates |
Token ID | 689 |
Feature activation | +6.35e-01 |
Pos logit contributions | |
outage | +0.169 |
coat | +0.155 |
stump | +0.150 |
bush | +0.150 |
rito | +0.139 |
Neg logit contributions | |
their | -0.166 |
Their | -0.156 |
both | -0.154 |
Ben | -0.150 |
at | -0.148 |
Token | . |
Token ID | 13 |
Feature activation | -4.10e-01 |
Pos logit contributions | |
outage | +0.024 |
coat | +0.022 |
bush | +0.022 |
stump | +0.022 |
smanship | +0.021 |
Neg logit contributions | |
their | -0.010 |
both | -0.009 |
Their | -0.009 |
at | -0.008 |
Ben | -0.008 |
Token | Lily |
Token ID | 20037 |
Feature activation | +6.27e-01 |
Pos logit contributions | |
their | +0.009 |
faces | +0.009 |
both | +0.009 |
mouths | +0.009 |
our | +0.008 |
Neg logit contributions | |
stump | -0.010 |
outage | -0.010 |
opener | -0.010 |
bush | -0.009 |
coat | -0.009 |
Token | loved |
Token ID | 6151 |
Feature activation | +5.54e-02 |
Pos logit contributions | |
outage | +0.022 |
coat | +0.020 |
bush | +0.020 |
stump | +0.020 |
smanship | +0.018 |
Neg logit contributions | |
their | -0.012 |
Their | -0.011 |
both | -0.011 |
at | -0.010 |
Ben | -0.010 |
Token | ch |
Token ID | 442 |
Feature activation | -3.34e-01 |
Pos logit contributions | |
outage | +0.002 |
coat | +0.002 |
stump | +0.002 |
bush | +0.002 |
ock | +0.002 |
Neg logit contributions | |
Their | -0.001 |
their | -0.001 |
both | -0.001 |
at | -0.001 |
mouths | -0.001 |
Token | filled |
Token ID | 5901 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
their | +0.070 |
both | +0.065 |
Their | +0.064 |
at | +0.064 |
Ben | +0.061 |
Neg logit contributions | |
outage | -0.094 |
coat | -0.086 |
stump | -0.084 |
bush | -0.083 |
smanship | -0.078 |
Token | his |
Token ID | 465 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
stump | +0.042 |
bush | +0.042 |
outage | +0.042 |
coat | +0.040 |
remedy | +0.039 |
Neg logit contributions | |
mouths | -0.022 |
Their | -0.022 |
faces | -0.019 |
both | -0.019 |
at | -0.019 |
Token | wings |
Token ID | 12098 |
Feature activation | +2.85e+00 |
Pos logit contributions | |
outage | +0.041 |
stump | +0.039 |
coat | +0.039 |
bush | +0.038 |
remedy | +0.035 |
Neg logit contributions | |
their | -0.032 |
Their | -0.032 |
Ben | -0.031 |
both | -0.030 |
Tom | -0.030 |
Token | with |
Token ID | 351 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
outage | +0.125 |
coat | +0.114 |
remedy | +0.109 |
stump | +0.109 |
bush | +0.108 |
Neg logit contributions | |
their | -0.036 |
both | -0.035 |
at | -0.034 |
our | -0.023 |
Ben | -0.022 |
Token | tw |
Token ID | 665 |
Feature activation | +4.73e-01 |
Pos logit contributions | |
their | +0.033 |
Their | +0.030 |
both | +0.029 |
Ben | +0.028 |
at | +0.028 |
Neg logit contributions | |
outage | -0.069 |
coat | -0.064 |
bush | -0.063 |
stump | -0.063 |
smanship | -0.059 |
Token | igs |
Token ID | 9235 |
Feature activation | +6.29e+00 |
Pos logit contributions | |
outage | +0.014 |
coat | +0.012 |
stump | +0.012 |
bush | +0.011 |
remedy | +0.011 |
Neg logit contributions | |
their | -0.012 |
both | -0.012 |
at | -0.011 |
our | -0.011 |
mouths | -0.010 |
Token | it |
Token ID | 340 |
Feature activation | +8.93e-01 |
Pos logit contributions | |
outage | +0.261 |
coat | +0.242 |
stump | +0.240 |
bush | +0.238 |
remedy | +0.233 |
Neg logit contributions | |
their | -0.088 |
both | -0.075 |
at | -0.072 |
Their | -0.063 |
Ben | -0.061 |
Token | would |
Token ID | 561 |
Feature activation | -9.99e-01 |
Pos logit contributions | |
outage | +0.036 |
coat | +0.033 |
bush | +0.032 |
stump | +0.032 |
smanship | +0.031 |
Neg logit contributions | |
their | -0.013 |
both | -0.012 |
at | -0.012 |
Ben | -0.010 |
Their | -0.010 |
Token | give |
Token ID | 1577 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
their | +0.019 |
both | +0.019 |
at | +0.017 |
our | +0.016 |
Ben | +0.015 |
Neg logit contributions | |
outage | -0.035 |
coat | -0.032 |
bush | -0.031 |
smanship | -0.030 |
stump | -0.030 |
Token | him |
Token ID | 683 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
their | +0.019 |
both | +0.016 |
Their | +0.016 |
at | +0.015 |
Ben | +0.015 |
Neg logit contributions | |
outage | -0.052 |
coat | -0.048 |
stump | -0.047 |
bush | -0.047 |
smanship | -0.045 |
Token | a |
Token ID | 257 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
their | +0.019 |
both | +0.017 |
at | +0.016 |
our | +0.015 |
Their | +0.015 |
Neg logit contributions | |
outage | -0.046 |
coat | -0.042 |
stump | -0.041 |
bush | -0.041 |
smanship | -0.040 |
Token | it |
Token ID | 340 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
outage | +0.029 |
coat | +0.027 |
bush | +0.027 |
stump | +0.027 |
smanship | +0.026 |
Neg logit contributions | |
their | -0.009 |
both | -0.008 |
at | -0.008 |
Ben | -0.008 |
Tom | -0.008 |
Token | liked |
Token ID | 8288 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
outage | +0.038 |
coat | +0.035 |
smanship | +0.033 |
stump | +0.033 |
bush | +0.033 |
Neg logit contributions | |
their | -0.027 |
at | -0.025 |
both | -0.024 |
Their | -0.023 |
Ben | -0.022 |
Token | to |
Token ID | 284 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
their | +0.020 |
both | +0.018 |
Their | +0.018 |
at | +0.017 |
Ben | +0.017 |
Neg logit contributions | |
outage | -0.043 |
coat | -0.041 |
bush | -0.040 |
stump | -0.039 |
smanship | -0.038 |
Token | collect |
Token ID | 2824 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
outage | +0.063 |
coat | +0.056 |
bush | +0.055 |
smanship | +0.054 |
stump | +0.052 |
Neg logit contributions | |
their | -0.042 |
both | -0.038 |
Ben | -0.036 |
Their | -0.036 |
at | -0.035 |
Token | tw |
Token ID | 665 |
Feature activation | +9.12e-01 |
Pos logit contributions | |
outage | +0.039 |
coat | +0.035 |
bush | +0.033 |
stump | +0.033 |
smanship | +0.032 |
Neg logit contributions | |
their | -0.029 |
at | -0.027 |
both | -0.026 |
Their | -0.025 |
our | -0.025 |
Token | igs |
Token ID | 9235 |
Feature activation | +6.27e+00 |
Pos logit contributions | |
outage | +0.025 |
coat | +0.021 |
stump | +0.019 |
bush | +0.019 |
remedy | +0.019 |
Neg logit contributions | |
their | -0.026 |
both | -0.026 |
at | -0.025 |
our | -0.023 |
Ben | -0.023 |
Token | to |
Token ID | 284 |
Feature activation | +9.93e-01 |
Pos logit contributions | |
outage | +0.257 |
coat | +0.239 |
stump | +0.234 |
bush | +0.233 |
remedy | +0.227 |
Neg logit contributions | |
their | -0.089 |
both | -0.076 |
at | -0.075 |
Their | -0.068 |
Ben | -0.066 |
Token | make |
Token ID | 787 |
Feature activation | +2.07e+00 |
Pos logit contributions | |
outage | +0.032 |
coat | +0.029 |
bush | +0.028 |
stump | +0.027 |
smanship | +0.026 |
Neg logit contributions | |
their | -0.023 |
both | -0.021 |
Their | -0.020 |
Ben | -0.020 |
at | -0.020 |
Token | its |
Token ID | 663 |
Feature activation | +7.71e-01 |
Pos logit contributions | |
outage | +0.061 |
bush | +0.058 |
stump | +0.058 |
coat | +0.058 |
ock | +0.056 |
Neg logit contributions | |
Their | -0.042 |
their | -0.038 |
mouths | -0.037 |
Tom | -0.037 |
Ben | -0.036 |
Token | nest |
Token ID | 16343 |
Feature activation | +2.13e+00 |
Pos logit contributions | |
outage | +0.025 |
coat | +0.023 |
bush | +0.022 |
ock | +0.021 |
stump | +0.021 |
Neg logit contributions | |
their | -0.017 |
both | -0.017 |
at | -0.016 |
mouths | -0.015 |
our | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | +4.35e-02 |
Pos logit contributions | |
outage | +0.081 |
coat | +0.074 |
reetings | +0.071 |
remedy | +0.070 |
injection | +0.069 |
Neg logit contributions | |
their | -0.040 |
both | -0.036 |
at | -0.033 |
our | -0.030 |
faces | -0.028 |
Token | stack |
Token ID | 8931 |
Feature activation | +1.97e-01 |
Pos logit contributions | |
outage | +0.004 |
coat | +0.004 |
bush | +0.004 |
stump | +0.004 |
rito | +0.004 |
Neg logit contributions | |
their | -0.003 |
both | -0.003 |
Their | -0.003 |
at | -0.003 |
Ben | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
outage | +0.007 |
coat | +0.006 |
bush | +0.006 |
stump | +0.006 |
smanship | +0.006 |
Neg logit contributions | |
their | -0.004 |
Their | -0.004 |
both | -0.003 |
Ben | -0.003 |
Tom | -0.003 |
Token | They |
Token ID | 1119 |
Feature activation | +5.01e-01 |
Pos logit contributions | |
their | +0.002 |
our | +0.002 |
at | +0.002 |
cks | +0.002 |
wishes | +0.002 |
Neg logit contributions | |
outage | -0.003 |
stump | -0.003 |
bush | -0.003 |
coat | -0.003 |
First | -0.003 |
Token | gathered |
Token ID | 9272 |
Feature activation | +5.69e-01 |
Pos logit contributions | |
outage | +0.015 |
coat | +0.014 |
stump | +0.014 |
bush | +0.013 |
smanship | +0.013 |
Neg logit contributions | |
their | -0.012 |
Their | -0.011 |
both | -0.010 |
Ben | -0.010 |
at | -0.010 |
Token | tw |
Token ID | 665 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
outage | +0.018 |
coat | +0.017 |
bush | +0.017 |
stump | +0.016 |
smanship | +0.016 |
Neg logit contributions | |
Their | -0.010 |
their | -0.010 |
Ben | -0.009 |
Tom | -0.009 |
our | -0.009 |
Token | igs |
Token ID | 9235 |
Feature activation | +6.25e+00 |
Pos logit contributions | |
outage | +0.025 |
coat | +0.022 |
bush | +0.021 |
stump | +0.021 |
remedy | +0.018 |
Neg logit contributions | |
their | -0.040 |
both | -0.038 |
Their | -0.038 |
at | -0.037 |
Ben | -0.037 |
Token | , |
Token ID | 11 |
Feature activation | +6.26e-01 |
Pos logit contributions | |
outage | +0.248 |
coat | +0.231 |
stump | +0.226 |
bush | +0.226 |
rito | +0.214 |
Neg logit contributions | |
their | -0.092 |
both | -0.080 |
Their | -0.077 |
at | -0.075 |
Ben | -0.072 |
Token | stones |
Token ID | 14966 |
Feature activation | +2.35e+00 |
Pos logit contributions | |
outage | +0.019 |
coat | +0.018 |
bush | +0.017 |
stump | +0.017 |
rito | +0.016 |
Neg logit contributions | |
their | -0.015 |
both | -0.014 |
Their | -0.013 |
Ben | -0.013 |
at | -0.013 |
Token | , |
Token ID | 11 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
outage | +0.096 |
coat | +0.089 |
stump | +0.087 |
bush | +0.087 |
remedy | +0.084 |
Neg logit contributions | |
their | -0.033 |
both | -0.029 |
at | -0.027 |
Their | -0.026 |
Ben | -0.025 |
Token | leaves |
Token ID | 5667 |
Feature activation | +3.26e+00 |
Pos logit contributions | |
outage | +0.005 |
coat | +0.004 |
bush | +0.004 |
stump | +0.004 |
smanship | +0.004 |
Neg logit contributions | |
their | -0.002 |
both | -0.002 |
Their | -0.002 |
at | -0.002 |
Ben | -0.002 |
Token | , |
Token ID | 11 |
Feature activation | +1.75e-01 |
Pos logit contributions | |
outage | +0.139 |
coat | +0.127 |
bush | +0.125 |
stump | +0.124 |
remedy | +0.121 |
Neg logit contributions | |
their | -0.043 |
both | -0.036 |
at | -0.034 |
Their | -0.031 |
Ben | -0.030 |
Token | it |
Token ID | 340 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
Their | +0.019 |
ast | +0.018 |
cks | +0.018 |
mouths | +0.018 |
ss | +0.017 |
Neg logit contributions | |
outage | -0.025 |
colder | -0.024 |
bush | -0.024 |
coat | -0.023 |
iest | -0.023 |
Token | was |
Token ID | 373 |
Feature activation | -2.26e+00 |
Pos logit contributions | |
their | +0.041 |
Their | +0.040 |
mouths | +0.037 |
Ben | +0.036 |
our | +0.036 |
Neg logit contributions | |
outage | -0.059 |
bush | -0.056 |
coat | -0.055 |
stump | -0.053 |
ock | -0.050 |
Token | time |
Token ID | 640 |
Feature activation | +3.67e-02 |
Pos logit contributions | |
their | +0.040 |
both | +0.036 |
at | +0.034 |
Their | +0.034 |
Ben | +0.032 |
Neg logit contributions | |
outage | -0.085 |
coat | -0.078 |
bush | -0.077 |
stump | -0.076 |
smanship | -0.073 |
Token | for |
Token ID | 329 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
outage | +0.001 |
coat | +0.001 |
bush | +0.001 |
stump | +0.001 |
smanship | +0.001 |
Neg logit contributions | |
Their | -0.001 |
their | -0.001 |
mouths | -0.001 |
Ben | -0.001 |
both | -0.001 |
Token | the |
Token ID | 262 |
Feature activation | -9.57e-01 |
Pos logit contributions | |
Their | +0.025 |
mouths | +0.024 |
at | +0.024 |
ast | +0.022 |
cks | +0.022 |
Neg logit contributions | |
outage | -0.043 |
stump | -0.040 |
bush | -0.040 |
ock | -0.040 |
smanship | -0.039 |
Token | mer |
Token ID | 4017 |
Feature activation | -7.22e+00 |
Pos logit contributions | |
Their | +0.023 |
their | +0.022 |
both | +0.020 |
mouths | +0.020 |
Tom | +0.020 |
Neg logit contributions | |
outage | -0.028 |
coat | -0.026 |
stump | -0.025 |
bush | -0.025 |
ock | -0.024 |
Token | maid |
Token ID | 23151 |
Feature activation | -4.60e+00 |
Pos logit contributions | |
their | +0.190 |
Their | +0.189 |
Tom | +0.188 |
both | +0.180 |
Ben | +0.174 |
Neg logit contributions | |
outage | -0.207 |
rito | -0.189 |
coat | -0.188 |
bush | -0.185 |
iest | -0.179 |
Token | to |
Token ID | 284 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
their | +0.087 |
Their | +0.086 |
mouths | +0.080 |
both | +0.079 |
Ben | +0.079 |
Neg logit contributions | |
outage | -0.153 |
coat | -0.143 |
bush | -0.140 |
stump | -0.135 |
rito | -0.129 |
Token | return |
Token ID | 1441 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
Their | +0.024 |
their | +0.024 |
mouths | +0.023 |
at | +0.022 |
both | +0.022 |
Neg logit contributions | |
outage | -0.033 |
coat | -0.031 |
bush | -0.031 |
stump | -0.030 |
ock | -0.029 |
Token | home |
Token ID | 1363 |
Feature activation | -4.06e-01 |
Pos logit contributions | |
their | +0.022 |
Their | +0.021 |
both | +0.020 |
Ben | +0.019 |
at | +0.019 |
Neg logit contributions | |
outage | -0.045 |
coat | -0.042 |
bush | -0.041 |
stump | -0.041 |
smanship | -0.039 |
Token | . |
Token ID | 13 |
Feature activation | -3.07e-01 |
Pos logit contributions | |
their | +0.006 |
Their | +0.005 |
both | +0.005 |
Ben | +0.005 |
at | +0.005 |
Neg logit contributions | |
outage | -0.016 |
coat | -0.015 |
bush | -0.014 |
stump | -0.014 |
smanship | -0.013 |
Token | away |
Token ID | 8272 |
Feature activation | -5.22e+00 |
Pos logit contributions | |
their | +0.075 |
Their | +0.071 |
both | +0.070 |
Ben | +0.066 |
mouths | +0.066 |
Neg logit contributions | |
outage | -0.128 |
coat | -0.119 |
bush | -0.116 |
stump | -0.111 |
row | -0.107 |
Token | and |
Token ID | 290 |
Feature activation | -3.05e+00 |
Pos logit contributions | |
Their | +0.103 |
both | +0.102 |
their | +0.101 |
Ben | +0.097 |
Tom | +0.094 |
Neg logit contributions | |
outage | -0.151 |
bush | -0.142 |
coat | -0.138 |
row | -0.136 |
rito | -0.134 |
Token | c |
Token ID | 269 |
Feature activation | -3.67e+00 |
Pos logit contributions | |
their | +0.062 |
Their | +0.059 |
both | +0.056 |
at | +0.053 |
mouths | +0.053 |
Neg logit contributions | |
outage | -0.098 |
coat | -0.091 |
bush | -0.089 |
stump | -0.087 |
remedy | -0.082 |
Token | umin |
Token ID | 7230 |
Feature activation | -2.67e+00 |
Pos logit contributions | |
their | +0.077 |
Their | +0.070 |
both | +0.068 |
Tom | +0.068 |
Ben | +0.066 |
Neg logit contributions | |
outage | -0.115 |
coat | -0.111 |
bush | -0.111 |
rito | -0.102 |
stump | -0.101 |
Token | and |
Token ID | 290 |
Feature activation | -3.15e+00 |
Pos logit contributions | |
their | +0.047 |
Their | +0.042 |
both | +0.042 |
Ben | +0.040 |
at | +0.040 |
Neg logit contributions | |
outage | -0.096 |
coat | -0.089 |
bush | -0.087 |
stump | -0.086 |
rito | -0.082 |
Token | cor |
Token ID | 1162 |
Feature activation | -6.98e+00 |
Pos logit contributions | |
their | +0.063 |
Their | +0.061 |
both | +0.058 |
at | +0.055 |
mouths | +0.055 |
Neg logit contributions | |
outage | -0.101 |
coat | -0.094 |
bush | -0.092 |
stump | -0.090 |
remedy | -0.085 |
Token | i |
Token ID | 72 |
Feature activation | -1.87e+00 |
Pos logit contributions | |
their | +0.179 |
Their | +0.171 |
both | +0.154 |
Tom | +0.152 |
our | +0.151 |
Neg logit contributions | |
outage | -0.180 |
coat | -0.180 |
bush | -0.173 |
stump | -0.167 |
rito | -0.162 |
Token | ander |
Token ID | 4066 |
Feature activation | -2.32e+00 |
Pos logit contributions | |
their | +0.034 |
Their | +0.033 |
both | +0.030 |
Tom | +0.029 |
Ben | +0.029 |
Neg logit contributions | |
outage | -0.062 |
coat | -0.059 |
bush | -0.058 |
stump | -0.056 |
rito | -0.054 |
Token | and |
Token ID | 290 |
Feature activation | -3.25e+00 |
Pos logit contributions | |
their | +0.042 |
Their | +0.040 |
both | +0.038 |
Ben | +0.037 |
mouths | +0.037 |
Neg logit contributions | |
outage | -0.079 |
coat | -0.074 |
bush | -0.073 |
stump | -0.070 |
rito | -0.068 |
Token | card |
Token ID | 2657 |
Feature activation | -4.95e+00 |
Pos logit contributions | |
their | +0.065 |
Their | +0.063 |
both | +0.059 |
at | +0.057 |
mouths | +0.056 |
Neg logit contributions | |
outage | -0.103 |
coat | -0.096 |
bush | -0.094 |
stump | -0.092 |
remedy | -0.087 |
Token | am |
Token ID | 321 |
Feature activation | -3.21e+00 |
Pos logit contributions | |
their | +0.091 |
Their | +0.087 |
both | +0.085 |
Ben | +0.079 |
Tom | +0.079 |
Neg logit contributions | |
outage | -0.165 |
coat | -0.152 |
bush | -0.152 |
stump | -0.143 |
rito | -0.139 |
