TOP ACTIVATIONS
MAX = 10.381

bons . She had many rib bons of different colors and
. <|endoftext|> Ben was very exc ite to go to school
cat named Tom was very exc ite . He saw a
dog named Spot was very exc ite . He was going
very naughty and always mis beh aving . One day she
because it had flowers and rib bons . She thought it
. It has flowers and rib bons on it . She
show everyone . He had rib bons , balls , toys
a bell and many long rib bons that looked like tentacles
had balloons , others had rib bons , and some had
up . Some of the rib bons and clips had fallen
Anna was very exc ite . She said ,
It had spark les and rib bons and a big bow
a time there was a cater pillar . It lived outside
One day , a little aer opl ane was in the
in the sky . The aer opl ane liked to move
a long rope with colorful rib bons on it . Sam
<|endoftext|> Once there was a cater pillar in a garden who
, there was a little cater pillar . She was very
doll with pink and blue rib bons in her hair .

MIN ACTIVATIONS
MIN = -8.784

looked through the ey ep iece . He saw the tiny
looked through the ey ep iece and saw the tiny scales
Ab by promised , and the stranger let her
L ily promised , and the man found her
to always be on the lookout for animals in need of
man smiled back and said ,
Steve thanked her and said , " Thank you for not
bird thanked Lucy and said , " You are a good
to always be on the lookout for any dangers in their
She wanted to say sorry , but she could not .
And just like he promised , he came to life and
John promised , and he has kept his
was so happy and said ,
G ina promised , and so the old man
was so happy and said , " Thank you , Tim
the water ." Sam whispered , trying to be brave .
chie v ously and said , " Well , he thought
girl smiled , and said ,
Mary smiled and said , " That 's good ,
L ily smiled and said ,

INTERVAL 5.590 - 10.381
CONTAINS 2.998%

One day , Sara and Ben decide to make a
He stepped on the door and it made a loud sound
had a great time , and Tom promised to be a
She loved to play outside and run around in the grass
to build towers and houses and cars . They had many

INTERVAL 0.798 - 5.590
CONTAINS 28.993%

, there was a little boy named Danny . Danny wanted
to paint with her mom . They would use all kinds
there was a little girl named Daisy . Daisy was only
She likes to look for bugs and flowers . One day
started using zero in all kinds of ways . She used

INTERVAL -3.993 - 0.798
CONTAINS 61.954%

. She was walking through the woods and suddenly she saw
but the boy kept chasing after it . He
ara was sad and angry again . She did not want
mom to help her find a v ase . They found
wanted to rescue Anna 's car . He followed the dog

INTERVAL -8.784 - -3.993
CONTAINS 6.055%

. " OK , Mom . We will close
." Her brother replied , " But I promise
blue t eddy bear closed their eyes and went to sleep
the monster refused and ran away with the poem . Lucy
. But soon , the little bird became greedy
Tokenbons
Token ID23461
Feature activation+4.93e+00

Pos logit contributions
igator+0.218
leaf+0.210
 sorts+0.179
aling+0.158
icated+0.149
Neg logit contributions
angers-0.323
 Majesty-0.320
omm-0.309
ings-0.303
ail-0.302
Token.
Token ID13
Feature activation+1.14e+00

Pos logit contributions
leaf+0.179
 sorts+0.177
aling+0.161
weet+0.155
igator+0.152
Neg logit contributions
angers-0.117
pit-0.116
 bedroom-0.103
 Majesty-0.102
ider-0.102
Token She
Token ID1375
Feature activation+4.04e-01

Pos logit contributions
 sorts+0.032
+0.028
leaf+0.027
weet+0.026
aling+0.025
Neg logit contributions
 Majesty-0.038
 majesty-0.036
pit-0.035
ider-0.035
angers-0.034
Token had
Token ID550
Feature activation+2.56e+00

Pos logit contributions
leaf+0.013
 sorts+0.012
aling+0.011
weet+0.011
igator+0.011
Neg logit contributions
angers-0.011
pit-0.011
 bedroom-0.011
 Majesty-0.011
ider-0.010
Token many
Token ID867
Feature activation+3.40e+00

Pos logit contributions
leaf+0.069
 sorts+0.068
aling+0.059
igator+0.059
+0.056
Neg logit contributions
angers-0.082
pit-0.082
 Majesty-0.081
 bedroom-0.079
ider-0.075
Token rib
Token ID12183
Feature activation+1.04e+01

Pos logit contributions
leaf+0.102
 sorts+0.099
aling+0.092
igator+0.089
+0.086
Neg logit contributions
angers-0.098
pit-0.098
 Majesty-0.095
 bedroom-0.094
 majesty-0.089
Tokenbons
Token ID23461
Feature activation+6.06e+00

Pos logit contributions
igator+0.220
leaf+0.216
 sorts+0.185
aling+0.163
icated+0.160
Neg logit contributions
angers-0.383
 Majesty-0.369
omm-0.356
 majesty-0.350
pit-0.349
Token of
Token ID286
Feature activation+2.50e+00

Pos logit contributions
leaf+0.167
 sorts+0.165
aling+0.143
igator+0.138
+0.138
Neg logit contributions
angers-0.193
pit-0.193
 Majesty-0.185
 bedroom-0.178
ider-0.177
Token different
Token ID1180
Feature activation+9.55e-01

Pos logit contributions
leaf+0.072
aling+0.071
 sorts+0.071
igator+0.067
+0.063
Neg logit contributions
angers-0.072
 bedroom-0.069
 Majesty-0.067
pit-0.067
 majesty-0.064
Token colors
Token ID7577
Feature activation+2.11e+00

Pos logit contributions
leaf+0.024
 sorts+0.024
aling+0.021
igator+0.020
+0.020
Neg logit contributions
angers-0.032
pit-0.032
 Majesty-0.032
 bedroom-0.031
ider-0.030
Token and
Token ID290
Feature activation+6.91e+00

Pos logit contributions
leaf+0.058
 sorts+0.058
aling+0.050
+0.049
igator+0.049
Neg logit contributions
pit-0.066
angers-0.066
 Majesty-0.065
 bedroom-0.062
ider-0.061
Token.
Token ID13
Feature activation-6.33e-01

Pos logit contributions
leaf+0.098
 sorts+0.094
aling+0.088
igator+0.087
weet+0.082
Neg logit contributions
pit-0.055
angers-0.051
 bedroom-0.049
ider-0.048
 Majesty-0.048
Token<|endoftext|>
Token ID50256
Feature activation+4.06e+00

Pos logit contributions
pit+0.018
angers+0.017
 Majesty+0.017
 bedroom+0.016
ider+0.016
Neg logit contributions
 sorts-0.020
leaf-0.020
-0.017
aling-0.017
igator-0.017
TokenBen
Token ID11696
Feature activation+5.72e-01

Pos logit contributions
 sorts+0.141
leaf+0.141
+0.126
aling+0.125
igator+0.123
Neg logit contributions
 Majesty-0.097
pit-0.096
angers-0.096
 bedroom-0.089
ider-0.088
Token was
Token ID373
Feature activation+4.66e-01

Pos logit contributions
leaf+0.018
 sorts+0.017
aling+0.015
weet+0.015
igator+0.014
Neg logit contributions
pit-0.017
 Majesty-0.016
angers-0.016
 bedroom-0.016
 majesty-0.015
Token very
Token ID845
Feature activation+1.60e+00

Pos logit contributions
leaf+0.014
 sorts+0.014
 course+0.012
aling+0.012
igator+0.012
Neg logit contributions
angers-0.013
pit-0.013
 Majesty-0.013
 bedroom-0.013
ider-0.012
Token exc
Token ID2859
Feature activation+1.02e+01

Pos logit contributions
 sorts+0.042
leaf+0.042
+0.035
aling+0.035
igator+0.035
Neg logit contributions
pit-0.053
angers-0.053
 Majesty-0.052
 bedroom-0.049
ider-0.048
Tokenite
Token ID578
Feature activation+3.63e+00

Pos logit contributions
 sorts+0.230
leaf+0.225
 course+0.178
 thanks+0.176
igator+0.175
Neg logit contributions
angers-0.386
pit-0.360
ider-0.358
uffy-0.350
ail-0.340
Token to
Token ID284
Feature activation-4.93e-01

Pos logit contributions
leaf+0.125
 sorts+0.120
aling+0.109
+0.105
igator+0.103
Neg logit contributions
pit-0.092
angers-0.091
 Majesty-0.087
 bedroom-0.083
 principal-0.080
Token go
Token ID467
Feature activation+1.81e+00

Pos logit contributions
 teacher+0.012
 bedroom+0.011
 Majesty+0.011
 bathroom+0.011
 teachers+0.010
Neg logit contributions
leaf-0.016
able-0.016
ited-0.016
fy-0.015
sm-0.015
Token to
Token ID284
Feature activation-1.67e+00

Pos logit contributions
leaf+0.062
 sorts+0.062
igator+0.055
aling+0.055
+0.054
Neg logit contributions
angers-0.046
 bedroom-0.042
pit-0.042
 Majesty-0.040
 bathroom-0.039
Token school
Token ID1524
Feature activation-1.90e+00

Pos logit contributions
 bedroom+0.050
 Majesty+0.049
angers+0.047
 bathroom+0.047
pit+0.046
Neg logit contributions
leaf-0.049
 sorts-0.046
aling-0.043
igator-0.043
able-0.042
Token cat
Token ID3797
Feature activation+4.37e+00

Pos logit contributions
 sorts+0.027
leaf+0.027
aling+0.024
+0.024
igator+0.024
Neg logit contributions
pit-0.021
angers-0.021
 Majesty-0.021
 bedroom-0.019
ider-0.019
Token named
Token ID3706
Feature activation+4.82e+00

Pos logit contributions
leaf+0.140
 sorts+0.131
aling+0.117
icated+0.114
weet+0.113
Neg logit contributions
pit-0.118
 bedroom-0.114
angers-0.112
 cabinet-0.111
 Majesty-0.109
Token Tom
Token ID4186
Feature activation-7.48e-02

Pos logit contributions
 sorts+0.169
leaf+0.168
aling+0.151
 course+0.142
igator+0.140
Neg logit contributions
 Majesty-0.113
angers-0.112
 bedroom-0.112
pit-0.108
 cabinet-0.106
Token was
Token ID373
Feature activation+4.86e-02

Pos logit contributions
pit+0.002
angers+0.002
 Majesty+0.002
 bedroom+0.002
 cabinet+0.002
Neg logit contributions
leaf-0.003
 sorts-0.003
aling-0.002
weet-0.002
igator-0.002
Token very
Token ID845
Feature activation+1.15e+00

Pos logit contributions
 sorts+0.002
leaf+0.002
aling+0.001
+0.001
igator+0.001
Neg logit contributions
angers-0.001
pit-0.001
 Majesty-0.001
 bedroom-0.001
ider-0.001
Token exc
Token ID2859
Feature activation+1.01e+01

Pos logit contributions
 sorts+0.032
leaf+0.032
aling+0.027
+0.027
igator+0.027
Neg logit contributions
pit-0.036
angers-0.035
 Majesty-0.035
 bedroom-0.033
ider-0.033
Tokenite
Token ID578
Feature activation+3.52e+00

Pos logit contributions
 sorts+0.218
leaf+0.212
 thanks+0.173
 course+0.163
igator+0.159
Neg logit contributions
angers-0.391
uffy-0.370
ider-0.358
pit-0.348
ail-0.346
Token.
Token ID13
Feature activation+1.41e+00

Pos logit contributions
leaf+0.126
 sorts+0.123
aling+0.110
+0.108
weet+0.106
Neg logit contributions
angers-0.083
pit-0.081
 Majesty-0.078
 bedroom-0.075
ider-0.073
Token He
Token ID679
Feature activation-1.76e-01

Pos logit contributions
 sorts+0.040
leaf+0.038
aling+0.034
+0.034
weet+0.033
Neg logit contributions
 Majesty-0.044
angers-0.043
pit-0.043
ider-0.040
 bedroom-0.040
Token saw
Token ID2497
Feature activation-2.29e+00

Pos logit contributions
angers+0.004
 bedroom+0.004
uffy+0.004
ider+0.004
pit+0.004
Neg logit contributions
leaf-0.006
 sorts-0.006
aling-0.006
weet-0.006
icated-0.005
Token a
Token ID257
Feature activation-4.91e-02

Pos logit contributions
angers+0.066
 Majesty+0.066
pit+0.065
 bedroom+0.064
 bathroom+0.063
Neg logit contributions
leaf-0.065
 sorts-0.065
aling-0.060
-0.057
ited-0.054
Token dog
Token ID3290
Feature activation+4.53e+00

Pos logit contributions
leaf+0.156
 sorts+0.152
aling+0.149
+0.137
ez+0.134
Neg logit contributions
pit-0.065
 bedroom-0.063
 cabinet-0.063
uffy-0.062
 Lee-0.062
Token named
Token ID3706
Feature activation+5.01e+00

Pos logit contributions
leaf+0.123
 sorts+0.121
aling+0.104
weet+0.099
+0.099
Neg logit contributions
pit-0.143
angers-0.142
 Majesty-0.140
 bedroom-0.138
ider-0.132
Token Spot
Token ID15899
Feature activation+6.89e-01

Pos logit contributions
leaf+0.177
 sorts+0.176
aling+0.157
igator+0.148
 course+0.147
Neg logit contributions
 bedroom-0.114
 Lee-0.111
angers-0.110
uffy-0.109
 Majesty-0.108
Token was
Token ID373
Feature activation+1.07e-01

Pos logit contributions
leaf+0.023
 sorts+0.023
aling+0.020
weet+0.020
igator+0.020
Neg logit contributions
pit-0.017
angers-0.017
 Majesty-0.017
 bedroom-0.016
 bathroom-0.015
Token very
Token ID845
Feature activation+1.26e+00

Pos logit contributions
 sorts+0.003
leaf+0.003
aling+0.003
+0.003
igator+0.003
Neg logit contributions
pit-0.003
angers-0.003
 Majesty-0.003
 bedroom-0.003
ider-0.003
Token exc
Token ID2859
Feature activation+9.99e+00

Pos logit contributions
 sorts+0.037
leaf+0.037
aling+0.032
+0.031
igator+0.031
Neg logit contributions
angers-0.038
pit-0.038
 Majesty-0.037
 bedroom-0.036
ider-0.035
Tokenite
Token ID578
Feature activation+3.63e+00

Pos logit contributions
 sorts+0.227
leaf+0.218
 thanks+0.175
 course+0.168
igator+0.166
Neg logit contributions
angers-0.376
uffy-0.362
ider-0.351
eth-0.338
ail-0.336
Token.
Token ID13
Feature activation+1.30e+00

Pos logit contributions
leaf+0.123
 sorts+0.122
aling+0.108
+0.107
igator+0.105
Neg logit contributions
angers-0.091
pit-0.090
 Majesty-0.088
 bedroom-0.083
ider-0.082
Token He
Token ID679
Feature activation-3.18e-01

Pos logit contributions
 sorts+0.035
leaf+0.035
aling+0.030
+0.030
igator+0.029
Neg logit contributions
pit-0.041
angers-0.041
 Majesty-0.041
 bedroom-0.039
ider-0.038
Token was
Token ID373
Feature activation-4.57e-01

Pos logit contributions
angers+0.008
 bedroom+0.007
pit+0.007
 Majesty+0.007
 bathroom+0.007
Neg logit contributions
leaf-0.011
 sorts-0.011
aling-0.010
weet-0.009
 course-0.009
Token going
Token ID1016
Feature activation+3.18e+00

Pos logit contributions
angers+0.012
 Majesty+0.012
 bedroom+0.012
pit+0.011
ider+0.011
Neg logit contributions
 sorts-0.015
leaf-0.014
 course-0.013
-0.012
aling-0.012
Token very
Token ID845
Feature activation+6.76e-01

Pos logit contributions
angers+0.004
pit+0.004
 Majesty+0.004
 bedroom+0.004
ider+0.004
Neg logit contributions
 sorts-0.005
leaf-0.005
aling-0.004
-0.004
igator-0.004
Token naughty
Token ID45128
Feature activation+2.12e+00

Pos logit contributions
leaf+0.018
 sorts+0.018
igator+0.016
+0.016
aling+0.015
Neg logit contributions
pit-0.023
angers-0.021
 Majesty-0.021
 bedroom-0.020
atively-0.019
Token and
Token ID290
Feature activation+5.92e+00

Pos logit contributions
leaf+0.057
 sorts+0.056
aling+0.048
+0.047
igator+0.047
Neg logit contributions
pit-0.069
angers-0.069
 Majesty-0.068
 bedroom-0.065
ider-0.064
Token always
Token ID1464
Feature activation+1.05e+00

Pos logit contributions
leaf+0.215
 sorts+0.212
aling+0.192
weet+0.187
 course+0.184
Neg logit contributions
angers-0.122
 bedroom-0.121
pit-0.120
 cabinet-0.120
 Majesty-0.120
Token mis
Token ID2984
Feature activation+4.76e+00

Pos logit contributions
 sorts+0.029
leaf+0.029
aling+0.024
+0.024
igator+0.024
Neg logit contributions
pit-0.033
angers-0.033
 Majesty-0.033
 bedroom-0.031
ider-0.031
Tokenbeh
Token ID20709
Feature activation+9.98e+00

Pos logit contributions
leaf+0.114
 sorts+0.113
igator+0.093
 course+0.093
aling+0.092
Neg logit contributions
angers-0.165
pit-0.163
 Majesty-0.160
ider-0.154
 bedroom-0.152
Tokenaving
Token ID2703
Feature activation-1.39e-01

Pos logit contributions
leaf+0.291
 course+0.271
 sorts+0.263
igator+0.251
 thanks+0.251
Neg logit contributions
angers-0.286
pit-0.265
 Majesty-0.250
 bedroom-0.241
ider-0.241
Token.
Token ID13
Feature activation+5.57e-01

Pos logit contributions
pit+0.004
 Majesty+0.004
angers+0.004
 bedroom+0.003
ider+0.003
Neg logit contributions
 sorts-0.004
leaf-0.004
-0.004
aling-0.004
igator-0.004
Token One
Token ID1881
Feature activation-1.80e-01

Pos logit contributions
 sorts+0.015
leaf+0.014
+0.014
 course+0.013
weet+0.013
Neg logit contributions
 Majesty-0.018
pit-0.018
angers-0.018
ider-0.017
 majesty-0.017
Token day
Token ID1110
Feature activation-4.91e-02

Pos logit contributions
 bedroom+0.005
 cabinet+0.005
 teacher+0.004
 bathroom+0.004
 sister+0.004
Neg logit contributions
leaf-0.006
 sorts-0.006
aling-0.005
 course-0.005
bons-0.005
Token she
Token ID673
Feature activation-3.91e-01

Pos logit contributions
 Majesty+0.001
pit+0.001
angers+0.001
ider+0.001
 majesty+0.001
Neg logit contributions
-0.002
 sorts-0.001
leaf-0.001
 course-0.001
sm-0.001
Token because
Token ID780
Feature activation+2.80e+00

Pos logit contributions
leaf+0.051
 sorts+0.050
aling+0.045
igator+0.043
+0.043
Neg logit contributions
pit-0.044
angers-0.044
 Majesty-0.043
 bedroom-0.042
ider-0.040
Token it
Token ID340
Feature activation+6.53e-01

Pos logit contributions
leaf+0.097
aling+0.089
ez+0.086
 sorts+0.085
ited+0.084
Neg logit contributions
 bedroom-0.070
angers-0.069
 bathroom-0.063
 cabinet-0.063
 bedrooms-0.062
Token had
Token ID550
Feature activation+2.43e+00

Pos logit contributions
leaf+0.023
 sorts+0.022
aling+0.021
weet+0.021
icated+0.020
Neg logit contributions
pit-0.015
angers-0.015
 bedroom-0.015
 bathroom-0.014
 cabinet-0.014
Token flowers
Token ID12734
Feature activation+2.75e+00

Pos logit contributions
leaf+0.069
 sorts+0.068
aling+0.062
igator+0.062
+0.057
Neg logit contributions
angers-0.074
pit-0.073
 Majesty-0.073
 bedroom-0.072
 bathroom-0.068
Token and
Token ID290
Feature activation+7.76e+00

Pos logit contributions
leaf+0.082
 sorts+0.080
aling+0.070
igator+0.068
weet+0.066
Neg logit contributions
pit-0.084
angers-0.084
 bedroom-0.080
ider-0.077
 Majesty-0.076
Token rib
Token ID12183
Feature activation+9.95e+00

Pos logit contributions
leaf+0.279
aling+0.273
 sorts+0.272
igator+0.249
ited+0.240
Neg logit contributions
 bedroom-0.189
 Majesty-0.181
pit-0.181
angers-0.173
 bathroom-0.173
Tokenbons
Token ID23461
Feature activation+6.05e+00

Pos logit contributions
igator+0.197
leaf+0.190
 sorts+0.167
aling+0.152
icated+0.135
Neg logit contributions
 Majesty-0.393
angers-0.392
 bedroom-0.375
 majesty-0.372
pit-0.364
Token.
Token ID13
Feature activation+4.71e-01

Pos logit contributions
 sorts+0.202
leaf+0.201
aling+0.179
igator+0.175
weet+0.172
Neg logit contributions
angers-0.159
pit-0.157
 Majesty-0.143
ider-0.143
 bedroom-0.143
Token She
Token ID1375
Feature activation+3.08e-01

Pos logit contributions
+0.011
 sorts+0.011
leaf+0.008
 course+0.008
 thanks+0.008
Neg logit contributions
 Majesty-0.018
ider-0.017
 majesty-0.017
pit-0.017
 principal-0.016
Token thought
Token ID1807
Feature activation-6.98e-01

Pos logit contributions
leaf+0.009
 sorts+0.009
aling+0.008
igator+0.008
+0.008
Neg logit contributions
pit-0.009
angers-0.009
 Majesty-0.009
 bedroom-0.009
ider-0.008
Token it
Token ID340
Feature activation-2.05e-01

Pos logit contributions
pit+0.026
 Majesty+0.025
angers+0.025
 bedroom+0.024
ider+0.024
Neg logit contributions
 sorts-0.016
leaf-0.015
-0.013
aling-0.013
igator-0.012
Token.
Token ID13
Feature activation+1.74e+00

Pos logit contributions
 sorts+0.045
leaf+0.044
+0.039
aling+0.039
igator+0.039
Neg logit contributions
 Majesty-0.046
pit-0.046
angers-0.045
 majesty-0.042
 bedroom-0.042
Token It
Token ID632
Feature activation+2.04e+00

Pos logit contributions
 sorts+0.061
leaf+0.060
aling+0.054
+0.054
igator+0.053
Neg logit contributions
pit-0.042
angers-0.041
 Majesty-0.041
 bedroom-0.038
ider-0.038
Token has
Token ID468
Feature activation+3.69e+00

Pos logit contributions
leaf+0.075
 sorts+0.068
weet+0.064
aling+0.063
icated+0.062
Neg logit contributions
 bedroom-0.048
pit-0.047
angers-0.047
 bathroom-0.046
 cabinet-0.046
Token flowers
Token ID12734
Feature activation+3.09e+00

Pos logit contributions
 sorts+0.109
leaf+0.108
aling+0.102
igator+0.100
ited+0.094
Neg logit contributions
 bedroom-0.106
angers-0.105
 Majesty-0.105
pit-0.102
 bathroom-0.100
Token and
Token ID290
Feature activation+7.89e+00

Pos logit contributions
leaf+0.101
 sorts+0.099
aling+0.088
igator+0.086
weet+0.084
Neg logit contributions
angers-0.084
pit-0.084
 Majesty-0.079
 bedroom-0.078
ider-0.076
Token rib
Token ID12183
Feature activation+9.94e+00

Pos logit contributions
leaf+0.250
 sorts+0.243
aling+0.241
igator+0.223
ited+0.216
Neg logit contributions
 Majesty-0.223
 bedroom-0.216
pit-0.210
 majesty-0.209
angers-0.208
Tokenbons
Token ID23461
Feature activation+5.78e+00

Pos logit contributions
igator+0.201
leaf+0.198
 sorts+0.175
aling+0.155
+0.144
Neg logit contributions
 Majesty-0.379
angers-0.372
 majesty-0.362
omm-0.348
pit-0.347
Token on
Token ID319
Feature activation+2.36e+00

Pos logit contributions
leaf+0.183
 sorts+0.182
aling+0.163
igator+0.158
weet+0.154
Neg logit contributions
angers-0.162
pit-0.159
 Majesty-0.148
ider-0.146
 bedroom-0.145
Token it
Token ID340
Feature activation-1.58e+00

