TOP ACTIVATIONS
MAX = 13.398

cl apped her hands in amusement . The other boys had
they went to a big amusement park . Lily was so
took her to a famous amusement park . Lily was so
caul iflower and stopped qu arre ling . They said ,
says , " Stop qu arre ling , Tom and Lily
sharing is important and qu arre lling is not good .
They learn that qu arre ling is bad and sharing
on , they never qu arre led again and played together
They are tired from qu arre ling . They sit in
, why are you qu arre ling ?" But the birds
mum and understood that qu arre lling was not a good
? Why are you qu arre ling ?" The
he found a rabbit qu arre lling with a squirrel .
walking by saw them qu arre ling . She was very
Finally , after much qu arre ling , one of the
Lily and Jack never qu arre led again . They learned
friends didn 't stop qu arre ling and were getting louder
she was sorry for qu arre ling . From that day
told them to stop qu arre lling and to share the
Tom and Mia stop qu arre ling . They see the

MIN ACTIVATIONS
MIN = -14.629

friends . N emo tried to swim away ,
it . N emo 's friend , D ory
. N emo saw a big jet flying
He said , " N emo , you must keep swimming
first ." N emo asked , " What do
far ?" N emo replied , " I want
you ." N emo was grateful for Tim my
. N emo said , " Please give
dangerous ." N emo was sad because he wanted
. N emo 's friend , Sammy the
. N emo was so happy to be
anxious . N emo sw am away from the
. N emo sw am up to his
caught ! N emo was scared and didn 't
water . N emo 's friends warned him not
. N emo asked the dolphins for help
o . N emo sw am under the blanket
mouths !" N emo tried his best , but
. N emo 's mom saw him and
ocean ." N emo was curious and wanted to

INTERVAL 6.391 - 13.398
CONTAINS 0.612%

head and said , " That was a terrible joke !"
there was a big books he lf with many books .
makes mistakes !". This made Rob the happiest robot
When they reached the finish line , the teacher said ,
her face , dreaming about all the cards she would find

INTERVAL -0.615 - 6.391
CONTAINS 66.080%

't know , Lily . Maybe it is under the sofa
to Tim my 's house and got his homework . On
. Inside was a small , cute puppy . The puppy
of wood near the trees . They wanted to build a
L ily was disappointed but she remembered something her

INTERVAL -7.622 - -0.615
CONTAINS 33.076%

to get lost ." They held hands and walked
he had a great friend in Billy who would always be
. Sue was scared ! But then , the
liked to play outside and explore . One day , Tim
he reached his destination . He had a great visit ,

INTERVAL -14.629 - -7.622
CONTAINS 0.233%

day , their mom m ies and d add ies said
small as a pe b ble can be valuable and worth
to the edge of the Root tree . The rabbit wanted
me ?" Fl uffy was so happy . It
was a shy little tw ig . It wanted to be
Token cl
Token ID537
Feature activation+2.59e+00

Pos logit contributions
oph+0.424
cake+0.410
cakes+0.403
board+0.353
uct+0.349
Neg logit contributions
emo-0.460
cker-0.412
eer-0.403
 sailor-0.393
ba-0.393
Tokenapped
Token ID6320
Feature activation+8.71e-01

Pos logit contributions
cake+0.175
oph+0.174
cakes+0.174
board+0.151
 amusement+0.145
Neg logit contributions
emo-0.217
cker-0.182
eer-0.178
ba-0.175
 crew-0.172
Token her
Token ID607
Feature activation+1.04e+00

Pos logit contributions
cake+0.072
oph+0.072
cakes+0.071
board+0.064
uct+0.060
Neg logit contributions
emo-0.060
cker-0.049
 sailor-0.048
eer-0.048
 crew-0.047
Token hands
Token ID2832
Feature activation+6.84e-01

Pos logit contributions
oph+0.071
cake+0.071
cakes+0.070
board+0.062
 amusement+0.058
Neg logit contributions
emo-0.084
cker-0.073
eer-0.071
 sailor-0.069
rito-0.067
Token in
Token ID287
Feature activation-3.54e+00

Pos logit contributions
oph+0.064
cakes+0.060
cake+0.058
board+0.055
uct+0.054
Neg logit contributions
emo-0.036
cker-0.030
eer-0.030
 sailor-0.029
ba-0.028
Token amusement
Token ID30184
Feature activation+1.31e+01

Pos logit contributions
emo+0.247
 sailor+0.218
 crew+0.211
 sail+0.207
eer+0.205
Neg logit contributions
cakes-0.290
cake-0.281
oph-0.270
board-0.252
liv-0.228
Token.
Token ID13
Feature activation+1.57e-01

Pos logit contributions
cake+1.190
cakes+1.183
oph+1.156
uct+1.079
Those+1.051
Neg logit contributions
emo-0.624
eer-0.578
 sailor-0.566
fish-0.495
 crew-0.475
Token The
Token ID383
Feature activation-1.29e-01

Pos logit contributions
oph+0.012
cake+0.011
cakes+0.010
board+0.010
 amusement+0.009
Neg logit contributions
emo-0.012
cker-0.010
eer-0.010
 Albert-0.009
 crew-0.009
Token other
Token ID584
Feature activation+1.29e+00

Pos logit contributions
emo+0.008
 crew+0.008
 sailor+0.007
eer+0.007
 sailors+0.007
Neg logit contributions
oph-0.011
cake-0.010
uct-0.009
cakes-0.009
liv-0.009
Token boys
Token ID6510
Feature activation+4.84e+00

Pos logit contributions
oph+0.108
cake+0.104
uct+0.098
cakes+0.090
liv+0.088
Neg logit contributions
emo-0.080
 crew-0.075
eer-0.072
 sailors-0.069
cker-0.068
Token had
Token ID550
Feature activation+1.64e+00

Pos logit contributions
oph+0.319
cake+0.312
cakes+0.305
board+0.261
uct+0.250
Neg logit contributions
emo-0.389
cker-0.350
 sailor-0.344
eer-0.344
ba-0.337
Token they
Token ID484
Feature activation-6.81e-01

Pos logit contributions
emo+0.045
cker+0.040
eer+0.040
 sailor+0.038
rito+0.038
Neg logit contributions
cake-0.026
oph-0.026
cakes-0.025
board-0.022
 amusement-0.020
Token went
Token ID1816
Feature activation-1.32e-01

Pos logit contributions
emo+0.063
cker+0.056
rito+0.055
eer+0.055
fish+0.052
Neg logit contributions
oph-0.038
cake-0.036
cakes-0.035
board-0.032
 amusement-0.030
Token to
Token ID284
Feature activation+3.04e-01

Pos logit contributions
emo+0.012
cker+0.011
eer+0.011
rito+0.011
 sailor+0.010
Neg logit contributions
cakes-0.007
cake-0.007
oph-0.007
board-0.006
 amusement-0.006
Token a
Token ID257
Feature activation-2.18e-01

Pos logit contributions
oph+0.015
 amusement+0.014
cake+0.013
cakes+0.013
 Rebecca+0.012
Neg logit contributions
emo-0.030
cker-0.027
rito-0.027
eer-0.027
fish-0.026
Token big
Token ID1263
Feature activation+1.03e+00

Pos logit contributions
emo+0.017
cker+0.014
eer+0.014
rito+0.014
ba+0.013
Neg logit contributions
oph-0.016
cake-0.016
cakes-0.015
board-0.014
 amusement-0.014
Token amusement
Token ID30184
Feature activation+1.31e+01

Pos logit contributions
cake+0.075
oph+0.074
cakes+0.073
board+0.065
uct+0.063
Neg logit contributions
emo-0.078
cker-0.067
eer-0.066
 sailor-0.065
ba-0.062
Token park
Token ID3952
Feature activation+5.27e+00