Token | the |
Token ID | 262 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
outage | +0.025 |
bush | +0.023 |
coat | +0.023 |
stump | +0.023 |
ock | +0.022 |
Neg logit contributions | |
Their | -0.008 |
their | -0.008 |
both | -0.008 |
mouths | -0.008 |
Ben | -0.007 |
Token | passport |
Token ID | 17981 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
outage | +0.033 |
coat | +0.030 |
bush | +0.030 |
stump | +0.030 |
smanship | +0.028 |
Neg logit contributions | |
their | -0.024 |
Their | -0.023 |
both | -0.022 |
Ben | -0.021 |
Tom | -0.021 |
Token | and |
Token ID | 290 |
Feature activation | -3.23e-01 |
Pos logit contributions | |
their | +0.017 |
both | +0.016 |
at | +0.015 |
Their | +0.014 |
Tom | +0.014 |
Neg logit contributions | |
outage | -0.046 |
coat | -0.043 |
bush | -0.041 |
stump | -0.041 |
rito | -0.040 |
Token | the |
Token ID | 262 |
Feature activation | +2.07e-01 |
Pos logit contributions | |
their | +0.006 |
Their | +0.006 |
both | +0.006 |
Ben | +0.005 |
mouths | +0.005 |
Neg logit contributions | |
outage | -0.011 |
bush | -0.010 |
coat | -0.010 |
stump | -0.010 |
remedy | -0.009 |
Token | magical |
Token ID | 10883 |
Feature activation | -2.51e+00 |
Pos logit contributions | |
outage | +0.006 |
coat | +0.006 |
bush | +0.006 |
stump | +0.006 |
remedy | +0.005 |
Neg logit contributions | |
their | -0.005 |
Their | -0.005 |
both | -0.004 |
Tom | -0.004 |
mouths | -0.004 |
Token | mer |
Token ID | 4017 |
Feature activation | -6.77e+00 |
Pos logit contributions | |
their | +0.055 |
at | +0.050 |
both | +0.048 |
Ben | +0.047 |
mom | +0.045 |
Neg logit contributions | |
outage | -0.081 |
coat | -0.077 |
stump | -0.074 |
bush | -0.073 |
ock | -0.068 |
Token | maid |
Token ID | 23151 |
Feature activation | -4.15e+00 |
Pos logit contributions | |
Tom | +0.185 |
their | +0.183 |
Their | +0.180 |
Ben | +0.173 |
both | +0.172 |
Neg logit contributions | |
outage | -0.184 |
rito | -0.166 |
bush | -0.165 |
iest | -0.162 |
coat | -0.161 |
Token | was |
Token ID | 373 |
Feature activation | +3.25e-01 |
Pos logit contributions | |
Their | +0.082 |
their | +0.082 |
Ben | +0.078 |
Tom | +0.077 |
mouths | +0.077 |
Neg logit contributions | |
outage | -0.128 |
bush | -0.118 |
coat | -0.117 |
stump | -0.113 |
iest | -0.110 |
Token | grateful |
Token ID | 14066 |
Feature activation | -2.13e+00 |
Pos logit contributions | |
outage | +0.010 |
coat | +0.009 |
bush | +0.009 |
stump | +0.009 |
rito | +0.008 |
Neg logit contributions | |
Their | -0.007 |
mouths | -0.007 |
their | -0.006 |
Ben | -0.006 |
faces | -0.006 |
Token | to |
Token ID | 284 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
their | +0.036 |
Their | +0.033 |
both | +0.032 |
Ben | +0.030 |
at | +0.030 |
Neg logit contributions | |
outage | -0.078 |
coat | -0.073 |
bush | -0.071 |
stump | -0.071 |
smanship | -0.067 |
Token | get |
Token ID | 651 |
Feature activation | +3.95e-01 |
Pos logit contributions | |
outage | +0.048 |
bush | +0.043 |
stump | +0.042 |
reetings | +0.041 |
ock | +0.041 |
Neg logit contributions | |
mouths | -0.030 |
Their | -0.027 |
faces | -0.026 |
at | -0.026 |
their | -0.025 |
Token | of |
Token ID | 286 |
Feature activation | +8.68e-01 |
Pos logit contributions | |
outage | +0.011 |
coat | +0.010 |
bush | +0.010 |
stump | +0.010 |
smanship | +0.009 |
Neg logit contributions | |
their | -0.012 |
Their | -0.011 |
both | -0.011 |
Ben | -0.011 |
at | -0.011 |
Token | friends |
Token ID | 2460 |
Feature activation | +6.96e-01 |
Pos logit contributions | |
outage | +0.026 |
ock | +0.024 |
coat | +0.023 |
stump | +0.023 |
pleasures | +0.023 |
Neg logit contributions | |
Their | -0.015 |
Ben | -0.015 |
mouths | -0.014 |
ast | -0.014 |
their | -0.014 |
Token | and |
Token ID | 290 |
Feature activation | -9.82e-01 |
Pos logit contributions | |
outage | +0.021 |
stump | +0.019 |
smanship | +0.018 |
adows | +0.018 |
bush | +0.018 |
Neg logit contributions | |
Their | -0.014 |
mouths | -0.013 |
their | -0.013 |
faces | -0.013 |
Ben | -0.013 |
Token | whenever |
Token ID | 8797 |
Feature activation | -2.63e+00 |
Pos logit contributions | |
their | +0.016 |
Their | +0.016 |
both | +0.015 |
at | +0.015 |
Ben | +0.014 |
Neg logit contributions | |
outage | -0.034 |
coat | -0.031 |
stump | -0.031 |
bush | -0.031 |
smanship | -0.029 |
Token | the |
Token ID | 262 |
Feature activation | -1.97e+00 |
Pos logit contributions | |
Their | +0.040 |
ast | +0.038 |
both | +0.037 |
mouths | +0.036 |
at | +0.035 |
Neg logit contributions | |
outage | -0.086 |
stump | -0.080 |
pleasures | -0.078 |
colder | -0.077 |
iest | -0.076 |
Token | gorilla |
Token ID | 45314 |
Feature activation | -6.73e+00 |
Pos logit contributions | |
their | +0.043 |
Their | +0.040 |
both | +0.039 |
Ben | +0.038 |
at | +0.037 |
Neg logit contributions | |
outage | -0.062 |
coat | -0.057 |
stump | -0.056 |
bush | -0.056 |
remedy | -0.052 |
Token | was |
Token ID | 373 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
their | +0.144 |
Their | +0.138 |
our | +0.131 |
Ben | +0.130 |
both | +0.129 |
Neg logit contributions | |
outage | -0.202 |
coat | -0.186 |
stump | -0.184 |
bush | -0.184 |
smanship | -0.171 |
Token | in |
Token ID | 287 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
their | +0.029 |
Their | +0.027 |
both | +0.026 |
Ben | +0.025 |
Tom | +0.025 |
Neg logit contributions | |
outage | -0.047 |
coat | -0.044 |
bush | -0.043 |
stump | -0.042 |
rito | -0.040 |
Token | trouble |
Token ID | 5876 |
Feature activation | -9.16e-01 |
Pos logit contributions | |
Their | +0.021 |
their | +0.021 |
both | +0.020 |
mouths | +0.019 |
at | +0.019 |
Neg logit contributions | |
outage | -0.057 |
stump | -0.053 |
coat | -0.052 |
bush | -0.051 |
smanship | -0.049 |
Token | , |
Token ID | 11 |
Feature activation | +4.97e-01 |
Pos logit contributions | |
their | +0.014 |
Their | +0.013 |
both | +0.013 |
Ben | +0.012 |
at | +0.012 |
Neg logit contributions | |
outage | -0.034 |
coat | -0.032 |
bush | -0.031 |
stump | -0.031 |
smanship | -0.030 |
Token | the |
Token ID | 262 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
outage | +0.017 |
coat | +0.016 |
stump | +0.015 |
bush | +0.015 |
smanship | +0.014 |
Neg logit contributions | |
Their | -0.009 |
their | -0.008 |
both | -0.008 |
Ben | -0.008 |
mouths | -0.008 |
Token | together |
Token ID | 1978 |
Feature activation | -9.06e-01 |
Pos logit contributions | |
outage | +0.019 |
coat | +0.018 |
stump | +0.017 |
bush | +0.017 |
smanship | +0.017 |
Neg logit contributions | |
their | -0.006 |
Their | -0.006 |
Ben | -0.006 |
both | -0.005 |
mouths | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | -5.66e-01 |
Pos logit contributions | |
Their | +0.019 |
mouths | +0.017 |
faces | +0.017 |
our | +0.017 |
Ben | +0.017 |
Neg logit contributions | |
stump | -0.025 |
outage | -0.024 |
bush | -0.023 |
adows | -0.023 |
coat | -0.023 |
Token | And |
Token ID | 843 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
faces | +0.009 |
at | +0.009 |
their | +0.009 |
mouths | +0.009 |
both | +0.008 |
Neg logit contributions | |
outage | -0.019 |
stump | -0.018 |
bush | -0.017 |
ock | -0.017 |
coat | -0.017 |
Token | whenever |
Token ID | 8797 |
Feature activation | -2.96e+00 |
Pos logit contributions | |
faces | +0.034 |
Their | +0.034 |
mouths | +0.034 |
cks | +0.032 |
their | +0.030 |
Neg logit contributions | |
outage | -0.040 |
bush | -0.037 |
stump | -0.036 |
iest | -0.035 |
possible | -0.035 |
Token | the |
Token ID | 262 |
Feature activation | -2.28e+00 |
Pos logit contributions | |
Their | +0.045 |
mouths | +0.041 |
their | +0.040 |
faces | +0.040 |
both | +0.039 |
Neg logit contributions | |
outage | -0.102 |
stump | -0.095 |
bush | -0.093 |
pleasures | -0.090 |
colder | -0.090 |
Token | sailor |
Token ID | 43272 |
Feature activation | -6.57e+00 |
Pos logit contributions | |
their | +0.048 |
both | +0.045 |
Their | +0.044 |
Ben | +0.043 |
at | +0.043 |
Neg logit contributions | |
outage | -0.075 |
coat | -0.069 |
bush | -0.068 |
stump | -0.067 |
smanship | -0.063 |
Token | felt |
Token ID | 2936 |
Feature activation | -6.54e-01 |
Pos logit contributions | |
their | +0.138 |
Their | +0.129 |
both | +0.125 |
Ben | +0.120 |
Tom | +0.118 |
Neg logit contributions | |
outage | -0.210 |
coat | -0.195 |
bush | -0.191 |
stump | -0.190 |
smanship | -0.178 |
Token | hungry |
Token ID | 14720 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
their | +0.013 |
at | +0.012 |
both | +0.011 |
Ben | +0.011 |
Their | +0.011 |
Neg logit contributions | |
outage | -0.025 |
coat | -0.023 |
smanship | -0.022 |
bush | -0.022 |
stump | -0.022 |
Token | , |
Token ID | 11 |
Feature activation | +8.17e-01 |
Pos logit contributions | |
their | +0.027 |
both | +0.023 |
at | +0.023 |
Their | +0.023 |
Ben | +0.022 |
Neg logit contributions | |
outage | -0.071 |
coat | -0.066 |
bush | -0.065 |
stump | -0.065 |
smanship | -0.061 |
Token | he |
Token ID | 339 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
outage | +0.028 |
coat | +0.026 |
bush | +0.025 |
stump | +0.025 |
smanship | +0.024 |
Neg logit contributions | |
their | -0.015 |
Their | -0.014 |
both | -0.014 |
at | -0.013 |
Ben | -0.013 |
Token | knew |
Token ID | 2993 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
their | +0.029 |
both | +0.028 |
Their | +0.027 |
at | +0.027 |
Ben | +0.026 |
Neg logit contributions | |
outage | -0.036 |
coat | -0.033 |
bush | -0.031 |
stump | -0.031 |
rito | -0.029 |
Token | more |
Token ID | 517 |
Feature activation | +2.50e+00 |
Pos logit contributions | |
outage | +0.019 |
bush | +0.017 |
coat | +0.016 |
rito | +0.015 |
stump | +0.015 |
Neg logit contributions | |
their | -0.015 |
both | -0.014 |
at | -0.012 |
Tom | -0.012 |
our | -0.012 |
Token | sand |
Token ID | 6450 |
Feature activation | -1.98e+00 |
Pos logit contributions | |
outage | +0.073 |
coat | +0.067 |
stump | +0.065 |
bush | +0.065 |
ock | +0.060 |
Neg logit contributions | |
their | -0.060 |
Their | -0.057 |
both | -0.056 |
Ben | -0.054 |
at | -0.053 |
Token | together |
Token ID | 1978 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
Their | +0.038 |
their | +0.033 |
Ben | +0.033 |
both | +0.032 |
mouths | +0.032 |
Neg logit contributions | |
outage | -0.064 |
coat | -0.063 |
stump | -0.058 |
bush | -0.057 |
adows | -0.056 |
Token | until |
Token ID | 1566 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
Their | +0.023 |
their | +0.021 |
mouths | +0.020 |
our | +0.020 |
faces | +0.020 |
Neg logit contributions | |
outage | -0.041 |
coat | -0.039 |
stump | -0.038 |
bush | -0.037 |
adows | -0.035 |
Token | their |
Token ID | 511 |
Feature activation | -4.75e+00 |
Pos logit contributions | |
Their | +0.022 |
ast | +0.020 |
faces | +0.019 |
mouths | +0.019 |
eg | +0.018 |
Neg logit contributions | |
outage | -0.045 |
bush | -0.043 |
colder | -0.042 |
coat | -0.042 |
stump | -0.042 |
Token | castle |
Token ID | 16669 |
Feature activation | -6.51e+00 |
Pos logit contributions | |
their | +0.110 |
Their | +0.110 |
both | +0.100 |
Tom | +0.098 |
Ben | +0.097 |
Neg logit contributions | |
outage | -0.133 |
coat | -0.129 |
stump | -0.123 |
bush | -0.122 |
remedy | -0.115 |
Token | was |
Token ID | 373 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
their | +0.133 |
Their | +0.127 |
both | +0.120 |
Ben | +0.119 |
our | +0.116 |
Neg logit contributions | |
outage | -0.211 |
coat | -0.199 |
bush | -0.193 |
stump | -0.191 |
smanship | -0.178 |
Token | finished |
Token ID | 5201 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
their | +0.037 |
both | +0.035 |
at | +0.032 |
Ben | +0.030 |
Their | +0.030 |
Neg logit contributions | |
outage | -0.064 |
coat | -0.058 |
bush | -0.058 |
stump | -0.056 |
smanship | -0.055 |
Token | . |
Token ID | 13 |
Feature activation | -3.06e-02 |
Pos logit contributions | |
Their | +0.025 |
their | +0.024 |
both | +0.022 |
Ben | +0.022 |
Tom | +0.022 |
Neg logit contributions | |
outage | -0.052 |
coat | -0.049 |
stump | -0.048 |
bush | -0.047 |
smanship | -0.045 |
Token | |
Token ID | 220 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
their | +0.000 |
both | +0.000 |
Their | +0.000 |
at | +0.000 |
Ben | +0.000 |
Neg logit contributions | |
outage | -0.001 |
coat | -0.001 |
bush | -0.001 |
stump | -0.001 |
rito | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | -3.26e-01 |
Pos logit contributions | |
outage | +0.045 |
coat | +0.042 |
stump | +0.041 |
bush | +0.041 |
adows | +0.039 |
Neg logit contributions | |
their | -0.017 |
mouths | -0.015 |
both | -0.014 |
Their | -0.014 |
at | -0.014 |
Token | he |
Token ID | 339 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
their | +0.002 |
Their | +0.002 |
both | +0.002 |
mouths | +0.002 |
Ben | +0.002 |
Neg logit contributions | |
outage | -0.006 |
coat | -0.006 |
bush | -0.006 |
stump | -0.006 |
ock | -0.006 |
Token | could |
Token ID | 714 |
Feature activation | +2.49e-01 |
Pos logit contributions | |
their | +0.024 |
both | +0.023 |
Their | +0.022 |
at | +0.021 |
Ben | +0.021 |
Neg logit contributions | |
outage | -0.045 |
coat | -0.042 |
bush | -0.041 |
stump | -0.040 |
rito | -0.038 |
Token | do |
Token ID | 466 |
Feature activation | -2.56e+00 |
Pos logit contributions | |
outage | +0.008 |
coat | +0.008 |
bush | +0.008 |
stump | +0.007 |
rito | +0.007 |
Neg logit contributions | |
their | -0.005 |
both | -0.005 |
at | -0.005 |
Their | -0.004 |
Tom | -0.004 |
Token | anything |
Token ID | 1997 |
Feature activation | -3.36e-01 |
Pos logit contributions | |
their | +0.044 |
both | +0.040 |
Their | +0.039 |
at | +0.037 |
Ben | +0.037 |
Neg logit contributions | |
outage | -0.094 |
coat | -0.088 |
bush | -0.086 |
stump | -0.085 |
rito | -0.080 |
Token | if |
Token ID | 611 |
Feature activation | -8.39e-01 |
Pos logit contributions | |
their | +0.007 |
Their | +0.006 |
both | +0.006 |
at | +0.006 |
Ben | +0.006 |
Neg logit contributions | |
outage | -0.011 |
coat | -0.011 |
bush | -0.010 |
stump | -0.010 |
smanship | -0.010 |
Token | he |
Token ID | 258 |
Feature activation | -6.50e+00 |
Pos logit contributions | |
their | +0.017 |
both | +0.015 |
Their | +0.015 |
Ben | +0.015 |
at | +0.015 |
Neg logit contributions | |
outage | -0.029 |
coat | -0.027 |
bush | -0.026 |
stump | -0.026 |
rito | -0.024 |
Token | set |
Token ID | 900 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
their | +0.132 |
Their | +0.124 |
both | +0.121 |
Ben | +0.115 |
at | +0.114 |
Neg logit contributions | |
outage | -0.213 |
coat | -0.198 |
bush | -0.192 |
stump | -0.192 |
smanship | -0.180 |
Token | his |
Token ID | 465 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
Their | +0.026 |
their | +0.026 |
both | +0.024 |
mouths | +0.022 |
Ben | +0.022 |
Neg logit contributions | |
outage | -0.066 |
coat | -0.062 |
bush | -0.062 |
stump | -0.061 |
ock | -0.059 |
Token | mind |
Token ID | 2000 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
their | +0.035 |
Their | +0.033 |
both | +0.032 |
Ben | +0.030 |
at | +0.030 |
Neg logit contributions | |
outage | -0.057 |
coat | -0.054 |
stump | -0.052 |
bush | -0.052 |
remedy | -0.049 |
Token | to |
Token ID | 284 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
their | +0.003 |
both | +0.002 |
at | +0.002 |
Their | +0.002 |
Ben | +0.002 |
Neg logit contributions | |
outage | -0.005 |
coat | -0.005 |
bush | -0.005 |
stump | -0.005 |
rito | -0.005 |
Token | it |
Token ID | 340 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
outage | +0.006 |
coat | +0.006 |
bush | +0.005 |
stump | +0.005 |
smanship | +0.005 |
Neg logit contributions | |
their | -0.004 |
both | -0.004 |
Their | -0.004 |
at | -0.004 |
Ben | -0.004 |
Token | ignoring |
Token ID | 15482 |
Feature activation | -3.11e-01 |
Pos logit contributions | |
outage | +0.068 |
stump | +0.067 |
coat | +0.064 |
bush | +0.061 |
remedy | +0.060 |
Neg logit contributions | |
Their | -0.070 |
mouths | -0.065 |
their | -0.062 |
faces | -0.061 |
Ben | -0.061 |
Token | him |
Token ID | 683 |
Feature activation | -4.30e-01 |
Pos logit contributions | |
Their | +0.006 |
mouths | +0.005 |
ast | +0.005 |
cks | +0.005 |
their | +0.005 |
Neg logit contributions | |
ock | -0.009 |
stump | -0.008 |
outage | -0.008 |
pleasures | -0.008 |
heart | -0.008 |
Token | , |
Token ID | 11 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
their | +0.007 |
Their | +0.007 |
both | +0.006 |
Ben | +0.006 |
mouths | +0.006 |
Neg logit contributions | |
outage | -0.016 |
coat | -0.014 |
stump | -0.014 |
bush | -0.014 |
ock | -0.013 |
Token | until |
Token ID | 1566 |
Feature activation | -9.71e-01 |
Pos logit contributions | |
outage | +0.035 |
coat | +0.032 |
stump | +0.032 |
bush | +0.032 |
ock | +0.029 |
Neg logit contributions | |
their | -0.024 |
Their | -0.023 |
both | -0.022 |
Ben | -0.021 |
mouths | -0.020 |
Token | the |
Token ID | 262 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
Their | +0.019 |
faces | +0.017 |
mouths | +0.017 |
their | +0.017 |
ast | +0.017 |