Pos logit contributions
leaf+0.071
 sorts+0.067
aling+0.063
igator+0.058
ited+0.057
Neg logit contributions
angers-0.070
 bedroom-0.068
 Majesty-0.068
pit-0.067
aby-0.065
Token.
Token ID13
Feature activation+9.19e-01

Pos logit contributions
angers+0.040
pit+0.040
 Majesty+0.039
 bedroom+0.037
ider+0.036
Neg logit contributions
leaf-0.054
 sorts-0.052
aling-0.047
igator-0.045
-0.045
Token She
Token ID1375
Feature activation+4.87e-01

Pos logit contributions
 sorts+0.029
leaf+0.028
+0.025
aling+0.025
igator+0.025
Neg logit contributions
pit-0.025
 Majesty-0.025
angers-0.025
ider-0.023
 bedroom-0.023
Token show
Token ID905
Feature activation+4.05e-01

Pos logit contributions
leaf+0.011
 sorts+0.011
aling+0.010
+0.009
igator+0.009
Neg logit contributions
pit-0.010
angers-0.010
 Majesty-0.010
 bedroom-0.009
ider-0.009
Token everyone
Token ID2506
Feature activation-1.28e+00

Pos logit contributions
leaf+0.012
 sorts+0.012
aling+0.011
+0.010
igator+0.010
Neg logit contributions
 Majesty-0.012
angers-0.012
pit-0.012
 bedroom-0.011
 majesty-0.011
Token.
Token ID13
Feature activation+7.57e-01

Pos logit contributions
pit+0.033
 bedroom+0.031
angers+0.031
 Majesty+0.031
 cabinet+0.029
Neg logit contributions
leaf-0.041
 sorts-0.039
aling-0.037
weet-0.035
ez-0.035
Token He
Token ID679
Feature activation-3.30e-01

Pos logit contributions
leaf+0.024
 sorts+0.024
aling+0.021
weet+0.020
igator+0.020
Neg logit contributions
pit-0.021
 Majesty-0.020
angers-0.020
 bedroom-0.019
ider-0.019
Token had
Token ID550
Feature activation+2.44e+00

Pos logit contributions
pit+0.008
 Majesty+0.008
angers+0.008
 bedroom+0.008
 principal+0.007
Neg logit contributions
leaf-0.011
 sorts-0.011
aling-0.010
weet-0.010
igator-0.010
Token rib
Token ID12183
Feature activation+9.92e+00

Pos logit contributions
 sorts+0.068
leaf+0.068
aling+0.061
igator+0.059
 course+0.056
Neg logit contributions
 Majesty-0.074
pit-0.073
 bedroom-0.072
angers-0.071
 bathroom-0.069
Tokenbons
Token ID23461
Feature activation+6.06e+00

Pos logit contributions
igator+0.204
leaf+0.200
 sorts+0.167
aling+0.162
moving+0.156
Neg logit contributions
 Majesty-0.370
angers-0.351
omm-0.351
 majesty-0.346
pit-0.338
Token,
Token ID11
Feature activation-4.52e+00

Pos logit contributions
leaf+0.204
 sorts+0.202
aling+0.181
weet+0.175
igator+0.174
Neg logit contributions
pit-0.156
angers-0.154
 Majesty-0.147
 bedroom-0.140
ider-0.138
Token balls
Token ID11333
Feature activation+5.09e+00

Pos logit contributions
pit+0.113
angers+0.111
 bedroom+0.110
 Majesty+0.108
 teachers+0.107
Neg logit contributions
leaf-0.143
aling-0.143
 sorts-0.142
igator-0.126
ez-0.125
Token,
Token ID11
Feature activation-4.72e+00

Pos logit contributions
leaf+0.210
 sorts+0.209
aling+0.189
+0.186
igator+0.185
Neg logit contributions
pit-0.090
angers-0.089
 Majesty-0.086
 bedroom-0.079
ider-0.077
Token toys
Token ID14958
Feature activation+2.15e+00

Pos logit contributions
pit+0.131
angers+0.125
 bedroom+0.121
 Majesty+0.119
 bathroom+0.114
Neg logit contributions
leaf-0.152
 sorts-0.150
aling-0.139
igator-0.126
ez-0.125
Token a
Token ID257
Feature activation-8.93e-02

Pos logit contributions
leaf+0.029
aling+0.028
 sorts+0.028
igator+0.026
ited+0.026
Neg logit contributions
pit-0.022
 bedroom-0.022
 Majesty-0.022
angers-0.022
 bathroom-0.021
Token bell
Token ID8966
Feature activation+1.49e+00

Pos logit contributions
pit+0.003
angers+0.003
 Majesty+0.003
 bedroom+0.003
ider+0.003
Neg logit contributions
 sorts-0.002
leaf-0.002
aling-0.002
-0.002
igator-0.002
Token and
Token ID290
Feature activation+7.70e+00

Pos logit contributions
leaf+0.049
 sorts+0.049
aling+0.043
igator+0.042
 course+0.042
Neg logit contributions
pit-0.039
angers-0.039
 Majesty-0.037
 bedroom-0.036
ider-0.036
Token many
Token ID867
Feature activation+3.10e+00

Pos logit contributions
leaf+0.215
 sorts+0.214
aling+0.198
igator+0.197
able+0.179
Neg logit contributions
 Majesty-0.238
 bedroom-0.231
angers-0.229
pit-0.228
 majesty-0.220
Token long
Token ID890
Feature activation+2.41e+00

Pos logit contributions
leaf+0.106
 sorts+0.102
aling+0.100
weet+0.093
+0.093
Neg logit contributions
pit-0.075
angers-0.071
 Majesty-0.071
 bedroom-0.071
 bedrooms-0.068
Token rib
Token ID12183
Feature activation+9.90e+00

Pos logit contributions
 sorts+0.076
leaf+0.076
+0.067
aling+0.067
igator+0.065
Neg logit contributions
angers-0.064
pit-0.064
 Majesty-0.064
 bedroom-0.060
ider-0.059
Tokenbons
Token ID23461
Feature activation+5.42e+00

Pos logit contributions
igator+0.197
leaf+0.189
 sorts+0.168
+0.153
aling+0.142
Neg logit contributions
 Majesty-0.386
angers-0.374
 majesty-0.367
pit-0.362
ail-0.357
Token that
Token ID326
Feature activation-6.66e-01

Pos logit contributions
 sorts+0.197
leaf+0.197
aling+0.182
+0.174
weet+0.174
Neg logit contributions
angers-0.124
pit-0.123
ider-0.113
 Majesty-0.108
 bedroom-0.107
Token looked
Token ID3114
Feature activation-2.84e+00

Pos logit contributions
angers+0.018
pit+0.018
 Majesty+0.017
 bedroom+0.016
 majesty+0.016
Neg logit contributions
leaf-0.022
 sorts-0.021
aling-0.019
-0.018
weet-0.018
Token like
Token ID588
Feature activation+4.08e-01

Pos logit contributions
 Majesty+0.095
angers+0.095
pit+0.094
 bedroom+0.090
 majesty+0.088
Neg logit contributions
leaf-0.071
 sorts-0.068
aling-0.062
igator-0.059
 course-0.058
Token tentacles
Token ID41192
Feature activation+2.53e+00

Pos logit contributions
leaf+0.012
 sorts+0.012
aling+0.011
igator+0.010
ited+0.010
Neg logit contributions
pit-0.012
angers-0.012
 Majesty-0.012
 bedroom-0.012
 bathroom-0.011
Token had
Token ID550
Feature activation+3.07e+00

Pos logit contributions
leaf+0.077
 sorts+0.076
aling+0.073
igator+0.067
weet+0.066
Neg logit contributions
angers-0.061
pit-0.061
 teachers-0.059
 bedroom-0.058
 classmates-0.058
Token balloons
Token ID35485
Feature activation+5.88e+00

Pos logit contributions
 sorts+0.087
leaf+0.087
aling+0.078
igator+0.076
+0.074
Neg logit contributions
 Majesty-0.091
pit-0.091
angers-0.090
 bedroom-0.088
 majesty-0.084
Token,
Token ID11
Feature activation-3.68e+00

Pos logit contributions
 sorts+0.192
leaf+0.190
+0.168
aling+0.167
igator+0.165
Neg logit contributions
angers-0.154
 Majesty-0.154
pit-0.153
 bedroom-0.143
ider-0.141
Token others
Token ID1854
Feature activation-6.04e-01

Pos logit contributions
angers+0.097
 bedroom+0.095
pit+0.094
 bathroom+0.094
 teachers+0.090
Neg logit contributions
 sorts-0.117
aling-0.111
leaf-0.110
ited-0.105
ez-0.102
Token had
Token ID550
Feature activation+2.32e+00

Pos logit contributions
pit+0.017
angers+0.017
 Majesty+0.017
 bedroom+0.016
ider+0.016
Neg logit contributions
leaf-0.018
 sorts-0.018
aling-0.016
igator-0.015
weet-0.015
Token rib
Token ID12183
Feature activation+9.83e+00

Pos logit contributions
 sorts+0.067
leaf+0.067
aling+0.060
igator+0.059
+0.056
Neg logit contributions
pit-0.068
 Majesty-0.068
angers-0.067
 bedroom-0.065
 majesty-0.063
Tokenbons
Token ID23461
Feature activation+5.82e+00

Pos logit contributions
igator+0.211
leaf+0.193
 sorts+0.177
aling+0.150
icated+0.148
Neg logit contributions
angers-0.368
 Majesty-0.364
omm-0.350
 majesty-0.344
ings-0.340
Token,
Token ID11
Feature activation-4.46e+00

Pos logit contributions
leaf+0.176
 sorts+0.176
aling+0.154
igator+0.150
+0.149
Neg logit contributions
pit-0.168
angers-0.167
 Majesty-0.162
 bedroom-0.155
ider-0.153
Token and
Token ID290
Feature activation+6.69e+00

Pos logit contributions
pit+0.122
angers+0.121
 bedroom+0.116
 Majesty+0.116
 bathroom+0.112
Neg logit contributions
 sorts-0.142
leaf-0.136
aling-0.130
igator-0.124
ez-0.117
Token some
Token ID617
Feature activation+2.56e+00

Pos logit contributions
leaf+0.207
 sorts+0.206
aling+0.197
igator+0.186
ited+0.180
Neg logit contributions
 Majesty-0.180
 bedroom-0.175
pit-0.171
angers-0.170
 teachers-0.166
Token had
Token ID550
Feature activation+2.24e+00

Pos logit contributions
 sorts+0.077
leaf+0.076
aling+0.073
igator+0.066
weet+0.066
Neg logit contributions
angers-0.069
pit-0.069
 bedroom-0.068
 Majesty-0.068
 bedrooms-0.065
Token up
Token ID510
Feature activation-2.11e+00

Pos logit contributions
 sorts+0.003
+0.002
leaf+0.002
aling+0.002
icated+0.002
Neg logit contributions
 Majesty-0.005
pit-0.005
angers-0.005
 majesty-0.005
ider-0.005
Token.
Token ID13
Feature activation-2.83e-01

Pos logit contributions
pit+0.057
angers+0.057
 Majesty+0.056
 bedroom+0.053
ider+0.052
Neg logit contributions
leaf-0.067
 sorts-0.067
aling-0.059
-0.058
igator-0.058
Token Some
Token ID2773
Feature activation+2.12e+00

Pos logit contributions
pit+0.010
 Majesty+0.009
ider+0.009
angers+0.009
 majesty+0.009
Neg logit contributions
-0.007
 sorts-0.007
leaf-0.006
weet-0.006
 course-0.006
Token of
Token ID286
Feature activation+3.00e+00

Pos logit contributions
leaf+0.066
 sorts+0.065
aling+0.059
igator+0.055
weet+0.054
Neg logit contributions
pit-0.058
angers-0.058
 bedroom-0.056
 Majesty-0.054
 bathroom-0.054
Token the
Token ID262
Feature activation+7.03e-01

Pos logit contributions
leaf+0.094
 sorts+0.088
aling+0.088
fy+0.079
+0.077
Neg logit contributions
 bedroom-0.077
 bathroom-0.076
angers-0.076
pit-0.076
 cabinet-0.074
Token rib
Token ID12183
Feature activation+9.76e+00

Pos logit contributions
 sorts+0.024
leaf+0.023
aling+0.021
+0.021
igator+0.020
Neg logit contributions
pit-0.018
angers-0.018
 Majesty-0.018
 bedroom-0.017
ider-0.016
Tokenbons
Token ID23461
Feature activation+5.54e+00

Pos logit contributions
leaf+0.201
igator+0.187
 sorts+0.181
+0.149
icated+0.147
Neg logit contributions
 Majesty-0.365
angers-0.363
pit-0.353
 majesty-0.343
omm-0.340
Token and
Token ID290
Feature activation+7.25e+00

Pos logit contributions
leaf+0.184
 sorts+0.181
aling+0.162
weet+0.156
igator+0.153
Neg logit contributions
pit-0.145
angers-0.143
 Majesty-0.134
 bedroom-0.131
ider-0.129
Token clips
Token ID19166
Feature activation+4.66e+00

Pos logit contributions
leaf+0.223
 sorts+0.215
aling+0.198
igator+0.184
sm+0.179
Neg logit contributions
angers-0.203
 Majesty-0.202
pit-0.201
 bedroom-0.198
 bathroom-0.190
Token had
Token ID550
Feature activation+2.15e+00

Pos logit contributions
leaf+0.151
 sorts+0.150
aling+0.133
weet+0.128
igator+0.128
Neg logit contributions
angers-0.125
pit-0.124
 Majesty-0.116
 bedroom-0.112
ider-0.111
Token fallen
Token ID9292
Feature activation+4.23e-01

Pos logit contributions
 sorts+0.064
leaf+0.064
aling+0.057
igator+0.056
+0.053
Neg logit contributions
angers-0.061
pit-0.060
 Majesty-0.060
 bedroom-0.058
 bathroom-0.056
Token
Token ID198
Feature activation+1.23e+00

Pos logit contributions
leaf+0.032
 sorts+0.031
aling+0.030
igator+0.028
ited+0.027
Neg logit contributions
 bedroom-0.024
 bathroom-0.022
pit-0.021
angers-0.021
 cabinet-0.020
Token
Token ID198
Feature activation+1.31e+00

Pos logit contributions
leaf+0.041
 sorts+0.040
igator+0.035
aling+0.034
icated+0.033
Neg logit contributions
 Majesty-0.030
pit-0.030
angers-0.030
 bedroom-0.030
ider-0.028
TokenAnna
Token ID31160
Feature activation+1.22e+00

Pos logit contributions
leaf+0.042
 sorts+0.041
igator+0.036
 thanks+0.035
aling+0.035
Neg logit contributions
pit-0.034
 Majesty-0.034
angers-0.033
 bedroom-0.033
ider-0.032
Token was
Token ID373
Feature activation+2.71e-02

Pos logit contributions
leaf+0.037
 sorts+0.037
igator+0.032
weet+0.032
aling+0.031
Neg logit contributions
pit-0.036
 Majesty-0.035
 bedroom-0.034
 majesty-0.032
angers-0.032
Token very
Token ID845
Feature activation+4.80e-01

Pos logit contributions
leaf+0.001
 sorts+0.001
aling+0.001
 course+0.001
igator+0.001
Neg logit contributions
pit-0.001
 Majesty-0.001
angers-0.001
 bedroom-0.001
ider-0.001
Token exc
Token ID2859
Feature activation+9.76e+00

Pos logit contributions
 sorts+0.014
leaf+0.014
+0.012
aling+0.012
igator+0.012
Neg logit contributions
pit-0.015
angers-0.014
 Majesty-0.014
 bedroom-0.013
ider-0.013
Tokenite
Token ID578
Feature activation+2.97e+00

Pos logit contributions
 sorts+0.217
leaf+0.202
 thanks+0.171
weet+0.161
igator+0.160
Neg logit contributions
angers-0.365
uffy-0.354
ider-0.348
pit-0.334
ail-0.327
Token.
Token ID13
Feature activation+4.88e-01

Pos logit contributions
leaf+0.098
 sorts+0.095
aling+0.085
+0.082
igator+0.081
Neg logit contributions
pit-0.078
angers-0.078
 Majesty-0.075
 bedroom-0.072
ider-0.070
Token She
Token ID1375
Feature activation+4.38e-01

Pos logit contributions
 sorts+0.015
leaf+0.015
+0.014
aling+0.013
weet+0.013
Neg logit contributions
pit-0.013
 Majesty-0.013
angers-0.013
ider-0.012
 majesty-0.012
Token said
Token ID531
Feature activation-2.88e+00

Pos logit contributions
 sorts+0.015
leaf+0.014
icated+0.013
weet+0.013
aling+0.013
Neg logit contributions
pit-0.011
 bedroom-0.010
angers-0.010
 Majesty-0.010
 principal-0.010
Token,
Token ID11
Feature activation-6.49e+00

Pos logit contributions
pit+0.078
angers+0.074
 bedroom+0.071
 Majesty+0.070
ider+0.067
Neg logit contributions
leaf-0.096
 sorts-0.091
-0.091
igator-0.084
 course-0.084
Token It
Token ID632
Feature activation+1.83e+00

Pos logit contributions
 sorts+0.015
+0.014
leaf+0.013
 juicy+0.012
igator+0.012
Neg logit contributions
 Majesty-0.025
pit-0.025
ider-0.023
 majesty-0.023
angers-0.022
Token had
Token ID550
Feature activation+2.56e+00

Pos logit contributions
 sorts+0.056
leaf+0.056
aling+0.049
+0.049
igator+0.048
Neg logit contributions
pit-0.051
angers-0.051
 Majesty-0.051
 bedroom-0.048
ider-0.047
Token spark
Token ID9009
Feature activation+5.05e+00

Pos logit contributions
 sorts+0.070
leaf+0.069
igator+0.062
aling+0.062
 course+0.058
Neg logit contributions
 Majesty-0.080
angers-0.079
pit-0.078
 bedroom-0.078
 majesty-0.074
Tokenles
Token ID829
Feature activation+1.66e+00

Pos logit contributions
 sorts+0.124
leaf+0.123
aling+0.105
+0.103
igator+0.103
Neg logit contributions
angers-0.176
pit-0.174
 Majesty-0.172
 bedroom-0.162
ider-0.162
Token and
Token ID290
Feature activation+7.32e+00

Pos logit contributions
leaf+0.050
 sorts+0.049
igator+0.043
aling+0.042
 course+0.041
Neg logit contributions
pit-0.050
angers-0.050
 bedroom-0.047
ider-0.046
 Majesty-0.045
Token rib
Token ID12183
Feature activation+9.76e+00

Pos logit contributions
leaf+0.186
 sorts+0.185
aling+0.161
igator+0.157
+0.152
Neg logit contributions
pit-0.244
angers-0.244
 Majesty-0.243
 bedroom-0.235
ider-0.227
Tokenbons
Token ID23461
Feature activation+5.86e+00

Pos logit contributions
igator+0.182
leaf+0.175
 sorts+0.154
aling+0.139
+0.123
Neg logit contributions
angers-0.385
 Majesty-0.385
 majesty-0.366
omm-0.365
pit-0.361
Token and
Token ID290
Feature activation+7.29e+00

Pos logit contributions
leaf+0.174
 sorts+0.173
aling+0.153
igator+0.150
weet+0.146
Neg logit contributions
pit-0.174
angers-0.173
ider-0.160
 bedroom-0.156
 Majesty-0.155
Token a
Token ID257
Feature activation-5.58e-02

Pos logit contributions
leaf+0.215
 sorts+0.214
aling+0.201
igator+0.194
 course+0.182
Neg logit contributions
 Majesty-0.213
pit-0.209
angers-0.209
 bedroom-0.206
 majesty-0.199
Token big
Token ID1263
Feature activation+2.57e+00

Pos logit contributions
angers+0.002
pit+0.002
 Majesty+0.002
ider+0.002
 bedroom+0.002
Neg logit contributions
 sorts-0.001
leaf-0.001
-0.001
aling-0.001
igator-0.001
Token bow
Token ID9563
Feature activation+1.71e+00

Pos logit contributions
 sorts+0.084
leaf+0.084
+0.074
aling+0.073
igator+0.073
Neg logit contributions
angers-0.067
pit-0.066
 Majesty-0.066
 bedroom-0.061
ider-0.061
Token a
Token ID257
Feature activation+9.97e-01

Pos logit contributions
leaf+0.055
 sorts+0.055
aling+0.050
igator+0.049
 course+0.045
Neg logit contributions
 bedroom-0.047
 bathroom-0.044
pit-0.044
 Majesty-0.042
angers-0.042
Token time
Token ID640
Feature activation+8.75e-01

Pos logit contributions
leaf+0.032
 sorts+0.031
aling+0.028
igator+0.027
weet+0.026
Neg logit contributions
pit-0.027
 Majesty-0.026
 bedroom-0.026
angers-0.025
ider-0.025
Token there
Token ID612
Feature activation-1.95e-01

Pos logit contributions
+0.029
 sorts+0.026
 course+0.025
igator+0.024
sm+0.023
Neg logit contributions
 Majesty-0.025
angers-0.025
 principal-0.023
pit-0.023
 majesty-0.022
Token was
Token ID373
Feature activation+1.08e+00

Pos logit contributions
angers+0.006
 Majesty+0.006
pit+0.006
ider+0.006
 majesty+0.006
Neg logit contributions
 sorts-0.006
leaf-0.005
-0.005
 course-0.005
igator-0.005
Token a
Token ID257
Feature activation+8.12e-01

Pos logit contributions
leaf+0.039
aling+0.037
 sorts+0.037
igator+0.034
ited+0.033
Neg logit contributions
 bedroom-0.025
 bathroom-0.023
pit-0.021
angers-0.021
tub-0.020
Token cater
Token ID20825
Feature activation+9.76e+00

Pos logit contributions
 sorts+0.027
leaf+0.027
aling+0.023
+0.023
igator+0.023
Neg logit contributions
pit-0.021
angers-0.021
 Majesty-0.021
 bedroom-0.020
ider-0.019
Tokenpillar
Token ID41643
Feature activation+3.70e+00

Pos logit contributions
 sorts+0.237
leaf+0.236
bons+0.205
 helium+0.198
 thanks+0.198
Neg logit contributions
angers-0.299
 cabinet-0.284
uffy-0.278
pit-0.275
ider-0.272
Token.
Token ID13
Feature activation+2.00e+00

Pos logit contributions
leaf+0.133
 sorts+0.125
aling+0.115
+0.108
weet+0.107
Neg logit contributions
pit-0.087
 bedroom-0.086
angers-0.086
ider-0.082
 Majesty-0.082
Token It
Token ID632
Feature activation+1.93e+00

Pos logit contributions
leaf+0.062
 sorts+0.057
aling+0.052
igator+0.050
+0.050
Neg logit contributions
angers-0.057
pit-0.057
 bedroom-0.056
 Majesty-0.055
 cabinet-0.054
Token lived
Token ID5615
Feature activation-1.62e-01

Pos logit contributions
leaf+0.077
 sorts+0.071
aling+0.067
weet+0.066
icated+0.065
Neg logit contributions
 bedroom-0.038
pit-0.037
 cabinet-0.036
 Majesty-0.035
angers-0.035
Token outside
Token ID2354
Feature activation-1.40e+00

Pos logit contributions
pit+0.005
angers+0.005
 Majesty+0.005
 bedroom+0.005
ider+0.005
Neg logit contributions
 sorts-0.004
leaf-0.004
aling-0.004
-0.004
igator-0.004
TokenOne
Token ID3198
Feature activation+1.16e+00

Pos logit contributions
 sorts+0.123
leaf+0.122
+0.109
aling+0.106
 course+0.104
Neg logit contributions
 Majesty-0.115
pit-0.113
angers-0.113
 bedroom-0.105
ider-0.105
Token day
Token ID1110
Feature activation+2.87e-01

Pos logit contributions
leaf+0.040
aling+0.033
ez+0.032
pill+0.032
bons+0.032
Neg logit contributions
 bedroom-0.030
 teacher-0.028
 bathroom-0.028
pit-0.028
tub-0.026
Token,
Token ID11
Feature activation-3.52e+00

Pos logit contributions
+0.009
 sorts+0.008
leaf+0.008
ch+0.008
igator+0.008
Neg logit contributions
 Majesty-0.008
angers-0.008
pit-0.008
 principal-0.008
 majesty-0.007
Token a
Token ID257
Feature activation+8.09e-01

Pos logit contributions
pit+0.124
angers+0.123
 Majesty+0.122
 bedroom+0.118
ider+0.116
Neg logit contributions
 sorts-0.083
leaf-0.083
aling-0.070
-0.067
igator-0.067
Token little
Token ID1310
Feature activation+3.81e+00