Pos logit contributions
oph+0.864
ishly+0.852
uct+0.847
cake+0.841
cakes+0.835
Neg logit contributions
emo-0.977
 sailor-0.878
fish-0.834
eer-0.805
cker-0.779
Token.
Token ID13
Feature activation+1.10e-01

Pos logit contributions
oph+0.501
cake+0.464
cakes+0.449
uct+0.430
icious+0.415
Neg logit contributions
emo-0.286
cker-0.252
eer-0.233
 sailor-0.217
fish-0.214
Token Lily
Token ID20037
Feature activation+1.35e+00

Pos logit contributions
oph+0.007
cake+0.007
cakes+0.007
board+0.006
uct+0.006
Neg logit contributions
emo-0.009
eer-0.007
cker-0.007
 sailor-0.007
rito-0.007
Token was
Token ID373
Feature activation+6.32e-01

Pos logit contributions
oph+0.085
cake+0.083
cakes+0.081
board+0.074
 amusement+0.068
Neg logit contributions
emo-0.117
cker-0.102
eer-0.100
rito-0.098
 sailor-0.096
Token so
Token ID523
Feature activation+4.04e+00

Pos logit contributions
cake+0.040
oph+0.040
cakes+0.039
board+0.034
 amusement+0.032
Neg logit contributions
emo-0.054
cker-0.047
eer-0.046
 sailor-0.045
rito-0.045
Token took
Token ID1718
Feature activation+4.11e-01

Pos logit contributions
emo+0.135
cker+0.118
eer+0.115
 sailor+0.111
rito+0.111
Neg logit contributions
oph-0.103
cake-0.103
cakes-0.100
board-0.090
 amusement-0.083
Token her
Token ID607
Feature activation+1.01e+00

Pos logit contributions
cake+0.028
oph+0.028
cakes+0.027
board+0.024
uct+0.023
Neg logit contributions
emo-0.033
cker-0.029
eer-0.028
 sailor-0.027
ba-0.027
Token to
Token ID284
Feature activation+1.81e-01

Pos logit contributions
cake+0.069
oph+0.068
cakes+0.067
board+0.061
 amusement+0.057
Neg logit contributions
emo-0.081
cker-0.069
eer-0.067
rito-0.064
ba-0.064
Token a
Token ID257
Feature activation-4.23e-01

Pos logit contributions
cake+0.012
oph+0.012
cakes+0.011
board+0.010
uct+0.009
Neg logit contributions
emo-0.015
cker-0.013
eer-0.013
 sailor-0.013
rito-0.013
Token famous
Token ID5863
Feature activation-6.12e-01

Pos logit contributions
emo+0.032
cker+0.027
eer+0.027
ba+0.025
rito+0.025
Neg logit contributions
cake-0.032
oph-0.031
cakes-0.030
board-0.028
 amusement-0.027
Token amusement
Token ID30184
Feature activation+1.28e+01

Pos logit contributions
emo+0.046
cker+0.040
eer+0.039
 sailor+0.038
rito+0.037
Neg logit contributions
cake-0.044
oph-0.044
cakes-0.043
board-0.038
uct-0.037
Token park
Token ID3952
Feature activation+4.99e+00

Pos logit contributions
oph+0.812
cake+0.801
cakes+0.798
uct+0.757
Those+0.742
Neg logit contributions
emo-0.917
 sailor-0.866
eer-0.825
fish-0.818
cker-0.787
Token.
Token ID13
Feature activation-1.69e-01

Pos logit contributions
oph+0.416
cake+0.394
cakes+0.381
uct+0.356
That+0.342
Neg logit contributions
emo-0.304
cker-0.272
eer-0.265
 sailor-0.255
fish-0.250
Token Lily
Token ID20037
Feature activation+1.08e+00

Pos logit contributions
emo+0.015
eer+0.012
cker+0.012
 sailor+0.012
 Albert+0.012
Neg logit contributions
cake-0.010
oph-0.010
cakes-0.010
board-0.009
 amusement-0.008
Token was
Token ID373
Feature activation+3.79e-01

Pos logit contributions
cake+0.074
oph+0.074
cakes+0.072
board+0.064
 amusement+0.060
Neg logit contributions
emo-0.086
cker-0.074
eer-0.073
 sailor-0.071
ba-0.070
Token so
Token ID523
Feature activation+3.82e+00

Pos logit contributions
oph+0.023
cake+0.023
cakes+0.022
board+0.019
 amusement+0.017
Neg logit contributions
emo-0.034
cker-0.029
eer-0.029
 sailor-0.028
ba-0.028
Token caul
Token ID46087
Feature activation-7.16e+00

Pos logit contributions
emo+0.009
cker+0.009
ba+0.008
rito+0.008
eer+0.008
Neg logit contributions
oph-0.009
cakes-0.009
cake-0.009
board-0.008
 batch-0.008
Tokeniflower
Token ID42642
Feature activation-1.01e+01

Pos logit contributions
emo+0.389
eer+0.333
cker+0.327
 crew+0.321
 sailor+0.315
Neg logit contributions
cake-0.649
oph-0.639
cakes-0.635
board-0.556
That-0.554
Token and
Token ID290
Feature activation+4.91e-01

Pos logit contributions
emo+0.843
cker+0.730
eer+0.717
 sailor+0.697
ba+0.681
Neg logit contributions
oph-0.664
cake-0.656
cakes-0.637
board-0.566
 amusement-0.545
Token stopped
Token ID5025
Feature activation-1.11e+00

Pos logit contributions
cake+0.030
oph+0.030
cakes+0.029
board+0.026
 amusement+0.024
Neg logit contributions
emo-0.043
cker-0.037
eer-0.037
 sailor-0.035
rito-0.035
Token qu
Token ID627
Feature activation+5.98e-01

Pos logit contributions
emo+0.098
rito+0.095
oster+0.092
eer+0.091
ba+0.088
Neg logit contributions
cake-0.053
oph-0.051
cakes-0.049
That-0.045
uct-0.044
Tokenarre
Token ID9624
Feature activation+1.28e+01

Pos logit contributions
cake+0.035
oph+0.035
cakes+0.034
 amusement+0.031
 Rebecca+0.031
Neg logit contributions
emo-0.054
cker-0.046
eer-0.044
ba-0.043
rito-0.042
Tokenling
Token ID1359
Feature activation-4.25e+00

Pos logit contributions
cake+1.116
cakes+1.104
oph+1.098
board+1.010
uct+0.958
Neg logit contributions
emo-0.774
cker-0.624
eer-0.594
 sailor-0.582
rito-0.576
Token.
Token ID13
Feature activation+1.70e-01

Pos logit contributions
emo+0.279
eer+0.239
cker+0.234
 sailor+0.228
ba+0.217
Neg logit contributions
oph-0.358
cake-0.334
cakes-0.331
uct-0.302
board-0.300
Token They
Token ID1119
Feature activation+3.31e-01

Pos logit contributions
cake+0.010
oph+0.010
cakes+0.010
board+0.008
 amusement+0.008
Neg logit contributions
emo-0.016
cker-0.014
eer-0.013
 sailor-0.013
rito-0.013
Token said
Token ID531
Feature activation+2.42e+00

Pos logit contributions
cake+0.023
cakes+0.023
oph+0.022
board+0.020
oga+0.020
Neg logit contributions
emo-0.026
cker-0.022
 sailor-0.022
eer-0.021
fish-0.021
Token,
Token ID11
Feature activation-4.05e-01

Pos logit contributions
cake+0.147
oph+0.145
cakes+0.144
board+0.124
 amusement+0.114
Neg logit contributions
emo-0.213
cker-0.192
eer-0.186
rito-0.180
ba-0.178
Token says
Token ID1139
Feature activation+1.58e+00