Neg logit contributions | |
outage | -0.029 |
stump | -0.028 |
colder | -0.026 |
bush | -0.026 |
coat | -0.025 |
Token | knight |
Token ID | 22062 |
Feature activation | -6.50e+00 |
Pos logit contributions | |
their | +0.044 |
Their | +0.043 |
both | +0.040 |
Tom | +0.038 |
mouths | +0.038 |
Neg logit contributions | |
outage | -0.044 |
stump | -0.040 |
coat | -0.039 |
bush | -0.039 |
ock | -0.037 |
Token | finally |
Token ID | 3443 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
their | +0.154 |
Their | +0.152 |
our | +0.140 |
mouths | +0.140 |
faces | +0.132 |
Neg logit contributions | |
outage | -0.184 |
coat | -0.176 |
stump | -0.171 |
bush | -0.169 |
boat | -0.155 |
Token | defeated |
Token ID | 9772 |
Feature activation | -2.62e+00 |
Pos logit contributions | |
their | +0.030 |
Their | +0.029 |
both | +0.028 |
Ben | +0.027 |
at | +0.027 |
Neg logit contributions | |
outage | -0.046 |
coat | -0.042 |
bush | -0.042 |
stump | -0.041 |
ock | -0.038 |
Token | the |
Token ID | 262 |
Feature activation | -9.91e-01 |
Pos logit contributions | |
Their | +0.043 |
mouths | +0.036 |
their | +0.036 |
both | +0.035 |
faces | +0.033 |
Neg logit contributions | |
outage | -0.086 |
stump | -0.085 |
bush | -0.080 |
ock | -0.078 |
coat | -0.076 |
Token | dragon |
Token ID | 10441 |
Feature activation | -5.65e+00 |
Pos logit contributions | |
Their | +0.025 |
their | +0.025 |
both | +0.023 |
Tom | +0.022 |
mouths | +0.022 |
Neg logit contributions | |
outage | -0.028 |
stump | -0.026 |
bush | -0.024 |
coat | -0.024 |
ock | -0.023 |
Token | . |
Token ID | 13 |
Feature activation | -2.36e-01 |
Pos logit contributions | |
Their | +0.121 |
their | +0.116 |
mouths | +0.111 |
Ben | +0.106 |
faces | +0.103 |
Neg logit contributions | |
outage | -0.179 |
stump | -0.175 |
bush | -0.163 |
coat | -0.151 |
ock | -0.150 |
Token | was |
Token ID | 373 |
Feature activation | -2.85e-01 |
Pos logit contributions | |
their | +0.077 |
Their | +0.074 |
Ben | +0.071 |
both | +0.069 |
Tom | +0.069 |
Neg logit contributions | |
outage | -0.123 |
coat | -0.111 |
bush | -0.111 |
stump | -0.109 |
smanship | -0.103 |
Token | happy |
Token ID | 3772 |
Feature activation | -2.07e+00 |
Pos logit contributions | |
their | +0.005 |
both | +0.005 |
Their | +0.005 |
at | +0.004 |
Ben | +0.004 |
Neg logit contributions | |
outage | -0.010 |
coat | -0.009 |
bush | -0.009 |
stump | -0.009 |
smanship | -0.009 |
Token | and |
Token ID | 290 |
Feature activation | +4.58e-01 |
Pos logit contributions | |
their | +0.034 |
Their | +0.032 |
both | +0.031 |
Ben | +0.029 |
mouths | +0.028 |
Neg logit contributions | |
outage | -0.076 |
coat | -0.070 |
bush | -0.069 |
stump | -0.069 |
smanship | -0.065 |
Token | sailed |
Token ID | 33835 |
Feature activation | -1.90e+00 |
Pos logit contributions | |
outage | +0.015 |
coat | +0.013 |
bush | +0.013 |
stump | +0.013 |
smanship | +0.012 |
Neg logit contributions | |
their | -0.009 |
Their | -0.009 |
both | -0.008 |
Ben | -0.008 |
mouths | -0.008 |
Token | away |
Token ID | 1497 |
Feature activation | -8.25e-01 |
Pos logit contributions | |
their | +0.031 |
Their | +0.030 |
both | +0.029 |
Ben | +0.028 |
mouths | +0.028 |
Neg logit contributions | |
outage | -0.067 |
coat | -0.063 |
bush | -0.062 |
stump | -0.061 |
ock | -0.059 |
Token | mer |
Token ID | 4017 |
Feature activation | -6.42e+00 |
Pos logit contributions | |
their | +0.014 |
Their | +0.013 |
both | +0.013 |
Ben | +0.012 |
Tom | +0.012 |
Neg logit contributions | |
outage | -0.029 |
coat | -0.027 |
bush | -0.027 |
stump | -0.027 |
smanship | -0.025 |
Token | rily |
Token ID | 28904 |
Feature activation | -4.48e+00 |
Pos logit contributions | |
Tom | +0.178 |
Ben | +0.172 |
Their | +0.164 |
their | +0.155 |
both | +0.150 |
Neg logit contributions | |
outage | -0.163 |
rated | -0.144 |
bush | -0.142 |
wood | -0.140 |
adows | -0.140 |
Token | . |
Token ID | 13 |
Feature activation | -6.67e-01 |
Pos logit contributions | |
Their | +0.082 |
their | +0.079 |
both | +0.072 |
mouths | +0.072 |
our | +0.070 |
Neg logit contributions | |
outage | -0.147 |
coat | -0.138 |
bush | -0.137 |
stump | -0.136 |
pleasures | -0.127 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
faces | +0.012 |
their | +0.011 |
at | +0.011 |
mouths | +0.011 |
both | +0.010 |
Neg logit contributions | |
outage | -0.022 |
stump | -0.021 |
bush | -0.020 |
coat | -0.019 |
adows | -0.018 |
Token | Once |
Token ID | 7454 |
Feature activation | -2.49e+00 |
Pos logit contributions | |
outage | +0.047 |
coat | +0.044 |
stump | +0.044 |
bush | +0.043 |
ock | +0.040 |
Neg logit contributions | |
their | -0.022 |
Their | -0.020 |
mouths | -0.020 |
both | -0.020 |
faces | -0.019 |
Token | there |
Token ID | 612 |
Feature activation | +9.67e-02 |
Pos logit contributions | |
their | +0.081 |
Their | +0.078 |
mouths | +0.078 |
both | +0.078 |
faces | +0.077 |
Neg logit contributions | |
outage | -0.048 |
coat | -0.039 |
bush | -0.038 |
stump | -0.037 |
ock | -0.034 |
Token | in |
Token ID | 287 |
Feature activation | -2.98e-01 |
Pos logit contributions | |
outage | +0.065 |
coat | +0.062 |
bush | +0.061 |
stump | +0.059 |
ock | +0.057 |
Neg logit contributions | |
their | -0.031 |
Their | -0.030 |
both | -0.028 |
Ben | -0.028 |
mouths | -0.027 |
Token | the |
Token ID | 262 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
Their | +0.005 |
ast | +0.005 |
am | +0.005 |
icked | +0.005 |
cks | +0.004 |
Neg logit contributions | |
kinds | -0.008 |
ock | -0.008 |
stump | -0.008 |
sorts | -0.008 |
outage | -0.008 |
Token | air |
Token ID | 1633 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
outage | +0.023 |
bush | +0.022 |
stump | +0.022 |
coat | +0.021 |
pleasures | +0.021 |
Neg logit contributions | |
Their | -0.026 |
their | -0.026 |
Tom | -0.025 |
both | -0.024 |
Ben | -0.024 |
Token | when |
Token ID | 618 |
Feature activation | +2.88e-01 |
Pos logit contributions | |
outage | +0.062 |
coat | +0.059 |
bush | +0.057 |
stump | +0.056 |
ock | +0.053 |
Neg logit contributions | |
their | -0.030 |
Their | -0.029 |
both | -0.027 |
Ben | -0.026 |
our | -0.026 |
Token | the |
Token ID | 262 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
outage | +0.010 |
bush | +0.010 |
stump | +0.009 |
coat | +0.009 |
colder | +0.009 |
Neg logit contributions | |
Their | -0.004 |
ast | -0.003 |
their | -0.003 |
both | -0.003 |
at | -0.003 |
Token | prince |
Token ID | 19716 |
Feature activation | -6.41e+00 |
Pos logit contributions | |
their | +0.033 |
Their | +0.033 |
both | +0.029 |
Their | +0.029 |
Tom | +0.028 |
Neg logit contributions | |
outage | -0.033 |
coat | -0.031 |
bush | -0.031 |
stump | -0.031 |
ock | -0.029 |
Token | and |
Token ID | 290 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
their | +0.150 |
Their | +0.147 |
our | +0.137 |
Their | +0.133 |
mouths | +0.132 |
Neg logit contributions | |
outage | -0.173 |
coat | -0.171 |
bush | -0.166 |
stump | -0.160 |
forest | -0.149 |
Token | princess |
Token ID | 21752 |
Feature activation | -5.11e+00 |
Pos logit contributions | |
Their | +0.032 |
Their | +0.029 |
both | +0.029 |
cks | +0.028 |
mouths | +0.028 |
Neg logit contributions | |
outage | -0.045 |
bush | -0.043 |
stump | -0.043 |
coat | -0.043 |
kinds | -0.040 |
Token | stepped |
Token ID | 10764 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
Their | +0.112 |
their | +0.109 |
our | +0.104 |
mouths | +0.104 |
Ben | +0.101 |
Neg logit contributions | |
outage | -0.138 |
coat | -0.137 |
bush | -0.130 |
stump | -0.122 |
row | -0.120 |
Token | out |
Token ID | 503 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
Their | +0.004 |
their | +0.004 |
mouths | +0.004 |
Tom | +0.004 |
Ben | +0.003 |
Neg logit contributions | |
coat | -0.006 |
outage | -0.006 |
bush | -0.006 |
stump | -0.006 |
rito | -0.005 |
Token | of |
Token ID | 286 |
Feature activation | -8.17e-01 |
Pos logit contributions | |
mouths | +0.057 |
Their | +0.057 |
Ben | +0.055 |
Tom | +0.054 |
eg | +0.053 |
Neg logit contributions | |
outage | -0.035 |
ock | -0.028 |
bush | -0.028 |
iest | -0.028 |
stump | -0.027 |
Token | so |
Token ID | 523 |
Feature activation | +7.87e-01 |
Pos logit contributions | |
outage | +0.021 |
coat | +0.019 |
bush | +0.019 |
stump | +0.019 |
remedy | +0.018 |
Neg logit contributions | |
their | -0.011 |
Their | -0.010 |
mouths | -0.010 |
both | -0.010 |
Ben | -0.010 |
Token | excited |
Token ID | 6568 |
Feature activation | -8.54e-01 |
Pos logit contributions | |
outage | +0.027 |
coat | +0.025 |
bush | +0.024 |
stump | +0.024 |
rito | +0.023 |
Neg logit contributions | |
their | -0.014 |
Their | -0.013 |
both | -0.013 |
mouths | -0.013 |
Ben | -0.013 |
Token | and |
Token ID | 290 |
Feature activation | +8.73e-01 |
Pos logit contributions | |
their | +0.014 |
Their | +0.012 |
both | +0.012 |
Ben | +0.011 |
at | +0.011 |
Neg logit contributions | |
outage | -0.032 |
coat | -0.030 |
bush | -0.029 |
stump | -0.029 |
smanship | -0.028 |
Token | when |
Token ID | 618 |
Feature activation | -9.45e-01 |
Pos logit contributions | |
outage | +0.027 |
coat | +0.025 |
bush | +0.024 |
stump | +0.024 |
remedy | +0.022 |
Neg logit contributions | |
their | -0.018 |
Their | -0.018 |
both | -0.017 |
mouths | -0.016 |
Ben | -0.016 |
Token | the |
Token ID | 262 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
their | +0.020 |
Their | +0.020 |
both | +0.019 |
mouths | +0.018 |
at | +0.018 |
Neg logit contributions | |
outage | -0.028 |
coat | -0.026 |
bush | -0.026 |
stump | -0.026 |
remedy | -0.024 |
Token | mer |
Token ID | 4017 |
Feature activation | -6.36e+00 |
Pos logit contributions | |
their | +0.023 |
Their | +0.021 |
both | +0.021 |
at | +0.020 |
Ben | +0.020 |
Neg logit contributions | |
outage | -0.031 |
coat | -0.028 |
bush | -0.028 |
stump | -0.028 |
smanship | -0.026 |
Token | maid |
Token ID | 23151 |
Feature activation | -5.27e+00 |
Pos logit contributions | |
Tom | +0.165 |
their | +0.155 |
Their | +0.152 |
Ben | +0.151 |
both | +0.145 |
Neg logit contributions | |
outage | -0.176 |
iest | -0.159 |
bush | -0.158 |
heart | -0.156 |
coat | -0.152 |
Token | saw |
Token ID | 2497 |
Feature activation | -2.04e+00 |
Pos logit contributions | |
their | +0.114 |
Their | +0.113 |
our | +0.103 |
mouths | +0.102 |
Tom | +0.101 |
Neg logit contributions | |
outage | -0.152 |
bush | -0.144 |
coat | -0.143 |
stump | -0.135 |
guard | -0.127 |
Token | him |
Token ID | 683 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
Their | +0.034 |
mouths | +0.032 |
their | +0.031 |
both | +0.031 |
our | +0.029 |
Neg logit contributions | |
outage | -0.065 |
bush | -0.063 |
stump | -0.061 |
iest | -0.061 |
coat | -0.059 |
Token | she |
Token ID | 673 |
Feature activation | -9.18e-01 |
Pos logit contributions | |
their | +0.023 |
Their | +0.022 |
both | +0.021 |
Ben | +0.020 |
mouths | +0.020 |
Neg logit contributions | |
outage | -0.047 |
coat | -0.044 |
stump | -0.044 |
bush | -0.044 |
smanship | -0.041 |
Token | gave |
Token ID | 2921 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
their | +0.019 |
Their | +0.019 |
Ben | +0.017 |
mouths | +0.017 |
our | +0.017 |
Neg logit contributions | |
outage | -0.028 |
coat | -0.026 |
bush | -0.026 |
stump | -0.026 |
smanship | -0.024 |
Token | ever |
Token ID | 1683 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
outage | +0.030 |
coat | +0.027 |
bush | +0.027 |
stump | +0.026 |
smanship | +0.025 |
Neg logit contributions | |
their | -0.019 |
Their | -0.018 |
both | -0.018 |
Ben | -0.017 |
mouths | -0.017 |
Token | and |
Token ID | 290 |
Feature activation | -3.47e-01 |
Pos logit contributions | |
their | +0.033 |
Their | +0.032 |
both | +0.030 |
Ben | +0.029 |
mouths | +0.029 |
Neg logit contributions | |
outage | -0.060 |
coat | -0.055 |
bush | -0.054 |
stump | -0.054 |
ock | -0.052 |
Token | he |
Token ID | 339 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
Their | +0.007 |
their | +0.007 |
mouths | +0.007 |
both | +0.007 |
Ben | +0.006 |
Neg logit contributions | |
outage | -0.010 |
bush | -0.009 |
stump | -0.009 |
coat | -0.009 |
remedy | -0.008 |
Token | thanked |
Token ID | 26280 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
their | +0.022 |
Their | +0.021 |
Tom | +0.020 |
mouths | +0.020 |
Ben | +0.019 |
Neg logit contributions | |
outage | -0.031 |
coat | -0.029 |
bush | -0.029 |
stump | -0.028 |
ock | -0.027 |
Token | the |
Token ID | 262 |
Feature activation | +1.84e-01 |
Pos logit contributions | |
Their | +0.026 |
mouths | +0.026 |
at | +0.023 |
their | +0.023 |
both | +0.022 |
Neg logit contributions | |
outage | -0.053 |
ock | -0.052 |
bush | -0.051 |
stump | -0.051 |
iona | -0.049 |
Token | mer |
Token ID | 4017 |
Feature activation | -6.35e+00 |
Pos logit contributions | |
outage | +0.005 |
bush | +0.005 |
coat | +0.005 |
stump | +0.005 |
remedy | +0.005 |
Neg logit contributions | |
their | -0.004 |
Their | -0.004 |
both | -0.004 |
mouths | -0.004 |
Tom | -0.004 |
Token | maid |
Token ID | 23151 |
Feature activation | -3.44e+00 |
Pos logit contributions | |
Tom | +0.187 |
their | +0.177 |
Their | +0.173 |
Ben | +0.172 |
both | +0.170 |
Neg logit contributions | |
outage | -0.159 |
rito | -0.146 |
bush | -0.144 |
iest | -0.144 |
heart | -0.142 |
Token | for |
Token ID | 329 |
Feature activation | -4.85e-01 |
Pos logit contributions | |
their | +0.064 |
Their | +0.062 |
mouths | +0.058 |
both | +0.057 |
Tom | +0.057 |
Neg logit contributions | |
outage | -0.111 |
bush | -0.105 |
coat | -0.104 |
stump | -0.102 |
ock | -0.097 |
Token | being |
Token ID | 852 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
mouths | +0.009 |
Their | +0.009 |
at | +0.008 |
their | +0.008 |
both | +0.008 |
Neg logit contributions | |
outage | -0.014 |
stump | -0.014 |
ock | -0.013 |
coat | -0.013 |
bush | -0.013 |
Token | so |
Token ID | 523 |
Feature activation | -3.33e-01 |
Pos logit contributions | |
outage | +0.045 |
coat | +0.042 |
iest | +0.040 |
bush | +0.040 |
stump | +0.040 |
Neg logit contributions | |
mouths | -0.032 |
Their | -0.031 |
faces | -0.029 |
their | -0.029 |
Ben | -0.026 |
Token | kind |
Token ID | 1611 |
Feature activation | -9.36e-01 |
Pos logit contributions | |
their | +0.008 |
Their | +0.008 |
both | +0.008 |
Ben | +0.007 |
at | +0.007 |
Neg logit contributions | |
outage | -0.010 |
coat | -0.009 |
bush | -0.008 |
stump | -0.008 |
smanship | -0.008 |
Token | their |
Token ID | 511 |
Feature activation | -2.51e+00 |
Pos logit contributions | |
outage | +0.041 |
coat | +0.039 |
bush | +0.038 |
stump | +0.038 |
rito | +0.036 |
Neg logit contributions | |
their | -0.021 |
both | -0.018 |
Their | -0.018 |
at | -0.017 |
Ben | -0.017 |
Token | plane |
Token ID | 6614 |
Feature activation | -3.97e+00 |
Pos logit contributions | |
Their | +0.049 |
their | +0.047 |
Ben | +0.046 |
Tom | +0.044 |
both | +0.044 |
Neg logit contributions | |
outage | -0.081 |
coat | -0.072 |
bush | -0.068 |
stump | -0.066 |
pleasures | -0.065 |
Token | was |
Token ID | 373 |
Feature activation | -7.01e-01 |
Pos logit contributions | |
their | +0.084 |
Their | +0.079 |
Ben | +0.076 |
both | +0.075 |
mouths | +0.073 |
Neg logit contributions | |
outage | -0.130 |
coat | -0.118 |
bush | -0.116 |
stump | -0.115 |
smanship | -0.108 |
Token | ready |
Token ID | 3492 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
their | +0.015 |
Their | +0.015 |
both | +0.014 |
Ben | +0.014 |
mouths | +0.014 |
Neg logit contributions | |
outage | -0.022 |
coat | -0.020 |
bush | -0.020 |
stump | -0.020 |
rito | -0.018 |
Token | for |
Token ID | 329 |
Feature activation | -8.09e-01 |
Pos logit contributions | |
their | +0.020 |
both | +0.018 |
Their | +0.018 |
at | +0.017 |
Ben | +0.017 |
Neg logit contributions | |
outage | -0.042 |
coat | -0.040 |
bush | -0.039 |
stump | -0.038 |
smanship | -0.036 |
Token | boarding |
Token ID | 25523 |
Feature activation | -6.34e+00 |
Pos logit contributions | |
Their | +0.013 |
mouths | +0.013 |
at | +0.011 |
faces | +0.011 |
both | +0.011 |
Neg logit contributions | |
outage | -0.026 |
stump | -0.024 |
ock | -0.023 |
iest | -0.022 |
reating | -0.022 |
Token | . |
Token ID | 13 |
Feature activation | -2.76e-01 |
Pos logit contributions | |
Their | +0.126 |
their | +0.121 |
mouths | +0.117 |
both | +0.115 |
Ben | +0.110 |
Neg logit contributions | |
outage | -0.196 |
coat | -0.179 |
ock | -0.175 |
bush | -0.172 |
iest | -0.168 |
Token |
|
Token ID | 198 |
Feature activation | -2.62e-01 |
Pos logit contributions | |
their | +0.006 |
faces | +0.005 |
at | +0.005 |
mouths | +0.005 |
our | +0.005 |
Neg logit contributions | |
outage | -0.008 |
stump | -0.007 |
bush | -0.007 |
coat | -0.007 |
wood | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | -4.73e-01 |
Pos logit contributions | |
their | +0.004 |
mouths | +0.004 |
at | +0.004 |
both | +0.004 |
faces | +0.004 |
Neg logit contributions | |
outage | -0.010 |
stump | -0.009 |
bush | -0.009 |
coat | -0.009 |
ock | -0.008 |
Token | The |
Token ID | 464 |
Feature activation | -1.75e-01 |