Pos logit contributions
 sorts+0.027
leaf+0.027
aling+0.024
+0.023
igator+0.023
Neg logit contributions
pit-0.021
angers-0.021
 Majesty-0.020
 bedroom-0.019
ider-0.019
Token aer
Token ID9551
Feature activation+9.75e+00

Pos logit contributions
leaf+0.152
 sorts+0.148
aling+0.144
+0.133
ez+0.129
Neg logit contributions
pit-0.069
 bedroom-0.067
 cabinet-0.067
angers-0.066
uffy-0.066
Tokenopl
Token ID20106
Feature activation+4.61e+00

Pos logit contributions
leaf+0.196
 sorts+0.186
+0.162
 juicy+0.136
 helium+0.133
Neg logit contributions
angers-0.373
 Majesty-0.365
pit-0.365
ider-0.357
 principal-0.356
Tokenane
Token ID1531
Feature activation+3.83e+00

Pos logit contributions
leaf+0.120
 sorts+0.115
aling+0.102
+0.100
 course+0.097
Neg logit contributions
 Majesty-0.154
pit-0.152
angers-0.146
 bedroom-0.146
 majesty-0.141
Token was
Token ID373
Feature activation+4.71e-01

Pos logit contributions
leaf+0.145
 sorts+0.137
aling+0.119
weet+0.119
icated+0.118
Neg logit contributions
pit-0.080
ider-0.075
angers-0.075
 Majesty-0.074
 bedroom-0.072
Token in
Token ID287
Feature activation+2.44e+00

Pos logit contributions
leaf+0.014
 sorts+0.014
 course+0.012
icated+0.012
igator+0.012
Neg logit contributions
angers-0.013
 Majesty-0.013
pit-0.013
 bedroom-0.013
ider-0.013
Token the
Token ID262
Feature activation+1.82e+00

Pos logit contributions
leaf+0.081
fy+0.068
 sorts+0.068
aling+0.067
igator+0.067
Neg logit contributions
 bedroom-0.070
 bathroom-0.067
 Majesty-0.063
 cabinet-0.061
 Lee-0.061
Token in
Token ID287
Feature activation+2.44e+00

Pos logit contributions
leaf+0.014
 sorts+0.014
 course+0.012
icated+0.012
igator+0.012
Neg logit contributions
angers-0.013
 Majesty-0.013
pit-0.013
 bedroom-0.013
ider-0.013
Token the
Token ID262
Feature activation+1.82e+00

Pos logit contributions
leaf+0.081
fy+0.068
 sorts+0.068
aling+0.067
igator+0.067
Neg logit contributions
 bedroom-0.070
 bathroom-0.067
 Majesty-0.063
 cabinet-0.061
 Lee-0.061
Token sky
Token ID6766
Feature activation+1.28e-01

Pos logit contributions
leaf+0.067
 sorts+0.062
igator+0.057
sm+0.055
aling+0.055
Neg logit contributions
 bedroom-0.045
 Majesty-0.043
 bathroom-0.043
pit-0.042
angers-0.039
Token.
Token ID13
Feature activation+1.66e+00

Pos logit contributions
leaf+0.005
 sorts+0.005
aling+0.004
igator+0.004
+0.004
Neg logit contributions
pit-0.003
angers-0.003
 bedroom-0.003
 Majesty-0.003
ider-0.003
Token The
Token ID383
Feature activation+2.85e+00

Pos logit contributions
leaf+0.052
 sorts+0.049
aling+0.044
igator+0.043
 course+0.043
Neg logit contributions
angers-0.045
 bedroom-0.044
pit-0.042
 Lee-0.042
 cabinet-0.042
Token aer
Token ID9551
Feature activation+9.74e+00

Pos logit contributions
 sorts+0.087
leaf+0.086
aling+0.077
ez+0.072
+0.072
Neg logit contributions
 Majesty-0.085
angers-0.080
 bedroom-0.080
pit-0.079
 majesty-0.077
Tokenopl
Token ID20106
Feature activation+4.76e+00

Pos logit contributions
leaf+0.190
 sorts+0.175
+0.151
igator+0.141
 juicy+0.132
Neg logit contributions
angers-0.384
 Majesty-0.374
pit-0.372
 principal-0.358
omm-0.356
Tokenane
Token ID1531
Feature activation+3.71e+00

Pos logit contributions
 sorts+0.137
leaf+0.137
aling+0.119
+0.117
igator+0.116
Neg logit contributions
pit-0.142
 Majesty-0.142
angers-0.142
 bedroom-0.134
ider-0.131
Token liked
Token ID8288
Feature activation+1.03e+00

Pos logit contributions
leaf+0.147
 sorts+0.137
weet+0.123
aling+0.122
ion+0.121
Neg logit contributions
pit-0.074
ider-0.068
 bedroom-0.067
 Majesty-0.067
angers-0.067
Token to
Token ID284
Feature activation+4.73e-01

Pos logit contributions
leaf+0.041
 sorts+0.041
aling+0.038
+0.038
ited+0.036
Neg logit contributions
 Majesty-0.018
angers-0.018
pit-0.017
 bedroom-0.017
 principal-0.016
Token move
Token ID1445
Feature activation+1.25e+00

Pos logit contributions
leaf+0.015
 sorts+0.015
+0.013
sm+0.013
able+0.013
Neg logit contributions
 Majesty-0.013
pit-0.012
 bedroom-0.012
 majesty-0.012
angers-0.012
Token a
Token ID257
Feature activation-5.57e-02

Pos logit contributions
pit+0.006
 bedroom+0.006
angers+0.006
 Majesty+0.006
 bathroom+0.006
Neg logit contributions
leaf-0.005
 sorts-0.005
aling-0.004
 course-0.004
igator-0.004
Token long
Token ID890
Feature activation+2.25e+00

Pos logit contributions
pit+0.002
 Majesty+0.002
angers+0.002
 bedroom+0.002
ider+0.002
Neg logit contributions
leaf-0.002
 sorts-0.002
aling-0.001
-0.001
igator-0.001
Token rope
Token ID17182
Feature activation+4.31e+00

Pos logit contributions
leaf+0.078
 sorts+0.075
aling+0.068
+0.065
weet+0.065
Neg logit contributions
pit-0.058
 Majesty-0.056
 bedroom-0.055
angers-0.054
ider-0.051
Token with
Token ID351
Feature activation+2.19e+00

Pos logit contributions
leaf+0.161
 sorts+0.151
aling+0.135
weet+0.134
icated+0.134
Neg logit contributions
pit-0.105
ider-0.094
 bedroom-0.091
box-0.091
angers-0.089
Token colorful
Token ID20239
Feature activation+3.87e+00

Pos logit contributions
leaf+0.073
aling+0.070
ited+0.067
igator+0.067
 sorts+0.066
Neg logit contributions
pit-0.048
 bedroom-0.047
 Majesty-0.047
 door-0.045
 bathroom-0.045
Token rib
Token ID12183
Feature activation+9.74e+00

Pos logit contributions
leaf+0.110
 sorts+0.106
aling+0.100
igator+0.098
weet+0.089
Neg logit contributions
pit-0.119
angers-0.117
 bedroom-0.114
 Majesty-0.114
 bathroom-0.106
Tokenbons
Token ID23461
Feature activation+5.22e+00

Pos logit contributions
igator+0.230
leaf+0.209
 sorts+0.192
able+0.162
icated+0.160
Neg logit contributions
angers-0.320
 Majesty-0.315
ings-0.309
omm-0.306
 majesty-0.299
Token on
Token ID319
Feature activation+2.12e+00

Pos logit contributions
 sorts+0.185
leaf+0.185
aling+0.162
igator+0.160
weet+0.158
Neg logit contributions
pit-0.129
angers-0.124
ider-0.117
 bedroom-0.108
box-0.108
Token it
Token ID340
Feature activation-2.11e+00

Pos logit contributions
leaf+0.066
 sorts+0.064
aling+0.058
weet+0.055
icated+0.054
Neg logit contributions
pit-0.060
angers-0.059
 Majesty-0.058
atively-0.056
 bedroom-0.055
Token.
Token ID13
Feature activation+3.13e-01

Pos logit contributions
pit+0.047
angers+0.046
 Majesty+0.043
 bedroom+0.043
ider+0.042
Neg logit contributions
leaf-0.079
 sorts-0.076
aling-0.068
igator-0.067
weet-0.067
Token Sam
Token ID3409
Feature activation-3.91e-01

Pos logit contributions
 sorts+0.009
leaf+0.009
+0.008
aling+0.008
 course+0.008
Neg logit contributions
 Majesty-0.009
angers-0.009
pit-0.009
ider-0.009
 bedroom-0.009
Token<|endoftext|>
Token ID50256
Feature activation+3.81e+00

Pos logit contributions
 bedroom+0.015
omm+0.015
angers+0.014
 Majesty+0.014
tub+0.013
Neg logit contributions
leaf-0.034
igator-0.031
 sorts-0.030
ited-0.030
aling-0.029
TokenOnce
Token ID7454
Feature activation-2.96e+00

Pos logit contributions
leaf+0.126
 sorts+0.125
aling+0.111
igator+0.109
+0.108
Neg logit contributions
pit-0.097
angers-0.097
 Majesty-0.094
 bedroom-0.091
ider-0.088
Token there
Token ID612
Feature activation-4.97e-01

Pos logit contributions
 Majesty+0.076
angers+0.072
ider+0.069
pit+0.069
 majesty+0.065
Neg logit contributions
 sorts-0.105
igator-0.095
-0.094
leaf-0.094
 course-0.091
Token was
Token ID373
Feature activation+9.00e-01

Pos logit contributions
angers+0.017
 Majesty+0.017
ider+0.016
pit+0.016
 majesty+0.016
Neg logit contributions
 sorts-0.013
-0.012
leaf-0.012
 course-0.011
igator-0.011
Token a
Token ID257
Feature activation+6.60e-01

Pos logit contributions
leaf+0.032
aling+0.031
 sorts+0.030
igator+0.028
ited+0.027
Neg logit contributions
 bedroom-0.020
 birthday-0.018
 bathroom-0.018
 kitchen-0.017
pit-0.016
Token cater
Token ID20825
Feature activation+9.73e+00

Pos logit contributions
leaf+0.023
 sorts+0.023
aling+0.020
+0.020
igator+0.020
Neg logit contributions
pit-0.016
 Majesty-0.016
angers-0.016
 bedroom-0.015
ider-0.014
Tokenpillar
Token ID41643
Feature activation+3.64e+00

Pos logit contributions
leaf+0.244
 sorts+0.242
bons+0.228
 helium+0.214
+0.202
Neg logit contributions
angers-0.281
uffy-0.270
 cabinet-0.256
 teacher-0.254
tub-0.252
Token in
Token ID287
Feature activation+2.08e+00

Pos logit contributions
leaf+0.144
 sorts+0.134
aling+0.124
igator+0.117
+0.117
Neg logit contributions
pit-0.072
 bedroom-0.071
angers-0.070
 Majesty-0.067
ider-0.067
Token a
Token ID257
Feature activation+7.30e-01

Pos logit contributions
leaf+0.072
fy+0.062
 sorts+0.061
aling+0.059
ited+0.056
Neg logit contributions
 bedroom-0.055
 bathroom-0.053
 Majesty-0.052
 cabinet-0.050
 Lee-0.050
Token garden
Token ID11376
Feature activation-7.19e-01

Pos logit contributions
 sorts+0.021
leaf+0.021
+0.018
aling+0.018
igator+0.018
Neg logit contributions
angers-0.022
pit-0.022
 Majesty-0.022
ider-0.021
 bedroom-0.020
Token who
Token ID508
Feature activation+4.79e+00

Pos logit contributions
pit+0.018
angers+0.018
 Majesty+0.018
 bedroom+0.017
ider+0.016
Neg logit contributions
leaf-0.025
 sorts-0.024
aling-0.022
-0.021
igator-0.021
Token,
Token ID11
Feature activation-3.67e+00

Pos logit contributions
+0.030
 sorts+0.028
 course+0.026
igator+0.026
sm+0.025
Neg logit contributions
 Majesty-0.028
angers-0.028
 principal-0.025
pit-0.025
 majesty-0.025
Token there
Token ID612
Feature activation-2.08e-01

Pos logit contributions
pit+0.096
angers+0.095
 Majesty+0.094
 bedroom+0.090
ider+0.087
Neg logit contributions
leaf-0.121
 sorts-0.120
aling-0.106
-0.103
igator-0.102
Token was
Token ID373
Feature activation+8.39e-01

Pos logit contributions
angers+0.007
 Majesty+0.007
ider+0.007
pit+0.007
 majesty+0.007
Neg logit contributions
 sorts-0.006
-0.005
leaf-0.005
 course-0.005
igator-0.004
Token a
Token ID257
Feature activation+6.95e-01

Pos logit contributions
leaf+0.030
aling+0.030
 sorts+0.029
igator+0.027
ited+0.027
Neg logit contributions
 bedroom-0.019
 bathroom-0.017
pit-0.016
angers-0.015
tub-0.015
Token little
Token ID1310
Feature activation+3.81e+00

Pos logit contributions
 sorts+0.023
leaf+0.023
aling+0.020
+0.020
igator+0.020
Neg logit contributions
pit-0.018
angers-0.018
 Majesty-0.018
 bedroom-0.017
ider-0.016
Token cater
Token ID20825
Feature activation+9.73e+00

Pos logit contributions
leaf+0.152
 sorts+0.148
aling+0.145
+0.133
ez+0.131
Neg logit contributions
pit-0.074
 bedroom-0.072
 cabinet-0.071
 Majesty-0.069
angers-0.068
Tokenpillar
Token ID41643
Feature activation+3.66e+00

Pos logit contributions
leaf+0.226
 sorts+0.226
bons+0.194
 helium+0.192
 thanks+0.185
Neg logit contributions
angers-0.312
 cabinet-0.293
pit-0.292
uffy-0.289
ider-0.287
Token.
Token ID13
Feature activation+1.74e+00

Pos logit contributions
leaf+0.125
 sorts+0.117
aling+0.107
+0.101
weet+0.100
Neg logit contributions
pit-0.093
angers-0.092
 bedroom-0.092
ider-0.089
 Majesty-0.088
Token She
Token ID1375
Feature activation+4.97e-01

Pos logit contributions
leaf+0.057
 sorts+0.051
aling+0.048
sm+0.046
 course+0.045
Neg logit contributions
angers-0.046
pit-0.046
 bedroom-0.045
 cabinet-0.045
 Majesty-0.044
Token was
Token ID373
Feature activation-2.04e-01

Pos logit contributions
leaf+0.017
 sorts+0.017
aling+0.016
weet+0.015
icated+0.014
Neg logit contributions
angers-0.011
 Majesty-0.011
 bedroom-0.011
pit-0.011
 majesty-0.011
Token very
Token ID845
Feature activation+9.36e-01

Pos logit contributions
angers+0.005
 Majesty+0.005
pit+0.005
 bedroom+0.005
 majesty+0.005
Neg logit contributions
leaf-0.007
 sorts-0.007
aling-0.006
 course-0.006
-0.006
Token doll
Token ID3654
Feature activation+1.09e+00

Pos logit contributions
leaf+0.086
 sorts+0.082
aling+0.080
+0.073
weet+0.073
Neg logit contributions
pit-0.081
 bedroom-0.079
 Majesty-0.078
angers-0.075
 cabinet-0.073
Token with
Token ID351
Feature activation+1.94e+00

Pos logit contributions
leaf+0.037
 sorts+0.036
aling+0.033
igator+0.032
weet+0.031
Neg logit contributions
pit-0.028
angers-0.027
 bedroom-0.027
ider-0.026
 Majesty-0.026
Token pink
Token ID11398
Feature activation+3.87e+00

Pos logit contributions
aling+0.057
 sorts+0.056
leaf+0.056
igator+0.054
ited+0.050
Neg logit contributions
 Majesty-0.051
 bedroom-0.050
angers-0.049
pit-0.049
 teachers-0.047
Token and
Token ID290
Feature activation+6.67e+00

Pos logit contributions
 sorts+0.121
leaf+0.121
aling+0.106
+0.105
igator+0.104
Neg logit contributions
pit-0.106
angers-0.106
 Majesty-0.105
 bedroom-0.100
ider-0.097
Token blue
Token ID4171
Feature activation+4.30e+00

Pos logit contributions
leaf+0.191
 sorts+0.189
aling+0.180
igator+0.174
 course+0.167
Neg logit contributions
 bedroom-0.198
 Majesty-0.195
pit-0.191
angers-0.191
 bathroom-0.182
Token rib
Token ID12183
Feature activation+9.71e+00

Pos logit contributions
 sorts+0.146
leaf+0.146
aling+0.129
+0.128
igator+0.127
Neg logit contributions
pit-0.106
angers-0.106
 Majesty-0.105
 bedroom-0.098
ider-0.096
Tokenbons
Token ID23461
Feature activation+5.54e+00

Pos logit contributions
igator+0.209
leaf+0.186
 sorts+0.175
aling+0.155
igators+0.154
Neg logit contributions
 Majesty-0.358
omm-0.346
angers-0.342
 majesty-0.339
pit-0.329
Token in
Token ID287
Feature activation+4.42e-01

Pos logit contributions
 sorts+0.205
leaf+0.202
aling+0.188
igator+0.181
weet+0.179
Neg logit contributions
pit-0.127
angers-0.124
ider-0.116
 bedroom-0.107
 Majesty-0.107
Token her
Token ID607
Feature activation-3.99e+00

Pos logit contributions
leaf+0.014
aling+0.013
 sorts+0.012
igator+0.012
vious+0.011
Neg logit contributions
 bedroom-0.013
pit-0.012
 Majesty-0.012
 door-0.011
 Lee-0.011
Token hair
Token ID4190
Feature activation+1.59e+00

Pos logit contributions
angers+0.089
pit+0.088
 Majesty+0.087
ider+0.080
 bedroom+0.079
Neg logit contributions
 sorts-0.145
leaf-0.145
-0.130
aling-0.128
igator-0.127
Token.
Token ID13
Feature activation+2.23e-01

Pos logit contributions
 sorts+0.049
leaf+0.049
+0.043
aling+0.043
igator+0.041
Neg logit contributions
 Majesty-0.044
angers-0.043
pit-0.043
 bedroom-0.041
 majesty-0.040
Token looked
Token ID3114
Feature activation-3.28e+00

Pos logit contributions
leaf+0.202
 sorts+0.198
weet+0.177
igator+0.176
aling+0.173
Neg logit contributions
pit-0.180
 bedroom-0.175
angers-0.173
 Majesty-0.169
 bathroom-0.167
Token through
Token ID832
Feature activation-1.76e+00

Pos logit contributions
pit+0.096
angers+0.096
 Majesty+0.096
 bedroom+0.090
ider+0.088
Neg logit contributions
 sorts-0.097
leaf-0.097
aling-0.084
-0.083
igator-0.082
Token the
Token ID262
Feature activation-1.08e+00

Pos logit contributions
pit+0.059
 bedroom+0.058
 Majesty+0.057
angers+0.057
 bathroom+0.055
Neg logit contributions
leaf-0.047
 sorts-0.044
aling-0.040
igator-0.039
weet-0.038
Token ey
Token ID1926
Feature activation+9.77e-01

Pos logit contributions
pit+0.024
angers+0.023
 Majesty+0.023
 bedroom+0.023
 bathroom+0.021
Neg logit contributions
 sorts-0.041
leaf-0.041
aling-0.037
-0.036
igator-0.036
Tokenep
Token ID538
Feature activation+1.39e-01

Pos logit contributions
 sorts+0.032
leaf+0.031
+0.026
igator+0.026
weet+0.026
Neg logit contributions
pit-0.027
angers-0.027
 Majesty-0.026
ider-0.025
 bedroom-0.024
Tokeniece
Token ID8535
Feature activation-8.78e+00

Pos logit contributions
 sorts+0.005
leaf+0.005
aling+0.004
+0.004
igator+0.004
Neg logit contributions
pit-0.003
angers-0.003
 Majesty-0.003
 bedroom-0.003
ider-0.003
Token.
Token ID13
Feature activation-1.66e-01

Pos logit contributions
 Majesty+0.242
angers+0.242
pit+0.239
 bedroom+0.225
ider+0.221
Neg logit contributions
 sorts-0.270
leaf-0.267
-0.237
aling-0.237
igator-0.231
Token He
Token ID679
Feature activation-6.10e-01

Pos logit contributions
pit+0.006
 Majesty+0.006
angers+0.005
ider+0.005
 majesty+0.005
Neg logit contributions
 sorts-0.004
leaf-0.004
-0.003
aling-0.003
 thanks-0.003
Token saw
Token ID2497
Feature activation-3.24e+00

Pos logit contributions
pit+0.014
angers+0.014
 Majesty+0.014
 bedroom+0.013
 principal+0.013
Neg logit contributions
leaf-0.022
 sorts-0.021
igator-0.019
aling-0.019
weet-0.019
Token the
Token ID262
Feature activation-4.58e-01

Pos logit contributions
pit+0.104
 Majesty+0.102
angers+0.102
 bedroom+0.098
 principal+0.096
Neg logit contributions
leaf-0.088
 sorts-0.086
aling-0.076
-0.075
igator-0.072
Token tiny
Token ID7009
Feature activation+2.06e+00

Pos logit contributions
pit+0.013
 bedroom+0.013
 Majesty+0.012
 bathroom+0.012
angers+0.012
Neg logit contributions
 sorts-0.015
leaf-0.014
aling-0.014
-0.013
igator-0.012
Token looked
Token ID3114
Feature activation-2.90e+00

Pos logit contributions
pit+0.015
angers+0.013
 Majesty+0.013
 bedroom+0.013
 bathroom+0.013
Neg logit contributions
leaf-0.020
 sorts-0.019
weet-0.018
aling-0.017
igator-0.017
Token through
Token ID832
Feature activation-1.32e+00

Pos logit contributions
pit+0.073
 Majesty+0.072
angers+0.068
 bedroom+0.068
 cabinet+0.063
Neg logit contributions
leaf-0.097
 sorts-0.095
weet-0.087
aling-0.085
icated-0.084
Token the
Token ID262
Feature activation-6.92e-01

Pos logit contributions
 bedroom+0.041
pit+0.041
 Majesty+0.039
angers+0.039
 bathroom+0.038
Neg logit contributions
leaf-0.038
 sorts-0.035
aling-0.033
igator-0.032
weet-0.031
Token ey
Token ID1926
Feature activation+1.55e+00

Pos logit contributions
pit+0.014
 bedroom+0.013
angers+0.013
 Majesty+0.013
 bathroom+0.013
Neg logit contributions
 sorts-0.027
leaf-0.027
aling-0.025
-0.024
igator-0.024
Tokenep
Token ID538
Feature activation+6.00e-01

Pos logit contributions
 sorts+0.052
leaf+0.050
+0.042
icated+0.042
igator+0.042
Neg logit contributions
pit-0.042
angers-0.041
 Majesty-0.040
ider-0.039
 bedroom-0.037
Tokeniece
Token ID8535
Feature activation-8.46e+00

Pos logit contributions
 sorts+0.019
leaf+0.019
aling+0.017
+0.017
igator+0.017
Neg logit contributions
angers-0.016
 Majesty-0.016
pit-0.016
 bedroom-0.015
ider-0.014
Token and
Token ID290
Feature activation+6.39e+00

Pos logit contributions
angers+0.293
 Majesty+0.293
pit+0.291
 bedroom+0.277
ider+0.274
Neg logit contributions
 sorts-0.201
leaf-0.198
aling-0.168
-0.168
igator-0.163
Token saw
Token ID2497
Feature activation-3.42e+00

Pos logit contributions
 sorts+0.194
leaf+0.192
aling+0.170
+0.169
igator+0.163
Neg logit contributions
angers-0.184
 Majesty-0.180
pit-0.178
omm-0.170
ider-0.170
Token the
Token ID262
Feature activation-5.90e-01

Pos logit contributions
pit+0.113
 Majesty+0.113
angers+0.111
 bedroom+0.107
 principal+0.105
Neg logit contributions
leaf-0.087
 sorts-0.085
aling-0.076
-0.074
igator-0.071
Token tiny
Token ID7009
Feature activation+1.80e+00

Pos logit contributions
pit+0.017
 bedroom+0.017
 Majesty+0.016
 bathroom+0.016
 cabinet+0.016
Neg logit contributions
 sorts-0.019
leaf-0.018
aling-0.017
ez-0.015
igator-0.015
Token scales
Token ID16252
Feature activation+1.10e-01