Pos logit contributions
oph+0.215
cake+0.213
cakes+0.205
board+0.182
uct+0.172
Neg logit contributions
emo-0.239
cker-0.209
eer-0.206
 sailor-0.197
ba-0.196
Token,
Token ID11
Feature activation-4.11e-01

Pos logit contributions
cake+0.103
oph+0.102
cakes+0.100
board+0.088
 amusement+0.082
Neg logit contributions
emo-0.133
cker-0.116
eer-0.114
 sailor-0.110
rito-0.109
Token "
Token ID366
Feature activation+2.36e+00

Pos logit contributions
emo+0.037
cker+0.032
eer+0.031
 sailor+0.030
rito+0.030
Neg logit contributions
cake-0.025
oph-0.024
cakes-0.024
board-0.021
uct-0.019
TokenStop
Token ID19485
Feature activation+4.44e+00

Pos logit contributions
cake+0.162
cakes+0.161
oph+0.152
board+0.147
ishly+0.132
Neg logit contributions
emo-0.182
ba-0.161
cker-0.152
Ar-0.147
 sailor-0.144
Token qu
Token ID627
Feature activation+5.81e-01

Pos logit contributions
cake+0.293
oph+0.293
cakes+0.285
board+0.254
uct+0.237
Neg logit contributions
emo-0.369
cker-0.319
eer-0.313
 sailor-0.304
ba-0.299
Tokenarre
Token ID9624
Feature activation+1.28e+01

Pos logit contributions
cake+0.034
cakes+0.033
oph+0.032
 amusement+0.027
 Rebecca+0.026
Neg logit contributions
emo-0.054
cker-0.046
ba-0.045
eer-0.044
oster-0.042
Tokenling
Token ID1359
Feature activation-4.27e+00

Pos logit contributions
cake+1.130
oph+1.118
cakes+1.116
board+1.038
That+0.983
Neg logit contributions
emo-0.746
cker-0.603
eer-0.571
 sailor-0.561
rito-0.558
Token,
Token ID11
Feature activation-4.13e-01

Pos logit contributions
emo+0.265
eer+0.231
ba+0.219
 sailor+0.214
cker+0.211
Neg logit contributions
oph-0.377
cake-0.361
cakes-0.358
uct-0.326
 amusement-0.307
Token Tom
Token ID4186
Feature activation+4.51e+00

Pos logit contributions
emo+0.025
 sailor+0.024
eer+0.022
ba+0.021
 exc+0.021
Neg logit contributions
oph-0.033
cake-0.033
cakes-0.032
oga-0.029
board-0.029
Token and
Token ID290
Feature activation+4.67e-01

Pos logit contributions
oph+0.306
cake+0.306
cakes+0.305
board+0.261
 amusement+0.256
Neg logit contributions
emo-0.365
cker-0.319
eer-0.315
ba-0.299
 sailor-0.298
Token Lily
Token ID20037
Feature activation+1.38e+00

Pos logit contributions
oph+0.033
cake+0.032
cakes+0.030
board+0.027
 amusement+0.026
Neg logit contributions
emo-0.038
eer-0.033
cker-0.033
 sailor-0.032
ba-0.031
Token sharing
Token ID7373
Feature activation+3.99e+00

Pos logit contributions
oph+0.283
cake+0.281
cakes+0.273
board+0.252
uct+0.227
Neg logit contributions
emo-0.305
cker-0.256
eer-0.247
 sailor-0.245
 crew-0.237
Token is
Token ID318
Feature activation-3.52e-01

Pos logit contributions
oph+0.282
cake+0.280
cakes+0.272
board+0.244
uct+0.232
Neg logit contributions
emo-0.314
cker-0.268
eer-0.263
 sailor-0.253
ba-0.248
Token important
Token ID1593
Feature activation-2.05e+00

Pos logit contributions
emo+0.025
cker+0.021
eer+0.021
 sailor+0.020
rito+0.019
Neg logit contributions
cake-0.028
oph-0.027
cakes-0.027
board-0.024
uct-0.023
Token and
Token ID290
Feature activation+4.80e-01

Pos logit contributions
emo+0.158
eer+0.133
cker+0.132
 sailor+0.127
 crew+0.124
Neg logit contributions
oph-0.150
cake-0.146
cakes-0.142
board-0.125
uct-0.125
Token qu
Token ID627
Feature activation+5.81e-01

Pos logit contributions
cake+0.032
cakes+0.032
oph+0.032
board+0.028
That+0.027
Neg logit contributions
emo-0.039
cker-0.034
eer-0.033
rito-0.032
 sailor-0.032
Tokenarre
Token ID9624
Feature activation+1.28e+01

Pos logit contributions
oph+0.023
cake+0.023
cakes+0.021
board+0.017
 amusement+0.017
Neg logit contributions
emo-0.065
cker-0.058
eer-0.056
rito-0.055
ba-0.054
Tokenlling
Token ID2680
Feature activation+2.10e+00

Pos logit contributions
cakes+0.989
cake+0.978
oph+0.946
board+0.887
That+0.854
Neg logit contributions
emo-0.855
cker-0.724
 sailor-0.704
rito-0.687
eer-0.686
Token is
Token ID318
Feature activation-3.54e-01

Pos logit contributions
oph+0.150
cake+0.149
cakes+0.144
board+0.129
 amusement+0.123
Neg logit contributions
emo-0.164
cker-0.140
eer-0.138
 sailor-0.132
ba-0.130
Token not
Token ID407
Feature activation-1.07e+00

Pos logit contributions
emo+0.028
eer+0.024
cker+0.024
 sailor+0.023
rito+0.023
Neg logit contributions
cake-0.024
cakes-0.024
oph-0.023
That-0.021
uct-0.021
Token good
Token ID922
Feature activation-1.98e+00

Pos logit contributions
emo+0.088
cker+0.077
eer+0.076
rito+0.074
 sailor+0.074
Neg logit contributions
cake-0.067
oph-0.066
cakes-0.064
uct-0.056
That-0.055
Token.
Token ID13
Feature activation+1.51e-01

Pos logit contributions
emo+0.155
cker+0.130
eer+0.129
 sailor+0.124
 crew+0.120
Neg logit contributions
oph-0.142
cake-0.142
cakes-0.138
board-0.124
uct-0.118
Token
Token ID198
Feature activation-1.87e+00

Pos logit contributions
emo+0.162
cker+0.147
eer+0.144
 sailor+0.140
rito+0.139
Neg logit contributions
cake-0.111
oph-0.108
cakes-0.107
board-0.094
That-0.091
TokenThey
Token ID2990
Feature activation+2.29e+00

Pos logit contributions
emo+0.160
cker+0.135
ba+0.130
 sailor+0.126
oster+0.125
Neg logit contributions
oph-0.127
cake-0.124
cakes-0.123
board-0.109
uct-0.100
Token learn
Token ID2193
Feature activation+5.08e+00

Pos logit contributions
cake+0.163
cakes+0.163
oph+0.162
board+0.141
uct+0.133
Neg logit contributions
emo-0.174
cker-0.153
 sailor-0.151
eer-0.148
ba-0.147
Token that
Token ID326
Feature activation+3.90e+00

Pos logit contributions
oph+0.359
cake+0.341
cakes+0.325
board+0.302
uct+0.285
Neg logit contributions
emo-0.416
cker-0.346
eer-0.342
 sailor-0.341
 crew-0.333
Token qu
Token ID627
Feature activation+6.01e-01

Pos logit contributions
cake+0.234
cakes+0.229
oph+0.227
 amusement+0.202
board+0.200
Neg logit contributions
emo-0.334
cker-0.294
rito-0.292
eer-0.288
ba-0.281
Tokenarre
Token ID9624
Feature activation+1.28e+01