Pos logit contributions | |
their | +0.012 |
Their | +0.011 |
both | +0.011 |
at | +0.011 |
Ben | +0.011 |
Neg logit contributions | |
outage | -0.014 |
coat | -0.012 |
bush | -0.012 |
stump | -0.012 |
ock | -0.011 |
Token | little |
Token ID | 1310 |
Feature activation | -2.23e+00 |
Pos logit contributions | |
their | +0.003 |
Their | +0.003 |
mouths | +0.003 |
both | +0.003 |
Ben | +0.003 |
Neg logit contributions | |
outage | -0.006 |
coat | -0.006 |
stump | -0.005 |
bush | -0.005 |
ock | -0.005 |
Token | in |
Token ID | 287 |
Feature activation | -7.57e-01 |
Pos logit contributions | |
their | +0.000 |
at | +0.000 |
both | +0.000 |
our | +0.000 |
Ben | +0.000 |
Neg logit contributions | |
outage | -0.000 |
coat | -0.000 |
bush | -0.000 |
stump | -0.000 |
remedy | -0.000 |
Token | the |
Token ID | 262 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
their | +0.008 |
Their | +0.008 |
both | +0.007 |
at | +0.007 |
Ben | +0.007 |
Neg logit contributions | |
outage | -0.032 |
coat | -0.029 |
stump | -0.029 |
bush | -0.029 |
smanship | -0.028 |
Token | sea |
Token ID | 5417 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
their | +0.004 |
both | +0.003 |
Their | +0.003 |
at | +0.003 |
Ben | +0.003 |
Neg logit contributions | |
outage | -0.004 |
coat | -0.003 |
bush | -0.003 |
stump | -0.003 |
smanship | -0.003 |
Token | that |
Token ID | 326 |
Feature activation | +2.27e-01 |
Pos logit contributions | |
their | +0.024 |
both | +0.021 |
at | +0.020 |
Their | +0.019 |
Ben | +0.019 |
Neg logit contributions | |
outage | -0.066 |
coat | -0.062 |
bush | -0.059 |
stump | -0.059 |
rito | -0.057 |
Token | the |
Token ID | 262 |
Feature activation | -5.83e-01 |
Pos logit contributions | |
outage | +0.007 |
coat | +0.007 |
bush | +0.007 |
stump | +0.007 |
smanship | +0.006 |
Neg logit contributions | |
their | -0.005 |
Their | -0.004 |
both | -0.004 |
at | -0.004 |
Ben | -0.004 |
Token | mer |
Token ID | 4017 |
Feature activation | -6.29e+00 |
Pos logit contributions | |
Their | +0.015 |
their | +0.015 |
both | +0.013 |
Tom | +0.013 |
at | +0.013 |
Neg logit contributions | |
outage | -0.016 |
bush | -0.014 |
stump | -0.014 |
coat | -0.014 |
pleasures | -0.013 |
Token | maid |
Token ID | 23151 |
Feature activation | -4.16e+00 |
Pos logit contributions | |
Tom | +0.170 |
Ben | +0.160 |
Their | +0.159 |
their | +0.157 |
both | +0.143 |
Neg logit contributions | |
outage | -0.170 |
bush | -0.155 |
iest | -0.151 |
rated | -0.145 |
rito | -0.145 |
Token | carefully |
Token ID | 7773 |
Feature activation | -4.74e-01 |
Pos logit contributions | |
their | +0.091 |
Their | +0.089 |
Tom | +0.083 |
Ben | +0.082 |
our | +0.081 |
Neg logit contributions | |
outage | -0.126 |
bush | -0.114 |
coat | -0.114 |
stump | -0.111 |
adows | -0.103 |
Token | chose |
Token ID | 7690 |
Feature activation | +9.53e-01 |
Pos logit contributions | |
their | +0.010 |
Their | +0.009 |
both | +0.009 |
at | +0.009 |
Ben | +0.009 |
Neg logit contributions | |
outage | -0.015 |
coat | -0.014 |
bush | -0.014 |
stump | -0.014 |
smanship | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | -7.67e-02 |
Pos logit contributions | |
outage | +0.037 |
coat | +0.035 |
bush | +0.033 |
stump | +0.033 |
smanship | +0.032 |
Neg logit contributions | |
their | -0.015 |
both | -0.013 |
at | -0.013 |
Their | -0.013 |
Ben | -0.012 |
Token | It |
Token ID | 632 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
their | +0.001 |
faces | +0.001 |
both | +0.001 |
mouths | +0.001 |
at | +0.001 |
Neg logit contributions | |
outage | -0.003 |
bush | -0.002 |
stump | -0.002 |
coat | -0.002 |
rito | -0.002 |
Token | for |
Token ID | 329 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
Their | +0.016 |
mouths | +0.016 |
their | +0.015 |
both | +0.014 |
cks | +0.014 |
Neg logit contributions | |
outage | -0.036 |
bush | -0.033 |
stump | -0.033 |
coat | -0.032 |
remedy | -0.031 |
Token | helping |
Token ID | 5742 |
Feature activation | -8.60e-01 |
Pos logit contributions | |
Their | +0.025 |
at | +0.024 |
mouths | +0.024 |
their | +0.023 |
both | +0.023 |
Neg logit contributions | |
outage | -0.044 |
stump | -0.040 |
coat | -0.039 |
bush | -0.038 |
remedy | -0.038 |
Token | them |
Token ID | 606 |
Feature activation | -2.20e+00 |
Pos logit contributions | |
Their | +0.013 |
their | +0.013 |
mouths | +0.012 |
both | +0.012 |
at | +0.011 |
Neg logit contributions | |
outage | -0.030 |
coat | -0.028 |
bush | -0.027 |
stump | -0.027 |
ock | -0.027 |
Token | when |
Token ID | 618 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
their | +0.046 |
Their | +0.044 |
Ben | +0.041 |
both | +0.041 |
Tom | +0.041 |
Neg logit contributions | |
outage | -0.070 |
coat | -0.063 |
bush | -0.063 |
stump | -0.063 |
ock | -0.059 |
Token | the |
Token ID | 262 |
Feature activation | -2.86e+00 |
Pos logit contributions | |
their | +0.020 |
Their | +0.019 |
both | +0.018 |
at | +0.017 |
Ben | +0.017 |
Neg logit contributions | |
outage | -0.051 |
coat | -0.047 |
stump | -0.047 |
bush | -0.047 |
pleasures | -0.044 |
Token | crab |
Token ID | 32202 |
Feature activation | -6.29e+00 |
Pos logit contributions | |
their | +0.062 |
Their | +0.058 |
both | +0.057 |
at | +0.055 |
Ben | +0.054 |
Neg logit contributions | |
outage | -0.091 |
coat | -0.084 |
bush | -0.081 |
stump | -0.081 |
ock | -0.076 |
Token | was |
Token ID | 373 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
their | +0.141 |
Their | +0.137 |
both | +0.128 |
our | +0.128 |
mouths | +0.124 |
Neg logit contributions | |
outage | -0.178 |
coat | -0.171 |
bush | -0.165 |
stump | -0.162 |
guard | -0.150 |
Token | so |
Token ID | 523 |
Feature activation | -6.68e-01 |
Pos logit contributions | |
their | +0.040 |
Their | +0.037 |
both | +0.036 |
Ben | +0.035 |
at | +0.034 |
Neg logit contributions | |
outage | -0.063 |
coat | -0.059 |
bush | -0.057 |
stump | -0.057 |
rito | -0.053 |
Token | mean |
Token ID | 1612 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
their | +0.013 |
both | +0.012 |
Their | +0.012 |
at | +0.012 |
Ben | +0.011 |
Neg logit contributions | |
outage | -0.023 |
coat | -0.021 |
bush | -0.021 |
stump | -0.021 |
smanship | -0.020 |
Token | . |
Token ID | 13 |
Feature activation | -6.97e-01 |
Pos logit contributions | |
their | +0.027 |
Their | +0.025 |
both | +0.024 |
Ben | +0.022 |
mouths | +0.022 |
Neg logit contributions | |
outage | -0.061 |
coat | -0.057 |
bush | -0.055 |
stump | -0.055 |
ock | -0.053 |
Token | They |
Token ID | 1119 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
their | +0.012 |
faces | +0.011 |
at | +0.011 |
mouths | +0.011 |
our | +0.010 |
Neg logit contributions | |
outage | -0.022 |
stump | -0.022 |
coat | -0.021 |
bush | -0.021 |
pleasures | -0.019 |
Token | she |
Token ID | 673 |
Feature activation | -2.39e+00 |
Pos logit contributions | |
Their | +0.039 |
their | +0.037 |
mouths | +0.035 |
both | +0.035 |
at | +0.033 |
Neg logit contributions | |
outage | -0.054 |
bush | -0.050 |
coat | -0.049 |
stump | -0.048 |
smanship | -0.046 |
Token | was |
Token ID | 373 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
Their | +0.056 |
their | +0.055 |
mouths | +0.053 |
faces | +0.051 |
our | +0.050 |
Neg logit contributions | |
outage | -0.067 |
coat | -0.062 |
bush | -0.061 |
stump | -0.058 |
ock | -0.057 |
Token | finished |
Token ID | 5201 |
Feature activation | -9.29e-01 |
Pos logit contributions | |
their | +0.028 |
Their | +0.028 |
mouths | +0.028 |
faces | +0.026 |
our | +0.025 |
Neg logit contributions | |
outage | -0.042 |
coat | -0.039 |
bush | -0.038 |
stump | -0.036 |
ock | -0.035 |
Token | , |
Token ID | 11 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
their | +0.015 |
Their | +0.014 |
both | +0.014 |
Ben | +0.013 |
at | +0.013 |
Neg logit contributions | |
outage | -0.035 |
coat | -0.032 |
bush | -0.032 |
stump | -0.031 |
smanship | -0.030 |
Token | the |
Token ID | 262 |
Feature activation | +4.41e-01 |
Pos logit contributions | |
outage | +0.031 |
bush | +0.028 |
coat | +0.027 |
stump | +0.026 |
smanship | +0.026 |
Neg logit contributions | |
Their | -0.030 |
their | -0.029 |
mouths | -0.028 |
our | -0.027 |
both | -0.026 |
Token | mer |
Token ID | 4017 |
Feature activation | -6.25e+00 |
Pos logit contributions | |
outage | +0.014 |
coat | +0.013 |
bush | +0.013 |
stump | +0.013 |
smanship | +0.012 |
Neg logit contributions | |
their | -0.009 |
Their | -0.009 |
both | -0.009 |
at | -0.008 |
Ben | -0.008 |
Token | maid |
Token ID | 23151 |
Feature activation | -3.80e+00 |
Pos logit contributions | |
Tom | +0.177 |
their | +0.169 |
Their | +0.164 |
Ben | +0.161 |
both | +0.161 |
Neg logit contributions | |
outage | -0.164 |
iest | -0.146 |
bush | -0.140 |
row | -0.138 |
rito | -0.137 |
Token | thanked |
Token ID | 26280 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
their | +0.079 |
Their | +0.078 |
Tom | +0.072 |
our | +0.071 |
mouths | +0.071 |
Neg logit contributions | |
outage | -0.115 |
bush | -0.107 |
coat | -0.106 |
stump | -0.101 |
guard | -0.096 |
Token | her |
Token ID | 607 |
Feature activation | -3.72e-01 |
Pos logit contributions | |
mouths | +0.034 |
Their | +0.032 |
their | +0.027 |
our | +0.027 |
cks | +0.027 |
Neg logit contributions | |
outage | -0.040 |
ock | -0.040 |
reating | -0.039 |
smanship | -0.039 |
bush | -0.038 |
Token | for |
Token ID | 329 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
their | +0.007 |
Their | +0.007 |
mouths | +0.007 |
both | +0.006 |
Tom | +0.006 |
Neg logit contributions | |
outage | -0.012 |
bush | -0.011 |
stump | -0.011 |
coat | -0.011 |
smanship | -0.010 |
Token | coming |
Token ID | 2406 |
Feature activation | -2.84e+00 |
Pos logit contributions | |
Their | +0.003 |
mouths | +0.003 |
their | +0.003 |
both | +0.003 |
at | +0.003 |
Neg logit contributions | |
outage | -0.005 |
coat | -0.005 |
stump | -0.005 |
bush | -0.005 |
ock | -0.005 |
Token | be |
Token ID | 307 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
their | +0.000 |
both | +0.000 |
Their | +0.000 |
Ben | +0.000 |
at | +0.000 |
Neg logit contributions | |
outage | -0.000 |
coat | -0.000 |
bush | -0.000 |
stump | -0.000 |
rito | -0.000 |
Token | respectful |
Token ID | 25923 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
outage | +0.050 |
coat | +0.046 |
stump | +0.044 |
bush | +0.043 |
ock | +0.043 |
Neg logit contributions | |
their | -0.030 |
both | -0.027 |
at | -0.026 |
Their | -0.024 |
our | -0.024 |
Token | and |
Token ID | 290 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
outage | +0.057 |
stump | +0.056 |
coat | +0.056 |
bush | +0.054 |
rito | +0.053 |
Neg logit contributions | |
their | -0.023 |
at | -0.023 |
both | -0.020 |
Ben | -0.018 |
Tom | -0.018 |
Token | responsible |
Token ID | 4497 |
Feature activation | -3.63e-01 |
Pos logit contributions | |
their | +0.023 |
both | +0.020 |
at | +0.020 |
Their | +0.020 |
our | +0.019 |
Neg logit contributions | |
outage | -0.034 |
coat | -0.033 |
bush | -0.031 |
stump | -0.031 |
rito | -0.030 |
Token | when |
Token ID | 618 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
their | +0.006 |
both | +0.005 |
Their | +0.005 |
at | +0.005 |
Ben | +0.005 |
Neg logit contributions | |
outage | -0.014 |
coat | -0.013 |
bush | -0.013 |
stump | -0.013 |
rito | -0.012 |
Token | out |
Token ID | 503 |
Feature activation | -6.24e+00 |
Pos logit contributions | |
their | +0.029 |
both | +0.026 |
Their | +0.025 |
at | +0.025 |
Ben | +0.025 |
Neg logit contributions | |
outage | -0.062 |
coat | -0.058 |
bush | -0.056 |
stump | -0.056 |
rito | -0.054 |
Token | and |
Token ID | 290 |
Feature activation | -1.97e+00 |
Pos logit contributions | |
their | +0.114 |
Their | +0.106 |
both | +0.105 |
Ben | +0.099 |
Tom | +0.097 |
Neg logit contributions | |
outage | -0.217 |
coat | -0.200 |
bush | -0.196 |
stump | -0.194 |
smanship | -0.183 |
Token | about |
Token ID | 546 |
Feature activation | -3.05e+00 |
Pos logit contributions | |
their | +0.041 |
both | +0.037 |
at | +0.035 |
Their | +0.035 |
Ben | +0.034 |
Neg logit contributions | |
outage | -0.066 |
coat | -0.063 |
bush | -0.060 |
stump | -0.060 |
rito | -0.058 |
Token | . |
Token ID | 13 |
Feature activation | -8.60e-01 |
Pos logit contributions | |
their | +0.048 |
Their | +0.043 |
both | +0.043 |
at | +0.040 |
Ben | +0.040 |
Neg logit contributions | |
outage | -0.115 |
coat | -0.107 |
bush | -0.105 |
stump | -0.105 |
smanship | -0.099 |
Token | That |
Token ID | 1320 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
their | +0.016 |
both | +0.015 |
Their | +0.015 |
at | +0.014 |
Ben | +0.014 |
Neg logit contributions | |
outage | -0.029 |
coat | -0.027 |
bush | -0.027 |
stump | -0.026 |
smanship | -0.025 |
Token | made |
Token ID | 925 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
their | +0.020 |
both | +0.017 |
at | +0.016 |
Their | +0.016 |
Ben | +0.016 |
Neg logit contributions | |
outage | -0.049 |
coat | -0.049 |
stump | -0.046 |
rito | -0.045 |
bush | -0.045 |
Token | and |
Token ID | 290 |
Feature activation | +2.72e-01 |
Pos logit contributions | |
mouths | +0.058 |
Their | +0.055 |
ra | +0.053 |
cks | +0.053 |
arrest | +0.053 |
Neg logit contributions | |
outage | -0.066 |
coat | -0.061 |
ock | -0.061 |
stump | -0.060 |
bush | -0.058 |
Token | cl |
Token ID | 537 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
outage | +0.009 |
coat | +0.008 |
stump | +0.008 |
bush | +0.008 |
smanship | +0.007 |
Neg logit contributions | |
their | -0.006 |
Their | -0.005 |
both | -0.005 |
at | -0.005 |
Ben | -0.005 |
Token | ap |
Token ID | 499 |
Feature activation | -3.97e-01 |
Pos logit contributions | |
their | +0.035 |
Their | +0.033 |
both | +0.032 |
Tom | +0.031 |
our | +0.031 |
Neg logit contributions | |
outage | -0.042 |
coat | -0.038 |
adows | -0.037 |
bush | -0.037 |
stump | -0.036 |
Token | when |
Token ID | 618 |
Feature activation | -2.90e-01 |
Pos logit contributions | |
arrest | +0.006 |
mouths | +0.006 |
Their | +0.006 |
cks | +0.006 |
ra | +0.006 |
Neg logit contributions | |
outage | -0.012 |
pleasures | -0.011 |
coat | -0.011 |
ock | -0.011 |
adows | -0.010 |
Token | the |
Token ID | 262 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
Their | +0.003 |
their | +0.003 |
both | +0.003 |
at | +0.003 |
mouths | +0.002 |
Neg logit contributions | |
outage | -0.012 |
coat | -0.011 |
stump | -0.011 |
bush | -0.011 |
pleasures | -0.010 |
Token | princess |
Token ID | 21752 |
Feature activation | -6.23e+00 |
Pos logit contributions | |
their | +0.028 |
Their | +0.027 |
both | +0.026 |
at | +0.025 |
Ben | +0.024 |
Neg logit contributions | |
outage | -0.041 |
coat | -0.037 |
stump | -0.036 |
bush | -0.035 |
ock | -0.035 |
Token | escapes |
Token ID | 32695 |
Feature activation | -2.75e+00 |
Pos logit contributions | |
Their | +0.135 |
their | +0.130 |
both | +0.122 |
Their | +0.118 |
our | +0.117 |
Neg logit contributions | |
outage | -0.181 |
coat | -0.169 |
bush | -0.158 |
stump | -0.154 |
adows | -0.151 |
Token | from |
Token ID | 422 |
Feature activation | -3.13e+00 |
Pos logit contributions | |
Their | +0.049 |
mouths | +0.048 |
their | +0.046 |
both | +0.045 |
faces | +0.042 |
Neg logit contributions | |
outage | -0.092 |
coat | -0.082 |
bush | -0.080 |
ock | -0.080 |
stump | -0.078 |
Token | the |
Token ID | 262 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
Their | +0.050 |
mouths | +0.040 |
ast | +0.038 |
both | +0.038 |
their | +0.037 |
Neg logit contributions | |
outage | -0.108 |
stump | -0.102 |
coat | -0.099 |
ock | -0.096 |
colder | -0.095 |
Token | dragon |
Token ID | 10441 |
Feature activation | -6.13e+00 |
Pos logit contributions | |
their | +0.027 |
Their | +0.027 |
both | +0.025 |
at | +0.024 |
Tom | +0.024 |
Neg logit contributions | |
outage | -0.036 |
coat | -0.033 |
stump | -0.031 |
bush | -0.030 |
ock | -0.030 |
Token | . |
Token ID | 13 |
Feature activation | -4.29e-01 |
Pos logit contributions | |
Their | +0.132 |
their | +0.125 |
both | +0.118 |
Their | +0.114 |
our | +0.114 |
Neg logit contributions | |
outage | -0.187 |
stump | -0.167 |
bush | -0.163 |
coat | -0.162 |
adows | -0.152 |
Token | so |
Token ID | 523 |
Feature activation | +6.25e-01 |
Pos logit contributions | |
outage | +0.017 |
stump | +0.016 |
coat | +0.016 |
bush | +0.016 |
rito | +0.015 |
Neg logit contributions | |
Their | -0.010 |
their | -0.010 |
mouths | -0.010 |
faces | -0.010 |
Ben | -0.009 |
Token | happy |
Token ID | 3772 |
Feature activation | -2.17e+00 |
Pos logit contributions | |
outage | +0.017 |
bush | +0.015 |
stump | +0.015 |
iest | +0.015 |
coat | +0.014 |
Neg logit contributions | |
mouths | -0.014 |
their | -0.013 |
Their | -0.013 |
Ben | -0.013 |
faces | -0.013 |
Token | and |
Token ID | 290 |
Feature activation | +5.80e-01 |
Pos logit contributions | |
their | +0.037 |
Their | +0.036 |
both | +0.033 |
mouths | +0.032 |
Ben | +0.031 |
Neg logit contributions | |
outage | -0.078 |
coat | -0.071 |
bush | -0.070 |
stump | -0.070 |