Pos logit contributions
leaf+0.055
 sorts+0.054
aling+0.049
igator+0.046
+0.046
Neg logit contributions
pit-0.053
 Majesty-0.051
angers-0.051
 bedroom-0.050
ider-0.047
Token
Token ID198
Feature activation-3.28e-01

Pos logit contributions
pit+0.086
 Majesty+0.084
angers+0.083
 bedroom+0.079
ider+0.079
Neg logit contributions
 sorts-0.079
leaf-0.078
-0.072
aling-0.069
weet-0.065
Token
Token ID198
Feature activation+7.65e-02

Pos logit contributions
angers+0.007
pit+0.007
 Majesty+0.007
 bedroom+0.007
ider+0.007
Neg logit contributions
 sorts-0.012
leaf-0.011
aling-0.010
igator-0.010
weet-0.010
TokenAb
Token ID4826
Feature activation+4.07e-01

Pos logit contributions
 sorts+0.002
leaf+0.002
icated+0.002
weet+0.002
aling+0.002
Neg logit contributions
pit-0.002
 Majesty-0.002
orman-0.002
ider-0.002
atively-0.002
Tokenby
Token ID1525
Feature activation-4.15e+00

Pos logit contributions
leaf+0.016
 sorts+0.016
aling+0.014
igator+0.014
weet+0.014
Neg logit contributions
pit-0.008
 Majesty-0.008
angers-0.008
 bedroom-0.008
 majesty-0.007
Token promised
Token ID8072
Feature activation+2.51e-01

Pos logit contributions
 Majesty+0.110
pit+0.106
 majesty+0.100
 bedroom+0.100
ider+0.098
Neg logit contributions
leaf-0.139
 sorts-0.137
weet-0.122
icated-0.119
aling-0.119
Token,
Token ID11
Feature activation-7.95e+00

Pos logit contributions
leaf+0.008
 sorts+0.008
+0.007
aling+0.007
igator+0.006
Neg logit contributions
pit-0.007
angers-0.007
 Majesty-0.007
 bedroom-0.007
ider-0.007
Token and
Token ID290
Feature activation+4.78e+00

Pos logit contributions
 Majesty+0.171
 Lee+0.171
omm+0.168
 conscience+0.168
 parents+0.168
Neg logit contributions
 sorts-0.277
leaf-0.272
igator-0.248
aling-0.246
icated-0.241
Token the
Token ID262
Feature activation+4.06e-02

Pos logit contributions
leaf+0.146
 sorts+0.140
icated+0.129
aling+0.128
weet+0.127
Neg logit contributions
 Majesty-0.132
pit-0.125
 bedroom-0.122
atively-0.122
 majesty-0.120
Token stranger
Token ID16195
Feature activation-6.58e-01

Pos logit contributions
 sorts+0.001
leaf+0.001
aling+0.001
weet+0.001
+0.001
Neg logit contributions
pit-0.001
 Majesty-0.001
 bedroom-0.001
angers-0.001
 principal-0.001
Token let
Token ID1309
Feature activation+3.94e+00

Pos logit contributions
 Majesty+0.018
pit+0.018
 bedroom+0.017
angers+0.016
atively+0.016
Neg logit contributions
leaf-0.021
 sorts-0.020
weet-0.018
icated-0.018
aling-0.018
Token her
Token ID607
Feature activation-5.01e+00

Pos logit contributions
leaf+0.122
 sorts+0.121
aling+0.108
icated+0.103
weet+0.103
Neg logit contributions
 Majesty-0.108
pit-0.105
angers-0.104
 bedroom-0.101
omm-0.097
Token
Token ID198
Feature activation+5.25e-03

Pos logit contributions
 Majesty+0.020
angers+0.020
pit+0.020
 bedroom+0.019
omm+0.018
Neg logit contributions
leaf-0.030
 sorts-0.029
aling-0.026
igator-0.026
 course-0.025
Token
Token ID198
Feature activation+4.72e-01

Pos logit contributions
leaf+0.000
 sorts+0.000
igator+0.000
aling+0.000
vious+0.000
Neg logit contributions
angers-0.000
 Majesty-0.000
 bedroom-0.000
pit-0.000
orman-0.000
TokenL
Token ID43
Feature activation+3.59e+00

Pos logit contributions
leaf+0.015
 sorts+0.015
igator+0.013
 thanks+0.013
vious+0.013
Neg logit contributions
pit-0.012
 Majesty-0.011
angers-0.011
ider-0.011
orman-0.011
Tokenily
Token ID813
Feature activation+2.80e-01

Pos logit contributions
leaf+0.116
 sorts+0.116
aling+0.103
+0.101
igator+0.100
Neg logit contributions
pit-0.095
 Majesty-0.095
angers-0.094
 bedroom-0.089
ider-0.086
Token promised
Token ID8072
Feature activation+3.50e-01

Pos logit contributions
leaf+0.008
 sorts+0.008
weet+0.007
aling+0.007
igator+0.007
Neg logit contributions
pit-0.008
 Majesty-0.008
angers-0.008
 bedroom-0.008
 majesty-0.007
Token,
Token ID11
Feature activation-7.90e+00

Pos logit contributions
leaf+0.011
 sorts+0.010
+0.009
aling+0.009
 course+0.009
Neg logit contributions
pit-0.011
angers-0.010
 Majesty-0.010
ider-0.010
 bedroom-0.010
Token and
Token ID290
Feature activation+4.58e+00

Pos logit contributions
 Majesty+0.169
angers+0.168
 bedroom+0.163
pit+0.159
 Lee+0.158
Neg logit contributions
 sorts-0.298
leaf-0.294
aling-0.262
igator-0.262
able-0.254
Token the
Token ID262
Feature activation-1.71e-01

Pos logit contributions
leaf+0.153
 sorts+0.151
aling+0.136
igator+0.133
icated+0.132
Neg logit contributions
 Majesty-0.115
angers-0.114
pit-0.112
 bedroom-0.108
 majesty-0.105
Token man
Token ID582
Feature activation-5.31e-01

Pos logit contributions
 Majesty+0.004
 bedroom+0.004
pit+0.004
 bathroom+0.004
 majesty+0.004
Neg logit contributions
 sorts-0.006
leaf-0.006
aling-0.006
ez-0.005
weet-0.005
Token found
Token ID1043
Feature activation-3.22e+00

Pos logit contributions
pit+0.014
 Majesty+0.014
atively+0.013
 bedroom+0.013
 servant+0.012
Neg logit contributions
leaf-0.017
 sorts-0.017
weet-0.016
aling-0.015
icated-0.015
Token her
Token ID607
Feature activation-4.15e+00

Pos logit contributions
 Majesty+0.089
angers+0.088
pit+0.087
 bedroom+0.084
 cabinet+0.083
Neg logit contributions
leaf-0.096
 sorts-0.093
aling-0.089
weet-0.083
icated-0.082
Token to
Token ID284
Feature activation-9.84e-01

Pos logit contributions
angers+0.005
pit+0.005
 Majesty+0.005
 bedroom+0.005
ider+0.005
Neg logit contributions
 sorts-0.007
leaf-0.007
aling-0.006
-0.006
igator-0.006
Token always
Token ID1464
Feature activation-8.67e-01

Pos logit contributions
 Majesty+0.023
 bedroom+0.021
 majesty+0.021
pit+0.020
angers+0.020
Neg logit contributions
leaf-0.035
 sorts-0.035
igator-0.031
aling-0.031
icated-0.030
Token be
Token ID307
Feature activation-7.21e-01

Pos logit contributions
 Majesty+0.022
pit+0.022
angers+0.022
 bedroom+0.021
ider+0.021
Neg logit contributions
leaf-0.028
 sorts-0.028
aling-0.025
igator-0.025
-0.024
Token on
Token ID319
Feature activation+1.35e+00

Pos logit contributions
 Majesty+0.019
pit+0.018
angers+0.018
 bedroom+0.018
 majesty+0.017
Neg logit contributions
leaf-0.024
 sorts-0.022
aling-0.020
icated-0.020
igator-0.020
Token the
Token ID262
Feature activation-2.01e+00

Pos logit contributions
leaf+0.048
 sorts+0.045
igator+0.044
aling+0.043
icated+0.039
Neg logit contributions
 Majesty-0.035
 bedroom-0.033
 majesty-0.031
angers-0.031
 bathroom-0.030
Token lookout
Token ID40497
Feature activation-7.89e+00

Pos logit contributions
 Majesty+0.054
pit+0.053
 bedroom+0.051
angers+0.051
 majesty+0.048
Neg logit contributions
 sorts-0.066
leaf-0.066
aling-0.059
igator-0.057
-0.056
Token for
Token ID329
Feature activation+1.27e+00

Pos logit contributions
 Majesty+0.213
angers+0.213
pit+0.208
 bedroom+0.205
ider+0.195
Neg logit contributions
leaf-0.250
 sorts-0.246
aling-0.220
igator-0.213
 course-0.212
Token animals
Token ID4695
Feature activation-1.00e+00

Pos logit contributions
leaf+0.040
 sorts+0.040
aling+0.037
igator+0.036
+0.035
Neg logit contributions
 Majesty-0.035
 bedroom-0.033
angers-0.033
pit-0.032
 majesty-0.031
Token in
Token ID287
Feature activation-6.93e-01

Pos logit contributions
pit+0.021
 bedroom+0.021
angers+0.021
 Majesty+0.020
ider+0.020
Neg logit contributions
leaf-0.036
 sorts-0.036
aling-0.032
icated-0.031
weet-0.031
Token need
Token ID761
Feature activation+2.29e+00

Pos logit contributions
 bedroom+0.021
 bathroom+0.020
 Majesty+0.019
 cabinet+0.019
pit+0.019
Neg logit contributions
leaf-0.021
aling-0.019
igator-0.017
 sorts-0.017
cream-0.017
Token of
Token ID286
Feature activation+4.90e-01

Pos logit contributions
leaf+0.084
 sorts+0.082
aling+0.077
igator+0.075
+0.071
Neg logit contributions
angers-0.050
 Majesty-0.048
 bedroom-0.048
pit-0.048
ider-0.044
Token man
Token ID582
Feature activation-4.77e-02

Pos logit contributions
 sorts+0.092
leaf+0.091
aling+0.084
weet+0.082
+0.081
Neg logit contributions
 Majesty-0.048
pit-0.048
angers-0.045
 bedroom-0.044
 majesty-0.042
Token smiled
Token ID13541
Feature activation-1.71e+00

Pos logit contributions
 Majesty+0.001
pit+0.001
 majesty+0.001
ider+0.001
 bedroom+0.001
Neg logit contributions
 sorts-0.001
leaf-0.001
weet-0.001
icated-0.001
aling-0.001
Token back
Token ID736
Feature activation-4.09e+00

Pos logit contributions
angers+0.058
pit+0.058
 Majesty+0.058
 bedroom+0.055
ider+0.054
Neg logit contributions
 sorts-0.042
leaf-0.042
-0.035
aling-0.035
igator-0.034
Token and
Token ID290
Feature activation+4.57e+00

Pos logit contributions
pit+0.118
 Majesty+0.117
angers+0.117
 bedroom+0.111
ider+0.110
Neg logit contributions
 sorts-0.124
leaf-0.124
aling-0.107
igator-0.106
 course-0.103
Token said
Token ID531
Feature activation-4.01e+00

Pos logit contributions
leaf+0.148
 sorts+0.142
aling+0.133
weet+0.133
icated+0.132
Neg logit contributions
 Majesty-0.115
 majesty-0.109
pit-0.106
 parents-0.102
 Lee-0.101
Token,
Token ID11
Feature activation-7.85e+00

Pos logit contributions
pit+0.095
angers+0.092
 bedroom+0.085
 Majesty+0.083
ider+0.079
Neg logit contributions
leaf-0.144
 sorts-0.140
-0.140
igator-0.129
 course-0.129
Token
Token ID6184
Feature activation+1.70e+00

Pos logit contributions
angers+0.120
 Majesty+0.119
pit+0.119
 bedroom+0.106
ider+0.103
Neg logit contributions
 sorts-0.342
leaf-0.339
aling-0.309
igator-0.306
 course-0.303
Token
Token ID95
Feature activation+3.83e+00

Pos logit contributions
leaf+0.056
 sorts+0.055
aling+0.050
+0.049
igator+0.048
Neg logit contributions
pit-0.045
angers-0.044
 Majesty-0.044
 bedroom-0.042
 majesty-0.040
Token
Token ID26391
Feature activation-3.49e+00

Pos logit contributions
 sorts+0.119
leaf+0.114
igator+0.103
weet+0.102
icated+0.099
Neg logit contributions
 Majesty-0.106
angers-0.105
pit-0.104
ider-0.102
 bedroom-0.098
Token
Token ID129
Feature activation+3.99e+00

Pos logit contributions
pit+0.089
angers+0.088
 Majesty+0.087
 bedroom+0.082
ider+0.080
Neg logit contributions
 sorts-0.116
leaf-0.116
-0.103
aling-0.103
igator-0.100
Token
Token ID241
Feature activation-9.32e-01

Pos logit contributions
 sorts+0.147
leaf+0.143
igator+0.131
icated+0.126
sm+0.125
Neg logit contributions
 Majesty-0.092
angers-0.087
pit-0.082
ider-0.079
 majesty-0.078
Token Steve
Token ID6542
Feature activation-2.19e+00

Pos logit contributions
 Majesty+0.052
pit+0.052
angers+0.051
 bedroom+0.049
 majesty+0.048
Neg logit contributions
leaf-0.062
 sorts-0.061
aling-0.054
weet-0.052
igator-0.052
Token thanked
Token ID26280
Feature activation-2.96e+00

Pos logit contributions
pit+0.061
 Majesty+0.059
angers+0.056
 bedroom+0.055
atively+0.055
Neg logit contributions
leaf-0.068
 sorts-0.067
weet-0.059
aling-0.057
icated-0.056
Token her
Token ID607
Feature activation-6.80e+00

Pos logit contributions
pit+0.095
angers+0.095
 Majesty+0.095
 principal+0.091
 bedroom+0.091
Neg logit contributions
 sorts-0.077
leaf-0.075
aling-0.066
-0.064
igator-0.063
Token and
Token ID290
Feature activation+4.42e+00

Pos logit contributions
angers+0.221
pit+0.219
 Majesty+0.217
 bedroom+0.205
ider+0.204
Neg logit contributions
 sorts-0.179
leaf-0.178
-0.154
aling-0.151
igator-0.149
Token said
Token ID531
Feature activation-4.27e+00

Pos logit contributions
leaf+0.133
 sorts+0.131
weet+0.117
icated+0.114
aling+0.114
Neg logit contributions
 Majesty-0.125
pit-0.125
angers-0.122
 bedroom-0.118
 majesty-0.115
Token,
Token ID11
Feature activation-7.85e+00

Pos logit contributions
pit+0.121
angers+0.120
 Majesty+0.112
 bedroom+0.111
 principal+0.104
Neg logit contributions
leaf-0.135
 sorts-0.133
-0.127
igator-0.117
aling-0.116
Token "
Token ID366
Feature activation+1.17e+00

Pos logit contributions
angers+0.111
 Majesty+0.110
pit+0.109
 bedroom+0.098
ider+0.096
Neg logit contributions
 sorts-0.352
leaf-0.348
aling-0.316
igator-0.315
 course-0.311
TokenThank
Token ID10449
Feature activation+2.05e-01

Pos logit contributions
 sorts+0.035
leaf+0.033
igator+0.032
igators+0.031
icated+0.030
Neg logit contributions
ider-0.028
pit-0.028
 Majesty-0.027
abies-0.025
atively-0.024
Token you
Token ID345
Feature activation+2.93e-01

Pos logit contributions
 sorts+0.006
leaf+0.006
aling+0.005
weet+0.005
igator+0.005
Neg logit contributions
ider-0.006
 Majesty-0.006
angers-0.006
pit-0.006
omm-0.006
Token for
Token ID329
Feature activation+1.12e+00

Pos logit contributions
 sorts+0.010
leaf+0.009
+0.009
aling+0.008
igator+0.008
Neg logit contributions
angers-0.008
pit-0.008
 Majesty-0.007
 bedroom-0.007
ider-0.007
Token not
Token ID407
Feature activation-7.97e-01

Pos logit contributions
 sorts+0.038
leaf+0.038
aling+0.033
igator+0.033
+0.033
Neg logit contributions
 Majesty-0.027
 bedroom-0.026
pit-0.026
angers-0.025
 principal-0.025
Token bird
Token ID6512
Feature activation+1.74e+00

Pos logit contributions
leaf+0.080
 sorts+0.076
aling+0.073
icated+0.066
+0.066
Neg logit contributions
pit-0.072
 Majesty-0.071
 bedroom-0.068
angers-0.066
 majesty-0.065
Token thanked
Token ID26280
Feature activation-2.56e+00

Pos logit contributions
leaf+0.064
 sorts+0.058
icated+0.055
aling+0.054
weet+0.051
Neg logit contributions
pit-0.041
ail-0.040
 Majesty-0.039
 bedroom-0.038
atively-0.036
Token Lucy
Token ID22162
Feature activation-3.34e+00

Pos logit contributions
 bedroom+0.059
pit+0.059
 Majesty+0.059
 Lee+0.057
omm+0.057
Neg logit contributions
 sorts-0.088
leaf-0.087
aling-0.083
-0.074
weet-0.074
Token and
Token ID290
Feature activation+4.99e+00

Pos logit contributions
pit+0.088
 bedroom+0.084
 Majesty+0.084
angers+0.083
ail+0.081
Neg logit contributions
leaf-0.114
 sorts-0.108
aling-0.096
igator-0.094
weet-0.091
Token said
Token ID531
Feature activation-4.22e+00

Pos logit contributions
leaf+0.159
 sorts+0.153
aling+0.148
weet+0.140
icated+0.138
Neg logit contributions
 Majesty-0.127
pit-0.126
 bedroom-0.124
atively-0.120
 majesty-0.119
Token,
Token ID11
Feature activation-7.82e+00

Pos logit contributions
pit+0.119
angers+0.117
 Majesty+0.109
 bedroom+0.107
ider+0.104
Neg logit contributions
leaf-0.136
 sorts-0.134
-0.126
 course-0.120
igator-0.119
Token "
Token ID366
Feature activation+1.44e+00

Pos logit contributions
angers+0.090
 Majesty+0.088
pit+0.085
 bedroom+0.076
ider+0.074
Neg logit contributions
 sorts-0.374
leaf-0.367
igator-0.338
aling-0.337
 course-0.330
TokenYou
Token ID1639
Feature activation+3.44e+00

Pos logit contributions
 sorts+0.043
leaf+0.043
igator+0.042
aling+0.041
igators+0.040
Neg logit contributions
pit-0.030
 Majesty-0.029
omm-0.027
abies-0.026
-0.026
Token are
Token ID389
Feature activation-2.19e+00

Pos logit contributions
leaf+0.118
 sorts+0.115
aling+0.108
ion+0.103
weet+0.102
Neg logit contributions
 Majesty-0.084
 majesty-0.077
pit-0.074
 bedroom-0.072
 servant-0.070
Token a
Token ID257
Feature activation-1.23e+00

Pos logit contributions
 Majesty+0.062
 bedroom+0.059
pit+0.059
 majesty+0.057
 cabinet+0.056
Neg logit contributions
leaf-0.067
 sorts-0.061
aling-0.058
ited-0.055
weet-0.055
Token good
Token ID922
Feature activation+1.15e+00

Pos logit contributions
 Majesty+0.030
 majesty+0.027
 bedroom+0.026
 servant+0.026
pit+0.025
Neg logit contributions
leaf-0.044
 sorts-0.043
aling-0.041
weet-0.040
icated-0.039
Token to
Token ID284
Feature activation-8.04e-01

Pos logit contributions
angers+0.002
 Majesty+0.002
pit+0.002
 bedroom+0.002
 principal+0.002
Neg logit contributions
 sorts-0.003
leaf-0.003
aling-0.003
igator-0.002
-0.002
Token always
Token ID1464
Feature activation-7.13e-01

Pos logit contributions
 Majesty+0.020
 bedroom+0.019
pit+0.019
 majesty+0.019
angers+0.018
Neg logit contributions
leaf-0.027
 sorts-0.027
aling-0.024
icated-0.024
igator-0.023
Token be
Token ID307
Feature activation-5.93e-01

Pos logit contributions
 Majesty+0.018
pit+0.018
angers+0.018
 bedroom+0.017
ider+0.016
Neg logit contributions
leaf-0.024
 sorts-0.024
aling-0.021
igator-0.021
-0.020
Token on
Token ID319
Feature activation+1.47e+00

Pos logit contributions
 Majesty+0.016
pit+0.016
angers+0.016
 bedroom+0.015
 majesty+0.015
Neg logit contributions
leaf-0.019
 sorts-0.018
aling-0.016
igator-0.016
icated-0.016
Token the
Token ID262
Feature activation-1.76e+00

Pos logit contributions
leaf+0.049
 sorts+0.046
igator+0.044
aling+0.042
icated+0.040
Neg logit contributions
 Majesty-0.041
 bedroom-0.037
angers-0.036
 majesty-0.035
pit-0.034
Token lookout
Token ID40497
Feature activation-7.81e+00

Pos logit contributions
 Majesty+0.047
pit+0.044
 bedroom+0.044
angers+0.042
 majesty+0.041
Neg logit contributions
leaf-0.060
 sorts-0.060
aling-0.053
igator-0.052
icated-0.050
Token for
Token ID329
Feature activation+1.42e+00

Pos logit contributions
 Majesty+0.209
angers+0.208
pit+0.207
 bedroom+0.202
ider+0.192
Neg logit contributions
leaf-0.249
 sorts-0.243
aling-0.217
weet-0.211
igator-0.211
Token any
Token ID597
Feature activation-1.98e+00

Pos logit contributions
leaf+0.042
 sorts+0.042
aling+0.038
igator+0.037
+0.035
Neg logit contributions
 Majesty-0.042
 bedroom-0.040
angers-0.040
pit-0.039
 majesty-0.038
Token dangers
Token ID16169
Feature activation-2.11e-01

Pos logit contributions
 bedroom+0.045
 Majesty+0.044
pit+0.042
 bathroom+0.041
 bedrooms+0.041
Neg logit contributions
leaf-0.069
 sorts-0.066
aling-0.064
igator-0.060
icated-0.060
Token in
Token ID287
Feature activation-6.57e-01

Pos logit contributions
angers+0.005
pit+0.005
ider+0.005
tub+0.005
 cabinet+0.005
Neg logit contributions
 sorts-0.007
leaf-0.007
Ta-0.006
icated-0.006
aling-0.005
Token their
Token ID511
Feature activation-3.83e+00

Pos logit contributions
 bedroom+0.021
 Majesty+0.021
pit+0.021
angers+0.021
 bathroom+0.020
Neg logit contributions
leaf-0.018
 sorts-0.016
aling-0.014
icated-0.014
weet-0.013
Token She
Token ID1375
Feature activation-7.30e-01

Pos logit contributions
pit+0.047
 Majesty+0.046
angers+0.046
ider+0.044
 majesty+0.042
Neg logit contributions
 sorts-0.039
-0.038
leaf-0.038
weet-0.034
aling-0.033
Token wanted
Token ID2227
Feature activation+1.26e+00

Pos logit contributions
 Majesty+0.020
pit+0.020
angers+0.020
 bedroom+0.019
ider+0.019
Neg logit contributions
 sorts-0.022
leaf-0.022
aling-0.019
igator-0.019
weet-0.019
Token to
Token ID284
Feature activation-1.26e+00

Pos logit contributions
 sorts+0.042
leaf+0.042
aling+0.037
+0.036
igator+0.036
Neg logit contributions
angers-0.032
pit-0.032
 Majesty-0.032
 bedroom-0.030
ider-0.029
Token say
Token ID910
Feature activation-2.59e+00

Pos logit contributions
pit+0.038
angers+0.038
 Majesty+0.037
 bedroom+0.035
ider+0.035
Neg logit contributions
 sorts-0.037
leaf-0.037
aling-0.032
-0.032
igator-0.031
Token sorry
Token ID7926
Feature activation-2.89e+00

Pos logit contributions
pit+0.073
angers+0.071
 bedroom+0.063
ider+0.062
 bedrooms+0.060
Neg logit contributions
leaf-0.083
-0.080
 course-0.080
 sorts-0.078
 thanks-0.077
Token,
Token ID11
Feature activation-7.81e+00