Pos logit contributions
oph+0.029
cake+0.029
cakes+0.028
board+0.023
 amusement+0.022
Neg logit contributions
emo-0.061
cker-0.054
eer-0.053
rito-0.051
 sailor-0.051
Tokenling
Token ID1359
Feature activation-4.25e+00

Pos logit contributions
cakes+0.950
cake+0.935
oph+0.905
board+0.866
That+0.840
Neg logit contributions
emo-0.868
cker-0.743
 sailor-0.727
 Albert-0.711
rito-0.711
Token is
Token ID318
Feature activation-3.47e-01

Pos logit contributions
emo+0.350
cker+0.303
eer+0.296
 sailor+0.288
rito+0.284
Neg logit contributions
cake-0.281
oph-0.277
cakes-0.274
board-0.246
 amusement-0.227
Token bad
Token ID2089
Feature activation+2.32e+00

Pos logit contributions
emo+0.027
eer+0.024
cker+0.023
 sailor+0.022
rito+0.022
Neg logit contributions
cake-0.024
cakes-0.023
oph-0.023
That-0.021
uct-0.021
Token and
Token ID290
Feature activation+4.84e-01

Pos logit contributions
cake+0.146
cakes+0.142
oph+0.142
board+0.129
 amusement+0.116
Neg logit contributions
emo-0.199
cker-0.174
eer-0.167
 sailor-0.164
rito-0.164
Token sharing
Token ID7373
Feature activation+3.99e+00

Pos logit contributions
cake+0.029
cakes+0.029
oph+0.027
That+0.026
board+0.025
Neg logit contributions
emo-0.041
cker-0.035
eer-0.035
rito-0.035
ba-0.035
Token on
Token ID319
Feature activation+1.44e+00

Pos logit contributions
oph+0.015
cake+0.015
cakes+0.015
board+0.013
 amusement+0.013
Neg logit contributions
emo-0.011
eer-0.009
cker-0.009
ba-0.009
 sailor-0.009
Token,
Token ID11
Feature activation-3.98e-01

Pos logit contributions
oph+0.084
cake+0.083
cakes+0.082
board+0.072
 amusement+0.067
Neg logit contributions
emo-0.129
cker-0.116
eer-0.113
rito-0.110
ba-0.109
Token they
Token ID484
Feature activation-6.10e-01

Pos logit contributions
emo+0.034
cker+0.028
 sailor+0.028
eer+0.028
ba+0.027
Neg logit contributions
cake-0.026
oph-0.025
cakes-0.025
board-0.023
uct-0.020
Token never
Token ID1239
Feature activation+2.50e-01

Pos logit contributions
emo+0.049
cker+0.042
ba+0.041
 sailor+0.041
eer+0.041
Neg logit contributions
cake-0.043
cakes-0.042
oph-0.041
board-0.037
 amusement-0.035
Token qu
Token ID627
Feature activation+6.01e-01

Pos logit contributions
cake+0.018
cakes+0.018
oph+0.018
board+0.016
uct+0.015
Neg logit contributions
emo-0.019
cker-0.017
eer-0.016
 sailor-0.016
ba-0.016
Tokenarre
Token ID9624
Feature activation+1.28e+01

Pos logit contributions
cake+0.025
oph+0.024
cakes+0.023
 amusement+0.020
 Rebecca+0.019
Neg logit contributions
emo-0.066
cker-0.056
eer-0.055
ba-0.054
rito-0.054
Tokenled
Token ID992
Feature activation-5.03e+00

Pos logit contributions
cake+1.018
oph+1.009
cakes+1.007
board+0.912
uct+0.875
Neg logit contributions
emo-0.860
cker-0.727
eer-0.697
 sailor-0.689
rito-0.677
Token again
Token ID757
Feature activation+4.69e+00

Pos logit contributions
emo+0.473
cker+0.417
eer+0.410
 sailor+0.397
rito+0.394
Neg logit contributions
cake-0.276
oph-0.275
cakes-0.267
board-0.231
 amusement-0.213
Token and
Token ID290
Feature activation+4.87e-01

Pos logit contributions
cake+0.274
oph+0.274
cakes+0.263
board+0.233
 amusement+0.220
Neg logit contributions
emo-0.421
cker-0.369
eer-0.363
rito-0.352
 sailor-0.349
Token played
Token ID2826
Feature activation+9.20e-01

Pos logit contributions
cake+0.035
oph+0.034
cakes+0.034
board+0.031
uct+0.028
Neg logit contributions
emo-0.039
cker-0.033
eer-0.032
 sailor-0.031
ba-0.031
Token together
Token ID1978
Feature activation+1.68e+00

Pos logit contributions
oph+0.066
cake+0.065
cakes+0.063
board+0.056
uct+0.054
Neg logit contributions
emo-0.073
eer-0.060
cker-0.060
 sailor-0.059
 crew-0.058
TokenThey
Token ID2990
Feature activation+2.29e+00

Pos logit contributions
emo+0.163
cker+0.142
ba+0.133
eer+0.133
 sailor+0.132
Neg logit contributions
oph-0.123
cake-0.120
cakes-0.117
board-0.106
uct-0.095
Token are
Token ID389
Feature activation+3.14e+00

Pos logit contributions
cake+0.178
cakes+0.176
oph+0.174
board+0.151
uct+0.142
Neg logit contributions
emo-0.163
 sailor-0.144
cker-0.139
eer-0.136
ba-0.131
Token tired
Token ID10032
Feature activation-5.54e-01

Pos logit contributions
cake+0.224
oph+0.220
cakes+0.219
uct+0.193
 amusement+0.190
Neg logit contributions
emo-0.231
cker-0.205
eer-0.200
rito-0.192
ba-0.188
Token from
Token ID422
Feature activation+1.29e+00

Pos logit contributions
emo+0.042
eer+0.036
 sailor+0.036
cker+0.035
ba+0.034
Neg logit contributions
oph-0.042
cake-0.039
cakes-0.039
uct-0.035
liv-0.034
Token qu
Token ID627
Feature activation+5.92e-01

Pos logit contributions
cake+0.080
oph+0.080
cakes+0.078
board+0.068
 amusement+0.067
Neg logit contributions
emo-0.111
cker-0.097
eer-0.095
rito-0.093
ba-0.092
Tokenarre
Token ID9624
Feature activation+1.28e+01

Pos logit contributions
cake+0.035
oph+0.034
cakes+0.033
 amusement+0.028
 Rebecca+0.028
Neg logit contributions
emo-0.056
cker-0.048
eer-0.046
ba-0.045
fish-0.044
Tokenling
Token ID1359
Feature activation-4.25e+00

Pos logit contributions
cake+1.073
cakes+1.070
oph+1.042
board+0.985
That+0.939
Neg logit contributions
emo-0.775
cker-0.627
rito-0.601
eer-0.593
 sailor-0.587
Token.
Token ID13
Feature activation+1.57e-01

Pos logit contributions
emo+0.247
eer+0.210
cker+0.198
 sailor+0.191
fish+0.181
Neg logit contributions
oph-0.403
cake-0.378
cakes-0.372
uct-0.337
board-0.331
Token They
Token ID1119
Feature activation+3.25e-01

Pos logit contributions
cake+0.013
oph+0.013
cakes+0.013
board+0.012
uct+0.011
Neg logit contributions
emo-0.011
eer-0.008
cker-0.008
 sailor-0.008
 crew-0.007
Token sit
Token ID1650
Feature activation-1.79e+00

Pos logit contributions
cake+0.024
oph+0.024
cakes+0.023
board+0.020
uct+0.019
Neg logit contributions
emo-0.025
cker-0.021
eer-0.021
 sailor-0.021
ba-0.020
Token in
Token ID287
Feature activation-3.55e+00