ock | -0.066 |
Token | thanked |
Token ID | 26280 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
outage | +0.016 |
bush | +0.016 |
stump | +0.015 |
coat | +0.015 |
boat | +0.014 |
Neg logit contributions | |
Their | -0.012 |
their | -0.011 |
mouths | -0.011 |
Ben | -0.010 |
Their | -0.010 |
Token | the |
Token ID | 262 |
Feature activation | +5.37e-01 |
Pos logit contributions | |
mouths | +0.025 |
Their | +0.024 |
at | +0.022 |
both | +0.021 |
ast | +0.021 |
Neg logit contributions | |
ock | -0.042 |
outage | -0.041 |
stump | -0.041 |
bush | -0.040 |
heart | -0.039 |
Token | mer |
Token ID | 4017 |
Feature activation | -6.21e+00 |
Pos logit contributions | |
outage | +0.015 |
bush | +0.013 |
stump | +0.013 |
coat | +0.013 |
remedy | +0.013 |
Neg logit contributions | |
their | -0.013 |
Their | -0.013 |
both | -0.012 |
Tom | -0.012 |
mouths | -0.012 |
Token | maid |
Token ID | 23151 |
Feature activation | -3.41e+00 |
Pos logit contributions | |
their | +0.170 |
Tom | +0.169 |
Their | +0.166 |
both | +0.160 |
Ben | +0.158 |
Neg logit contributions | |
outage | -0.158 |
rito | -0.152 |
iest | -0.150 |
row | -0.148 |
bush | -0.146 |
Token | many |
Token ID | 867 |
Feature activation | +6.08e-01 |
Pos logit contributions | |
their | +0.062 |
Their | +0.062 |
mouths | +0.057 |
Tom | +0.056 |
Ben | +0.055 |
Neg logit contributions | |
outage | -0.107 |
bush | -0.102 |
stump | -0.101 |
coat | -0.098 |
row | -0.094 |
Token | times |
Token ID | 1661 |
Feature activation | +2.28e+00 |
Pos logit contributions | |
outage | +0.015 |
ock | +0.014 |
pleasures | +0.013 |
iest | +0.013 |
smanship | +0.013 |
Neg logit contributions | |
Their | -0.016 |
their | -0.015 |
Ben | -0.015 |
Tom | -0.015 |
both | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
outage | +0.079 |
coat | +0.072 |
stump | +0.071 |
bush | +0.071 |
ock | +0.067 |
Neg logit contributions | |
their | -0.039 |
Their | -0.038 |
mouths | -0.036 |
both | -0.035 |
Ben | -0.034 |
Token | With |
Token ID | 2080 |
Feature activation | -2.13e+00 |
Pos logit contributions | |
their | +0.002 |
both | +0.002 |
faces | +0.002 |
our | +0.002 |
mouths | +0.002 |
Neg logit contributions | |
outage | -0.003 |
bush | -0.003 |
stump | -0.003 |
coat | -0.003 |
wood | -0.003 |
Token | , |
Token ID | 11 |
Feature activation | -8.25e-01 |
Pos logit contributions | |
their | +0.014 |
both | +0.013 |
at | +0.012 |
Ben | +0.012 |
Their | +0.012 |
Neg logit contributions | |
outage | -0.041 |
coat | -0.038 |
bush | -0.038 |
stump | -0.038 |
smanship | -0.036 |
Token | please |
Token ID | 3387 |
Feature activation | -8.06e-01 |
Pos logit contributions | |
their | +0.016 |
both | +0.015 |
Ben | +0.015 |
at | +0.014 |
Their | +0.014 |
Neg logit contributions | |
outage | -0.029 |
coat | -0.026 |
stump | -0.026 |
bush | -0.026 |
smanship | -0.025 |
Token | wait |
Token ID | 4043 |
Feature activation | +7.81e-01 |
Pos logit contributions | |
their | +0.013 |
at | +0.011 |
Ben | +0.011 |
both | +0.011 |
Tom | +0.011 |
Neg logit contributions | |
outage | -0.032 |
stump | -0.029 |
bush | -0.029 |
coat | -0.029 |
smanship | -0.028 |
Token | until |
Token ID | 1566 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
outage | +0.027 |
coat | +0.026 |
bush | +0.025 |
stump | +0.025 |
rito | +0.023 |
Neg logit contributions | |
their | -0.014 |
Their | -0.013 |
both | -0.013 |
Ben | -0.012 |
mouths | -0.012 |
Token | your |
Token ID | 534 |
Feature activation | -2.85e+00 |
Pos logit contributions | |
Their | +0.020 |
their | +0.020 |
both | +0.018 |
mouths | +0.018 |
at | +0.017 |
Neg logit contributions | |
outage | -0.040 |
coat | -0.038 |
bush | -0.037 |
stump | -0.037 |
remedy | -0.035 |
Token | birthday |
Token ID | 10955 |
Feature activation | -6.15e+00 |
Pos logit contributions | |
their | +0.047 |
both | +0.043 |
Their | +0.043 |
at | +0.038 |
Ben | +0.036 |
Neg logit contributions | |
outage | -0.107 |
coat | -0.101 |
stump | -0.093 |
bush | -0.092 |
remedy | -0.090 |
Token | . |
Token ID | 13 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
their | +0.115 |
Their | +0.110 |
both | +0.109 |
Ben | +0.098 |
at | +0.096 |
Neg logit contributions | |
outage | -0.208 |
coat | -0.196 |
bush | -0.186 |
stump | -0.183 |
smanship | -0.175 |
Token | OK |
Token ID | 7477 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
their | +0.020 |
both | +0.018 |
at | +0.017 |
Their | +0.016 |
mouths | +0.016 |
Neg logit contributions | |
outage | -0.048 |
coat | -0.044 |
stump | -0.043 |
bush | -0.043 |
rito | -0.041 |
Token | ?" |
Token ID | 1701 |
Feature activation | +1.78e-01 |
Pos logit contributions | |
their | +0.033 |
at | +0.032 |
our | +0.029 |
mom | +0.029 |
both | +0.028 |
Neg logit contributions | |
outage | -0.055 |
stump | -0.054 |
coat | -0.053 |
bush | -0.053 |
smanship | -0.051 |
Token |
|
Token ID | 198 |
Feature activation | -3.90e-01 |
Pos logit contributions | |
outage | +0.006 |
coat | +0.006 |
stump | +0.005 |
bush | +0.005 |
opener | +0.005 |
Neg logit contributions | |
mouths | -0.003 |
both | -0.003 |
their | -0.003 |
our | -0.003 |
ra | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | -6.77e-01 |
Pos logit contributions | |
mouths | +0.006 |
their | +0.006 |
both | +0.006 |
at | +0.006 |
Their | +0.006 |
Neg logit contributions | |
outage | -0.013 |
stump | -0.012 |
coat | -0.012 |
bush | -0.012 |
ock | -0.012 |
Token | and |
Token ID | 290 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
Their | +0.015 |
their | +0.014 |
both | +0.013 |
mouths | +0.013 |
Ben | +0.013 |
Neg logit contributions | |
outage | -0.023 |
coat | -0.022 |
stump | -0.021 |
bush | -0.021 |
ock | -0.020 |
Token | faster |
Token ID | 5443 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
their | +0.005 |
both | +0.005 |
Their | +0.004 |
at | +0.004 |
Ben | +0.004 |
Neg logit contributions | |
outage | -0.003 |
coat | -0.003 |
bush | -0.003 |
stump | -0.003 |
smanship | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | +2.59e-02 |
Pos logit contributions | |
Their | +0.026 |
their | +0.025 |
both | +0.023 |
mouths | +0.022 |
Ben | +0.022 |
Neg logit contributions | |
outage | -0.043 |
coat | -0.041 |
stump | -0.040 |
bush | -0.039 |
ock | -0.038 |
Token | She |
Token ID | 1375 |
Feature activation | +4.64e-01 |
Pos logit contributions | |
outage | +0.001 |
coat | +0.001 |
bush | +0.001 |
stump | +0.001 |
smanship | +0.001 |
Neg logit contributions | |
their | -0.000 |
Their | -0.000 |
both | -0.000 |
Ben | -0.000 |
at | -0.000 |
Token | felt |
Token ID | 2936 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
outage | +0.015 |
coat | +0.014 |
bush | +0.014 |
stump | +0.014 |
ock | +0.013 |
Neg logit contributions | |
their | -0.010 |
Their | -0.009 |
both | -0.009 |
Ben | -0.008 |
Tom | -0.008 |
Token | wind |
Token ID | 2344 |
Feature activation | +4.83e+00 |
Pos logit contributions | |
outage | +0.072 |
coat | +0.068 |
stump | +0.066 |
bush | +0.066 |
smanship | +0.064 |
Neg logit contributions | |
their | -0.024 |
both | -0.021 |
at | -0.020 |
Ben | -0.018 |
Their | -0.018 |
Token | all |
Token ID | 477 |
Feature activation | +3.47e+00 |
Pos logit contributions | |
outage | +0.131 |
bush | +0.117 |
stump | +0.115 |
coat | +0.115 |
remedy | +0.109 |
Neg logit contributions | |
their | -0.130 |
both | -0.125 |
at | -0.124 |
Ben | -0.113 |
Their | -0.113 |
Token | around |
Token ID | 1088 |
Feature activation | -3.16e-01 |
Pos logit contributions | |
outage | +0.122 |
stump | +0.114 |
coat | +0.113 |
bush | +0.113 |
remedy | +0.109 |
Neg logit contributions | |
their | -0.069 |
at | -0.064 |
both | -0.064 |
our | -0.056 |
Tom | -0.056 |
Token | her |
Token ID | 607 |
Feature activation | +9.53e-02 |
Pos logit contributions | |
their | +0.005 |
Their | +0.005 |
both | +0.004 |
mouths | +0.004 |
our | +0.004 |
Neg logit contributions | |
outage | -0.011 |
coat | -0.011 |
bush | -0.011 |
stump | -0.011 |
ock | -0.010 |
Token | and |
Token ID | 290 |
Feature activation | -8.42e-01 |
Pos logit contributions | |
outage | +0.003 |
coat | +0.003 |
stump | +0.003 |
bush | +0.003 |
adows | +0.003 |
Neg logit contributions | |
their | -0.002 |
Their | -0.002 |
both | -0.001 |
Ben | -0.001 |
Tom | -0.001 |
Token | she |
Token ID | 673 |
Feature activation | -4.21e-01 |
Pos logit contributions | |
their | +0.015 |
both | +0.014 |
at | +0.013 |
Ben | +0.013 |
Their | +0.013 |
Neg logit contributions | |
outage | -0.031 |
coat | -0.028 |
bush | -0.028 |
stump | -0.028 |
rito | -0.027 |
Token | Twe |
Token ID | 24205 |
Feature activation | +3.48e-01 |
Pos logit contributions | |
their | +0.011 |
both | +0.010 |
Their | +0.010 |
Tom | +0.009 |
at | +0.009 |
Neg logit contributions | |
outage | -0.021 |
coat | -0.018 |
bush | -0.018 |
smanship | -0.017 |
stump | -0.017 |
Token | ety |
Token ID | 2963 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
outage | +0.008 |
bush | +0.007 |
coat | +0.007 |
stump | +0.007 |
remedy | +0.006 |
Neg logit contributions | |
their | -0.010 |
both | -0.010 |
Their | -0.010 |
at | -0.010 |
Tom | -0.010 |
Token | loved |
Token ID | 6151 |
Feature activation | +5.15e-01 |
Pos logit contributions | |
outage | +0.061 |
coat | +0.056 |
bush | +0.055 |
stump | +0.053 |
remedy | +0.052 |
Neg logit contributions | |
their | -0.028 |
both | -0.026 |
at | -0.025 |
Their | -0.024 |
Ben | -0.022 |
Token | to |
Token ID | 284 |
Feature activation | +2.58e+00 |
Pos logit contributions | |
outage | +0.020 |
coat | +0.018 |
bush | +0.018 |
stump | +0.018 |
smanship | +0.017 |
Neg logit contributions | |
their | -0.009 |
both | -0.007 |
Their | -0.007 |
at | -0.007 |
Ben | -0.007 |
Token | whistle |
Token ID | 16121 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
outage | +0.085 |
bush | +0.075 |
coat | +0.074 |
smanship | +0.073 |
stump | +0.071 |
Neg logit contributions | |
their | -0.061 |
both | -0.054 |
Their | -0.053 |
Ben | -0.051 |
at | -0.050 |
Token | all |
Token ID | 477 |
Feature activation | +4.83e+00 |
Pos logit contributions | |
outage | +0.042 |
coat | +0.039 |
bush | +0.038 |
stump | +0.038 |
smanship | +0.036 |
Neg logit contributions | |
their | -0.016 |
both | -0.014 |
Their | -0.014 |
at | -0.014 |
Ben | -0.013 |
Token | day |
Token ID | 1110 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
outage | +0.140 |
coat | +0.132 |
bush | +0.127 |
stump | +0.124 |
remedy | +0.118 |
Neg logit contributions | |
their | -0.130 |
both | -0.117 |
at | -0.114 |
Their | -0.114 |
our | -0.110 |
Token | long |
Token ID | 890 |
Feature activation | +6.40e-01 |
Pos logit contributions | |
outage | +0.044 |
coat | +0.041 |
stump | +0.040 |
bush | +0.039 |
ock | +0.037 |
Neg logit contributions | |
their | -0.029 |
Their | -0.028 |
mouths | -0.027 |
Tom | -0.026 |
Ben | -0.026 |
Token | . |
Token ID | 13 |
Feature activation | +2.08e-01 |
Pos logit contributions | |
outage | +0.024 |
coat | +0.022 |
stump | +0.022 |
bush | +0.022 |
ock | +0.021 |
Neg logit contributions | |
their | -0.010 |
Their | -0.009 |
both | -0.009 |
Ben | -0.008 |
mouths | -0.008 |
Token | One |
Token ID | 1881 |
Feature activation | +2.28e+00 |
Pos logit contributions | |
outage | +0.008 |
smanship | +0.007 |
coat | +0.007 |
bush | +0.007 |
guard | +0.007 |
Neg logit contributions | |
their | -0.004 |
Their | -0.004 |
Tom | -0.004 |
Ben | -0.003 |
both | -0.003 |
Token | day |
Token ID | 1110 |
Feature activation | +9.96e-01 |
Pos logit contributions | |
outage | +0.062 |
coat | +0.057 |
bush | +0.056 |
stump | +0.053 |
smanship | +0.051 |
Neg logit contributions | |
their | -0.062 |
Their | -0.057 |
both | -0.057 |
at | -0.056 |
Ben | -0.055 |
Token | handsome |
Token ID | 22665 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
outage | +0.012 |
coat | +0.011 |
stump | +0.011 |
bush | +0.011 |
remedy | +0.010 |
Neg logit contributions | |
their | -0.007 |
Their | -0.007 |
both | -0.007 |
mouths | -0.006 |
at | -0.006 |
Token | boy |
Token ID | 2933 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
Their | +0.056 |
their | +0.056 |
both | +0.054 |
mouths | +0.054 |
cks | +0.052 |
Neg logit contributions | |
coat | -0.040 |
outage | -0.039 |
bush | -0.035 |
stump | -0.034 |
rito | -0.033 |
Token | . |
Token ID | 13 |
Feature activation | +6.55e-01 |
Pos logit contributions | |
outage | +0.044 |
coat | +0.041 |
stump | +0.040 |
bush | +0.038 |
ock | +0.037 |
Neg logit contributions | |
mouths | -0.027 |
their | -0.026 |
both | -0.026 |
faces | -0.026 |
Ben | -0.026 |
Token | They |
Token ID | 1119 |
Feature activation | +2.16e+00 |
Pos logit contributions | |
outage | +0.025 |
bush | +0.023 |
coat | +0.023 |
stump | +0.022 |
rito | +0.022 |
Neg logit contributions | |
their | -0.012 |
Their | -0.011 |
Tom | -0.011 |
Ben | -0.011 |
both | -0.010 |
Token | loved |
Token ID | 6151 |
Feature activation | +5.04e-01 |
Pos logit contributions | |
outage | +0.067 |
coat | +0.063 |
stump | +0.060 |
bush | +0.060 |
ock | +0.057 |
Neg logit contributions | |
their | -0.046 |
Their | -0.043 |
both | -0.041 |
Ben | -0.041 |
at | -0.040 |
Token | each |
Token ID | 1123 |
Feature activation | +4.72e+00 |
Pos logit contributions | |
outage | +0.015 |
coat | +0.014 |
stump | +0.014 |
bush | +0.013 |
remedy | +0.013 |
Neg logit contributions | |
Their | -0.010 |
both | -0.010 |
their | -0.009 |
Ben | -0.009 |
mouths | -0.009 |
Token | other |
Token ID | 584 |
Feature activation | +3.00e+00 |
Pos logit contributions | |
outage | +0.156 |
coat | +0.149 |
ock | +0.144 |
stump | +0.143 |
bush | +0.139 |
Neg logit contributions | |
mouths | -0.078 |
their | -0.078 |
Their | -0.077 |
Ben | -0.074 |
both | -0.074 |
Token | , |
Token ID | 11 |
Feature activation | +2.52e+00 |
Pos logit contributions | |
outage | +0.126 |
bush | +0.117 |
coat | +0.117 |
stump | +0.114 |
rito | +0.111 |
Neg logit contributions | |
their | -0.040 |
both | -0.036 |
at | -0.031 |
Their | -0.031 |
Tom | -0.027 |
Token | so |
Token ID | 523 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
outage | +0.073 |
coat | +0.068 |
bush | +0.065 |
stump | +0.065 |
ock | +0.061 |
Neg logit contributions | |
their | -0.060 |
Their | -0.057 |
both | -0.056 |
Ben | -0.054 |
at | -0.054 |
Token | they |
Token ID | 484 |
Feature activation | +3.63e-01 |
Pos logit contributions | |
outage | +0.040 |
coat | +0.037 |
bush | +0.037 |
stump | +0.037 |
ock | +0.035 |
Neg logit contributions | |
Their | -0.013 |
their | -0.013 |
Ben | -0.012 |
both | -0.012 |
mouths | -0.011 |
Token | got |
Token ID | 1392 |
Feature activation | +7.06e-01 |
Pos logit contributions | |
outage | +0.011 |
coat | +0.010 |
bush | +0.010 |
stump | +0.010 |
ock | +0.009 |
Neg logit contributions | |
their | -0.008 |
Their | -0.007 |
Ben | -0.007 |
mouths | -0.007 |
Tom | -0.007 |
Token | clay |
Token ID | 21558 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
Their | +0.007 |
horror | +0.006 |
ra | +0.006 |
mouths | +0.006 |
both | +0.006 |
Neg logit contributions | |
outage | -0.013 |
coat | -0.013 |
ock | -0.012 |
stump | -0.012 |
textures | -0.012 |
Token | , |
Token ID | 11 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
outage | +0.060 |
coat | +0.056 |
stump | +0.056 |
bush | +0.054 |
smanship | +0.052 |
Neg logit contributions | |
their | -0.031 |
Their | -0.030 |
both | -0.027 |
Tom | -0.027 |
Ben | -0.026 |
Token | he |
Token ID | 339 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
outage | +0.045 |
bush | +0.040 |
coat | +0.040 |
stump | +0.038 |
rito | +0.038 |
Neg logit contributions | |
their | -0.035 |
both | -0.033 |
Their | -0.031 |
at | -0.031 |
Ben | -0.031 |
Token | would |
Token ID | 561 |
Feature activation | -9.63e-03 |
Pos logit contributions | |
outage | +0.006 |
coat | +0.006 |
stump | +0.005 |
bush | +0.005 |
smanship | +0.005 |
Neg logit contributions | |
their | -0.005 |
Their | -0.005 |
both | -0.005 |
Ben | -0.005 |
Tom | -0.005 |
Token | make |
Token ID | 787 |
Feature activation | +2.31e+00 |
Pos logit contributions | |
their | +0.000 |
both | +0.000 |
Their | +0.000 |
at | +0.000 |
Ben | +0.000 |
Neg logit contributions | |
outage | -0.000 |
coat | -0.000 |
bush | -0.000 |
stump | -0.000 |
smanship | -0.000 |
Token | all |
Token ID | 477 |
Feature activation | +4.77e+00 |
Pos logit contributions | |
outage | +0.061 |
stump | +0.057 |
ock | +0.056 |
bush | +0.055 |
textures | +0.054 |
Neg logit contributions | |
Their | -0.047 |
mouths | -0.045 |
Ben | -0.043 |
Tom | -0.043 |
their | -0.042 |
Token | sorts |
Token ID | 10524 |
Feature activation | +3.91e+00 |
Pos logit contributions | |
outage | +0.159 |
coat | +0.150 |
bush | +0.145 |
stump | +0.142 |
rito | +0.134 |
Neg logit contributions | |
their | -0.106 |
both | -0.095 |
Their | -0.093 |
at | -0.091 |
our | -0.088 |
Token | of |
Token ID | 286 |
Feature activation | +2.38e+00 |
Pos logit contributions | |
outage | +0.099 |
coat | +0.089 |
bush | +0.086 |
stump | +0.085 |
ock | +0.078 |
Neg logit contributions | |
their | -0.111 |
Their | -0.105 |