Pos logit contributions
angers+0.109
pit+0.108
 Majesty+0.106
ider+0.104
 bedroom+0.099
Neg logit contributions
 sorts-0.058
-0.057
 thanks-0.055
weet-0.052
leaf-0.052
Token but
Token ID475
Feature activation+1.41e+00

Pos logit contributions
pit+0.146
angers+0.144
 Majesty+0.144
 bedroom+0.135
ider+0.131
Neg logit contributions
 sorts-0.320
leaf-0.316
aling-0.282
igator-0.278
able-0.270
Token she
Token ID673
Feature activation-1.21e+00

Pos logit contributions
leaf+0.053
 sorts+0.052
aling+0.047
weet+0.045
igator+0.044
Neg logit contributions
pit-0.031
 bedroom-0.030
 Majesty-0.029
angers-0.029
 bathroom-0.028
Token could
Token ID714
Feature activation-1.69e+00

Pos logit contributions
pit+0.031
 Majesty+0.030
angers+0.029
 bedroom+0.028
ider+0.028
Neg logit contributions
 sorts-0.041
leaf-0.041
aling-0.036
weet-0.036
igator-0.035
Token not
Token ID407
Feature activation+6.81e-02

Pos logit contributions
angers+0.039
pit+0.039
 Majesty+0.037
 bedroom+0.033
ider+0.033
Neg logit contributions
leaf-0.061
 sorts-0.061
-0.058
aling-0.056
igator-0.055
Token.
Token ID13
Feature activation-1.16e+00

Pos logit contributions
 sorts+0.002
leaf+0.002
+0.002
aling+0.002
igator+0.002
Neg logit contributions
angers-0.002
pit-0.002
 Majesty-0.002
 bedroom-0.002
ider-0.002
Token And
Token ID843
Feature activation+1.89e+00

Pos logit contributions
angers+0.005
pit+0.005
 Majesty+0.005
 bedroom+0.005
ider+0.004
Neg logit contributions
leaf-0.007
 sorts-0.007
aling-0.006
igator-0.006
 course-0.006
Token just
Token ID655
Feature activation+1.67e+00

Pos logit contributions
leaf+0.060
 sorts+0.058
aling+0.052
igator+0.052
weet+0.050
Neg logit contributions
pit-0.052
angers-0.052
 Majesty-0.051
 bedroom-0.050
ider-0.047
Token like
Token ID588
Feature activation+2.03e-02

Pos logit contributions
leaf+0.043
 sorts+0.041
aling+0.035
igator+0.034
 course+0.034
Neg logit contributions
 Majesty-0.056
pit-0.055
 bedroom-0.053
angers-0.053
 majesty-0.051
Token he
Token ID339
Feature activation-1.51e+00

Pos logit contributions
leaf+0.001
 sorts+0.001
aling+0.001
igator+0.001
+0.001
Neg logit contributions
 Majesty-0.001
angers-0.001
pit-0.001
 bedroom-0.001
 principal-0.000
Token promised
Token ID8072
Feature activation+3.01e-01

Pos logit contributions
pit+0.036
 Majesty+0.036
 bedroom+0.034
angers+0.032
 principal+0.032
Neg logit contributions
leaf-0.053
 sorts-0.050
igator-0.046
weet-0.045
icated-0.043
Token,
Token ID11
Feature activation-7.81e+00

Pos logit contributions
 sorts+0.009
leaf+0.009
+0.008
 course+0.008
aling+0.008
Neg logit contributions
pit-0.009
 Majesty-0.009
angers-0.009
ider-0.008
 bedroom-0.008
Token he
Token ID339
Feature activation-2.21e+00

Pos logit contributions
angers+0.131
 Lee+0.127
 Majesty+0.126
 bedroom+0.125
 teacher+0.121
Neg logit contributions
leaf-0.322
 sorts-0.313
igator-0.295
able-0.281
aling-0.278
Token came
Token ID1625
Feature activation-3.54e+00

Pos logit contributions
 Majesty+0.040
pit+0.039
 bedroom+0.036
 majesty+0.034
angers+0.034
Neg logit contributions
leaf-0.088
 sorts-0.083
weet-0.080
icated-0.077
igator-0.076
Token to
Token ID284
Feature activation-1.37e+00

Pos logit contributions
pit+0.089
 Majesty+0.089
angers+0.088
 bedroom+0.084
ider+0.080
Neg logit contributions
leaf-0.120
 sorts-0.119
igator-0.104
aling-0.104
 course-0.104
Token life
Token ID1204
Feature activation+8.92e-01

Pos logit contributions
 Majesty+0.040
 bedroom+0.038
pit+0.038
angers+0.037
 majesty+0.037
Neg logit contributions
leaf-0.041
 sorts-0.040
aling-0.037
igator-0.036
-0.035
Token and
Token ID290
Feature activation+5.08e+00

Pos logit contributions
leaf+0.031
 sorts+0.030
aling+0.027
igator+0.026
weet+0.026
Neg logit contributions
pit-0.023
angers-0.022
 Majesty-0.022
 bedroom-0.021
ider-0.020
Token
Token ID220
Feature activation-2.95e+00

Pos logit contributions
pit+0.014
 Majesty+0.014
angers+0.014
 bedroom+0.014
omm+0.013
Neg logit contributions
leaf-0.019
 sorts-0.019
aling-0.017
igator-0.017
 course-0.016
Token
Token ID198
Feature activation-4.34e-01

Pos logit contributions
pit+0.093
 Majesty+0.092
angers+0.090
ider+0.087
 bedroom+0.086
Neg logit contributions
 sorts-0.080
leaf-0.079
-0.075
aling-0.070
weet-0.066
Token
Token ID198
Feature activation-8.45e-03

Pos logit contributions
angers+0.010
pit+0.010
 Majesty+0.010
 bedroom+0.010
 principal+0.009
Neg logit contributions
 sorts-0.015
leaf-0.015
igator-0.013
aling-0.013
weet-0.013
TokenJohn
Token ID7554
Feature activation-7.53e-01

Pos logit contributions
pit+0.000
orman+0.000
 bedroom+0.000
 principal+0.000
 Majesty+0.000
Neg logit contributions
 sorts-0.000
leaf-0.000
igator-0.000
icated-0.000
weet-0.000
Token promised
Token ID8072
Feature activation+3.18e-01

Pos logit contributions
 Majesty+0.018
pit+0.018
 bedroom+0.018
ail+0.017
 majesty+0.016
Neg logit contributions
leaf-0.027
 sorts-0.025
igator-0.023
icated-0.023
weet-0.023
Token,
Token ID11
Feature activation-7.80e+00

Pos logit contributions
leaf+0.009
 sorts+0.009
+0.008
aling+0.008
 course+0.008
Neg logit contributions
pit-0.010
angers-0.009
 Majesty-0.009
ider-0.009
 bedroom-0.009
Token and
Token ID290
Feature activation+4.72e+00

Pos logit contributions
 bedroom+0.163
 Lee+0.153
 parents+0.151
omm+0.151
 Majesty+0.150
Neg logit contributions
leaf-0.286
 sorts-0.281
igator-0.260
aling-0.254
colored-0.252
Token he
Token ID339
Feature activation-1.65e+00

Pos logit contributions
leaf+0.160
 sorts+0.152
aling+0.141
weet+0.140
icated+0.138
Neg logit contributions
 Majesty-0.115
pit-0.115
 bedroom-0.115
angers-0.109
 majesty-0.106
Token has
Token ID468
Feature activation+2.39e+00

Pos logit contributions
 Majesty+0.037
ail+0.036
 bedroom+0.036
 parents+0.035
pit+0.035
Neg logit contributions
leaf-0.059
weet-0.055
icated-0.055
 sorts-0.054
igator-0.052
Token kept
Token ID4030
Feature activation-1.04e+00

Pos logit contributions
leaf+0.072
igator+0.067
 sorts+0.065
aling+0.061
weet+0.058
Neg logit contributions
 bedroom-0.067
 Majesty-0.067
pit-0.065
 bathroom-0.064
box-0.061
Token his
Token ID465
Feature activation-4.73e+00

Pos logit contributions
 bedroom+0.027
 Majesty+0.026
angers+0.026
 bathroom+0.025
pit+0.023
Neg logit contributions
leaf-0.035
 sorts-0.034
igator-0.034
weet-0.031
icated-0.030
Token was
Token ID373
Feature activation-1.20e+00

Pos logit contributions
 Majesty+0.029
 majesty+0.027
pit+0.026
 bedroom+0.025
 cabinet+0.024
Neg logit contributions
leaf-0.040
 sorts-0.039
weet-0.038
icated-0.036
aling-0.036
Token so
Token ID523
Feature activation+6.45e-01

Pos logit contributions
 Majesty+0.034
pit+0.033
 bedroom+0.032
 majesty+0.031
angers+0.031
Neg logit contributions
leaf-0.037
 sorts-0.036
icated-0.031
 course-0.031
aling-0.031
Token happy
Token ID3772
Feature activation+7.40e-01

Pos logit contributions
leaf+0.021
 sorts+0.020
 course+0.018
aling+0.018
weet+0.017
Neg logit contributions
 Majesty-0.017
 majesty-0.016
pit-0.016
 bedroom-0.016
angers-0.016
Token and
Token ID290
Feature activation+4.53e+00

Pos logit contributions
leaf+0.023
 sorts+0.023
aling+0.020
igator+0.020
weet+0.019
Neg logit contributions
pit-0.021
angers-0.020
 Majesty-0.020
 bedroom-0.019
ider-0.019
Token said
Token ID531
Feature activation-3.88e+00

Pos logit contributions
leaf+0.135
 sorts+0.127
weet+0.119
ez+0.118
 course+0.118
Neg logit contributions
 Majesty-0.132
 majesty-0.125
 bedroom-0.117
pit-0.116
 parents-0.112
Token,
Token ID11
Feature activation-7.79e+00

Pos logit contributions
pit+0.105
angers+0.103
 Majesty+0.097
 bedroom+0.097
ider+0.092
Neg logit contributions
leaf-0.127
 sorts-0.124
-0.116
igator-0.112
 course-0.109
Token
Token ID6184
Feature activation+1.87e+00

Pos logit contributions
 Majesty+0.089
angers+0.084
pit+0.079
 bedroom+0.072
ider+0.069
Neg logit contributions
 sorts-0.378
leaf-0.368
igator-0.338
aling-0.337
able-0.335
Token
Token ID95
Feature activation+3.79e+00

Pos logit contributions
leaf+0.063
 sorts+0.061
aling+0.056
+0.056
 course+0.054
Neg logit contributions
pit-0.048
angers-0.047
 Majesty-0.046
 bedroom-0.045
 majesty-0.042
Token
Token ID26391
Feature activation-3.48e+00

Pos logit contributions
 sorts+0.120
leaf+0.117
igator+0.103
weet+0.103
icated+0.099
Neg logit contributions
 Majesty-0.103
pit-0.103
angers-0.103
ider-0.099
 bedroom-0.097
Token
Token ID129
Feature activation+3.94e+00

Pos logit contributions
pit+0.089
angers+0.089
 Majesty+0.087
 bedroom+0.083
ider+0.081
Neg logit contributions
 sorts-0.115
leaf-0.114
-0.103
aling-0.102
igator-0.098
Token
Token ID241
Feature activation-9.87e-01

Pos logit contributions
 sorts+0.140
leaf+0.137
igator+0.122
 course+0.119
+0.118
Neg logit contributions
 Majesty-0.096
angers-0.093
pit-0.090
ider-0.085
 bedroom-0.085
Token
Token ID198
Feature activation-1.62e-01

Pos logit contributions
pit+0.084
angers+0.084
 Majesty+0.083
 bedroom+0.078
ider+0.077
Neg logit contributions
 sorts-0.102
leaf-0.102
aling-0.090
-0.089
igator-0.088
Token
Token ID198
Feature activation+2.80e-01

Pos logit contributions
angers+0.003
 Majesty+0.003
 bedroom+0.003
pit+0.003
orman+0.003
Neg logit contributions
 sorts-0.006
leaf-0.006
igator-0.006
aling-0.005
icated-0.005
TokenG
Token ID38
Feature activation+1.03e+00

Pos logit contributions
leaf+0.009
 sorts+0.009
igator+0.009
icated+0.008
 thanks+0.008
Neg logit contributions
angers-0.006
 Majesty-0.006
orman-0.006
pit-0.006
eth-0.006
Tokenina
Token ID1437
Feature activation+8.60e-01

Pos logit contributions
 sorts+0.037
leaf+0.037
aling+0.033
+0.033
igator+0.032
Neg logit contributions
pit-0.023
angers-0.023
 Majesty-0.023
 bedroom-0.022
ider-0.021
Token promised
Token ID8072
Feature activation+2.87e-01

Pos logit contributions
 sorts+0.028
leaf+0.027
weet+0.024
icated+0.024
aling+0.024
Neg logit contributions
 Majesty-0.023
pit-0.022
 bedroom-0.021
angers-0.021
 majesty-0.021
Token,
Token ID11
Feature activation-7.79e+00

Pos logit contributions
leaf+0.009
 sorts+0.009
+0.008
aling+0.008
 course+0.008
Neg logit contributions
pit-0.008
angers-0.008
 Majesty-0.008
 bedroom-0.007
ider-0.007
Token and
Token ID290
Feature activation+4.81e+00

Pos logit contributions
 Majesty+0.180
 bedroom+0.175
angers+0.172
 Lee+0.171
 parents+0.170
Neg logit contributions
 sorts-0.266
leaf-0.264
igator-0.247
aling-0.230
ez-0.228
Token so
Token ID523
Feature activation+2.33e-01

Pos logit contributions
leaf+0.159
 sorts+0.151
igator+0.143
icated+0.141
aling+0.139
Neg logit contributions
 Majesty-0.121
angers-0.115
 bedroom-0.113
pit-0.111
 majesty-0.110
Token the
Token ID262
Feature activation+6.28e-02

Pos logit contributions
leaf+0.008
 sorts+0.008
aling+0.007
igator+0.007
weet+0.007
Neg logit contributions
 Majesty-0.006
angers-0.006
pit-0.006
 bedroom-0.005
 majesty-0.005
Token old
Token ID1468
Feature activation+2.36e+00

Pos logit contributions
leaf+0.002
 sorts+0.002
aling+0.002
ez+0.002
weet+0.002
Neg logit contributions
 Majesty-0.002
 bedroom-0.002
pit-0.002
 cabinet-0.001
 bathroom-0.001
Token man
Token ID582
Feature activation-1.53e-01

Pos logit contributions
leaf+0.099
 sorts+0.098
aling+0.093
weet+0.091
icated+0.091
Neg logit contributions
pit-0.040
 Majesty-0.039
 bedroom-0.036
angers-0.036
 cabinet-0.034
Token was
Token ID373
Feature activation-1.17e+00

Pos logit contributions
pit+0.015
 Majesty+0.015
angers+0.015
 bedroom+0.014
ider+0.014
Neg logit contributions
leaf-0.017
 sorts-0.017
aling-0.015
weet-0.015
igator-0.015
Token so
Token ID523
Feature activation+7.53e-01

Pos logit contributions
pit+0.035
 Majesty+0.035
angers+0.034
 bedroom+0.033
ider+0.032
Neg logit contributions
leaf-0.035
 sorts-0.034
aling-0.030
igator-0.029
-0.029
Token happy
Token ID3772
Feature activation+7.13e-01

Pos logit contributions
 sorts+0.021
leaf+0.021
aling+0.018
+0.018
igator+0.018
Neg logit contributions
pit-0.023
angers-0.023
 Majesty-0.023
 bedroom-0.022
ider-0.021
Token and
Token ID290
Feature activation+4.65e+00

Pos logit contributions
leaf+0.021
 sorts+0.021
aling+0.018
igator+0.018
+0.018
Neg logit contributions
pit-0.021
angers-0.021
 Majesty-0.021
 bedroom-0.020
ider-0.020
Token said
Token ID531
Feature activation-4.01e+00

Pos logit contributions
leaf+0.129
 sorts+0.123
aling+0.110
igator+0.107
 course+0.107
Neg logit contributions
 Majesty-0.146
pit-0.141
angers-0.139
 bedroom-0.138
 majesty-0.138
Token,
Token ID11
Feature activation-7.78e+00

Pos logit contributions
angers+0.101
pit+0.101
 bedroom+0.093
 Majesty+0.088
ider+0.086
Neg logit contributions
leaf-0.138
-0.135
 sorts-0.133
igator-0.127
 course-0.127
Token "
Token ID366
Feature activation+1.31e+00

Pos logit contributions
pit+0.115
angers+0.114
 Majesty+0.113
 bedroom+0.101
ider+0.097
Neg logit contributions
 sorts-0.342
leaf-0.342
aling-0.312
-0.310
igator-0.308
TokenThank
Token ID10449
Feature activation+2.37e-01

Pos logit contributions
 sorts+0.041
igator+0.041
igators+0.039
ion+0.038
leaf+0.038
Neg logit contributions
 Majesty-0.029
pit-0.029
 Lee-0.027
-0.027
ider-0.026
Token you
Token ID345
Feature activation+4.35e-01

Pos logit contributions
 sorts+0.008
leaf+0.007
aling+0.007
igator+0.007
weet+0.006
Neg logit contributions
ider-0.006
angers-0.006
 Majesty-0.006
 Lee-0.006
omm-0.006
Token,
Token ID11
Feature activation-6.99e+00

Pos logit contributions
 sorts+0.016
leaf+0.016
+0.015
aling+0.014
igator+0.014
Neg logit contributions
angers-0.010
pit-0.010
 Majesty-0.009
 bedroom-0.009
ider-0.009
Token Tim
Token ID5045
Feature activation-5.19e-01

Pos logit contributions
 teacher+0.132
 Lee+0.122
 mom+0.121
 sister+0.120
 Majesty+0.115
Neg logit contributions
leaf-0.310
 sorts-0.296
ited-0.280
sm-0.276
able-0.273
Token the
Token ID262
Feature activation-1.71e+00

Pos logit contributions
 Majesty+0.043
pit+0.040
 bedroom+0.040
angers+0.040
 majesty+0.039
Neg logit contributions
leaf-0.043
 sorts-0.043
aling-0.037
igator-0.036
-0.036
Token water
Token ID1660
Feature activation-8.65e-01

Pos logit contributions
angers+0.054
pit+0.050
ider+0.049
 Majesty+0.048
omm+0.047
Neg logit contributions
 sorts-0.047
leaf-0.047
 course-0.042
-0.041
igator-0.041
Token."
Token ID526
Feature activation+2.00e-01

Pos logit contributions
pit+0.023
 Majesty+0.021
angers+0.021
 bedroom+0.021
 bathroom+0.020
Neg logit contributions
leaf-0.030
 sorts-0.029
aling-0.025
weet-0.024
icated-0.024
Token Sam
Token ID3409
Feature activation-2.29e+00

Pos logit contributions
 sorts+0.005
leaf+0.005
+0.005
 course+0.004
aling+0.004
Neg logit contributions
pit-0.007
 Majesty-0.007
angers-0.007
ider-0.007
 majesty-0.006
Token whispered
Token ID25029
Feature activation-3.39e+00

Pos logit contributions
pit+0.071
angers+0.068
 Majesty+0.068
 bedroom+0.066
ider+0.064
Neg logit contributions
 sorts-0.065
leaf-0.064
aling-0.056
igator-0.053
weet-0.053
Token,
Token ID11
Feature activation-7.77e+00

Pos logit contributions
 Majesty+0.117
angers+0.114
 majesty+0.112
pit+0.111
 principal+0.107
Neg logit contributions
-0.082
leaf-0.072
igator-0.071
sm-0.070
 sorts-0.070
Token trying
Token ID2111
Feature activation-2.27e+00

Pos logit contributions
angers+0.222
pit+0.219
 Majesty+0.218
 bedroom+0.204
 majesty+0.199
Neg logit contributions
leaf-0.234
 sorts-0.232
-0.208
aling-0.207
igator-0.201
Token to
Token ID284
Feature activation-1.37e+00

Pos logit contributions
 Majesty+0.078
angers+0.078
pit+0.077
 majesty+0.071
ider+0.071
Neg logit contributions
 sorts-0.057
leaf-0.056
-0.053
sm-0.048
 thanks-0.048
Token be
Token ID307
Feature activation-8.01e-01

Pos logit contributions
 Majesty+0.034
pit+0.033
 bedroom+0.033
 bathroom+0.032
angers+0.031
Neg logit contributions
 sorts-0.047
leaf-0.046
aling-0.041
-0.040
weet-0.039
Token brave
Token ID14802
Feature activation+4.71e-01

Pos logit contributions
 Majesty+0.025
pit+0.025
angers+0.025
 bedroom+0.024
ider+0.024
Neg logit contributions
leaf-0.022
 sorts-0.022
aling-0.019
-0.018
igator-0.018
Token.
Token ID13
Feature activation-1.35e+00

Pos logit contributions
leaf+0.015
 sorts+0.015
aling+0.013
igator+0.013
weet+0.012
Neg logit contributions
pit-0.013
 Majesty-0.013
angers-0.013
 bedroom-0.012
ider-0.012
Tokenchie
Token ID3043
Feature activation+3.40e+00

Pos logit contributions
leaf+0.094
 sorts+0.094
 course+0.083
weet+0.081
igator+0.081
Neg logit contributions
angers-0.088
pit-0.088
 Majesty-0.086
ider-0.083
 principal-0.078
Tokenv
Token ID85
Feature activation+1.28e+00

Pos logit contributions
leaf+0.071
 helium+0.066
aling+0.062
 course+0.061
 sorts+0.059
Neg logit contributions
orman-0.100
atively-0.099
pit-0.098
 Majesty-0.093
 tone-0.093
Tokenously
Token ID3481
Feature activation-3.82e+00

Pos logit contributions
 sorts+0.039
leaf+0.036
igator+0.034
 course+0.034
+0.033
Neg logit contributions
 Majesty-0.038
angers-0.037
 bedroom-0.035
pit-0.034
ider-0.034
Token and
Token ID290
Feature activation+5.47e+00

Pos logit contributions
pit+0.104
angers+0.104
 Majesty+0.103
 bedroom+0.097
ider+0.095
Neg logit contributions
 sorts-0.120
leaf-0.120
aling-0.105
-0.104
igator-0.103
Token said
Token ID531
Feature activation-3.93e+00

Pos logit contributions
 sorts+0.149
leaf+0.149
aling+0.128
+0.126
igator+0.125
Neg logit contributions
pit-0.172
angers-0.172
 Majesty-0.171
 bedroom-0.163
ider-0.159
Token,
Token ID11
Feature activation-7.76e+00

Pos logit contributions
angers+0.120
pit+0.118
 bedroom+0.109
 bedrooms+0.105
 principal+0.102
Neg logit contributions
-0.119
leaf-0.113
 sorts-0.107
igator-0.105
 course-0.104
Token "
Token ID366
Feature activation+1.24e+00

Pos logit contributions
pit+0.144
angers+0.142
 Majesty+0.139
 bedroom+0.126
 majesty+0.121
Neg logit contributions
leaf-0.314
 sorts-0.309
-0.292
aling-0.282
igator-0.278
TokenWell
Token ID5779
Feature activation+3.43e+00

Pos logit contributions
 sorts+0.038
leaf+0.035
igator+0.035
 thanks+0.033
aling+0.032
Neg logit contributions
pit-0.031
ider-0.031
angers-0.029
 Majesty-0.029
orman-0.029
Token,
Token ID11
Feature activation-6.36e+00

Pos logit contributions
 sorts+0.144
leaf+0.143
aling+0.130
+0.130
igator+0.129
Neg logit contributions
angers-0.059
pit-0.059
 Majesty-0.058
 bedroom-0.053
ider-0.051
Token he
Token ID339
Feature activation-1.37e+00

Pos logit contributions
 Majesty+0.171
 bedroom+0.158
 majesty+0.156
 cabinet+0.152
pit+0.152
Neg logit contributions
leaf-0.213
 sorts-0.208
aling-0.191
ited-0.185
ez-0.184
Token thought
Token ID1807
Feature activation-1.85e+00

Pos logit contributions
 Majesty+0.036
 majesty+0.033
pit+0.032
 bedroom+0.030
 cabinet+0.029
Neg logit contributions
leaf-0.046
 sorts-0.044
weet-0.041
aling-0.039
colored-0.039
Token girl
Token ID2576
Feature activation-5.15e-01

Pos logit contributions
leaf+0.120
 sorts+0.115
aling+0.110
weet+0.104
+0.102
Neg logit contributions
pit-0.063
 Majesty-0.059
 bedroom-0.058
angers-0.056
 cabinet-0.055
Token smiled
Token ID13541
Feature activation-1.35e+00