Pos logit contributions
emo+0.147
cker+0.127
eer+0.125
rito+0.120
 sailor+0.119
Neg logit contributions
cake-0.119
oph-0.117
cakes-0.117
board-0.104
 amusement-0.098
Token,
Token ID11
Feature activation-3.99e-01

Pos logit contributions
oph+0.067
cake+0.067
cakes+0.065
board+0.060
 amusement+0.059
Neg logit contributions
emo-0.063
cker-0.055
eer-0.054
rito-0.052
ba-0.050
Token why
Token ID1521
Feature activation+6.75e-01

Pos logit contributions
emo+0.030
cker+0.025
eer+0.025
 sailor+0.025
ba+0.023
Neg logit contributions
oph-0.030
cake-0.030
cakes-0.029
board-0.026
uct-0.025
Token are
Token ID389
Feature activation+3.13e+00

Pos logit contributions
cake+0.048
oph+0.047
cakes+0.047
board+0.042
 amusement+0.040
Neg logit contributions
emo-0.052
cker-0.045
eer-0.043
rito-0.042
 sailor-0.041
Token you
Token ID345
Feature activation-1.28e+00

Pos logit contributions
cakes+0.194
oph+0.192
cake+0.191
board+0.161
uct+0.159
Neg logit contributions
emo-0.266
cker-0.238
eer-0.231
rito-0.230
 sailor-0.217
Token qu
Token ID627
Feature activation+5.92e-01

Pos logit contributions
emo+0.107
cker+0.094
eer+0.093
rito+0.090
 sailor+0.087
Neg logit contributions
cake-0.081
oph-0.080
cakes-0.077
board-0.070
uct-0.067
Tokenarre
Token ID9624
Feature activation+1.28e+01

Pos logit contributions
cake+0.023
oph+0.022
cakes+0.022
 amusement+0.017
board+0.017
Neg logit contributions
emo-0.067
cker-0.058
eer-0.056
ba-0.056
rito-0.054
Tokenling
Token ID1359
Feature activation-4.25e+00

Pos logit contributions
cake+0.981
cakes+0.979
oph+0.958
board+0.888
uct+0.850
Neg logit contributions
emo-0.859
cker-0.706
eer-0.685
 sailor-0.683
rito-0.680
Token?"
Token ID1701
Feature activation-4.02e+00

Pos logit contributions
emo+0.224
cker+0.177
eer+0.171
 sailor+0.162
rito+0.157
Neg logit contributions
cake-0.408
oph-0.407
cakes-0.400
board-0.369
uct-0.354
Token But
Token ID887
Feature activation-2.53e+00

Pos logit contributions
emo+0.355
cker+0.310
eer+0.304
 sailor+0.296
ba+0.290
Neg logit contributions
oph-0.244
cake-0.243
cakes-0.237
board-0.207
 amusement-0.193
Token the
Token ID262
Feature activation+3.15e-01

Pos logit contributions
emo+0.218
cker+0.188
eer+0.187
rito+0.181
 sailor+0.176
Neg logit contributions
cake-0.157
oph-0.155
cakes-0.150
board-0.133
 amusement-0.128
Token birds
Token ID10087
Feature activation-7.11e-02

Pos logit contributions
oph+0.026
cake+0.026
cakes+0.026
board+0.023
uct+0.022
Neg logit contributions
emo-0.021
cker-0.018
eer-0.017
 sailor-0.017
ba-0.016
Token mum
Token ID25682
Feature activation+5.85e-01

Pos logit contributions
emo+0.009
 crew+0.007
 sailor+0.007
cker+0.007
eer+0.007
Neg logit contributions
oph-0.014
cake-0.014
cakes-0.013
board-0.012
uct-0.012
Token and
Token ID290
Feature activation+4.82e-01

Pos logit contributions
oph+0.040
cake+0.039
cakes+0.038
board+0.033
uct+0.031
Neg logit contributions
emo-0.045
cker-0.042
eer-0.041
 sailor-0.040
 crew-0.039
Token understood
Token ID7247
Feature activation+3.14e+00

Pos logit contributions
cake+0.036
oph+0.036
cakes+0.035
board+0.031
uct+0.030
Neg logit contributions
emo-0.037
cker-0.031
 sailor-0.031
eer-0.030
 crew-0.030
Token that
Token ID326
Feature activation+3.89e+00

Pos logit contributions
oph+0.229
cake+0.226
cakes+0.220
board+0.198
uct+0.182
Neg logit contributions
emo-0.241
cker-0.206
eer-0.200
 sailor-0.198
 crew-0.190
Token qu
Token ID627
Feature activation+6.15e-01

Pos logit contributions
oph+0.294
cake+0.293
cakes+0.285
board+0.258
uct+0.243
Neg logit contributions
emo-0.287
cker-0.245
eer-0.239
 sailor-0.234
ba-0.225
Tokenarre
Token ID9624
Feature activation+1.28e+01

Pos logit contributions
oph+0.022
cake+0.022
cakes+0.020
board+0.016
 amusement+0.014
Neg logit contributions
emo-0.071
cker-0.063
eer-0.062
rito-0.060
ba-0.060
Tokenlling
Token ID2680
Feature activation+2.12e+00

Pos logit contributions
cakes+0.960
cake+0.951
oph+0.925
board+0.862
That+0.829
Neg logit contributions
emo-0.896
cker-0.741
 sailor-0.728
eer-0.716
rito-0.713
Token was
Token ID373
Feature activation+6.75e-01

Pos logit contributions
oph+0.144
cake+0.143
cakes+0.139
board+0.123
uct+0.117
Neg logit contributions
emo-0.171
cker-0.148
eer-0.146
 sailor-0.141
ba-0.137
Token not
Token ID407
Feature activation-1.06e+00

Pos logit contributions
cake+0.046
oph+0.045
cakes+0.045
board+0.039
uct+0.038
Neg logit contributions
emo-0.054
cker-0.046
eer-0.046
 sailor-0.044
ba-0.044
Token a
Token ID257
Feature activation-1.61e-01

Pos logit contributions
emo+0.089
cker+0.076
eer+0.075
rito+0.073
ba+0.073
Neg logit contributions
cake-0.065
oph-0.064
cakes-0.063
 amusement-0.054
uct-0.054
Token good
Token ID922
Feature activation-1.97e+00

Pos logit contributions
emo+0.012
cker+0.010
eer+0.010
ba+0.010
rito+0.009
Neg logit contributions
cake-0.012
oph-0.012
cakes-0.011
board-0.011
 amusement-0.010
Token?
Token ID30
Feature activation-6.11e-01

Pos logit contributions
emo+0.052
cker+0.041
eer+0.039
 sailor+0.037
rito+0.036
Neg logit contributions
cake-0.101
oph-0.101
cakes-0.099
board-0.092
uct-0.088
Token Why
Token ID4162
Feature activation+3.14e+00

Pos logit contributions
emo+0.055
cker+0.049
eer+0.048
 sailor+0.046
rito+0.046
Neg logit contributions
cake-0.036
oph-0.035
cakes-0.035
board-0.030
 amusement-0.028
Token are
Token ID389
Feature activation+3.14e+00

Pos logit contributions
cake+0.177
cakes+0.176
oph+0.176
board+0.154
 amusement+0.140
Neg logit contributions
emo-0.286
cker-0.253
eer-0.245
rito-0.242
 sailor-0.237
Token you
Token ID345
Feature activation-1.28e+00

Pos logit contributions
cake+0.217
oph+0.216
cakes+0.213
board+0.188
uct+0.178
Neg logit contributions
emo-0.248
cker-0.215
eer-0.210
 sailor-0.201
rito-0.201
Token qu
Token ID627
Feature activation+5.96e-01