both | -0.104 |
Ben | -0.101 |
at | -0.100 |
Token | things |
Token ID | 1243 |
Feature activation | +2.69e+00 |
Pos logit contributions | |
outage | +0.081 |
coat | +0.075 |
bush | +0.073 |
stump | +0.073 |
smanship | +0.069 |
Neg logit contributions | |
their | -0.047 |
Their | -0.043 |
both | -0.043 |
at | -0.040 |
Ben | -0.040 |
Token | like |
Token ID | 588 |
Feature activation | -1.97e+00 |
Pos logit contributions | |
outage | +0.103 |
coat | +0.096 |
bush | +0.094 |
stump | +0.094 |
smanship | +0.089 |
Neg logit contributions | |
their | -0.040 |
Their | -0.037 |
both | -0.036 |
Ben | -0.034 |
at | -0.033 |
Token | cars |
Token ID | 5006 |
Feature activation | +3.82e-01 |
Pos logit contributions | |
their | +0.038 |
Their | +0.038 |
both | +0.036 |
Ben | +0.035 |
Tom | +0.035 |
Neg logit contributions | |
outage | -0.061 |
stump | -0.057 |
coat | -0.056 |
bush | -0.055 |
ock | -0.051 |
Token | and |
Token ID | 290 |
Feature activation | +3.92e-01 |
Pos logit contributions | |
outage | +0.007 |
coat | +0.006 |
bush | +0.006 |
stump | +0.006 |
smanship | +0.006 |
Neg logit contributions | |
their | -0.003 |
both | -0.003 |
Their | -0.003 |
at | -0.003 |
Ben | -0.003 |
Token | found |
Token ID | 1043 |
Feature activation | +2.02e-01 |
Pos logit contributions | |
outage | +0.012 |
coat | +0.012 |
stump | +0.011 |
bush | +0.011 |
remedy | +0.010 |
Neg logit contributions | |
their | -0.008 |
Their | -0.008 |
both | -0.007 |
mouths | -0.007 |
Ben | -0.007 |
Token | lots |
Token ID | 6041 |
Feature activation | +2.21e+00 |
Pos logit contributions | |
outage | +0.009 |
coat | +0.008 |
bush | +0.008 |
stump | +0.008 |
smanship | +0.008 |
Neg logit contributions | |
their | -0.003 |
both | -0.002 |
Their | -0.002 |
Ben | -0.002 |
at | -0.002 |
Token | of |
Token ID | 286 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
outage | +0.084 |
rated | +0.083 |
coat | +0.082 |
reetings | +0.081 |
stump | +0.077 |
Neg logit contributions | |
their | -0.040 |
at | -0.039 |
both | -0.033 |
Tom | -0.029 |
our | -0.028 |
Token | tw |
Token ID | 665 |
Feature activation | +9.09e-01 |
Pos logit contributions | |
outage | +0.065 |
coat | +0.062 |
bush | +0.058 |
reetings | +0.058 |
rated | +0.056 |
Neg logit contributions | |
their | -0.039 |
both | -0.034 |
at | -0.034 |
our | -0.032 |
wishes | -0.032 |
Token | igs |
Token ID | 9235 |
Feature activation | +5.20e+00 |
Pos logit contributions | |
outage | +0.027 |
coat | +0.023 |
stump | +0.022 |
bush | +0.021 |
remedy | +0.021 |
Neg logit contributions | |
their | -0.023 |
at | -0.023 |
both | -0.023 |
our | -0.021 |
cks | -0.020 |
Token | , |
Token ID | 11 |
Feature activation | +5.01e-01 |
Pos logit contributions | |
outage | +0.210 |
coat | +0.196 |
bush | +0.194 |
stump | +0.192 |
remedy | +0.185 |
Neg logit contributions | |
their | -0.073 |
both | -0.063 |
at | -0.062 |
Their | -0.057 |
Ben | -0.055 |
Token | feathers |
Token ID | 27400 |
Feature activation | +2.81e+00 |
Pos logit contributions | |
outage | +0.018 |
coat | +0.016 |
bush | +0.015 |
smanship | +0.015 |
reetings | +0.015 |
Neg logit contributions | |
their | -0.011 |
both | -0.010 |
at | -0.009 |
our | -0.008 |
Ben | -0.008 |
Token | , |
Token ID | 11 |
Feature activation | +2.60e-01 |
Pos logit contributions | |
outage | +0.123 |
coat | +0.113 |
bush | +0.112 |
remedy | +0.111 |
stump | +0.110 |
Neg logit contributions | |
their | -0.034 |
at | -0.030 |
both | -0.029 |
Tom | -0.023 |
Ben | -0.023 |
Token | and |
Token ID | 290 |
Feature activation | -5.13e-01 |
Pos logit contributions | |
outage | +0.011 |
coat | +0.010 |
bush | +0.010 |
stump | +0.010 |
smanship | +0.010 |
Neg logit contributions | |
their | -0.003 |
both | -0.003 |
at | -0.003 |
Their | -0.003 |
Ben | -0.003 |
Token | leaves |
Token ID | 5667 |
Feature activation | +2.65e+00 |
Pos logit contributions | |
their | +0.012 |
both | +0.011 |
at | +0.010 |
Their | +0.010 |
Ben | +0.010 |
Neg logit contributions | |
outage | -0.017 |
coat | -0.016 |
bush | -0.015 |
smanship | -0.015 |
stump | -0.015 |
Token | twist |
Token ID | 14528 |
Feature activation | +2.09e+00 |
Pos logit contributions | |
their | +0.034 |
both | +0.031 |
Their | +0.031 |
Ben | +0.030 |
at | +0.030 |
Neg logit contributions | |
outage | -0.047 |
coat | -0.043 |
bush | -0.042 |
stump | -0.042 |
smanship | -0.040 |
Token | . |
Token ID | 13 |
Feature activation | -6.33e-01 |
Pos logit contributions | |
outage | +0.061 |
coat | +0.057 |
stump | +0.056 |
bush | +0.056 |
remedy | +0.053 |
Neg logit contributions | |
their | -0.050 |
at | -0.046 |
both | -0.046 |
Ben | -0.044 |
Their | -0.044 |
Token | Instead |
Token ID | 5455 |
Feature activation | -3.32e-01 |
Pos logit contributions | |
their | +0.013 |
both | +0.011 |
at | +0.011 |
Their | +0.011 |
faces | +0.011 |
Neg logit contributions | |
outage | -0.021 |
stump | -0.019 |
coat | -0.019 |
bush | -0.019 |
rito | -0.017 |
Token | of |
Token ID | 286 |
Feature activation | +5.68e-01 |
Pos logit contributions | |
their | +0.004 |
our | +0.003 |
at | +0.003 |
Tom | +0.003 |
both | +0.003 |
Neg logit contributions | |
outage | -0.014 |
coat | -0.014 |
stump | -0.014 |
rito | -0.014 |
bush | -0.013 |
Token | tagging |
Token ID | 49620 |
Feature activation | -5.79e-01 |
Pos logit contributions | |
outage | +0.019 |
coat | +0.018 |
bush | +0.017 |
stump | +0.017 |
rito | +0.016 |
Neg logit contributions | |
their | -0.012 |
both | -0.011 |
Ben | -0.010 |
at | -0.010 |
Their | -0.010 |
Token | each |
Token ID | 1123 |
Feature activation | +2.04e+00 |
Pos logit contributions | |
Their | +0.009 |
their | +0.009 |
both | +0.008 |
mouths | +0.008 |
at | +0.007 |
Neg logit contributions | |
outage | -0.021 |
coat | -0.020 |
bush | -0.019 |
stump | -0.019 |
ock | -0.019 |
Token | other |
Token ID | 584 |
Feature activation | +5.84e-01 |
Pos logit contributions | |
outage | +0.078 |
coat | +0.073 |
bush | +0.071 |
stump | +0.071 |
ock | +0.068 |
Neg logit contributions | |
their | -0.031 |
Their | -0.028 |
both | -0.027 |
at | -0.026 |
Ben | -0.026 |
Token | , |
Token ID | 11 |
Feature activation | +5.33e-01 |
Pos logit contributions | |
outage | +0.021 |
coat | +0.019 |
bush | +0.019 |
stump | +0.019 |
smanship | +0.018 |
Neg logit contributions | |
their | -0.010 |
Their | -0.010 |
both | -0.009 |
at | -0.009 |
Ben | -0.009 |
Token | we |
Token ID | 356 |
Feature activation | +9.29e-01 |
Pos logit contributions | |
outage | +0.019 |
coat | +0.017 |
bush | +0.017 |
stump | +0.017 |
ock | +0.016 |
Neg logit contributions | |
Their | -0.008 |
their | -0.008 |
both | -0.007 |
mouths | -0.007 |
at | -0.007 |
Token | have |
Token ID | 423 |
Feature activation | -8.39e-01 |
Pos logit contributions | |
outage | +0.030 |
coat | +0.028 |
bush | +0.027 |
stump | +0.027 |
smanship | +0.025 |
Neg logit contributions | |
both | -0.020 |
their | -0.020 |
at | -0.018 |
Ben | -0.018 |
Their | -0.018 |
Token | to |
Token ID | 284 |
Feature activation | +8.90e-02 |
Pos logit contributions | |
their | +0.015 |
Their | +0.015 |
both | +0.014 |
Ben | +0.013 |
at | +0.013 |
Neg logit contributions | |
outage | -0.029 |
coat | -0.027 |
bush | -0.026 |
stump | -0.026 |
remedy | -0.024 |
Token | tree |
Token ID | 5509 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
both | +0.018 |
their | +0.017 |
at | +0.017 |
Tom | +0.017 |
Ben | +0.016 |
Neg logit contributions | |
outage | -0.022 |
bush | -0.018 |
reetings | -0.018 |
rito | -0.018 |
coat | -0.018 |
Token | . |
Token ID | 13 |
Feature activation | +2.82e-01 |
Pos logit contributions | |
their | +0.024 |
both | +0.021 |
Their | +0.021 |
at | +0.020 |
Ben | +0.020 |
Neg logit contributions | |
outage | -0.063 |
coat | -0.059 |
bush | -0.058 |
stump | -0.057 |
smanship | -0.054 |
Token | She |
Token ID | 1375 |
Feature activation | +7.85e-01 |
Pos logit contributions | |
outage | +0.008 |
coat | +0.008 |
bush | +0.008 |
stump | +0.008 |
remedy | +0.007 |
Neg logit contributions | |
their | -0.006 |
both | -0.006 |
our | -0.005 |
at | -0.005 |
mouths | -0.005 |
Token | felt |
Token ID | 2936 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
outage | +0.027 |
coat | +0.025 |
bush | +0.024 |
stump | +0.024 |
smanship | +0.022 |
Neg logit contributions | |
their | -0.016 |
both | -0.014 |
Their | -0.014 |
at | -0.014 |
Ben | -0.014 |
Token | proud |
Token ID | 6613 |
Feature activation | -6.01e-01 |
Pos logit contributions | |
outage | +0.071 |
coat | +0.066 |
bush | +0.064 |
stump | +0.063 |
smanship | +0.063 |
Neg logit contributions | |
their | -0.024 |
both | -0.021 |
at | -0.020 |
Their | -0.018 |
Ben | -0.017 |
Token | of |
Token ID | 286 |
Feature activation | +2.59e+00 |
Pos logit contributions | |
their | +0.015 |
Their | +0.014 |
both | +0.014 |
Ben | +0.013 |
at | +0.013 |
Neg logit contributions | |
outage | -0.018 |
coat | -0.016 |
bush | -0.016 |
stump | -0.015 |
ock | -0.014 |
Token | herself |
Token ID | 5223 |
Feature activation | +4.13e+00 |
Pos logit contributions | |
outage | +0.069 |
coat | +0.062 |
stump | +0.062 |
bush | +0.061 |
ock | +0.057 |
Neg logit contributions | |
their | -0.067 |
Their | -0.065 |
both | -0.063 |
mouths | -0.062 |
at | -0.062 |
Token | for |
Token ID | 329 |
Feature activation | +8.18e-01 |
Pos logit contributions | |
outage | +0.127 |
stump | +0.117 |
coat | +0.115 |
bush | +0.113 |
smanship | +0.107 |
Neg logit contributions | |
their | -0.088 |
Their | -0.088 |
mouths | -0.084 |
Ben | -0.080 |
both | -0.078 |
Token | being |
Token ID | 852 |
Feature activation | +2.32e+00 |
Pos logit contributions | |
outage | +0.024 |
coat | +0.022 |
stump | +0.022 |
bush | +0.021 |
remedy | +0.020 |
Neg logit contributions | |
their | -0.018 |
Their | -0.018 |
both | -0.017 |
mouths | -0.017 |
Ben | -0.017 |
Token | able |
Token ID | 1498 |
Feature activation | -9.17e-01 |
Pos logit contributions | |
outage | +0.073 |
coat | +0.067 |
bush | +0.066 |
stump | +0.065 |
smanship | +0.061 |
Neg logit contributions | |
their | -0.052 |
Their | -0.048 |
both | -0.048 |
at | -0.046 |
Ben | -0.045 |
Token | to |
Token ID | 284 |
Feature activation | +3.46e-01 |
Pos logit contributions | |
their | +0.014 |
both | +0.013 |
at | +0.013 |
Ben | +0.011 |
Tom | +0.011 |
Neg logit contributions | |
outage | -0.036 |
coat | -0.034 |
bush | -0.033 |
stump | -0.033 |
smanship | -0.032 |
Token | so |
Token ID | 523 |
Feature activation | +8.14e-01 |
Pos logit contributions | |
outage | +0.031 |
coat | +0.029 |
stump | +0.029 |
bush | +0.028 |
remedy | +0.027 |
Neg logit contributions | |
their | -0.015 |
Their | -0.014 |
Ben | -0.013 |
both | -0.013 |
mouths | -0.013 |
Token | happy |
Token ID | 3772 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
outage | +0.027 |
coat | +0.025 |
stump | +0.025 |
bush | +0.024 |
remedy | +0.023 |
Neg logit contributions | |
their | -0.015 |
Their | -0.014 |
Ben | -0.013 |
mouths | -0.013 |
both | -0.013 |
Token | ! |
Token ID | 0 |
Feature activation | +8.57e-01 |
Pos logit contributions | |
their | +0.030 |
Their | +0.027 |
both | +0.026 |
Ben | +0.025 |
at | +0.024 |
Neg logit contributions | |
outage | -0.069 |
coat | -0.065 |
bush | -0.063 |
stump | -0.063 |
ock | -0.059 |
Token | She |
Token ID | 1375 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
outage | +0.028 |
coat | +0.025 |
ock | +0.024 |
smanship | +0.024 |
stump | +0.024 |
Neg logit contributions | |
their | -0.018 |
Their | -0.018 |
Ben | -0.018 |
Tom | -0.018 |
both | -0.017 |
Token | ate |
Token ID | 15063 |
Feature activation | +6.86e-02 |
Pos logit contributions | |
coat | +0.028 |
outage | +0.027 |
stump | +0.027 |
bush | +0.026 |
remedy | +0.025 |
Neg logit contributions | |
their | -0.021 |
Their | -0.020 |
Ben | -0.019 |
mouths | -0.019 |
our | -0.019 |
Token | all |
Token ID | 477 |
Feature activation | +4.47e+00 |
Pos logit contributions | |
outage | +0.003 |
coat | +0.002 |
bush | +0.002 |
stump | +0.002 |
remedy | +0.002 |
Neg logit contributions | |
their | -0.001 |
Their | -0.001 |
both | -0.001 |
Ben | -0.001 |
at | -0.001 |
Token | the |
Token ID | 262 |
Feature activation | +2.68e+00 |
Pos logit contributions | |
outage | +0.206 |
coat | +0.193 |
stump | +0.190 |
bush | +0.188 |
smanship | +0.179 |
Neg logit contributions | |
their | -0.049 |
both | -0.037 |
Their | -0.034 |
at | -0.033 |
Tom | -0.031 |
Token | beef |
Token ID | 12023 |
Feature activation | -4.42e-01 |
Pos logit contributions | |
outage | +0.086 |
coat | +0.078 |
bush | +0.076 |
stump | +0.073 |
ock | +0.068 |
Neg logit contributions | |
their | -0.066 |
both | -0.061 |
at | -0.058 |
Their | -0.057 |
our | -0.057 |
Token | and |
Token ID | 290 |
Feature activation | -8.30e-01 |
Pos logit contributions | |
their | +0.007 |
Their | +0.006 |
both | +0.006 |
Ben | +0.006 |
Tom | +0.006 |
Neg logit contributions | |
outage | -0.016 |
coat | -0.015 |
stump | -0.015 |
bush | -0.015 |
smanship | -0.014 |
Token | felt |
Token ID | 2936 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
Their | +0.015 |
their | +0.015 |
both | +0.014 |
at | +0.014 |
our | +0.013 |
Neg logit contributions | |
outage | -0.026 |
coat | -0.025 |
stump | -0.025 |
bush | -0.025 |
remedy | -0.024 |
Token | very |
Token ID | 845 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
outage | +0.044 |
coat | +0.041 |
bush | +0.040 |
stump | +0.040 |
rito | +0.038 |
Neg logit contributions | |
their | -0.023 |
Their | -0.021 |
both | -0.020 |
Ben | -0.020 |
Tom | -0.019 |
Token | my |
Token ID | 1820 |
Feature activation | -5.52e-01 |
Pos logit contributions | |
their | +0.016 |
Their | +0.016 |
both | +0.015 |
at | +0.015 |
Ben | +0.015 |
Neg logit contributions | |
outage | -0.007 |
coat | -0.006 |
stump | -0.006 |
bush | -0.006 |
ock | -0.005 |
Token | was |
Token ID | 373 |
Feature activation | +6.99e-01 |
Pos logit contributions | |
their | +0.008 |
Their | +0.008 |
both | +0.008 |
mouths | +0.007 |
our | +0.007 |
Neg logit contributions | |
outage | -0.020 |
coat | -0.019 |
stump | -0.018 |
bush | -0.018 |
ock | -0.017 |
Token | playing |
Token ID | 2712 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
outage | +0.023 |
coat | +0.023 |
stump | +0.021 |
bush | +0.021 |
remedy | +0.020 |
Neg logit contributions | |
their | -0.013 |
Their | -0.012 |
mouths | -0.012 |
both | -0.011 |
Ben | -0.011 |
Token | with |
Token ID | 351 |
Feature activation | -6.62e-01 |
Pos logit contributions | |
outage | +0.040 |
coat | +0.039 |
stump | +0.037 |
bush | +0.037 |
ock | +0.035 |
Neg logit contributions | |
their | -0.018 |
Their | -0.018 |
mouths | -0.017 |
both | -0.017 |
Ben | -0.016 |
Token | his |
Token ID | 465 |
Feature activation | +4.23e-01 |
Pos logit contributions | |
Their | +0.008 |
their | +0.008 |
mouths | +0.007 |
at | +0.007 |
both | +0.007 |
Neg logit contributions | |
outage | -0.025 |
coat | -0.024 |
stump | -0.023 |
ock | -0.023 |
bush | -0.022 |
Token | toys |
Token ID | 14958 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
coat | +0.011 |
outage | +0.011 |
stump | +0.009 |
iest | +0.009 |
ock | +0.009 |
Neg logit contributions | |
Ben | -0.010 |
Their | -0.010 |
their | -0.010 |
Tom | -0.009 |
mouths | -0.009 |
Token | outside |
Token ID | 2354 |
Feature activation | -5.20e-02 |
Pos logit contributions | |
outage | +0.037 |
coat | +0.035 |
bush | +0.034 |
stump | +0.034 |
smanship | +0.032 |
Neg logit contributions | |
their | -0.017 |
Their | -0.015 |
both | -0.015 |
Ben | -0.014 |
at | -0.014 |
Token | when |
Token ID | 618 |
Feature activation | +2.78e-01 |
Pos logit contributions | |
Their | +0.001 |
their | +0.001 |
mouths | +0.001 |
faces | +0.001 |
both | +0.001 |
Neg logit contributions | |
outage | -0.002 |
stump | -0.002 |
coat | -0.001 |
ock | -0.001 |
smanship | -0.001 |
Token | his |
Token ID | 465 |
Feature activation | -3.08e+00 |
Pos logit contributions | |
outage | +0.010 |
coat | +0.009 |
bush | +0.009 |
stump | +0.009 |
rito | +0.008 |
Neg logit contributions | |
their | -0.005 |
both | -0.005 |
Their | -0.005 |
Ben | -0.005 |
at | -0.005 |
Token | mom |
Token ID | 1995 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
their | +0.049 |
Their | +0.049 |
cks | +0.045 |
both | +0.043 |
our | +0.042 |
Neg logit contributions | |
outage | -0.107 |
coat | -0.107 |
stump | -0.093 |
guard | -0.090 |
bush | -0.089 |
Token | called |
Token ID | 1444 |
Feature activation | -5.17e-01 |
Pos logit contributions | |
their | +0.041 |
Their | +0.039 |
mouths | +0.038 |
our | +0.038 |
both | +0.037 |
Neg logit contributions | |
outage | -0.048 |
coat | -0.048 |
stump | -0.043 |
bush | -0.042 |
ock | -0.042 |
Token | Tim |
Token ID | 14967 |
Feature activation | -4.48e-01 |
Pos logit contributions | |
their | +0.002 |
Their | +0.002 |
both | +0.002 |
at | +0.002 |
Ben | +0.002 |
Neg logit contributions | |
outage | -0.002 |
coat | -0.002 |
bush | -0.002 |
stump | -0.002 |
ock | -0.002 |
Token | my |
Token ID | 1820 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
their | +0.015 |