Pos logit contributions
pit+0.015
 Majesty+0.015
angers+0.014
 bedroom+0.014
ider+0.014
Neg logit contributions
leaf-0.015
 sorts-0.015
aling-0.013
igator-0.013
weet-0.013
Token,
Token ID11
Feature activation-6.86e+00

Pos logit contributions
angers+0.048
 Majesty+0.047
pit+0.047
 majesty+0.045
ider+0.044
Neg logit contributions
 sorts-0.031
leaf-0.030
-0.028
 thanks-0.026
aling-0.025
Token and
Token ID290
Feature activation+5.13e+00

Pos logit contributions
 Majesty+0.161
 bedroom+0.157
pit+0.154
 majesty+0.144
 bathroom+0.144
Neg logit contributions
 sorts-0.243
leaf-0.240
igator-0.220
aling-0.215
icated-0.211
Token said
Token ID531
Feature activation-3.71e+00

Pos logit contributions
leaf+0.170
 sorts+0.168
aling+0.154
igator+0.152
icated+0.150
Neg logit contributions
 Majesty-0.126
pit-0.123
 bedroom-0.120
angers-0.119
 Lee-0.116
Token,
Token ID11
Feature activation-7.75e+00

Pos logit contributions
pit+0.096
angers+0.093
 bedroom+0.087
ider+0.082
 Majesty+0.082
Neg logit contributions
-0.127
leaf-0.124
 sorts-0.120
igator-0.112
 course-0.109
Token
Token ID6184
Feature activation+1.90e+00

Pos logit contributions
pit+0.144
angers+0.142
 Majesty+0.139
 bedroom+0.126
ider+0.124
Neg logit contributions
leaf-0.312
 sorts-0.309
-0.289
aling-0.280
weet-0.276
Token
Token ID95
Feature activation+4.04e+00

Pos logit contributions
leaf+0.062
 sorts+0.059
+0.055
aling+0.055
 course+0.053
Neg logit contributions
pit-0.051
angers-0.049
 Majesty-0.048
 bedroom-0.046
 principal-0.043
Token
Token ID26391
Feature activation-3.27e+00

Pos logit contributions
 sorts+0.124
leaf+0.123
aling+0.107
igator+0.107
+0.106
Neg logit contributions
angers-0.113
pit-0.113
 Majesty-0.113
 bedroom-0.107
ider-0.105
Token
Token ID129
Feature activation+4.20e+00

Pos logit contributions
pit+0.077
angers+0.075
 Majesty+0.073
ider+0.069
 bedroom+0.069
Neg logit contributions
 sorts-0.114
leaf-0.110
-0.108
aling-0.102
weet-0.098
Token
Token ID241
Feature activation-5.97e-01

Pos logit contributions
 sorts+0.146
leaf+0.145
igator+0.130
 course+0.126
+0.125
Neg logit contributions
 Majesty-0.102
angers-0.101
pit-0.097
 bedroom-0.092
ider-0.090
Token
Token ID198
Feature activation+2.04e-02

Pos logit contributions
angers+0.016
 Majesty+0.016
pit+0.016
 bedroom+0.016
 majesty+0.015
Neg logit contributions
 sorts-0.016
leaf-0.016
aling-0.014
igator-0.013
-0.013
TokenMary
Token ID24119
Feature activation-9.22e-01

Pos logit contributions
 sorts+0.001
leaf+0.001
aling+0.001
igator+0.001
vious+0.001
Neg logit contributions
pit-0.001
 bedroom-0.001
 Majesty-0.001
angers-0.000
aby-0.000
Token smiled
Token ID13541
Feature activation-1.58e+00

Pos logit contributions
 Majesty+0.027
pit+0.026
 bedroom+0.025
 majesty+0.025
 bathroom+0.024
Neg logit contributions
 sorts-0.028
leaf-0.028
weet-0.024
igator-0.024
aling-0.024
Token and
Token ID290
Feature activation+4.60e+00

Pos logit contributions
angers+0.059
pit+0.058
 Majesty+0.058
 bedroom+0.055
ider+0.054
Neg logit contributions
 sorts-0.035
leaf-0.034
-0.029
aling-0.028
igator-0.027
Token said
Token ID531
Feature activation-4.03e+00

Pos logit contributions
 sorts+0.136
leaf+0.132
aling+0.119
igator+0.117
weet+0.114
Neg logit contributions
 Majesty-0.134
pit-0.128
 majesty-0.127
angers-0.127
 bedroom-0.125
Token,
Token ID11
Feature activation-7.75e+00

Pos logit contributions
pit+0.105
angers+0.100
 bedroom+0.094
 Majesty+0.091
 principal+0.091
Neg logit contributions
leaf-0.135
-0.132
 sorts-0.128
 thanks-0.121
 course-0.120
Token "
Token ID366
Feature activation+1.63e+00

Pos logit contributions
pit+0.148
angers+0.144
 Majesty+0.139
 bedroom+0.128
ider+0.122
Neg logit contributions
leaf-0.308
 sorts-0.301
-0.287
aling-0.276
weet-0.275
TokenThat
Token ID2504
Feature activation+2.05e+00

Pos logit contributions
 sorts+0.044
aling+0.041
leaf+0.041
igator+0.040
vious+0.036
Neg logit contributions
ider-0.048
 Majesty-0.047
pit-0.046
 Lee-0.045
 majesty-0.044
Token's
Token ID338
Feature activation-1.10e+00

Pos logit contributions
leaf+0.073
aling+0.071
 sorts+0.070
igator+0.064
weet+0.063
Neg logit contributions
 bedroom-0.046
 Majesty-0.046
pit-0.045
 bathroom-0.043
 cabinet-0.041
Token good
Token ID922
Feature activation+2.35e+00

Pos logit contributions
 Majesty+0.030
pit+0.029
 bedroom+0.028
angers+0.028
 majesty+0.027
Neg logit contributions
leaf-0.036
 sorts-0.034
aling-0.031
igator-0.030
weet-0.029
Token,
Token ID11
Feature activation-6.26e+00

Pos logit contributions
 sorts+0.078
leaf+0.075
+0.068
igator+0.066
weet+0.065
Neg logit contributions
angers-0.064
pit-0.063
 Majesty-0.062
ider-0.058
 principal-0.057
TokenL
Token ID43
Feature activation+3.00e+00

Pos logit contributions
ider+0.001
angers+0.001
pit+0.001
 principal+0.001
 bathroom+0.001
Neg logit contributions
 sorts-0.001
leaf-0.001
igator-0.001
icated-0.001
 thanks-0.001
Tokenily
Token ID813
Feature activation-4.42e-01

Pos logit contributions
 sorts+0.105
leaf+0.104
aling+0.092
+0.091
igator+0.090
Neg logit contributions
pit-0.073
angers-0.073
 Majesty-0.072
 bedroom-0.067
ider-0.066
Token smiled
Token ID13541
Feature activation-1.70e+00

Pos logit contributions
pit+0.013
 Majesty+0.013
angers+0.012
 bedroom+0.012
 majesty+0.012
Neg logit contributions
leaf-0.014
 sorts-0.013
aling-0.012
weet-0.011
igator-0.011
Token and
Token ID290
Feature activation+4.72e+00

Pos logit contributions
angers+0.066
pit+0.064
 Majesty+0.064
 principal+0.061
 majesty+0.061
Neg logit contributions
 sorts-0.035
leaf-0.033
-0.031
 thanks-0.028
aling-0.027
Token said
Token ID531
Feature activation-3.97e+00

Pos logit contributions
 sorts+0.150
leaf+0.148
igator+0.136
aling+0.135
icated+0.135
Neg logit contributions
 Majesty-0.125
 majesty-0.115
pit-0.114
 bedroom-0.113
angers-0.111
Token,
Token ID11
Feature activation-7.75e+00

Pos logit contributions
pit+0.104
angers+0.097
 bedroom+0.091
 Majesty+0.087
 bedrooms+0.085
Neg logit contributions
leaf-0.136
-0.136
 sorts-0.128
 course-0.123
igator-0.120
Token
Token ID6184
Feature activation+1.85e+00

Pos logit contributions
pit+0.152
angers+0.147
 Majesty+0.144
 bedroom+0.133
ider+0.127
Neg logit contributions
leaf-0.305
 sorts-0.298
-0.286
aling-0.273
weet-0.269
Token
Token ID95
Feature activation+4.14e+00

Pos logit contributions
leaf+0.061
 sorts+0.059
aling+0.054
+0.054
 course+0.052
Neg logit contributions
pit-0.049
angers-0.047
 Majesty-0.047
 bedroom-0.045
 majesty-0.043
Token
Token ID26391
Feature activation-3.15e+00

Pos logit contributions
 sorts+0.128
leaf+0.125
igator+0.110
weet+0.109
aling+0.108
Neg logit contributions
angers-0.115
 Majesty-0.114
pit-0.114
ider-0.109
 bedroom-0.107
Token
Token ID129
Feature activation+4.22e+00

Pos logit contributions
pit+0.075
angers+0.074
 Majesty+0.072
 bedroom+0.069
ider+0.066
Neg logit contributions
 sorts-0.109
leaf-0.107
-0.102
aling-0.098
 course-0.095
Token
Token ID241
Feature activation-6.89e-01

Pos logit contributions
 sorts+0.155
leaf+0.151
igator+0.137
icated+0.133
 course+0.133
Neg logit contributions
 Majesty-0.095
angers-0.094
pit-0.089
ider-0.085
 bedroom-0.084
Token
Token ID198
Feature activation+1.02e+00

Pos logit contributions
 sorts+0.019
leaf+0.019
+0.017
aling+0.016
igator+0.016
Neg logit contributions
 Majesty-0.019
pit-0.019
angers-0.018
ider-0.017
 bedroom-0.017
TokenOne
Token ID3198
Feature activation+4.25e-01

Pos logit contributions
leaf+0.031
 sorts+0.031
aling+0.027
igator+0.026
weet+0.026
Neg logit contributions
pit-0.029
angers-0.029
 Majesty-0.028
ider-0.027
 bedroom-0.027
Token day
Token ID1110
Feature activation-5.28e-03

Pos logit contributions
leaf+0.012
 sorts+0.010
aling+0.010
 course+0.009
+0.009
Neg logit contributions
 bedroom-0.014
pit-0.013
angers-0.013
 bathroom-0.013
 teacher-0.013
Token,
Token ID11
Feature activation-4.29e+00

Pos logit contributions
 Majesty+0.000
angers+0.000
pit+0.000
 principal+0.000
 bedroom+0.000
Neg logit contributions
-0.000
leaf-0.000
 sorts-0.000
 course-0.000
sm-0.000
Token Sara
Token ID24799
Feature activation+9.78e-01

Pos logit contributions
 Majesty+0.128
angers+0.125
pit+0.125
 bedroom+0.116
ider+0.116
Neg logit contributions
 sorts-0.126
leaf-0.125
-0.110
igator-0.108
 course-0.105
Token and
Token ID290
Feature activation+7.60e+00

Pos logit contributions
leaf+0.030
 sorts+0.028
igator+0.025
 course+0.025
aling+0.025
Neg logit contributions
pit-0.029
angers-0.028
 Majesty-0.028
 bedroom-0.027
 principal-0.026
Token Ben
Token ID3932
Feature activation-4.26e-01

Pos logit contributions
 sorts+0.205
leaf+0.203
+0.187
weet+0.178
 course+0.178
Neg logit contributions
ider-0.236
angers-0.233
pit-0.232
 Majesty-0.229
 bedroom-0.213
Token decide
Token ID5409
Feature activation-1.48e+00

Pos logit contributions
pit+0.012
 Majesty+0.011
angers+0.011
 bedroom+0.011
 principal+0.011
Neg logit contributions
leaf-0.013
 sorts-0.013
aling-0.011
weet-0.011
 course-0.011
Token to
Token ID284
Feature activation-1.21e+00

Pos logit contributions
pit+0.043
 Majesty+0.043
angers+0.042
ider+0.039
 bedroom+0.039
Neg logit contributions
leaf-0.046
 sorts-0.045
-0.040
aling-0.038
weet-0.038
Token make
Token ID787
Feature activation-2.23e-01

Pos logit contributions
 Majesty+0.031
angers+0.031
 bedroom+0.031
pit+0.030
 bathroom+0.029
Neg logit contributions
leaf-0.039
 sorts-0.038
aling-0.034
sm-0.034
weet-0.034
Token a
Token ID257
Feature activation-1.15e+00

Pos logit contributions
pit+0.009
angers+0.008
 Majesty+0.008
ider+0.008
 majesty+0.008
Neg logit contributions
 sorts-0.005
leaf-0.004
-0.004
aling-0.004
 course-0.003
Token He
Token ID679
Feature activation-3.18e-01

Pos logit contributions
angers+0.000
pit+0.000
 Majesty+0.000
 bedroom+0.000
ider+0.000
Neg logit contributions
leaf-0.000
 sorts-0.000
aling-0.000
igator-0.000
 course-0.000
Token stepped
Token ID10764
Feature activation+2.19e+00

Pos logit contributions
pit+0.008
 Majesty+0.008
angers+0.008
 bedroom+0.008
ider+0.008
Neg logit contributions
leaf-0.010
 sorts-0.010
aling-0.009
weet-0.009
igator-0.009
Token on
Token ID319
Feature activation+1.91e+00

Pos logit contributions
leaf+0.060
 sorts+0.060
+0.052
aling+0.052
igator+0.050
Neg logit contributions
 Majesty-0.069
angers-0.068
pit-0.068
 majesty-0.064
 bedroom-0.064
Token the
Token ID262
Feature activation-9.95e-01

Pos logit contributions
leaf+0.050
 sorts+0.049
aling+0.043
weet+0.042
igator+0.041
Neg logit contributions
 bedroom-0.063
pit-0.062
angers-0.062
 Majesty-0.061
 cabinet-0.059
Token door
Token ID3420
Feature activation-2.48e+00

Pos logit contributions
pit+0.018
 bedroom+0.018
 Majesty+0.018
angers+0.017
 cabinet+0.016
Neg logit contributions
 sorts-0.041
leaf-0.040
aling-0.037
weet-0.036
-0.036
Token and
Token ID290
Feature activation+6.51e+00

Pos logit contributions
pit+0.079
angers+0.079
 Majesty+0.078
 bedroom+0.075
ider+0.073
Neg logit contributions
leaf-0.066
 sorts-0.066
aling-0.056
-0.055
igator-0.055
Token it
Token ID340
Feature activation-2.68e-01

Pos logit contributions
 sorts+0.197
leaf+0.197
aling+0.171
+0.169
igator+0.168
Neg logit contributions
pit-0.186
angers-0.185
 Majesty-0.184
 bedroom-0.175
ider-0.170
Token made
Token ID925
Feature activation-3.49e-01

Pos logit contributions
angers+0.008
 Majesty+0.008
pit+0.008
 bedroom+0.007
ider+0.007
Neg logit contributions
 sorts-0.008
leaf-0.008
-0.007
aling-0.007
igator-0.007
Token a
Token ID257
Feature activation-1.12e+00

Pos logit contributions
angers+0.011
 Majesty+0.011
pit+0.011
 bedroom+0.011
 bathroom+0.010
Neg logit contributions
leaf-0.010
 sorts-0.009
aling-0.008
igator-0.008
 course-0.008
Token loud
Token ID7812
Feature activation+2.64e+00

Pos logit contributions
angers+0.038
pit+0.037
 Majesty+0.036
ider+0.035
 bedroom+0.034
Neg logit contributions
 sorts-0.029
leaf-0.028
-0.025
aling-0.023
weet-0.023
Token sound
Token ID2128
Feature activation-8.49e-01

Pos logit contributions
leaf+0.089
 sorts+0.088
aling+0.078
igator+0.077
+0.076
Neg logit contributions
pit-0.066
 Majesty-0.066
angers-0.065
 bedroom-0.062
ider-0.060
Token had
Token ID550
Feature activation+1.84e+00

Pos logit contributions
leaf+0.109
 sorts+0.096
aling+0.094
colored+0.091
icated+0.089
Neg logit contributions
pit-0.080
 bedroom-0.079
 Majesty-0.076
ail-0.075
atively-0.073
Token a
Token ID257
Feature activation+6.12e-02

Pos logit contributions
leaf+0.052
igator+0.050
 sorts+0.049
aling+0.047
icated+0.043
Neg logit contributions
 Majesty-0.055
 bedroom-0.053
pit-0.052
 majesty-0.050
 bathroom-0.050
Token great
Token ID1049
Feature activation+1.79e+00

Pos logit contributions
leaf+0.002
 sorts+0.002
aling+0.002
igator+0.002
weet+0.002
Neg logit contributions
 Majesty-0.002
 bedroom-0.002
pit-0.002
 bathroom-0.002
 majesty-0.002
Token time
Token ID640
Feature activation-1.04e+00

Pos logit contributions
leaf+0.065
igator+0.059
aling+0.059
 sorts+0.057
weet+0.055
Neg logit contributions
 bedroom-0.044
 Majesty-0.042
pit-0.039
 bathroom-0.038
 majesty-0.038
Token,
Token ID11
Feature activation-5.45e+00

Pos logit contributions
angers+0.023
pit+0.023
 Majesty+0.022
 bedroom+0.022
ider+0.021
Neg logit contributions
leaf-0.038
 sorts-0.038
igator-0.036
aling-0.034
weet-0.032
Token and
Token ID290
Feature activation+6.20e+00

Pos logit contributions
 bedroom+0.129
pit+0.127
 Majesty+0.123
angers+0.116
 majesty+0.114
Neg logit contributions
leaf-0.189
igator-0.184
 sorts-0.169
aling-0.167
vious-0.165
Token Tom
Token ID4186
Feature activation-1.34e+00

Pos logit contributions
leaf+0.208
 sorts+0.195
aling+0.183
igator+0.181
icated+0.174
Neg logit contributions
pit-0.157
 Majesty-0.155
angers-0.150
 bedroom-0.147
 majesty-0.140
Token promised
Token ID8072
Feature activation+3.22e-01

Pos logit contributions
 Majesty+0.032
pit+0.031
 bedroom+0.030
 majesty+0.029
ail+0.028
Neg logit contributions
leaf-0.049
 sorts-0.046
igator-0.041
weet-0.040
aling-0.040
Token to
Token ID284
Feature activation-2.45e+00

Pos logit contributions
leaf+0.010
 sorts+0.009
+0.009
 course+0.008
aling+0.008
Neg logit contributions
pit-0.010
angers-0.009
 Majesty-0.009
 bedroom-0.009
ider-0.009
Token be
Token ID307
Feature activation-1.13e+00

Pos logit contributions
 Majesty+0.063
pit+0.060
 bedroom+0.059
 majesty+0.058
angers+0.056
Neg logit contributions
leaf-0.084
 sorts-0.082
igator-0.072
aling-0.072
able-0.070
Token a
Token ID257
Feature activation-1.76e+00

Pos logit contributions
 Majesty+0.033
pit+0.031
 bedroom+0.030
 majesty+0.030
angers+0.029
Neg logit contributions
leaf-0.035
 sorts-0.033
icated-0.031
weet-0.030
igator-0.029
Token She
Token ID1375
Feature activation+4.36e-01

Pos logit contributions
 sorts+0.053
leaf+0.048
+0.047
weet+0.046
aling+0.044
Neg logit contributions
 Majesty-0.051
pit-0.048
angers-0.048
 majesty-0.046
ider-0.045
Token loved
Token ID6151
Feature activation+1.84e+00

Pos logit contributions
 sorts+0.012
leaf+0.012
aling+0.010
igator+0.010
+0.010
Neg logit contributions
angers-0.014
pit-0.014
 Majesty-0.014
 bedroom-0.013
ider-0.013
Token to
Token ID284
Feature activation+1.31e-01

Pos logit contributions
 sorts+0.070
leaf+0.070
aling+0.069
+0.066
igator+0.066
Neg logit contributions
angers-0.035
 bedroom-0.034
 bathroom-0.032
 Majesty-0.032
pit-0.031
Token play
Token ID711
Feature activation+6.38e-01

Pos logit contributions
leaf+0.004
 sorts+0.004
aling+0.004
able+0.004
ez+0.004
Neg logit contributions
 bedroom-0.004
 Majesty-0.003
angers-0.003
pit-0.003
 bathroom-0.003
Token outside
Token ID2354
Feature activation-3.21e+00

Pos logit contributions
leaf+0.015
 sorts+0.015
 course+0.014
aling+0.013
+0.013
Neg logit contributions
 Majesty-0.022
pit-0.022
angers-0.021
 majesty-0.021
ider-0.020
Token and
Token ID290
Feature activation+6.03e+00

Pos logit contributions
pit+0.083
 bedroom+0.082
angers+0.080
 cabinet+0.076
ider+0.074
Neg logit contributions
leaf-0.114
 sorts-0.105
aling-0.097
weet-0.095
icated-0.093
Token run
Token ID1057
Feature activation+3.90e+00

Pos logit contributions
leaf+0.195
 sorts+0.189
aling+0.169
ez+0.163
igator+0.163
Neg logit contributions
pit-0.158
 bedroom-0.157
 Majesty-0.157
angers-0.151
 bathroom-0.145
Token around
Token ID1088
Feature activation-3.72e-01

Pos logit contributions
leaf+0.086
 sorts+0.085
aling+0.070
weet+0.069
+0.068
Neg logit contributions
angers-0.144
pit-0.142
 Majesty-0.139
 bedroom-0.137
ider-0.133
Token in
Token ID287
Feature activation-5.98e-01

Pos logit contributions
pit+0.012
 Majesty+0.012
angers+0.012
 bedroom+0.011
ider+0.011
Neg logit contributions
 sorts-0.010
leaf-0.010
-0.009
aling-0.009
igator-0.009
Token the
Token ID262
Feature activation-1.07e-01

Pos logit contributions
 bedroom+0.019
pit+0.018
 bathroom+0.018
 bedrooms+0.017
 cabinet+0.017
Neg logit contributions
leaf-0.018
 sorts-0.015
aling-0.015
igator-0.015
ez-0.014
Token grass
Token ID8701
Feature activation+2.15e-01

Pos logit contributions
pit+0.003
 bedroom+0.003
 bathroom+0.003
 Majesty+0.003
angers+0.003
Neg logit contributions
leaf-0.003
 sorts-0.003
aling-0.003
igator-0.003
icated-0.003
Token to
Token ID284
Feature activation+7.59e-01

Pos logit contributions
leaf+0.051
 sorts+0.051
aling+0.046
+0.045
igator+0.044
Neg logit contributions
pit-0.035
angers-0.035
 Majesty-0.034
 bedroom-0.033
ider-0.031
Token build
Token ID1382
Feature activation-5.75e-01

Pos logit contributions
 sorts+0.025
leaf+0.023
igator+0.022
aling+0.021
+0.021
Neg logit contributions
angers-0.021
 Majesty-0.021
pit-0.020
ider-0.019
omm-0.019
Token towers
Token ID18028
Feature activation-1.80e+00

Pos logit contributions
ider+0.015
 Majesty+0.015
angers+0.015
omm+0.014
 majesty+0.014
Neg logit contributions
 sorts-0.019
leaf-0.017
 course-0.016
-0.016
 thanks-0.016
Token and
Token ID290
Feature activation+6.51e+00

Pos logit contributions
 Majesty+0.073
angers+0.068
 majesty+0.068
 bedroom+0.066
ider+0.066
Neg logit contributions
 sorts-0.037
leaf-0.029
-0.028
aling-0.028
 course-0.027
Token houses
Token ID7777
Feature activation+9.01e-02

Pos logit contributions
 sorts+0.219
leaf+0.210
+0.192
aling+0.190
igator+0.189
Neg logit contributions
 Majesty-0.168
angers-0.168
pit-0.162
ider-0.158
omm-0.154
Token and
Token ID290
Feature activation+6.88e+00

Pos logit contributions
 sorts+0.002
leaf+0.002
 course+0.002
+0.002
igator+0.002
Neg logit contributions
 Majesty-0.003
 majesty-0.003
angers-0.003
omm-0.003
uffy-0.003
Token cars
Token ID5006
Feature activation+3.92e+00

Pos logit contributions
 sorts+0.216
leaf+0.209
+0.189
igator+0.186
aling+0.185
Neg logit contributions
angers-0.193
 Majesty-0.193
pit-0.188
ider-0.182
omm-0.180
Token.
Token ID13
Feature activation+6.30e-01

Pos logit contributions
 sorts+0.113
leaf+0.106
aling+0.097
igator+0.096
 course+0.095
Neg logit contributions
 Majesty-0.126
angers-0.118
pit-0.116
 majesty-0.116
 bedroom-0.114
Token They
Token ID1119
Feature activation+2.12e+00