Pos logit contributions
emo+0.109
cker+0.096
eer+0.094
rito+0.090
 sailor+0.089
Neg logit contributions
cake-0.080
oph-0.078
cakes-0.076
board-0.068
uct-0.065
Tokenarre
Token ID9624
Feature activation+1.28e+01

Pos logit contributions
cake+0.025
oph+0.024
cakes+0.024
 amusement+0.019
 Rebecca+0.019
Neg logit contributions
emo-0.065
cker-0.056
eer-0.054
ba-0.054
rito-0.053
Tokenling
Token ID1359
Feature activation-4.25e+00

Pos logit contributions
cake+0.990
cakes+0.988
oph+0.967
board+0.894
uct+0.854
Neg logit contributions
emo-0.861
cker-0.713
eer-0.690
 sailor-0.688
rito-0.675
Token?"
Token ID1701
Feature activation-4.01e+00

Pos logit contributions
emo+0.244
cker+0.197
eer+0.194
 sailor+0.189
ba+0.178
Neg logit contributions
oph-0.389
cake-0.384
cakes-0.378
board-0.345
uct-0.337
Token
Token ID198
Feature activation-1.89e+00

Pos logit contributions
emo+0.341
cker+0.296
eer+0.290
 sailor+0.282
ba+0.277
Neg logit contributions
cake-0.255
oph-0.255
cakes-0.248
board-0.220
 amusement-0.205
Token
Token ID198
Feature activation-1.88e+00

Pos logit contributions
emo+0.148
cker+0.129
eer+0.127
 sailor+0.121
rito+0.120
Neg logit contributions
cake-0.133
oph-0.132
cakes-0.129
board-0.115
uct-0.108
TokenThe
Token ID464
Feature activation+2.64e+00

Pos logit contributions
emo+0.136
cker+0.112
 sailor+0.111
ba+0.110
Albert+0.105
Neg logit contributions
oph-0.138
cakes-0.134
cake-0.133
board-0.123
 amusement-0.115
Token he
Token ID339
Feature activation-2.08e+00

Pos logit contributions
emo+0.037
rito+0.034
cker+0.034
eer+0.033
oster+0.029
Neg logit contributions
That-0.018
 All-0.015
oph-0.015
 course-0.014
 Meg-0.014
Token found
Token ID1043
Feature activation-1.44e-01

Pos logit contributions
emo+0.190
eer+0.169
cker+0.167
rito+0.163
 sailor+0.154
Neg logit contributions
oph-0.123
cake-0.115
cakes-0.110
board-0.107
 amusement-0.094
Token a
Token ID257
Feature activation-1.55e-01

Pos logit contributions
emo+0.013
cker+0.012
eer+0.011
 sailor+0.011
ba+0.010
Neg logit contributions
cake-0.008
oph-0.008
cakes-0.008
board-0.007
That-0.007
Token rabbit
Token ID22746
Feature activation-3.87e-02

Pos logit contributions
emo+0.012
eer+0.010
cker+0.010
rito+0.009
ba+0.009
Neg logit contributions
cake-0.012
oph-0.012
cakes-0.011
board-0.010
 amusement-0.010
Token qu
Token ID627
Feature activation+5.96e-01

Pos logit contributions
emo+0.003
cker+0.002
eer+0.002
 sailor+0.002
fish+0.002
Neg logit contributions
oph-0.003
cakes-0.003
cake-0.003
board-0.003
uct-0.003
Tokenarre
Token ID9624
Feature activation+1.28e+01

Pos logit contributions
cake+0.042
cakes+0.042
oph+0.039
 amusement+0.037
 Rebecca+0.036
Neg logit contributions
emo-0.048
cker-0.039
ba-0.038
eer-0.037
rito-0.037
Tokenlling
Token ID2680
Feature activation+2.12e+00

Pos logit contributions
cake+1.034
oph+1.014
cakes+1.013
board+0.942
uct+0.888
Neg logit contributions
emo-0.831
cker-0.664
eer-0.640
 sailor-0.635
 crew-0.631
Token with
Token ID351
Feature activation+1.21e+00

Pos logit contributions
oph+0.165
cake+0.164
cakes+0.162
board+0.143
uct+0.137
Neg logit contributions
emo-0.152
cker-0.129
eer-0.127
 sailor-0.123
fish-0.118
Token a
Token ID257
Feature activation-1.74e-01

Pos logit contributions
cake+0.088
oph+0.088
cakes+0.086
board+0.077
uct+0.073
Neg logit contributions
emo-0.093
cker-0.079
eer-0.078
 sailor-0.075
rito-0.074
Token squirrel
Token ID33039
Feature activation-1.39e+00

Pos logit contributions
emo+0.012
cker+0.010
eer+0.010
 sailor+0.010
rito+0.010
Neg logit contributions
cake-0.014
oph-0.013
cakes-0.013
board-0.012
 amusement-0.011
Token.
Token ID13
Feature activation+1.59e-01

Pos logit contributions
emo+0.102
cker+0.090
eer+0.087
ba+0.083
fish+0.082
Neg logit contributions
oph-0.105
cake-0.103
cakes-0.103
board-0.089
uct-0.088
Token walking
Token ID6155
Feature activation-3.01e+00

Pos logit contributions
oph+0.051
cake+0.050
cakes+0.049
board+0.045
uct+0.042
Neg logit contributions
emo-0.049
cker-0.042
eer-0.041
 sailor-0.040
ba-0.039
Token by
Token ID416
Feature activation-3.09e-01

Pos logit contributions
emo+0.187
eer+0.170
cker+0.167
ba+0.161
 sailor+0.156
Neg logit contributions
oph-0.257
cake-0.243
cakes-0.236
uct-0.213
board-0.207
Token saw
Token ID2497
Feature activation+4.59e-01

Pos logit contributions
emo+0.023
cker+0.019
eer+0.018
ba+0.018
 sailor+0.017
Neg logit contributions
oph-0.024
cake-0.024
cakes-0.024
board-0.021
uct-0.020
Token them
Token ID606
Feature activation-2.92e+00

Pos logit contributions
cake+0.044
oph+0.043
cakes+0.041
board+0.038
uct+0.038
Neg logit contributions
emo-0.024
cker-0.019
eer-0.019
 sailor-0.017
ba-0.017
Token qu
Token ID627
Feature activation+5.86e-01

Pos logit contributions
emo+0.185
cker+0.169
eer+0.163
ba+0.160
 sailor+0.155
Neg logit contributions
oph-0.243
cake-0.226
cakes-0.223
board-0.196
uct-0.187
Tokenarre
Token ID9624
Feature activation+1.27e+01

Pos logit contributions
cake+0.028
oph+0.027
cakes+0.026
 amusement+0.022
 Rebecca+0.021
Neg logit contributions
emo-0.062
cker-0.054
eer-0.052
ba-0.051
rito-0.050
Tokenling
Token ID1359
Feature activation-4.25e+00

Pos logit contributions
cake+1.147
oph+1.132
cakes+1.130
board+1.046
uct+0.999
Neg logit contributions
emo-0.739
cker-0.583
eer-0.562
 sailor-0.549
rito-0.539
Token.
Token ID13
Feature activation+1.65e-01

Pos logit contributions
emo+0.233
eer+0.213
cker+0.205
ba+0.192
 sailor+0.191
Neg logit contributions
oph-0.382
cake-0.353
cakes-0.350
uct-0.322
liv-0.313
Token She
Token ID1375
Feature activation+3.10e+00

Pos logit contributions
oph+0.010
cake+0.009
cakes+0.009
 amusement+0.008
uct+0.008
Neg logit contributions
emo-0.014
 Albert-0.012
eer-0.012
cker-0.012
 exc-0.011
Token was
Token ID373
Feature activation+6.81e-01