both | +0.014 |
at | +0.014 |
Tom | +0.014 |
Ben | +0.014 |
Neg logit contributions | |
outage | -0.009 |
bush | -0.008 |
coat | -0.008 |
stump | -0.007 |
pleasures | -0.007 |
Token | was |
Token ID | 373 |
Feature activation | -1.72e-02 |
Pos logit contributions | |
their | +0.018 |
both | +0.016 |
at | +0.016 |
Their | +0.016 |
Ben | +0.016 |
Neg logit contributions | |
outage | -0.041 |
coat | -0.038 |
bush | -0.037 |
stump | -0.037 |
rito | -0.035 |
Token | so |
Token ID | 523 |
Feature activation | +5.61e-01 |
Pos logit contributions | |
Their | +0.000 |
their | +0.000 |
mouths | +0.000 |
faces | +0.000 |
both | +0.000 |
Neg logit contributions | |
outage | -0.001 |
stump | -0.001 |
coat | -0.001 |
bush | -0.001 |
remedy | -0.000 |
Token | brave |
Token ID | 14802 |
Feature activation | -3.45e-01 |
Pos logit contributions | |
outage | +0.019 |
stump | +0.017 |
bush | +0.017 |
coat | +0.016 |
rito | +0.016 |
Neg logit contributions | |
their | -0.011 |
mouths | -0.010 |
Their | -0.010 |
both | -0.009 |
faces | -0.009 |
Token | to |
Token ID | 284 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
their | +0.006 |
at | +0.005 |
both | +0.005 |
Ben | +0.005 |
Tom | +0.005 |
Neg logit contributions | |
outage | -0.013 |
coat | -0.012 |
bush | -0.012 |
stump | -0.011 |
rito | -0.011 |
Token | go |
Token ID | 467 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
outage | +0.040 |
coat | +0.036 |
stump | +0.036 |
bush | +0.036 |
remedy | +0.033 |
Neg logit contributions | |
their | -0.030 |
Their | -0.029 |
at | -0.028 |
mouths | -0.028 |
both | -0.027 |
Token | out |
Token ID | 503 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
their | +0.030 |
Their | +0.028 |
both | +0.027 |
Ben | +0.026 |
mouths | +0.026 |
Neg logit contributions | |
outage | -0.053 |
coat | -0.049 |
bush | -0.048 |
stump | -0.048 |
rito | -0.045 |
Token | and |
Token ID | 290 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
their | +0.029 |
Their | +0.028 |
both | +0.026 |
mouths | +0.026 |
Ben | +0.025 |
Neg logit contributions | |
outage | -0.053 |
coat | -0.047 |
stump | -0.047 |
bush | -0.047 |
ock | -0.044 |
Token | find |
Token ID | 1064 |
Feature activation | -9.93e-02 |
Pos logit contributions | |
outage | +0.005 |
coat | +0.005 |
bush | +0.005 |
stump | +0.004 |
smanship | +0.004 |
Neg logit contributions | |
their | -0.003 |
both | -0.003 |
Their | -0.003 |
at | -0.003 |
Ben | -0.003 |
Token | food |
Token ID | 2057 |
Feature activation | -8.72e-01 |
Pos logit contributions | |
Their | +0.002 |
mouths | +0.002 |
their | +0.002 |
both | +0.002 |
faces | +0.001 |
Neg logit contributions | |
outage | -0.003 |
ock | -0.003 |
stump | -0.003 |
bush | -0.003 |
remedy | -0.003 |
Token | and |
Token ID | 290 |
Feature activation | -2.07e-01 |
Pos logit contributions | |
outage | +0.033 |
coat | +0.031 |
stump | +0.031 |
bush | +0.031 |
ock | +0.029 |
Neg logit contributions | |
their | -0.015 |
Their | -0.014 |
both | -0.013 |
Ben | -0.013 |
Tom | -0.013 |
Token | the |
Token ID | 262 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
Their | +0.004 |
their | +0.004 |
our | +0.004 |
both | +0.004 |
mouths | +0.003 |
Neg logit contributions | |
outage | -0.006 |
stump | -0.006 |
bush | -0.006 |
coat | -0.006 |
colder | -0.005 |
Token | bubbles |
Token ID | 25037 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
outage | +0.052 |
coat | +0.048 |
bush | +0.046 |
stump | +0.046 |
rito | +0.043 |
Neg logit contributions | |
their | -0.035 |
Their | -0.032 |
both | -0.032 |
at | -0.031 |
Ben | -0.030 |
Token | . |
Token ID | 13 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
outage | +0.072 |
coat | +0.067 |
bush | +0.066 |
stump | +0.066 |
smanship | +0.062 |
Neg logit contributions | |
their | -0.029 |
Their | -0.026 |
both | -0.025 |
Ben | -0.024 |
at | -0.024 |
Token | He |
Token ID | 679 |
Feature activation | -4.25e-02 |
Pos logit contributions | |
outage | +0.003 |
stump | +0.003 |
coat | +0.002 |
bush | +0.002 |
rito | +0.002 |
Neg logit contributions | |
their | -0.002 |
both | -0.002 |
at | -0.002 |
our | -0.002 |
faces | -0.002 |
Token | did |
Token ID | 750 |
Feature activation | -1.98e+00 |
Pos logit contributions | |
their | +0.001 |
Their | +0.001 |
our | +0.001 |
mouths | +0.001 |
both | +0.001 |
Neg logit contributions | |
outage | -0.001 |
coat | -0.001 |
stump | -0.001 |
bush | -0.001 |
rito | -0.001 |
Token | not |
Token ID | 407 |
Feature activation | +3.12e-01 |
Pos logit contributions | |
Their | +0.037 |
mouths | +0.035 |
their | +0.032 |
both | +0.032 |
hands | +0.032 |
Neg logit contributions | |
outage | -0.060 |
stump | -0.055 |
bush | -0.055 |
coat | -0.054 |
colder | -0.050 |
Token | want |
Token ID | 765 |
Feature activation | -2.70e+00 |
Pos logit contributions | |
outage | +0.009 |
coat | +0.008 |
bush | +0.008 |
stump | +0.008 |
smanship | +0.007 |
Neg logit contributions | |
their | -0.008 |
both | -0.008 |
Their | -0.008 |
Ben | -0.007 |
at | -0.007 |
Token | to |
Token ID | 284 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
Their | +0.051 |
their | +0.049 |
both | +0.049 |
at | +0.047 |
mouths | +0.046 |
Neg logit contributions | |
outage | -0.084 |
coat | -0.076 |
stump | -0.073 |
ock | -0.073 |
bush | -0.073 |
Token | admit |
Token ID | 9159 |
Feature activation | -8.82e-01 |
Pos logit contributions | |
outage | +0.004 |
coat | +0.003 |
stump | +0.003 |
bush | +0.003 |
ock | +0.003 |
Neg logit contributions | |
their | -0.003 |
Their | -0.003 |
both | -0.002 |
at | -0.002 |
mouths | -0.002 |
Token | it |
Token ID | 340 |
Feature activation | +5.58e-01 |
Pos logit contributions | |
mouths | +0.018 |
both | +0.018 |
Their | +0.018 |
ra | +0.017 |
faces | +0.016 |
Neg logit contributions | |
outage | -0.025 |
bush | -0.021 |
coat | -0.021 |
stump | -0.021 |
ock | -0.021 |
Token | placed |
Token ID | 4624 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
outage | +0.003 |
coat | +0.003 |
bush | +0.003 |
stump | +0.003 |
rito | +0.003 |
Neg logit contributions | |
their | -0.002 |
Their | -0.002 |
both | -0.002 |
Ben | -0.002 |
at | -0.002 |
Token | it |
Token ID | 340 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
outage | +0.059 |
coat | +0.057 |
bush | +0.056 |
stump | +0.056 |
rito | +0.053 |
Neg logit contributions | |
their | -0.027 |
Their | -0.027 |
both | -0.024 |
at | -0.023 |
mouths | -0.023 |
Token | in |
Token ID | 287 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
outage | +0.064 |
coat | +0.060 |
bush | +0.059 |
stump | +0.059 |
smanship | +0.056 |
Neg logit contributions | |
their | -0.021 |
Their | -0.019 |
both | -0.019 |
Ben | -0.017 |
at | -0.017 |
Token | the |
Token ID | 262 |
Feature activation | +1.42e-02 |
Pos logit contributions | |
their | +0.017 |
Their | +0.015 |
both | +0.015 |
at | +0.014 |
Ben | +0.014 |
Neg logit contributions | |
outage | -0.056 |
coat | -0.053 |
stump | -0.052 |
bush | -0.052 |
smanship | -0.049 |
Token | sunshine |
Token ID | 34488 |
Feature activation | -2.47e-01 |
Pos logit contributions | |
outage | +0.000 |
coat | +0.000 |
bush | +0.000 |
stump | +0.000 |
smanship | +0.000 |
Neg logit contributions | |
their | -0.000 |
both | -0.000 |
Their | -0.000 |
Ben | -0.000 |
at | -0.000 |
Token | . |
Token ID | 13 |
Feature activation | +3.97e-02 |
Pos logit contributions | |
their | +0.003 |
both | +0.003 |
Their | +0.003 |
at | +0.003 |
Ben | +0.003 |
Neg logit contributions | |
outage | -0.010 |
coat | -0.009 |
bush | -0.009 |
stump | -0.009 |
smanship | -0.009 |
Token | She |
Token ID | 1375 |
Feature activation | +7.28e-01 |
Pos logit contributions | |
outage | +0.001 |
coat | +0.001 |
bush | +0.001 |
stump | +0.001 |
smanship | +0.001 |
Neg logit contributions | |
their | -0.001 |
Their | -0.001 |
both | -0.001 |
Ben | -0.001 |
Tom | -0.001 |
Token | waited |
Token ID | 13488 |
Feature activation | +2.73e+00 |
Pos logit contributions | |
outage | +0.023 |
coat | +0.022 |
bush | +0.021 |
stump | +0.021 |
smanship | +0.020 |
Neg logit contributions | |
their | -0.015 |
Their | -0.014 |
both | -0.014 |
Ben | -0.014 |
at | -0.013 |
Token | and |
Token ID | 290 |
Feature activation | +3.48e-01 |
Pos logit contributions | |
outage | +0.096 |
coat | +0.090 |
bush | +0.088 |
stump | +0.087 |
rito | +0.082 |
Neg logit contributions | |
their | -0.048 |
Their | -0.045 |
both | -0.043 |
Ben | -0.041 |
Tom | -0.041 |
Token | waited |
Token ID | 13488 |
Feature activation | +2.24e+00 |
Pos logit contributions | |
outage | +0.011 |
coat | +0.010 |
stump | +0.010 |
bush | +0.010 |
remedy | +0.009 |
Neg logit contributions | |
their | -0.007 |
Their | -0.007 |
both | -0.006 |
mouths | -0.006 |
at | -0.006 |
Token | until |
Token ID | 1566 |
Feature activation | -8.34e-02 |
Pos logit contributions | |
outage | +0.078 |
coat | +0.074 |
bush | +0.071 |
stump | +0.071 |
ock | +0.067 |
Neg logit contributions | |
their | -0.039 |
Their | -0.037 |
both | -0.035 |
mouths | -0.034 |
Ben | -0.034 |
Token | . |
Token ID | 13 |
Feature activation | -2.09e-01 |
Pos logit contributions | |
their | +0.000 |
Their | +0.000 |
both | +0.000 |
Ben | +0.000 |
mouths | +0.000 |
Neg logit contributions | |
outage | -0.001 |
coat | -0.001 |
bush | -0.001 |
stump | -0.001 |
ock | -0.001 |
Token | From |
Token ID | 3574 |
Feature activation | -8.00e-01 |
Pos logit contributions | |
their | +0.003 |
both | +0.003 |
Their | +0.003 |
at | +0.003 |
Ben | +0.003 |
Neg logit contributions | |
outage | -0.008 |
coat | -0.007 |
bush | -0.007 |
stump | -0.007 |
ock | -0.007 |
Token | then |
Token ID | 788 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
their | +0.010 |
both | +0.008 |
Their | +0.008 |
at | +0.008 |
Ben | +0.007 |
Neg logit contributions | |
outage | -0.034 |
coat | -0.032 |
stump | -0.031 |
bush | -0.031 |
smanship | -0.030 |
Token | on |
Token ID | 319 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
outage | +0.049 |
coat | +0.046 |
bush | +0.045 |
stump | +0.044 |
ock | +0.043 |
Neg logit contributions | |
their | -0.019 |
Their | -0.017 |
both | -0.017 |
Ben | -0.016 |
mouths | -0.016 |
Token | , |
Token ID | 11 |
Feature activation | +7.40e-01 |
Pos logit contributions | |
their | +0.021 |
Their | +0.019 |
both | +0.019 |
Ben | +0.017 |
at | +0.017 |
Neg logit contributions | |
outage | -0.046 |
coat | -0.043 |
bush | -0.043 |
stump | -0.042 |
smanship | -0.040 |
Token | the |
Token ID | 262 |
Feature activation | +6.10e-01 |
Pos logit contributions | |
outage | +0.022 |
coat | +0.021 |
bush | +0.021 |
stump | +0.020 |
smanship | +0.019 |
Neg logit contributions | |
their | -0.015 |
Their | -0.015 |
both | -0.014 |
mouths | -0.014 |
faces | -0.014 |
Token | bunny |
Token ID | 44915 |
Feature activation | -2.07e+00 |
Pos logit contributions | |
outage | +0.023 |
coat | +0.020 |
stump | +0.019 |
bush | +0.019 |
smanship | +0.019 |
Neg logit contributions | |
their | -0.011 |
both | -0.011 |
at | -0.011 |
Ben | -0.011 |
mom | -0.010 |
Token | wandered |
Token ID | 36036 |
Feature activation | +8.89e-01 |
Pos logit contributions | |
their | +0.046 |
both | +0.043 |
at | +0.042 |
Their | +0.042 |
Ben | +0.041 |
Neg logit contributions | |
outage | -0.066 |
coat | -0.060 |
stump | -0.058 |
bush | -0.058 |
rito | -0.055 |
Token | to |
Token ID | 284 |
Feature activation | +7.28e-01 |
Pos logit contributions | |
outage | +0.033 |
coat | +0.029 |
stump | +0.029 |
bush | +0.028 |
smanship | +0.028 |
Neg logit contributions | |
their | -0.018 |
both | -0.016 |
at | -0.016 |
Ben | -0.014 |
Their | -0.014 |
Token | the |
Token ID | 262 |
Feature activation | +6.06e-01 |
Pos logit contributions | |
outage | +0.028 |
coat | +0.026 |
bush | +0.025 |
stump | +0.025 |
smanship | +0.024 |
Neg logit contributions | |
their | -0.012 |
both | -0.010 |
Their | -0.010 |
Ben | -0.010 |
at | -0.009 |
Token | me |
Token ID | 502 |
Feature activation | -4.98e-02 |
Pos logit contributions | |
outage | +0.022 |
coat | +0.020 |
stump | +0.019 |
bush | +0.019 |
smanship | +0.019 |
Neg logit contributions | |
their | -0.011 |
both | -0.011 |
at | -0.010 |
Ben | -0.010 |
our | -0.010 |
Token | my |
Token ID | 1820 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
outage | +0.024 |
coat | +0.021 |
stump | +0.020 |
bush | +0.020 |
ock | +0.018 |
Neg logit contributions | |
their | -0.050 |
Their | -0.048 |
both | -0.048 |
Ben | -0.047 |
at | -0.046 |
Token | . |
Token ID | 13 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
outage | +0.038 |
stump | +0.036 |
coat | +0.036 |
ock | +0.034 |
bush | +0.033 |
Neg logit contributions | |
their | -0.020 |
Their | -0.019 |
mouths | -0.018 |
Ben | -0.018 |
both | -0.017 |
Token | Tim |
Token ID | 5045 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
their | +0.001 |
Their | +0.001 |
both | +0.001 |
Tom | +0.001 |
Ben | +0.001 |
Neg logit contributions | |
outage | -0.006 |
bush | -0.005 |
coat | -0.005 |
stump | -0.005 |
rito | -0.005 |
Token | my |
Token ID | 1820 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
outage | +0.030 |
bush | +0.027 |
coat | +0.026 |
stump | +0.024 |
remedy | +0.023 |
Neg logit contributions | |
their | -0.048 |
both | -0.046 |
Their | -0.045 |
at | -0.044 |
Tom | -0.044 |
Token | had |
Token ID | 550 |
Feature activation | +9.30e-01 |
Pos logit contributions | |
outage | +0.036 |
coat | +0.034 |
stump | +0.033 |
bush | +0.031 |
smanship | +0.030 |
Neg logit contributions | |
their | -0.028 |
Their | -0.026 |
both | -0.026 |
mouths | -0.025 |
Ben | -0.025 |
Token | a |
Token ID | 257 |
Feature activation | +3.53e-01 |
Pos logit contributions | |
coat | +0.027 |
outage | +0.026 |
stump | +0.026 |
colder | +0.023 |
remedy | +0.022 |
Neg logit contributions | |
mouths | -0.018 |
Their | -0.018 |
their | -0.017 |
cks | -0.016 |
faces | -0.016 |
Token | toy |
Token ID | 13373 |
Feature activation | +2.08e+00 |
Pos logit contributions | |
coat | +0.011 |
outage | +0.011 |
stump | +0.010 |
remedy | +0.010 |
bush | +0.010 |
Neg logit contributions | |
their | -0.007 |
both | -0.007 |
Their | -0.007 |
Tom | -0.006 |
cks | -0.006 |
Token | hammer |
Token ID | 15554 |
Feature activation | +4.14e+00 |
Pos logit contributions | |
outage | +0.064 |
coat | +0.059 |
stump | +0.058 |
bush | +0.054 |
smanship | +0.053 |
Neg logit contributions | |
their | -0.043 |
Their | -0.040 |
both | -0.038 |
cks | -0.037 |
Tom | -0.037 |
Token | that |
Token ID | 326 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
outage | +0.177 |
bush | +0.165 |
coat | +0.164 |
stump | +0.162 |
pleasures | +0.158 |
Neg logit contributions | |
their | -0.046 |
both | -0.041 |
at | -0.041 |
Their | -0.037 |
Ben | -0.035 |
Token | he |
Token ID | 339 |
Feature activation | -9.39e-01 |
Pos logit contributions | |
outage | +0.050 |
coat | +0.046 |
bush | +0.045 |
stump | +0.044 |
pleasures | +0.042 |
Neg logit contributions | |
their | -0.030 |
both | -0.027 |
Their | -0.026 |
Ben | -0.026 |
Tom | -0.026 |
Token | loved |
Token ID | 6151 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
their | +0.023 |
Their | +0.021 |
Ben | +0.021 |
Tom | +0.020 |
mouths | +0.020 |
Neg logit contributions | |
outage | -0.026 |
coat | -0.025 |
stump | -0.024 |
bush | -0.023 |
rito | -0.022 |
Token | the |
Token ID | 262 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
Their | +0.003 |
mouths | +0.003 |
faces | +0.003 |
their | +0.002 |
ast | +0.002 |
Neg logit contributions | |
outage | -0.006 |
coat | -0.006 |
bush | -0.005 |
iest | -0.005 |
stump | -0.005 |
Token | sund |
Token ID | 37437 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
outage | +0.040 |
coat | +0.038 |
stump | +0.036 |
bush | +0.036 |
remedy | +0.035 |
Neg logit contributions | |
their | -0.029 |
Their | -0.028 |
both | -0.026 |
Ben | -0.025 |
Tom | -0.025 |
Token | ae |
Token ID | 3609 |
Feature activation | -4.43e-02 |
Pos logit contributions | |
their | +0.030 |
Their | +0.028 |
both | +0.027 |
Ben | +0.026 |
at | +0.026 |
Neg logit contributions | |
outage | -0.034 |
coat | -0.031 |
bush | -0.030 |
stump | -0.030 |
smanship | -0.028 |
Token | over |
Token ID | 625 |
Feature activation | -2.05e+00 |
Pos logit contributions | |
Their | +0.001 |
their | +0.001 |
both | +0.001 |
Ben | +0.001 |
Tom | +0.001 |
Neg logit contributions | |
outage | -0.002 |
coat | -0.001 |
bush | -0.001 |
stump | -0.001 |
rito | -0.001 |
Token | , |
Token ID | 11 |
Feature activation | +9.09e-01 |
Pos logit contributions | |
Their | +0.038 |
our | +0.035 |
their | +0.035 |
cks | +0.034 |
both | +0.034 |
Neg logit contributions | |
outage | -0.061 |
coat | -0.060 |
bush | -0.057 |
stump | -0.057 |
smanship | -0.056 |
Token | Tim |
Token ID | 5045 |
Feature activation | -9.89e-01 |
Pos logit contributions | |
outage | +0.032 |
bush | +0.031 |
coat | +0.031 |
stump | +0.030 |
remedy | +0.028 |
Neg logit contributions | |
Their | -0.013 |
their | -0.013 |
mouths | -0.012 |
both | -0.012 |
faces | -0.011 |
Token | my |
Token ID | 1820 |
Feature activation | -9.26e-01 |