Pos logit contributions
 sorts+0.015
+0.014
leaf+0.012
 course+0.011
ch+0.011
Neg logit contributions
 Majesty-0.023
 majesty-0.022
pit-0.021
angers-0.021
ider-0.021
Token had
Token ID550
Feature activation+2.69e+00

Pos logit contributions
 sorts+0.055
leaf+0.055
aling+0.046
+0.046
igator+0.045
Neg logit contributions
pit-0.070
angers-0.070
 Majesty-0.069
 bedroom-0.066
ider-0.065
Token many
Token ID867
Feature activation+3.43e+00

Pos logit contributions
leaf+0.074
 sorts+0.073
aling+0.064
igator+0.062
+0.062
Neg logit contributions
pit-0.085
angers-0.085
 Majesty-0.084
 bedroom-0.081
ider-0.078
Token,
Token ID11
Feature activation-3.96e+00

Pos logit contributions
+0.021
 sorts+0.019
 course+0.018
igator+0.017
sm+0.017
Neg logit contributions
 Majesty-0.021
angers-0.021
 principal-0.019
pit-0.019
 majesty-0.019
Token there
Token ID612
Feature activation-2.13e-01

Pos logit contributions
 Majesty+0.124
angers+0.124
pit+0.119
 majesty+0.114
 principal+0.114
Neg logit contributions
 sorts-0.110
leaf-0.105
-0.101
igator-0.097
aling-0.094
Token was
Token ID373
Feature activation+9.21e-01

Pos logit contributions
angers+0.007
 Majesty+0.007
ider+0.007
pit+0.007
 majesty+0.007
Neg logit contributions
 sorts-0.006
-0.005
leaf-0.005
 course-0.005
igator-0.005
Token a
Token ID257
Feature activation+6.59e-01

Pos logit contributions
leaf+0.032
 sorts+0.032
aling+0.031
igator+0.028
ited+0.027
Neg logit contributions
 bedroom-0.022
 bathroom-0.021
angers-0.019
pit-0.019
tub-0.018
Token little
Token ID1310
Feature activation+3.49e+00

Pos logit contributions
 sorts+0.022
leaf+0.021
aling+0.019
+0.019
igator+0.019
Neg logit contributions
angers-0.017
pit-0.017
 Majesty-0.017
 bedroom-0.016
ider-0.016
Token boy
Token ID2933
Feature activation+1.32e+00

Pos logit contributions
leaf+0.139
 sorts+0.135
aling+0.134
+0.121
ez+0.120
Neg logit contributions
pit-0.068
 bedroom-0.066
 cabinet-0.066
 Majesty-0.064
 bathroom-0.062
Token named
Token ID3706
Feature activation+4.98e+00

Pos logit contributions
leaf+0.040
 sorts+0.038
aling+0.034
igator+0.032
+0.032
Neg logit contributions
pit-0.037
 bedroom-0.037
angers-0.037
 Majesty-0.036
ider-0.035
Token Danny
Token ID15105
Feature activation+4.42e-01

Pos logit contributions
 sorts+0.101
leaf+0.098
+0.087
igator+0.086
aling+0.083
Neg logit contributions
angers-0.193
 Majesty-0.193
pit-0.192
ider-0.184
 majesty-0.179
Token.
Token ID13
Feature activation+1.76e+00

Pos logit contributions
leaf+0.015
 sorts+0.015
aling+0.013
+0.013
igator+0.013
Neg logit contributions
pit-0.011
angers-0.011
 Majesty-0.011
 bedroom-0.010
ider-0.010
Token Danny
Token ID15105
Feature activation+6.47e-01

Pos logit contributions
 sorts+0.054
leaf+0.050
+0.045
aling+0.045
 thanks+0.043
Neg logit contributions
 Majesty-0.053
angers-0.051
pit-0.049
ider-0.049
 majesty-0.048
Token wanted
Token ID2227
Feature activation+2.48e+00

Pos logit contributions
leaf+0.020
 sorts+0.020
aling+0.018
weet+0.017
igator+0.017
Neg logit contributions
 bedroom-0.017
pit-0.017
 Majesty-0.017
angers-0.017
ider-0.016
Token to
Token ID284
Feature activation+1.53e-01

Pos logit contributions
 sorts+0.069
leaf+0.069
aling+0.067
+0.065
igator+0.065
Neg logit contributions
angers-0.038
 bedroom-0.036
 Majesty-0.035
pit-0.034
 bathroom-0.034
Token paint
Token ID7521
Feature activation+2.49e+00

Pos logit contributions
leaf+0.005
 sorts+0.005
aling+0.004
igator+0.004
+0.004
Neg logit contributions
 Majesty-0.004
angers-0.004
 bedroom-0.004
pit-0.004
 bathroom-0.004
Token with
Token ID351
Feature activation+1.25e+00

Pos logit contributions
leaf+0.075
 sorts+0.073
aling+0.065
igator+0.064
+0.063
Neg logit contributions
angers-0.073
pit-0.073
 Majesty-0.070
 bedroom-0.068
 cabinet-0.065
Token her
Token ID607
Feature activation-3.63e+00

Pos logit contributions
leaf+0.045
 sorts+0.042
aling+0.041
igator+0.039
+0.038
Neg logit contributions
angers-0.030
 bedroom-0.029
pit-0.028
 Majesty-0.027
 cabinet-0.026
Token mom
Token ID1995
Feature activation+7.26e-02

Pos logit contributions
 Majesty+0.074
pit+0.074
angers+0.073
ider+0.068
 bedroom+0.064
Neg logit contributions
 sorts-0.140
leaf-0.138
-0.124
 course-0.122
igator-0.122
Token.
Token ID13
Feature activation+9.86e-01

Pos logit contributions
leaf+0.002
 sorts+0.002
aling+0.002
igator+0.001
weet+0.001
Neg logit contributions
pit-0.002
angers-0.002
 bedroom-0.002
 Majesty-0.002
 cabinet-0.002
Token They
Token ID1119
Feature activation+2.06e+00

Pos logit contributions
 sorts+0.022
+0.019
leaf+0.018
weet+0.017
 course+0.017
Neg logit contributions
 Majesty-0.038
ider-0.036
pit-0.035
 majesty-0.035
 principal-0.034
Token would
Token ID561
Feature activation+2.20e-01

Pos logit contributions
leaf+0.062
 sorts+0.060
aling+0.055
weet+0.051
igator+0.051
Neg logit contributions
angers-0.059
pit-0.058
 bedroom-0.056
 Majesty-0.056
 cabinet-0.053
Token use
Token ID779
Feature activation+2.48e+00

Pos logit contributions
leaf+0.008
 sorts+0.007
ez+0.007
aling+0.007
able+0.007
Neg logit contributions
 bedroom-0.005
pit-0.005
angers-0.005
 Majesty-0.005
 bathroom-0.005
Token all
Token ID477
Feature activation+3.40e+00

Pos logit contributions
leaf+0.082
aling+0.076
 sorts+0.075
igator+0.071
ez+0.068
Neg logit contributions
angers-0.066
 bedroom-0.066
pit-0.063
 bathroom-0.062
 cabinet-0.060
Token kinds
Token ID6982
Feature activation+3.88e+00

Pos logit contributions
leaf+0.099
aling+0.092
ez+0.087
Run+0.082
+0.081
Neg logit contributions
 bedroom-0.095
angers-0.092
pit-0.087
ail-0.086
 bathroom-0.085
Token there
Token ID612
Feature activation-3.09e-01

Pos logit contributions
 Majesty+0.125
angers+0.124
pit+0.119
 majesty+0.115
 principal+0.114
Neg logit contributions
 sorts-0.107
leaf-0.103
-0.099
igator-0.096
aling-0.092
Token was
Token ID373
Feature activation+8.58e-01

Pos logit contributions
angers+0.011
 Majesty+0.011
ider+0.011
pit+0.010
 majesty+0.010
Neg logit contributions
 sorts-0.008
-0.007
leaf-0.007
 course-0.007
igator-0.006
Token a
Token ID257
Feature activation+6.62e-01

Pos logit contributions
leaf+0.030
 sorts+0.030
aling+0.029
igator+0.027
ited+0.026
Neg logit contributions
 bedroom-0.020
 bathroom-0.018
angers-0.017
pit-0.017
tub-0.016
Token little
Token ID1310
Feature activation+3.66e+00

Pos logit contributions
 sorts+0.022
leaf+0.022
aling+0.019
+0.019
igator+0.019
Neg logit contributions
angers-0.017
pit-0.017
 Majesty-0.017
 bedroom-0.016
ider-0.016
Token girl
Token ID2576
Feature activation+7.34e-01

Pos logit contributions
leaf+0.148
 sorts+0.143
aling+0.143
+0.130
ez+0.129
Neg logit contributions
pit-0.068
 cabinet-0.067
 bedroom-0.066
 Majesty-0.064
 bathroom-0.063
Token named
Token ID3706
Feature activation+5.03e+00

Pos logit contributions
leaf+0.023
 sorts+0.022
aling+0.020
icated+0.019
igator+0.019
Neg logit contributions
 bedroom-0.021
pit-0.020
angers-0.020
 Majesty-0.020
 cabinet-0.019
Token Daisy
Token ID40355
Feature activation-1.30e+00

Pos logit contributions
 sorts+0.123
+0.116
leaf+0.116
weet+0.109
igator+0.105
Neg logit contributions
 Majesty-0.176
pit-0.173
angers-0.168
ider-0.160
 majesty-0.159
Token.
Token ID13
Feature activation+1.61e+00

Pos logit contributions
pit+0.028
 bedroom+0.027
 Majesty+0.027
angers+0.027
 cabinet+0.024
Neg logit contributions
leaf-0.049
 sorts-0.047
aling-0.044
igator-0.042
 course-0.042
Token Daisy
Token ID40355
Feature activation-1.24e+00

Pos logit contributions
 sorts+0.049
leaf+0.046
+0.043
igator+0.041
 course+0.040
Neg logit contributions
angers-0.048
 Majesty-0.048
pit-0.047
ider-0.044
 principal-0.044
Token was
Token ID373
Feature activation-1.41e-01

Pos logit contributions
 bedroom+0.033
pit+0.031
 Majesty+0.031
angers+0.031
 cabinet+0.030
Neg logit contributions
leaf-0.041
 sorts-0.038
aling-0.036
weet-0.034
igator-0.033
Token only
Token ID691
Feature activation+2.87e+00

Pos logit contributions
angers+0.004
pit+0.004
 Majesty+0.004
 bedroom+0.004
ider+0.004
Neg logit contributions
leaf-0.004
 sorts-0.004
aling-0.003
-0.003
igator-0.003
Token She
Token ID1375
Feature activation+4.20e-01

Pos logit contributions
leaf+0.050
 sorts+0.049
aling+0.044
+0.043
igator+0.043
Neg logit contributions
pit-0.033
angers-0.032
 Majesty-0.032
 bedroom-0.030
ider-0.029
Token likes
Token ID7832
Feature activation+1.27e+00

Pos logit contributions
leaf+0.014
 sorts+0.013
weet+0.012
icated+0.011
aling+0.011
Neg logit contributions
pit-0.011
angers-0.011
 bedroom-0.011
 Majesty-0.011
 bathroom-0.011
Token to
Token ID284
Feature activation+2.26e-01

Pos logit contributions
leaf+0.048
 sorts+0.047
aling+0.045
+0.044
igator+0.042
Neg logit contributions
angers-0.027
pit-0.026
 bedroom-0.025
 Majesty-0.024
 bathroom-0.024
Token look
Token ID804
Feature activation-2.55e+00

Pos logit contributions
 sorts+0.007
leaf+0.007
aling+0.006
+0.006
igator+0.006
Neg logit contributions
pit-0.006
angers-0.006
 Majesty-0.006
 bedroom-0.006
ider-0.006
Token for
Token ID329
Feature activation+2.46e+00

Pos logit contributions
pit+0.082
 Majesty+0.081
angers+0.081
ider+0.077
 bedroom+0.076
Neg logit contributions
 sorts-0.068
leaf-0.068
aling-0.058
-0.057
igator-0.057
Token bugs
Token ID11316
Feature activation+1.87e+00

Pos logit contributions
leaf+0.074
 sorts+0.074
aling+0.066
+0.064
igator+0.064
Neg logit contributions
pit-0.070
angers-0.070
 Majesty-0.069
 bedroom-0.066
 majesty-0.063
Token and
Token ID290
Feature activation+6.86e+00

Pos logit contributions
leaf+0.060
 sorts+0.059
aling+0.052
+0.049
igator+0.049
Neg logit contributions
pit-0.052
angers-0.051
 Majesty-0.048
 bedroom-0.047
ider-0.046
Token flowers
Token ID12734
Feature activation+1.62e+00

Pos logit contributions
leaf+0.200
 sorts+0.198
aling+0.175
+0.169
igator+0.168
Neg logit contributions
pit-0.204
 Majesty-0.202
angers-0.201
 bedroom-0.193
 majesty-0.186
Token.
Token ID13
Feature activation+6.20e-01

Pos logit contributions
leaf+0.060
 sorts+0.059
aling+0.054
icated+0.052
weet+0.051
Neg logit contributions
pit-0.037
angers-0.036
 bedroom-0.033
 Majesty-0.033
ider-0.032
Token One
Token ID1881
Feature activation+2.49e-01

Pos logit contributions
 sorts+0.018
leaf+0.016
+0.016
 course+0.015
aling+0.015
Neg logit contributions
 Majesty-0.020
angers-0.019
ider-0.019
pit-0.018
 majesty-0.018
Token day
Token ID1110
Feature activation+1.33e-01

Pos logit contributions
leaf+0.007
aling+0.006
 sorts+0.006
ez+0.006
 course+0.006
Neg logit contributions
pit-0.008
 bedroom-0.008
 cabinet-0.007
angers-0.007
 bathroom-0.007
Token started
Token ID2067
Feature activation-3.44e+00

Pos logit contributions
pit+0.028
angers+0.028
 Majesty+0.027
 bedroom+0.026
ider+0.025
Neg logit contributions
leaf-0.031
 sorts-0.030
weet-0.027
icated-0.026
igator-0.026
Token using
Token ID1262
Feature activation+1.75e+00

Pos logit contributions
 Majesty+0.097
pit+0.096
angers+0.094
ider+0.091
 majesty+0.089
Neg logit contributions
 sorts-0.109
leaf-0.105
-0.094
aling-0.094
weet-0.089
Token zero
Token ID6632
Feature activation+1.55e+00

Pos logit contributions
leaf+0.047
 sorts+0.046
aling+0.041
igator+0.040
+0.039
Neg logit contributions
pit-0.055
angers-0.055
 Majesty-0.055
 bedroom-0.053
ider-0.050
Token in
Token ID287
Feature activation+1.11e-01

Pos logit contributions
 sorts+0.046
leaf+0.045
aling+0.039
+0.039
igator+0.039
Neg logit contributions
pit-0.045
angers-0.045
 Majesty-0.045
 bedroom-0.043
ider-0.042
Token all
Token ID477
Feature activation+3.22e+00

Pos logit contributions
leaf+0.003
 sorts+0.003
aling+0.003
+0.003
igator+0.003
Neg logit contributions
pit-0.003
angers-0.003
 Majesty-0.003
 bedroom-0.003
ider-0.003
Token kinds
Token ID6982
Feature activation+3.98e+00

Pos logit contributions
leaf+0.077
aling+0.063
icated+0.060
ch+0.058
 sorts+0.057
Neg logit contributions
pit-0.115
 bedroom-0.109
 cabinet-0.105
angers-0.105
 Majesty-0.101
Token of
Token ID286
Feature activation+2.26e+00

Pos logit contributions
leaf+0.058
 sorts+0.056
aling+0.043
igator+0.041
+0.040
Neg logit contributions
angers-0.176
pit-0.176
 Majesty-0.172
ider-0.168
 bedroom-0.167
Token ways
Token ID2842
Feature activation-2.09e+00

Pos logit contributions
 sorts+0.066
leaf+0.065
aling+0.056
+0.056
igator+0.055
Neg logit contributions
angers-0.068
pit-0.068
 Majesty-0.067
 bedroom-0.063
ider-0.063
Token.
Token ID13
Feature activation+3.69e-01

Pos logit contributions
pit+0.052
angers+0.052
 Majesty+0.051
 bedroom+0.049
ider+0.048
Neg logit contributions
leaf-0.070
 sorts-0.070
aling-0.062
igator-0.061
-0.060
Token She
Token ID1375
Feature activation-1.66e-01

Pos logit contributions
 sorts+0.012
leaf+0.012
+0.011
aling+0.011
igator+0.011
Neg logit contributions
pit-0.010
angers-0.010
 Majesty-0.009
 bedroom-0.009
ider-0.009
Token used
Token ID973
Feature activation+6.72e-01

Pos logit contributions
pit+0.005
angers+0.005
 Majesty+0.005
 bedroom+0.005
ider+0.004
Neg logit contributions
leaf-0.005
 sorts-0.005
weet-0.004
igator-0.004
aling-0.004
Token.
Token ID13
Feature activation+6.02e-01

Pos logit contributions
 sorts+0.054
leaf+0.054
aling+0.047
+0.047
igator+0.046
Neg logit contributions
pit-0.045
angers-0.045
 Majesty-0.044
 bedroom-0.042
ider-0.041
Token She
Token ID1375
Feature activation+7.60e-02

Pos logit contributions
 sorts+0.017
leaf+0.015
+0.015
 course+0.014
igator+0.013
Neg logit contributions
 Majesty-0.020
angers-0.020
pit-0.019
ider-0.018
 majesty-0.018
Token was
Token ID373
Feature activation-3.93e-01

Pos logit contributions
 sorts+0.002
leaf+0.002
+0.002
aling+0.002
igator+0.002
Neg logit contributions
angers-0.002
pit-0.002
 Majesty-0.002
ider-0.002
 majesty-0.002
Token walking
Token ID6155
Feature activation+2.02e+00

Pos logit contributions
pit+0.010
angers+0.010
 Majesty+0.010
 bedroom+0.009
ider+0.009
Neg logit contributions
 sorts-0.013
leaf-0.013
aling-0.012
-0.011
igator-0.011
Token through
Token ID832
Feature activation-6.86e-01

Pos logit contributions
leaf+0.055
 sorts+0.054
aling+0.047
+0.047
weet+0.046
Neg logit contributions
pit-0.064
angers-0.064
 Majesty-0.062
 bedroom-0.061
ider-0.059
Token the
Token ID262
Feature activation+8.51e-02

Pos logit contributions
 bedroom+0.023
pit+0.023
angers+0.022
 Majesty+0.022
 bathroom+0.022
Neg logit contributions
leaf-0.018
 sorts-0.016
aling-0.015
igator-0.015
-0.013
Token woods
Token ID16479
Feature activation-2.31e+00

Pos logit contributions
 sorts+0.003
leaf+0.003
aling+0.002
+0.002
igator+0.002
Neg logit contributions
angers-0.002
pit-0.002
 Majesty-0.002
ider-0.002
 bedroom-0.002
Token and
Token ID290
Feature activation+6.88e+00

Pos logit contributions
 Majesty+0.073
angers+0.070
pit+0.068
 majesty+0.068
omm+0.067
Neg logit contributions
 sorts-0.068
leaf-0.061
aling-0.056
 course-0.056
-0.056
Token suddenly
Token ID6451
Feature activation-7.78e-01

Pos logit contributions
 sorts+0.188
leaf+0.175
+0.170
aling+0.163
 course+0.161
Neg logit contributions
angers-0.218
 Majesty-0.214
omm-0.206
pit-0.206
 majesty-0.205
Token she
Token ID673
Feature activation-3.53e-01

Pos logit contributions
pit+0.023
angers+0.022
 Majesty+0.022
ider+0.022
omm+0.021
Neg logit contributions
 sorts-0.022
-0.022
weet-0.020
leaf-0.020
ch-0.019
Token saw
Token ID2497
Feature activation-2.73e+00

Pos logit contributions
angers+0.012
 Majesty+0.012
pit+0.011
omm+0.011
 majesty+0.011
Neg logit contributions
-0.008
 sorts-0.008
aling-0.007
ch-0.007
ez-0.007
Token but
Token ID475
Feature activation+1.79e+00

Pos logit contributions
pit+0.142
 bedroom+0.130
 bathroom+0.127
 Majesty+0.125
atively+0.123
Neg logit contributions
leaf-0.243
 sorts-0.241
icated-0.214
able-0.209
aling-0.202
Token the
Token ID262
Feature activation+4.45e-01

Pos logit contributions
leaf+0.053
 sorts+0.051
weet+0.044
aling+0.043
icated+0.042
Neg logit contributions
pit-0.053
 Majesty-0.052
 bedroom-0.051
angers-0.050
atively-0.049
Token boy
Token ID2933
Feature activation+5.47e-01

Pos logit contributions
 sorts+0.015
leaf+0.015
aling+0.014
weet+0.013
+0.013
Neg logit contributions
pit-0.012
 Majesty-0.011
 bedroom-0.011
angers-0.011
ider-0.011
Token kept
Token ID4030
Feature activation-8.06e-01

Pos logit contributions
leaf+0.019
 sorts+0.019
weet+0.017
aling+0.016
icated+0.016
Neg logit contributions
pit-0.013
 Majesty-0.013
 bedroom-0.012
angers-0.012
ider-0.012
Token chasing
Token ID20023
Feature activation+1.19e+00

Pos logit contributions
pit+0.017
 bedroom+0.017
 Majesty+0.016
 bathroom+0.016
angers+0.016
Neg logit contributions
leaf-0.030
 sorts-0.029
igator-0.027
icated-0.026
weet-0.026
Token after
Token ID706
Feature activation-2.72e+00

Pos logit contributions
 sorts+0.039
leaf+0.039
weet+0.032
aling+0.032
igator+0.032
Neg logit contributions
 Majesty-0.028
pit-0.028
angers-0.028
 Lee-0.027
atively-0.027
Token it
Token ID340
Feature activation-2.79e+00

Pos logit contributions
angers+0.082
 Majesty+0.082
pit+0.081
 bedroom+0.078
atively+0.076
Neg logit contributions
 sorts-0.077
leaf-0.076
aling-0.064
igator-0.062
-0.061
Token.
Token ID13
Feature activation-4.81e-01

Pos logit contributions
pit+0.067
angers+0.065
 Majesty+0.064
 bedroom+0.061
ider+0.060
Neg logit contributions
leaf-0.100
 sorts-0.097
aling-0.086
igator-0.084
weet-0.084
Token
Token ID198
Feature activation-1.92e-01

Pos logit contributions
angers+0.013
pit+0.013
 Majesty+0.013
 bedroom+0.012
ider+0.012
Neg logit contributions
leaf-0.015
 sorts-0.015
aling-0.013
igator-0.013
-0.013
Token
Token ID198
Feature activation+2.31e-01

Pos logit contributions
pit+0.005
angers+0.005
 Majesty+0.005
 bedroom+0.005
ider+0.005
Neg logit contributions
 sorts-0.006
leaf-0.006
-0.005
aling-0.005
igator-0.005
TokenHe
Token ID1544
Feature activation-1.40e+00

Pos logit contributions
 sorts+0.008
leaf+0.007
igator+0.006
weet+0.006
 thanks+0.006
Neg logit contributions
 Majesty-0.006
pit-0.006
ider-0.006
angers-0.006
orman-0.006
Tokenara
Token ID3301
Feature activation+4.54e-01

Pos logit contributions
 sorts+0.107
leaf+0.106
aling+0.095
+0.095
igator+0.094
Neg logit contributions
pit-0.055
angers-0.054
 Majesty-0.053
 bedroom-0.049
ider-0.049
Token was
Token ID373
Feature activation-8.71e-01

Pos logit contributions
 sorts+0.014
leaf+0.014
aling+0.012
+0.012
igator+0.012
Neg logit contributions
pit-0.013
angers-0.013
 Majesty-0.012
 bedroom-0.012
ider-0.012
Token sad
Token ID6507
Feature activation+1.36e+00

Pos logit contributions
pit+0.021
angers+0.021
 Majesty+0.021
 bedroom+0.019
ider+0.019
Neg logit contributions
 sorts-0.031
leaf-0.030
aling-0.027
-0.027
igator-0.027
Token and
Token ID290
Feature activation+5.61e+00

Pos logit contributions
 sorts+0.024
+0.024
 thanks+0.022
leaf+0.022
 of+0.021
Neg logit contributions
 Majesty-0.059
pit-0.055
angers-0.054
 majesty-0.054
omm-0.050
Token angry
Token ID7954
Feature activation+1.17e+00