Pos logit contributions
oph+0.218
cake+0.218
cakes+0.214
board+0.190
 amusement+0.180
Neg logit contributions
emo-0.239
cker-0.210
eer-0.203
ba-0.199
 sailor-0.198
Token very
Token ID845
Feature activation-1.72e+00

Pos logit contributions
oph+0.054
cake+0.053
cakes+0.052
board+0.048
 amusement+0.044
Neg logit contributions
emo-0.048
cker-0.040
eer-0.039
 sailor-0.038
ba-0.038
Token Finally
Token ID9461
Feature activation-1.72e+00

Pos logit contributions
oph+0.011
cake+0.011
cakes+0.010
board+0.009
 amusement+0.009
Neg logit contributions
emo-0.013
cker-0.011
eer-0.011
 crew-0.010
 sailor-0.010
Token,
Token ID11
Feature activation-4.10e-01

Pos logit contributions
emo+0.116
 sailor+0.096
cker+0.093
 crew+0.092
eer+0.089
Neg logit contributions
cake-0.141
oph-0.139
cakes-0.136
board-0.124
uct-0.119
Token after
Token ID706
Feature activation+5.26e+00

Pos logit contributions
emo+0.030
cker+0.025
 sailor+0.024
eer+0.023
 crew+0.023
Neg logit contributions
cake-0.032
oph-0.032
cakes-0.031
board-0.028
uct-0.026
Token much
Token ID881
Feature activation+1.03e-02

Pos logit contributions
oph+0.393
cake+0.388
cakes+0.373
board+0.339
uct+0.326
Neg logit contributions
emo-0.399
cker-0.337
eer-0.326
 sailor-0.322
 crew-0.318
Token qu
Token ID627
Feature activation+5.86e-01

Pos logit contributions
oph+0.001
cake+0.001
cakes+0.001
board+0.001
uct+0.001
Neg logit contributions
emo-0.001
cker-0.001
eer-0.001
 sailor-0.001
fish-0.001
Tokenarre
Token ID9624
Feature activation+1.27e+01

Pos logit contributions
cake+0.035
oph+0.034
cakes+0.033
 amusement+0.031
 Rebecca+0.030
Neg logit contributions
emo-0.052
cker-0.045
eer-0.041
ery-0.041
rito-0.041
Tokenling
Token ID1359
Feature activation-4.25e+00

Pos logit contributions
cake+1.132
oph+1.126
cakes+1.115
board+1.024
uct+0.977
Neg logit contributions
emo-0.762
cker-0.613
eer-0.594
 sailor-0.573
rito-0.563
Token,
Token ID11
Feature activation-4.06e-01

Pos logit contributions
emo+0.305
eer+0.258
cker+0.257
 sailor+0.247
fish+0.243
Neg logit contributions
oph-0.324
cake-0.313
cakes-0.303
uct-0.275
 amusement-0.266
Token one
Token ID530
Feature activation+2.29e+00

Pos logit contributions
emo+0.031
cker+0.026
 sailor+0.026
eer+0.026
 crew+0.025
Neg logit contributions
cake-0.030
oph-0.030
cakes-0.029
board-0.026
uct-0.024
Token of
Token ID286
Feature activation+2.80e+00

Pos logit contributions
oph+0.148
cake+0.146
cakes+0.145
board+0.124
uct+0.121
Neg logit contributions
emo-0.194
cker-0.171
eer-0.167
 sailor-0.164
fish-0.158
Token the
Token ID262
Feature activation+3.22e-01

Pos logit contributions
cake+0.216
oph+0.214
cakes+0.212
board+0.191
uct+0.173
Neg logit contributions
emo-0.210
cker-0.179
eer-0.174
 sailor-0.168
 crew-0.162
Token Lily
Token ID20037
Feature activation+1.40e+00

Pos logit contributions
emo+0.034
cker+0.028
 sailor+0.027
eer+0.027
 crew+0.027
Neg logit contributions
cake-0.027
oph-0.026
cakes-0.026
board-0.024
 amusement-0.022
Token and
Token ID290
Feature activation+4.84e-01

Pos logit contributions
cake+0.092
cakes+0.091
oph+0.091
board+0.077
 amusement+0.076
Neg logit contributions
emo-0.117
cker-0.101
eer-0.099
 sailor-0.097
ba-0.095
Token Jack
Token ID3619
Feature activation+5.40e+00

Pos logit contributions
cake+0.032
cakes+0.031
oph+0.028
board+0.027
aw+0.024
Neg logit contributions
emo-0.043
 sailor-0.036
eer-0.035
cker-0.035
 Albert-0.034
Token never
Token ID1239
Feature activation+2.39e-01

Pos logit contributions
cake+0.407
cakes+0.402
oph+0.401
board+0.354
uct+0.344
Neg logit contributions
emo-0.397
cker-0.348
eer-0.342
ba-0.329
 sailor-0.327
Token qu
Token ID627
Feature activation+5.85e-01

Pos logit contributions
cakes+0.018
cake+0.018
oph+0.017
board+0.015
uct+0.015
Neg logit contributions
emo-0.018
cker-0.015
eer-0.015
 sailor-0.014
ba-0.014
Tokenarre
Token ID9624
Feature activation+1.27e+01

Pos logit contributions
cake+0.026
oph+0.025
cakes+0.024
 amusement+0.021
 Rebecca+0.021
Neg logit contributions
emo-0.063
cker-0.053
eer-0.051
ba-0.051
ery-0.050
Tokenled
Token ID992
Feature activation-5.04e+00

Pos logit contributions
cake+1.054
oph+1.048
cakes+1.035
board+0.943
uct+0.899
Neg logit contributions
emo-0.837
cker-0.697
eer-0.674
 sailor-0.654
rito-0.642
Token again
Token ID757
Feature activation+4.69e+00

Pos logit contributions
emo+0.453
cker+0.392
eer+0.387
 sailor+0.381
ba+0.373
Neg logit contributions
cake-0.300
oph-0.298
cakes-0.293
board-0.259
uct-0.238
Token.
Token ID13
Feature activation+1.53e-01

Pos logit contributions
cake+0.316
oph+0.315
cakes+0.308
board+0.273
uct+0.257
Neg logit contributions
emo-0.387
cker-0.334
eer-0.327
 sailor-0.317
ba-0.312
Token They
Token ID1119
Feature activation+3.23e-01

Pos logit contributions
cake+0.010
oph+0.010
cakes+0.010
board+0.009
 amusement+0.009
Neg logit contributions
emo-0.013
eer-0.010
cker-0.010
 sailor-0.009
 crew-0.009
Token learned
Token ID4499
Feature activation+3.45e+00

Pos logit contributions
cake+0.023
cakes+0.023
oph+0.022
board+0.020
 amusement+0.018
Neg logit contributions
emo-0.026
cker-0.022
eer-0.022
ba-0.021
 sailor-0.021
Token friends
Token ID2460
Feature activation-1.47e+00

Pos logit contributions
cake+0.393
oph+0.389
cakes+0.371
board+0.348
uct+0.343
Neg logit contributions
emo-0.221
cker-0.180
 crew-0.177
 sailor-0.176
eer-0.175
Token didn
Token ID1422
Feature activation+9.36e-01

Pos logit contributions
emo+0.098
cker+0.093
 crew+0.090
eer+0.089
ba+0.089
Neg logit contributions
oph-0.115
cake-0.113
cakes-0.109
oga-0.091
board-0.090
Token't
Token ID470
Feature activation-1.16e+00