Pos logit contributions | |
their | +0.037 |
Their | +0.036 |
both | +0.035 |
at | +0.034 |
Ben | +0.034 |
Neg logit contributions | |
outage | -0.015 |
coat | -0.013 |
stump | -0.012 |
bush | -0.012 |
smanship | -0.011 |
Token | remembered |
Token ID | 12086 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
their | +0.019 |
Their | +0.018 |
our | +0.017 |
mouths | +0.016 |
both | +0.016 |
Neg logit contributions | |
outage | -0.028 |
coat | -0.028 |
bush | -0.027 |
stump | -0.027 |
remedy | -0.025 |
Token | what |
Token ID | 644 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
their | +0.014 |
Their | +0.013 |
both | +0.013 |
mouths | +0.012 |
Ben | +0.012 |
Neg logit contributions | |
outage | -0.039 |
coat | -0.036 |
bush | -0.036 |
stump | -0.035 |
remedy | -0.034 |
Token | his |
Token ID | 465 |
Feature activation | -2.73e+00 |
Pos logit contributions | |
their | +0.024 |
Their | +0.022 |
both | +0.022 |
at | +0.020 |
mouths | +0.020 |
Neg logit contributions | |
outage | -0.063 |
coat | -0.058 |
stump | -0.057 |
bush | -0.057 |
remedy | -0.054 |
Token | mom |
Token ID | 1995 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
their | +0.036 |
Their | +0.034 |
both | +0.029 |
Their | +0.028 |
our | +0.028 |
Neg logit contributions | |
outage | -0.104 |
coat | -0.098 |
stump | -0.098 |
remedy | -0.096 |
bush | -0.094 |
Token | up |
Token ID | 510 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
outage | +0.030 |
coat | +0.029 |
bush | +0.028 |
stump | +0.028 |
ock | +0.027 |
Neg logit contributions | |
Their | -0.031 |
mouths | -0.027 |
their | -0.026 |
both | -0.025 |
ast | -0.024 |
Token | the |
Token ID | 262 |
Feature activation | -1.73e-01 |
Pos logit contributions | |
their | +0.027 |
Their | +0.026 |
both | +0.024 |
Ben | +0.023 |
mouths | +0.023 |
Neg logit contributions | |
outage | -0.073 |
coat | -0.068 |
bush | -0.067 |
stump | -0.067 |
ock | -0.063 |
Token | mess |
Token ID | 2085 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
their | +0.003 |
both | +0.003 |
at | +0.003 |
mouths | +0.003 |
faces | +0.003 |
Neg logit contributions | |
outage | -0.006 |
coat | -0.006 |
bush | -0.006 |
stump | -0.006 |
adows | -0.006 |
Token | and |
Token ID | 290 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
outage | +0.005 |
coat | +0.005 |
bush | +0.005 |
stump | +0.005 |
ock | +0.005 |
Neg logit contributions | |
their | -0.003 |
Their | -0.002 |
both | -0.002 |
Ben | -0.002 |
mouths | -0.002 |
Token | say |
Token ID | 910 |
Feature activation | -1.95e+00 |
Pos logit contributions | |
their | +0.030 |
Their | +0.029 |
both | +0.028 |
at | +0.027 |
Ben | +0.026 |
Neg logit contributions | |
outage | -0.045 |
coat | -0.041 |
bush | -0.040 |
stump | -0.040 |
remedy | -0.037 |
Token | sorry |
Token ID | 7926 |
Feature activation | -3.26e+00 |
Pos logit contributions | |
their | +0.022 |
Their | +0.022 |
both | +0.020 |
cks | +0.020 |
mouths | +0.020 |
Neg logit contributions | |
outage | -0.071 |
coat | -0.065 |
bush | -0.063 |
injection | -0.061 |
ock | -0.061 |
Token | to |
Token ID | 284 |
Feature activation | -9.69e-01 |
Pos logit contributions | |
their | +0.057 |
both | +0.051 |
Their | +0.050 |
at | +0.049 |
Ben | +0.049 |
Neg logit contributions | |
outage | -0.119 |
coat | -0.112 |
bush | -0.110 |
stump | -0.109 |
smanship | -0.104 |
Token | each |
Token ID | 1123 |
Feature activation | +6.41e-01 |
Pos logit contributions | |
Their | +0.015 |
mouths | +0.014 |
icked | +0.013 |
at | +0.013 |
eg | +0.012 |
Neg logit contributions | |
outage | -0.028 |
ock | -0.027 |
stump | -0.027 |
reating | -0.026 |
bush | -0.026 |
Token | other |
Token ID | 584 |
Feature activation | -7.85e-01 |
Pos logit contributions | |
outage | +0.023 |
coat | +0.021 |
ock | +0.021 |
stump | +0.021 |
bush | +0.020 |
Neg logit contributions | |
their | -0.010 |
Their | -0.010 |
mouths | -0.009 |
both | -0.009 |
at | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | -6.42e-01 |
Pos logit contributions | |
their | +0.013 |
Their | +0.012 |
both | +0.012 |
Ben | +0.011 |
mouths | +0.011 |
Neg logit contributions | |
outage | -0.029 |
coat | -0.027 |
bush | -0.026 |
stump | -0.026 |
ock | -0.024 |
Token | And |
Token ID | 843 |
Feature activation | -2.30e+00 |
Pos logit contributions | |
their | +0.012 |
both | +0.011 |
at | +0.011 |
Their | +0.011 |
mouths | +0.010 |
Neg logit contributions | |
outage | -0.022 |
coat | -0.020 |
stump | -0.019 |
bush | -0.019 |
rito | -0.018 |
Token | the |
Token ID | 262 |
Feature activation | +2.04e-01 |
Pos logit contributions | |
stump | +0.028 |
bush | +0.026 |
outage | +0.026 |
remedy | +0.026 |
colder | +0.026 |
Neg logit contributions | |
mouths | -0.015 |
Their | -0.015 |
ra | -0.015 |
ast | -0.015 |
pler | -0.014 |
Token | big |
Token ID | 1263 |
Feature activation | -2.27e+00 |
Pos logit contributions | |
outage | +0.006 |
stump | +0.005 |
coat | +0.005 |
bush | +0.005 |
ock | +0.005 |
Neg logit contributions | |
Their | -0.005 |
their | -0.005 |
Tom | -0.004 |
both | -0.004 |
at | -0.004 |
Token | fish |
Token ID | 5916 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
their | +0.044 |
both | +0.039 |
Ben | +0.039 |
at | +0.038 |
Their | +0.038 |
Neg logit contributions | |
outage | -0.080 |
coat | -0.075 |
bush | -0.073 |
stump | -0.071 |
smanship | -0.068 |
Token | and |
Token ID | 290 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
their | +0.025 |
Their | +0.025 |
both | +0.023 |
Ben | +0.023 |
Tom | +0.023 |
Neg logit contributions | |
outage | -0.053 |
stump | -0.048 |
coat | -0.047 |
bush | -0.047 |
row | -0.045 |
Token | said |
Token ID | 531 |
Feature activation | -8.88e-02 |
Pos logit contributions | |
Their | +0.023 |
their | +0.022 |
mouths | +0.021 |
at | +0.021 |
both | +0.020 |
Neg logit contributions | |
outage | -0.039 |
stump | -0.037 |
coat | -0.036 |
bush | -0.036 |
colder | -0.034 |
Token | hello |
Token ID | 23748 |
Feature activation | -3.59e+00 |
Pos logit contributions | |
both | +0.002 |
mouths | +0.002 |
their | +0.002 |
ra | +0.002 |
cks | +0.002 |
Neg logit contributions | |
outage | -0.003 |
bush | -0.002 |
coat | -0.002 |
reetings | -0.002 |
stump | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | -4.77e-02 |
Pos logit contributions | |
Their | +0.072 |
their | +0.069 |
mouths | +0.067 |
both | +0.066 |
Ben | +0.063 |
Neg logit contributions | |
outage | -0.108 |
coat | -0.100 |
stump | -0.096 |
bush | -0.096 |
wood | -0.092 |
Token | The |
Token ID | 383 |
Feature activation | +5.94e-01 |
Pos logit contributions | |
their | +0.001 |
ast | +0.001 |
faces | +0.001 |
cks | +0.001 |
dad | +0.001 |
Neg logit contributions | |
bush | -0.001 |
stump | -0.001 |
outage | -0.001 |
wood | -0.001 |
coat | -0.001 |
Token | big |
Token ID | 1263 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
outage | +0.017 |
stump | +0.016 |
coat | +0.015 |
bush | +0.015 |
rito | +0.014 |
Neg logit contributions | |
their | -0.014 |
Their | -0.013 |
both | -0.013 |
Tom | -0.013 |
at | -0.012 |
Token | fish |
Token ID | 5916 |
Feature activation | -2.03e+00 |
Pos logit contributions | |
their | +0.029 |
Their | +0.027 |
both | +0.027 |
at | +0.025 |
Ben | +0.025 |
Neg logit contributions | |
outage | -0.047 |
coat | -0.044 |
stump | -0.043 |
bush | -0.043 |
smanship | -0.040 |
Token | was |
Token ID | 373 |
Feature activation | +5.43e-01 |
Pos logit contributions | |
their | +0.039 |
Their | +0.039 |
mouths | +0.037 |
Ben | +0.037 |
our | +0.036 |
Neg logit contributions | |
outage | -0.060 |
bush | -0.055 |
stump | -0.055 |
coat | -0.054 |
boat | -0.053 |
Token | the |
Token ID | 262 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
ast | +0.021 |
ra | +0.020 |
Their | +0.019 |
both | +0.018 |
eg | +0.017 |
Neg logit contributions | |
outage | -0.056 |
bush | -0.051 |
ock | -0.050 |
coat | -0.050 |
stump | -0.049 |
Token | sandbox |
Token ID | 35204 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
outage | +0.005 |
coat | +0.005 |
bush | +0.005 |
stump | +0.005 |
smanship | +0.004 |
Neg logit contributions | |
their | -0.004 |
Their | -0.004 |
both | -0.004 |
at | -0.004 |
Ben | -0.004 |
Token | , |
Token ID | 11 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
their | +0.017 |
Their | +0.015 |
both | +0.015 |
Ben | +0.014 |
at | +0.014 |
Neg logit contributions | |
outage | -0.041 |
coat | -0.038 |
bush | -0.037 |
stump | -0.037 |
smanship | -0.035 |
Token | the |
Token ID | 262 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
outage | +0.007 |
coat | +0.006 |
bush | +0.006 |
stump | +0.006 |
smanship | +0.006 |
Neg logit contributions | |
their | -0.002 |
both | -0.001 |
Their | -0.001 |
Ben | -0.001 |
at | -0.001 |
Token | sees |
Token ID | 7224 |
Feature activation | -2.43e+00 |
Pos logit contributions | |
their | +0.003 |
Their | +0.003 |
both | +0.003 |
at | +0.003 |
Ben | +0.003 |
Neg logit contributions | |
outage | -0.004 |
coat | -0.004 |
bush | -0.003 |
stump | -0.003 |
smanship | -0.003 |
Token | aw |
Token ID | 707 |
Feature activation | -3.69e+00 |
Pos logit contributions | |
Their | +0.041 |
their | +0.040 |
both | +0.038 |
our | +0.037 |
mouths | +0.036 |
Neg logit contributions | |
outage | -0.078 |
coat | -0.075 |
bush | -0.074 |
stump | -0.071 |
ock | -0.071 |
Token | , |
Token ID | 11 |
Feature activation | +6.82e-01 |
Pos logit contributions | |
Their | +0.066 |
their | +0.066 |
both | +0.061 |
mouths | +0.058 |
our | +0.058 |
Neg logit contributions | |
outage | -0.121 |
coat | -0.116 |
bush | -0.115 |
stump | -0.111 |
ock | -0.104 |
Token | the |
Token ID | 262 |
Feature activation | +2.13e-02 |
Pos logit contributions | |
outage | +0.027 |
coat | +0.026 |
bush | +0.025 |
stump | +0.025 |
smanship | +0.024 |
Neg logit contributions | |
their | -0.009 |
Their | -0.008 |
both | -0.008 |
at | -0.007 |
Ben | -0.007 |
Token | merry |
Token ID | 44570 |
Feature activation | -3.57e+00 |
Pos logit contributions | |
outage | +0.001 |
coat | +0.001 |
bush | +0.001 |
stump | +0.001 |
smanship | +0.001 |
Neg logit contributions | |
their | -0.000 |
Their | -0.000 |
both | -0.000 |
at | -0.000 |
Ben | -0.000 |
Token | - |
Token ID | 12 |
Feature activation | +4.53e-01 |
Pos logit contributions | |
Their | +0.093 |
both | +0.088 |
their | +0.086 |
Ben | +0.084 |
Tom | +0.078 |
Neg logit contributions | |
coat | -0.090 |
outage | -0.090 |
bush | -0.082 |
pleasures | -0.081 |
stump | -0.079 |
Token | go |
Token ID | 2188 |
Feature activation | -4.85e+00 |
Pos logit contributions | |
outage | +0.011 |
coat | +0.010 |
bush | +0.010 |
stump | +0.010 |
ock | +0.009 |
Neg logit contributions | |
their | -0.013 |
Ben | -0.012 |
Their | -0.012 |
both | -0.012 |
mouths | -0.012 |
Token | It |
Token ID | 632 |
Feature activation | +4.50e-01 |
Pos logit contributions | |
their | +0.005 |
Their | +0.005 |
both | +0.005 |
Ben | +0.005 |
Tom | +0.005 |
Neg logit contributions | |
outage | -0.012 |
coat | -0.011 |
bush | -0.011 |
stump | -0.011 |
smanship | -0.010 |
Token | makes |
Token ID | 1838 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
outage | +0.015 |
coat | +0.014 |
bush | +0.014 |
stump | +0.014 |
ock | +0.013 |
Neg logit contributions | |
their | -0.009 |
Their | -0.008 |
both | -0.008 |
Ben | -0.007 |
Tom | -0.007 |
Token | you |
Token ID | 345 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
outage | +0.051 |
ock | +0.047 |
coat | +0.046 |
bush | +0.046 |
stump | +0.045 |
Neg logit contributions | |
Their | -0.022 |
their | -0.022 |
mouths | -0.021 |
at | -0.019 |
both | -0.019 |
Token | and |
Token ID | 290 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
outage | +0.036 |
coat | +0.033 |
bush | +0.032 |
stump | +0.032 |
smanship | +0.030 |
Neg logit contributions | |
their | -0.024 |
both | -0.022 |
Their | -0.021 |
at | -0.021 |
Ben | -0.020 |
Token | others |
Token ID | 1854 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
Their | +0.021 |
their | +0.021 |
both | +0.020 |
at | +0.018 |
mouths | +0.017 |
Neg logit contributions | |
outage | -0.051 |
bush | -0.046 |
coat | -0.046 |
stump | -0.046 |
remedy | -0.043 |
Token | happy |
Token ID | 3772 |
Feature activation | -4.48e+00 |
Pos logit contributions | |
their | +0.003 |
both | +0.003 |
at | +0.003 |
Their | +0.002 |
our | +0.002 |
Neg logit contributions | |
outage | -0.005 |
coat | -0.005 |
bush | -0.005 |
stump | -0.005 |
rito | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | -3.47e-01 |
Pos logit contributions | |
their | +0.081 |
Their | +0.077 |
both | +0.073 |
Ben | +0.069 |
mouths | +0.069 |
Neg logit contributions | |
outage | -0.156 |
coat | -0.140 |
bush | -0.138 |
stump | -0.137 |
ock | -0.132 |
Token | Do |
Token ID | 2141 |
Feature activation | -3.10e+00 |
Pos logit contributions | |
their | +0.006 |
Their | +0.005 |
both | +0.005 |
Ben | +0.005 |
Tom | +0.005 |
Neg logit contributions | |
outage | -0.013 |
coat | -0.012 |
bush | -0.012 |
stump | -0.012 |
smanship | -0.011 |
Token | you |
Token ID | 345 |
Feature activation | +8.56e-01 |
Pos logit contributions | |
their | +0.052 |
Their | +0.051 |
mouths | +0.048 |
at | +0.047 |
both | +0.046 |
Neg logit contributions | |
outage | -0.100 |
coat | -0.091 |
ock | -0.091 |
bush | -0.090 |
pleasures | -0.089 |
Token | understand |
Token ID | 1833 |
Feature activation | -6.51e-01 |
Pos logit contributions | |
outage | +0.024 |
coat | +0.022 |
bush | +0.022 |
stump | +0.022 |
smanship | +0.020 |
Neg logit contributions | |
their | -0.022 |
both | -0.022 |
at | -0.021 |
Their | -0.021 |
Ben | -0.021 |
Token | ?" |
Token ID | 1701 |
Feature activation | +3.49e-01 |
Pos logit contributions | |
their | +0.017 |
Their | +0.016 |
both | +0.016 |
at | +0.016 |
Ben | +0.016 |
Neg logit contributions | |
outage | -0.018 |
coat | -0.017 |
stump | -0.016 |
bush | -0.016 |
smanship | -0.015 |
Token | and |
Token ID | 290 |
Feature activation | -2.04e+00 |
Pos logit contributions | |
their | +0.026 |
Their | +0.024 |
both | +0.023 |
Ben | +0.022 |
at | +0.022 |
Neg logit contributions | |
outage | -0.063 |
coat | -0.059 |
bush | -0.058 |
stump | -0.058 |
smanship | -0.055 |
Token | Tom |
Token ID | 4186 |
Feature activation | -2.36e+00 |
Pos logit contributions | |
mouths | +0.038 |
Their | +0.033 |
cks | +0.033 |
both | +0.032 |
their | +0.031 |
Neg logit contributions | |
coat | -0.057 |
outage | -0.057 |
bush | -0.054 |
stump | -0.054 |
reating | -0.053 |
Token | 's |
Token ID | 338 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
their | +0.039 |
Their | +0.037 |
both | +0.035 |
mouths | +0.033 |
Ben | +0.032 |
Neg logit contributions | |
outage | -0.085 |
coat | -0.080 |
stump | -0.078 |
bush | -0.077 |
smanship | -0.073 |
Token | dad |
Token ID | 9955 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
Their | +0.026 |
their | +0.025 |
both | +0.024 |
Their | +0.023 |
mouths | +0.022 |
Neg logit contributions | |
outage | -0.039 |
coat | -0.038 |
bush | -0.034 |
stump | -0.034 |
remedy | -0.031 |
Token | . |
Token ID | 13 |
Feature activation | -4.50e-01 |
Pos logit contributions | |
their | +0.032 |
Their | +0.031 |
both | +0.028 |
mouths | +0.027 |
Ben | +0.027 |
Neg logit contributions | |
outage | -0.062 |
coat | -0.059 |
stump | -0.057 |
bush | -0.056 |
ock | -0.054 |
Token | What |
Token ID | 1867 |
Feature activation | -3.49e+00 |
Pos logit contributions | |
their | +0.009 |
both | +0.009 |
Their | +0.009 |
mouths | +0.009 |
at | +0.008 |
Neg logit contributions | |
outage | -0.014 |
coat | -0.013 |
stump | -0.012 |
bush | -0.012 |
pleasures | -0.012 |
Token | a |
Token ID | 257 |
Feature activation | -3.53e+00 |
Pos logit contributions | |
their | +0.062 |
Their | +0.057 |
both | +0.056 |
at | +0.053 |
Ben | +0.053 |
Neg logit contributions | |
outage | -0.125 |
coat | -0.116 |
bush | -0.113 |
stump | -0.113 |
smanship | -0.107 |
Token | nice |
Token ID | 3621 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
mouths | +0.097 |
Their | +0.094 |
icked | +0.090 |
cks | +0.087 |
both | +0.085 |
Neg logit contributions | |
outage | -0.080 |
coat | -0.074 |
remedy | -0.070 |
stump | -0.069 |
ock | -0.066 |
Token | surprise |
Token ID | 5975 |
Feature activation | -2.58e+00 |
Pos logit contributions | |
their | +0.031 |
at | +0.028 |
Ben | +0.028 |
Tom | +0.028 |
Their | +0.028 |
Neg logit contributions | |
outage | -0.048 |
coat | -0.044 |
stump | -0.044 |
bush | -0.044 |
rito | -0.042 |
Token | . |
Token ID | 13 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
Their | +0.045 |
their | +0.044 |
mouths | +0.042 |
both | +0.042 |
faces | +0.039 |
Neg logit contributions | |
outage | -0.090 |
coat | -0.082 |
bush | -0.078 |
stump | -0.077 |
ock | -0.077 |
Token | Come |
Token ID | 7911 |
Feature activation | -7.98e-01 |
Pos logit contributions | |
their | +0.004 |
both | +0.004 |
at | +0.004 |
Their | +0.004 |
mouths | +0.004 |
Neg logit contributions | |
outage | -0.006 |
coat | -0.005 |
stump | -0.005 |
bush | -0.005 |
rito | -0.005 |