Pos logit contributions
 sorts+0.194
leaf+0.189
 course+0.163
aling+0.162
weet+0.161
Neg logit contributions
 Majesty-0.133
pit-0.133
 bedroom-0.132
angers-0.131
ider-0.128
Token again
Token ID757
Feature activation-1.23e+00

Pos logit contributions
 sorts+0.029
leaf+0.028
+0.027
 thanks+0.025
aling+0.025
Neg logit contributions
 Majesty-0.040
angers-0.039
pit-0.038
 majesty-0.037
 bedroom-0.037
Token.
Token ID13
Feature activation-3.91e-01

Pos logit contributions
angers+0.039
 Majesty+0.039
pit+0.038
 majesty+0.035
omm+0.035
Neg logit contributions
 sorts-0.034
leaf-0.032
-0.031
aling-0.028
 thanks-0.028
Token She
Token ID1375
Feature activation-4.40e-01

Pos logit contributions
pit+0.013
angers+0.012
 Majesty+0.012
ider+0.012
ail+0.012
Neg logit contributions
-0.010
 sorts-0.010
leaf-0.009
 thanks-0.009
weet-0.008
Token did
Token ID750
Feature activation-2.05e+00

Pos logit contributions
pit+0.011
 Majesty+0.011
angers+0.011
 bedroom+0.011
ider+0.010
Neg logit contributions
 sorts-0.015
leaf-0.015
aling-0.013
weet-0.013
igator-0.013
Token not
Token ID407
Feature activation+2.52e-01

Pos logit contributions
pit+0.027
 Majesty+0.026
angers+0.026
 bedroom+0.024
ider+0.023
Neg logit contributions
 sorts-0.094
leaf-0.094
aling-0.085
igator-0.085
-0.084
Token want
Token ID765
Feature activation+2.99e+00

Pos logit contributions
leaf+0.007
 sorts+0.007
 course+0.006
colored+0.006
ion+0.006
Neg logit contributions
 Majesty-0.007
pit-0.007
 principal-0.007
 bedroom-0.007
 teacher-0.007
Token mom
Token ID1995
Feature activation-1.24e+00

Pos logit contributions
angers+0.078
pit+0.078
 Majesty+0.075
ider+0.067
 bedroom+0.062
Neg logit contributions
 sorts-0.240
leaf-0.237
-0.220
igator-0.213
aling-0.213
Token to
Token ID284
Feature activation-9.82e-01

Pos logit contributions
pit+0.032
angers+0.031
 bedroom+0.030
 Majesty+0.030
 cabinet+0.028
Neg logit contributions
leaf-0.042
 sorts-0.039
aling-0.037
 course-0.035
ez-0.035
Token help
Token ID1037
Feature activation-2.75e+00

Pos logit contributions
 bedroom+0.024
 Majesty+0.023
 bathroom+0.023
angers+0.023
pit+0.023
Neg logit contributions
 sorts-0.033
leaf-0.033
aling-0.030
able-0.029
ez-0.029
Token her
Token ID607
Feature activation-5.66e+00

Pos logit contributions
pit+0.085
 Majesty+0.085
angers+0.083
ider+0.079
 majesty+0.078
Neg logit contributions
 sorts-0.079
leaf-0.078
-0.069
aling-0.066
igator-0.066
Token find
Token ID1064
Feature activation-2.93e+00

Pos logit contributions
angers+0.181
 Majesty+0.180
pit+0.179
ider+0.173
 majesty+0.167
Neg logit contributions
 sorts-0.153
-0.144
leaf-0.140
aling-0.124
igator-0.122
Token a
Token ID257
Feature activation-1.82e+00

Pos logit contributions
 bedroom+0.096
angers+0.096
 Majesty+0.094
pit+0.091
 bathroom+0.091
Neg logit contributions
leaf-0.077
 sorts-0.072
aling-0.069
igator-0.065
weet-0.064
Token v
Token ID410
Feature activation+4.47e+00

Pos logit contributions
angers+0.058
pit+0.057
 Majesty+0.056
ider+0.053
 bedroom+0.052
Neg logit contributions
 sorts-0.050
leaf-0.049
-0.043
 course-0.041
igator-0.041
Tokenase
Token ID589
Feature activation+5.14e-01

Pos logit contributions
 sorts+0.148
leaf+0.147
aling+0.129
igator+0.128
+0.128
Neg logit contributions
 Majesty-0.115
pit-0.114
angers-0.113
 bedroom-0.107
 majesty-0.103
Token.
Token ID13
Feature activation+5.22e-03

Pos logit contributions
leaf+0.018
 sorts+0.017
aling+0.015
+0.015
igator+0.015
Neg logit contributions
pit-0.013
angers-0.013
 Majesty-0.012
 bedroom-0.012
ider-0.012
Token They
Token ID1119
Feature activation+1.35e+00

Pos logit contributions
 sorts+0.000
leaf+0.000
+0.000
aling+0.000
 course+0.000
Neg logit contributions
 Majesty-0.000
pit-0.000
angers-0.000
ider-0.000
 majesty-0.000
Token found
Token ID1043
Feature activation-2.58e+00

Pos logit contributions
leaf+0.041
 sorts+0.040
aling+0.037
weet+0.036
icated+0.035
Neg logit contributions
pit-0.038
angers-0.038
 bedroom-0.037
 Majesty-0.036
 cabinet-0.034
Token wanted
Token ID2227
Feature activation+1.35e+00

Pos logit contributions
ider+0.027
pit+0.027
 Majesty+0.027
angers+0.026
 bedroom+0.026
Neg logit contributions
 sorts-0.048
leaf-0.046
weet-0.045
icated-0.043
aling-0.041
Token to
Token ID284
Feature activation-1.01e+00

Pos logit contributions
 sorts+0.045
leaf+0.045
aling+0.040
+0.039
igator+0.039
Neg logit contributions
angers-0.034
pit-0.034
 Majesty-0.034
 bedroom-0.032
ider-0.031
Token rescue
Token ID9992
Feature activation-2.60e+00

Pos logit contributions
 Majesty+0.027
pit+0.026
angers+0.025
 majesty+0.025
 bedroom+0.025
Neg logit contributions
 sorts-0.032
leaf-0.032
aling-0.028
weet-0.027
icated-0.027
Token Anna
Token ID11735
Feature activation-3.01e+00

Pos logit contributions
angers+0.078
pit+0.077
 Majesty+0.077
 bedroom+0.074
 principal+0.072
Neg logit contributions
leaf-0.075
 sorts-0.074
aling-0.064
-0.062
igator-0.062
Token's
Token ID338
Feature activation-3.62e+00

Pos logit contributions
pit+0.075
angers+0.073
 Majesty+0.072
 bedroom+0.069
ider+0.067
Neg logit contributions
leaf-0.106
 sorts-0.103
aling-0.090
weet-0.088
 course-0.088
Token car
Token ID1097
Feature activation+1.97e-02

Pos logit contributions
angers+0.084
pit+0.083
 Majesty+0.083
 bedroom+0.076
ider+0.075
Neg logit contributions
 sorts-0.129
leaf-0.128
aling-0.114
-0.114
igator-0.113
Token.
Token ID13
Feature activation-1.49e-01

Pos logit contributions
leaf+0.001
 sorts+0.001
aling+0.001
weet+0.001
+0.001
Neg logit contributions
pit-0.000
angers-0.000
 Majesty-0.000
ider-0.000
 bedroom-0.000
Token He
Token ID679
Feature activation-6.80e-01

Pos logit contributions
pit+0.005
angers+0.005
 Majesty+0.005
ail+0.005
ider+0.005
Neg logit contributions
 sorts-0.003
-0.003
leaf-0.003
 thanks-0.003
aling-0.003
Token followed
Token ID3940
Feature activation-1.03e+00

Pos logit contributions
pit+0.017
 Majesty+0.017
angers+0.016
 bedroom+0.016
ider+0.016
Neg logit contributions
 sorts-0.023
leaf-0.022
weet-0.021
icated-0.020
aling-0.019
Token the
Token ID262
Feature activation-2.04e+00

Pos logit contributions
pit+0.029
angers+0.028
 Majesty+0.028
ider+0.026
 bedroom+0.026
Neg logit contributions
leaf-0.032
 sorts-0.032
-0.029
aling-0.028
igator-0.028
Token dog
Token ID3290
Feature activation+1.34e+00

Pos logit contributions
pit+0.051
angers+0.051
 Majesty+0.051
 bedroom+0.048
ider+0.047
Neg logit contributions
 sorts-0.069
leaf-0.069
aling-0.061
-0.061
igator-0.060
Token.
Token ID13
Feature activation-1.50e+00

Pos logit contributions
pit+0.145
 Majesty+0.144
angers+0.140
 majesty+0.131
 bedroom+0.130
Neg logit contributions
leaf-0.107
-0.101
 sorts-0.097
sm-0.091
 course-0.090
Token
Token ID198
Feature activation-5.91e-01

Pos logit contributions
 Majesty+0.051
pit+0.050
angers+0.049
ider+0.046
 majesty+0.046
Neg logit contributions
 sorts-0.038
leaf-0.037
-0.036
weet-0.032
 course-0.032
Token
Token ID198
Feature activation-9.61e-02

Pos logit contributions
pit+0.018
angers+0.017
 Majesty+0.017
ider+0.016
 bedroom+0.016
Neg logit contributions
 sorts-0.018
leaf-0.017
-0.016
aling-0.015
 course-0.015
Token"
Token ID1
Feature activation+9.26e-01

Pos logit contributions
pit+0.002
angers+0.002
 Majesty+0.002
 bedroom+0.002
ider+0.002
Neg logit contributions
leaf-0.003
 sorts-0.003
aling-0.003
igator-0.003
weet-0.003
TokenOK
Token ID11380
Feature activation+7.08e-01

Pos logit contributions
 sorts+0.029
leaf+0.027
aling+0.025
igator+0.024
weet+0.024
Neg logit contributions
pit-0.026
ider-0.026
angers-0.025
 Majesty-0.025
 bedroom-0.024
Token,
Token ID11
Feature activation-6.96e+00

Pos logit contributions
+0.023
 thanks+0.020
 sorts+0.020
 course+0.019
leaf+0.019
Neg logit contributions
angers-0.022
pit-0.020
 Majesty-0.019
 principal-0.018
ider-0.018
Token Mom
Token ID11254
Feature activation-6.38e-01

Pos logit contributions
 Majesty+0.117
pit+0.116
 bedroom+0.111
angers+0.104
 majesty+0.103
Neg logit contributions
leaf-0.299
 sorts-0.298
aling-0.275
igator-0.262
ez-0.261
Token.
Token ID13
Feature activation-7.62e-01

Pos logit contributions
angers+0.017
pit+0.016
 Majesty+0.016
 bedroom+0.015
ider+0.015
Neg logit contributions
 sorts-0.021
leaf-0.021
-0.019
aling-0.018
igator-0.018
Token We
Token ID775
Feature activation+4.68e+00

Pos logit contributions
angers+0.026
pit+0.026
 Majesty+0.025
 bedroom+0.024
ider+0.024
Neg logit contributions
 sorts-0.019
leaf-0.019
-0.016
aling-0.016
igator-0.016
Token will
Token ID481
Feature activation-1.15e+00

Pos logit contributions
leaf+0.149
 sorts+0.146
aling+0.131
weet+0.131
icated+0.128
Neg logit contributions
 Majesty-0.123
pit-0.121
 bedroom-0.119
angers-0.117
 majesty-0.113
Token close
Token ID1969
Feature activation-1.35e+00

Pos logit contributions
angers+0.039
pit+0.038
ider+0.035
 Majesty+0.034
 principal+0.033
Neg logit contributions
-0.030
 sorts-0.030
leaf-0.029
 thanks-0.026
 course-0.025
Token."
Token ID526
Feature activation+4.68e-01

Pos logit contributions
pit+0.034
angers+0.033
 Majesty+0.033
 bedroom+0.032
ider+0.031
Neg logit contributions
leaf-0.036
 sorts-0.035
aling-0.031
-0.030
 course-0.030
Token
Token ID198
Feature activation-3.43e-01

Pos logit contributions
+0.007
 sorts+0.007
 course+0.005
leaf+0.005
 thanks+0.005
Neg logit contributions
ider-0.021
 Majesty-0.021
pit-0.021
angers-0.020
 majesty-0.020
Token
Token ID198
Feature activation+1.90e-01

Pos logit contributions
pit+0.013
 Majesty+0.013
ider+0.012
angers+0.012
 majesty+0.012
Neg logit contributions
 sorts-0.008
leaf-0.008
-0.007
weet-0.006
 course-0.006
TokenHer
Token ID9360
Feature activation-4.06e+00

Pos logit contributions
+0.006
 sorts+0.006
leaf+0.006
aling+0.006
weet+0.005
Neg logit contributions
pit-0.005
angers-0.005
 Majesty-0.005
 majesty-0.005
ider-0.005
Token brother
Token ID3956
Feature activation+1.19e+00

Pos logit contributions
pit+0.101
angers+0.098
 Majesty+0.098
ider+0.093
atively+0.089
Neg logit contributions
 sorts-0.141
-0.133
leaf-0.129
 thanks-0.127
 orange-0.124
Token replied
Token ID8712
Feature activation-4.00e+00

Pos logit contributions
 sorts+0.031
leaf+0.030
+0.029
 course+0.027
aling+0.026
Neg logit contributions
angers-0.040
 Majesty-0.039
pit-0.038
 majesty-0.036
ider-0.036
Token,
Token ID11
Feature activation-6.31e+00

Pos logit contributions
pit+0.120
 Majesty+0.119
angers+0.117
 majesty+0.111
 bedroom+0.108
Neg logit contributions
-0.120
sm-0.107
leaf-0.106
 sorts-0.105
 course-0.102
Token "
Token ID366
Feature activation+2.29e+00

Pos logit contributions
angers+0.153
pit+0.149
 Majesty+0.149
 majesty+0.137
 bedroom+0.135
Neg logit contributions
leaf-0.214
-0.206
 sorts-0.204
 course-0.196
igator-0.193
TokenBut
Token ID1537
Feature activation-1.35e+00

Pos logit contributions
leaf+0.068
 sorts+0.068
 thanks+0.064
igator+0.061
aling+0.059
Neg logit contributions
angers-0.058
ider-0.058
pit-0.055
orman-0.055
abies-0.052
Token I
Token ID314
Feature activation+4.84e+00

Pos logit contributions
angers+0.045
pit+0.044
 Majesty+0.043
ider+0.041
 bedroom+0.041
Neg logit contributions
 sorts-0.034
leaf-0.034
-0.031
 course-0.030
igator-0.029
Token promise
Token ID6991
Feature activation+1.28e+00

Pos logit contributions
leaf+0.140
 sorts+0.138
aling+0.120
igator+0.120
weet+0.118
Neg logit contributions
 Majesty-0.142
angers-0.142
pit-0.142
 bedroom-0.137
ider-0.133
Token blue
Token ID4171
Feature activation+3.49e+00

Pos logit contributions
leaf+0.003
 sorts+0.002
aling+0.002
weet+0.002
igator+0.002
Neg logit contributions
 bedroom-0.002
pit-0.002
 Majesty-0.002
 bathroom-0.002
 cabinet-0.002
Token t
Token ID256
Feature activation+2.27e+00

Pos logit contributions
leaf+0.115
 sorts+0.113
aling+0.103
+0.098
weet+0.097
Neg logit contributions
pit-0.094
angers-0.092
 Majesty-0.091
 bedroom-0.090
ider-0.085
Tokeneddy
Token ID21874
Feature activation+3.42e+00

Pos logit contributions
leaf+0.060
 sorts+0.060
aling+0.052
+0.051
 course+0.049
Neg logit contributions
angers-0.075
pit-0.074
 Majesty-0.072
 bedroom-0.070
ider-0.070
Token bear
Token ID6842
Feature activation+3.77e-01

Pos logit contributions
leaf+0.139
 sorts+0.130
aling+0.124
weet+0.116
+0.115
Neg logit contributions
pit-0.069
 bedroom-0.067
 Majesty-0.065
uffy-0.062
 cabinet-0.061
Token closed
Token ID4838
Feature activation-6.15e-01

Pos logit contributions
leaf+0.012
 sorts+0.011
aling+0.010
igator+0.010
icated+0.010
Neg logit contributions
pit-0.010
 Majesty-0.010
angers-0.010
 bedroom-0.010
 majesty-0.009
Token their
Token ID511
Feature activation-4.80e+00

Pos logit contributions
pit+0.018
angers+0.018
 Majesty+0.018
 bedroom+0.018
ider+0.017
Neg logit contributions
leaf-0.018
 sorts-0.018
aling-0.016
-0.015
igator-0.015
Token eyes
Token ID2951
Feature activation-6.84e-01

Pos logit contributions
angers+0.082
pit+0.079
 Majesty+0.074
ider+0.072
 principal+0.065
Neg logit contributions
 sorts-0.201
leaf-0.196
-0.185
 thanks-0.182
 course-0.178
Token and
Token ID290
Feature activation+6.04e+00

Pos logit contributions
pit+0.017
angers+0.017
 Majesty+0.017
 bedroom+0.017
ider+0.016
Neg logit contributions
leaf-0.023
 sorts-0.023
aling-0.020
igator-0.020
 course-0.019
Token went
Token ID1816
Feature activation+9.07e-01

Pos logit contributions
leaf+0.193
 sorts+0.179
aling+0.169
igator+0.165
weet+0.157
Neg logit contributions
 bedroom-0.170
 Majesty-0.162
pit-0.156
 majesty-0.155
 bathroom-0.152
Token to
Token ID284
Feature activation-2.11e+00

Pos logit contributions
 sorts+0.025
leaf+0.025
aling+0.023
+0.022
ch+0.021
Neg logit contributions
pit-0.028
 Majesty-0.028
angers-0.026
omm-0.026
ider-0.026
Token sleep
Token ID3993
Feature activation-9.38e-01

Pos logit contributions
 Majesty+0.055
angers+0.054
pit+0.054
 bedroom+0.052
 majesty+0.049
Neg logit contributions
leaf-0.070
 sorts-0.069
aling-0.061
igator-0.061
-0.060
Token the
Token ID262
Feature activation+9.29e-01

Pos logit contributions
pit+0.043
 Majesty+0.043
angers+0.043
 bedroom+0.041
ider+0.040
Neg logit contributions
leaf-0.028
 sorts-0.028
aling-0.023
igator-0.022
weet-0.022
Token monster
Token ID9234
Feature activation+2.13e-01

Pos logit contributions
 sorts+0.037
leaf+0.036
aling+0.034
weet+0.032
+0.032
Neg logit contributions
pit-0.018
 Majesty-0.018
 bedroom-0.018
 principal-0.017
 cabinet-0.017
Token refused
Token ID6520
Feature activation+1.50e-01

Pos logit contributions
leaf+0.007
 sorts+0.007
aling+0.006
weet+0.006
icated+0.006
Neg logit contributions
pit-0.006
 Majesty-0.005
angers-0.005
ider-0.005
 bedroom-0.005
Token and
Token ID290
Feature activation+5.38e+00

Pos logit contributions
leaf+0.004
 sorts+0.004
+0.004
 course+0.004
igator+0.004
Neg logit contributions
angers-0.005
 Majesty-0.005
pit-0.005
ider-0.004
 bedroom-0.004
Token ran
Token ID4966
Feature activation+2.50e+00

Pos logit contributions
 sorts+0.169
leaf+0.169
weet+0.147
aling+0.146
icated+0.146
Neg logit contributions
pit-0.145
 Majesty-0.143
angers-0.137
atively-0.136
 bedroom-0.135
Token away
Token ID1497
Feature activation-6.18e+00

Pos logit contributions
leaf+0.066
 sorts+0.066
aling+0.057
+0.057
igator+0.056
Neg logit contributions
pit-0.081
 Majesty-0.081
angers-0.081
 bedroom-0.077
 majesty-0.075
Token with
Token ID351
Feature activation+1.25e-01

Pos logit contributions
 Majesty+0.200
angers+0.200
pit+0.197
 majesty+0.184
 bedroom+0.182
Neg logit contributions
 sorts-0.167
leaf-0.161
-0.151
igator-0.141
aling-0.137
Token the
Token ID262
Feature activation-9.78e-01

Pos logit contributions
leaf+0.004
 sorts+0.003
aling+0.003
weet+0.003
icated+0.003
Neg logit contributions
 bedroom-0.004
 Majesty-0.004
pit-0.004
atively-0.004
 cabinet-0.004
Token poem
Token ID21247
Feature activation+1.81e+00

Pos logit contributions
 bedroom+0.022
 teacher+0.022
 Majesty+0.021
 bathroom+0.021
 door+0.021
Neg logit contributions
aling-0.035
 sorts-0.035
leaf-0.033
igator-0.030
cream-0.030
Token.
Token ID13
Feature activation-9.69e-02

Pos logit contributions
leaf+0.060
 sorts+0.060
aling+0.053
+0.052
igator+0.052
Neg logit contributions
pit-0.046
angers-0.046
 Majesty-0.045
 bedroom-0.043
ider-0.042
Token Lucy
Token ID22162
Feature activation-6.61e-01

Pos logit contributions
pit+0.003
angers+0.003
 Majesty+0.003
 bedroom+0.003
ider+0.003
Neg logit contributions
 sorts-0.003
leaf-0.003
-0.002
aling-0.002
igator-0.002
Token.
Token ID13
Feature activation+1.08e-01

Pos logit contributions
 sorts+0.003
leaf+0.003
+0.003
aling+0.003
 course+0.002
Neg logit contributions
angers-0.004
pit-0.004
 Majesty-0.004
ider-0.004
 bedroom-0.004
Token
Token ID198
Feature activation+5.59e-01

Pos logit contributions
leaf+0.004
 sorts+0.004
aling+0.003
igator+0.003
 course+0.003
Neg logit contributions
pit-0.003
angers-0.003
 Majesty-0.003
 bedroom-0.002
ider-0.002
Token
Token ID198
Feature activation+8.71e-01

Pos logit contributions
leaf+0.021
 sorts+0.020
igator+0.018
aling+0.017
icated+0.017
Neg logit contributions
angers-0.012
 bedroom-0.012
pit-0.012
 Majesty-0.012
 bathroom-0.011
TokenBut
Token ID1537
Feature activation-5.78e-01

Pos logit contributions
leaf+0.030
 sorts+0.029
igator+0.025
 thanks+0.025
vious+0.024
Neg logit contributions
pit-0.021
 Majesty-0.020
angers-0.020
 bedroom-0.020
ider-0.020
Token soon
Token ID2582
Feature activation-1.01e+00

Pos logit contributions
pit+0.019
angers+0.019
 Majesty+0.019
 bedroom+0.018
ider+0.018
Neg logit contributions
leaf-0.015
 sorts-0.015
aling-0.013
-0.012
igator-0.012
Token,
Token ID11
Feature activation-5.47e+00

Pos logit contributions
angers+0.026
pit+0.025
ider+0.024
 Majesty+0.024
 bedroom+0.023
Neg logit contributions
 sorts-0.033
leaf-0.032
-0.031
 course-0.030
aling-0.029
Token the
Token ID262
Feature activation+7.06e-01

Pos logit contributions
pit+0.165
 Majesty+0.164
angers+0.162
 bedroom+0.156
 majesty+0.150
Neg logit contributions
leaf-0.159
 sorts-0.158
aling-0.138
igator-0.131
-0.130
Token little
Token ID1310
Feature activation+3.04e+00

Pos logit contributions
 sorts+0.025
leaf+0.024
aling+0.022
ez+0.020
weet+0.020
Neg logit contributions
 Majesty-0.018
pit-0.018
 bedroom-0.018
 bathroom-0.017
 cabinet-0.017
Token bird
Token ID6512
Feature activation+2.19e+00

Pos logit contributions
leaf+0.124
 sorts+0.117
aling+0.114
ez+0.104
weet+0.104
Neg logit contributions
pit-0.064
 Majesty-0.060
 bedroom-0.059
 cabinet-0.055
 bathroom-0.054
Token became
Token ID2627
Feature activation-3.89e+00

Pos logit contributions
leaf+0.075
 sorts+0.070
aling+0.060
icated+0.060
weet+0.059
Neg logit contributions
pit-0.058
 Majesty-0.056
angers-0.053
 bedroom-0.051
ider-0.050
Token greedy
Token ID31828
Feature activation+1.27e+00

Pos logit contributions
 Majesty+0.106
pit+0.104
angers+0.101
 bedroom+0.098
 bathroom+0.093
Neg logit contributions
leaf-0.127
 sorts-0.121
aling-0.107
icated-0.105
weet-0.105