Pos logit contributions
oph+0.084
cake+0.079
cakes+0.076
board+0.073
 amusement+0.067
Neg logit contributions
emo-0.057
ba-0.044
cker-0.043
 exc-0.042
 sailor-0.041
Token stop
Token ID2245
Feature activation+3.80e+00

Pos logit contributions
emo+0.080
cker+0.066
eer+0.065
ba+0.064
 sailor+0.063
Neg logit contributions
oph-0.095
cake-0.093
cakes-0.093
board-0.084
uct-0.081
Token qu
Token ID627
Feature activation+5.78e-01

Pos logit contributions
oph+0.219
cake+0.219
cakes+0.212
board+0.185
 amusement+0.176
Neg logit contributions
emo-0.344
cker-0.301
eer-0.297
rito-0.286
 sailor-0.286
Tokenarre
Token ID9624
Feature activation+1.27e+01

Pos logit contributions
cake+0.029
oph+0.028
cakes+0.027
 amusement+0.024
 Rebecca+0.023
Neg logit contributions
emo-0.058
cker-0.049
ba-0.047
eer-0.046
ery-0.046
Tokenling
Token ID1359
Feature activation-4.26e+00

Pos logit contributions
oph+1.068
cake+1.066
cakes+1.038
board+0.946
 amusement+0.909
Neg logit contributions
emo-0.841
cker-0.703
eer-0.688
ba-0.649
 sailor-0.649
Token and
Token ID290
Feature activation+4.75e-01

Pos logit contributions
emo+0.282
eer+0.246
cker+0.239
 sailor+0.235
 crew+0.228
Neg logit contributions
oph-0.351
cake-0.335
cakes-0.326
board-0.289
uct-0.288
Token were
Token ID547
Feature activation+3.25e+00

Pos logit contributions
oph+0.035
cake+0.035
cakes+0.033
board+0.031
uct+0.028
Neg logit contributions
emo-0.036
cker-0.031
eer-0.031
 sailor-0.030
ba-0.029
Token getting
Token ID1972
Feature activation+1.56e-01

Pos logit contributions
oph+0.261
cake+0.252
cakes+0.248
board+0.232
ue+0.202
Neg logit contributions
emo-0.231
cker-0.198
eer-0.194
 sailor-0.188
 crew-0.187
Token louder
Token ID27089
Feature activation+2.54e+00

Pos logit contributions
cake+0.011
oph+0.011
cakes+0.011
board+0.010
 amusement+0.009
Neg logit contributions
emo-0.012
cker-0.010
eer-0.010
 sailor-0.010
rito-0.009
Token she
Token ID673
Feature activation+8.13e-01

Pos logit contributions
emo+0.218
cker+0.184
eer+0.183
 sailor+0.179
ba+0.174
Neg logit contributions
oph-0.177
cake-0.174
cakes-0.168
board-0.151
uct-0.143
Token was
Token ID373
Feature activation+6.64e-01

Pos logit contributions
oph+0.061
cake+0.060
cakes+0.059
board+0.053
 amusement+0.051
Neg logit contributions
emo-0.060
cker-0.051
eer-0.050
 sailor-0.048
ba-0.047
Token sorry
Token ID7926
Feature activation+3.57e-01

Pos logit contributions
cake+0.050
oph+0.050
cakes+0.049
board+0.044
uct+0.042
Neg logit contributions
emo-0.049
cker-0.042
eer-0.041
 sailor-0.039
rito-0.039
Token for
Token ID329
Feature activation+2.48e+00

Pos logit contributions
oph+0.026
cake+0.025
cakes+0.025
board+0.022
 amusement+0.022
Neg logit contributions
emo-0.027
cker-0.023
eer-0.023
 sailor-0.022
ba-0.022
Token qu
Token ID627
Feature activation+5.78e-01

Pos logit contributions
oph+0.172
cake+0.171
cakes+0.166
board+0.150
 amusement+0.137
Neg logit contributions
emo-0.199
cker-0.171
eer-0.166
 sailor-0.163
ba-0.160
Tokenarre
Token ID9624
Feature activation+1.27e+01

Pos logit contributions
oph+0.024
cake+0.024
cakes+0.022
 amusement+0.020
 Rebecca+0.019
Neg logit contributions
emo-0.064
cker-0.055
eer-0.053
ba-0.052
oster-0.051
Tokenling
Token ID1359
Feature activation-4.26e+00

Pos logit contributions
cake+1.161
oph+1.152
cakes+1.141
board+1.049
uct+1.003
Neg logit contributions
emo-0.732
cker-0.589
eer-0.569
 sailor-0.548
rito-0.534
Token.
Token ID13
Feature activation+1.57e-01

Pos logit contributions
emo+0.269
eer+0.235
cker+0.223
 sailor+0.218
ba+0.210
Neg logit contributions
oph-0.362
cake-0.339
cakes-0.333
uct-0.303
 amusement-0.296
Token From
Token ID3574
Feature activation+1.27e+00

Pos logit contributions
cake+0.010
oph+0.010
cakes+0.010
board+0.009
 amusement+0.009
Neg logit contributions
emo-0.013
cker-0.011
 Albert-0.011
eer-0.010
 sailor-0.010
Token that
Token ID326
Feature activation+3.89e+00

Pos logit contributions
cake+0.076
cakes+0.074
oph+0.073
board+0.065
oga+0.056
Neg logit contributions
emo-0.114
cker-0.103
 sailor-0.099
fish-0.097
eer-0.096
Token day
Token ID1110
Feature activation+1.78e-01

Pos logit contributions
cakes+0.374
oph+0.373
cake+0.369
board+0.328
 amusement+0.324
Neg logit contributions
emo-0.208
cker-0.162
eer-0.159
 sailor-0.155
fish-0.145
Token told
Token ID1297
Feature activation+1.05e+00

Pos logit contributions
oph+0.031
cake+0.031
cakes+0.030
board+0.027
 amusement+0.026
Neg logit contributions
emo-0.036
cker-0.031
eer-0.030
 sailor-0.029
ba-0.029
Token them
Token ID606
Feature activation-2.92e+00

Pos logit contributions
cake+0.097
oph+0.095
cakes+0.090
board+0.087
oga+0.078
Neg logit contributions
emo-0.060
cker-0.048
eer-0.045
ba-0.043
 sailor-0.043
Token to
Token ID284
Feature activation+3.46e-01

Pos logit contributions
emo+0.208
eer+0.166
 sailor+0.165
cker+0.165
fish+0.161
Neg logit contributions
oph-0.229
cake-0.219
cakes-0.200
board-0.189
uct-0.186
Token stop
Token ID2245
Feature activation+3.79e+00

Pos logit contributions
oph+0.030
cakes+0.030
cake+0.030
board+0.026
aw+0.025
Neg logit contributions
emo-0.021
cker-0.017
 sailor-0.016
 exc-0.016
ba-0.016
Token qu
Token ID627
Feature activation+5.77e-01

Pos logit contributions
cake+0.248
oph+0.248
cakes+0.241
board+0.214
uct+0.199
Neg logit contributions
emo-0.318
cker-0.275
eer-0.269
 sailor-0.262
ba-0.257
Tokenarre
Token ID9624
Feature activation+1.27e+01

Pos logit contributions
oph+0.028
cake+0.028
cakes+0.026
 amusement+0.025
 Rebecca+0.025
Neg logit contributions
emo-0.058
cker-0.049
eer-0.047
ery-0.046
ba-0.046
Tokenlling
Token ID2680
Feature activation+2.10e+00

Pos logit contributions
cake+1.180
oph+1.176
cakes+1.158
board+1.067
uct+1.020
Neg logit contributions
emo-0.719
cker-0.575
eer-0.557
 sailor-0.531
rito-0.517
Token and
Token ID290
Feature activation+4.73e-01

Pos logit contributions
oph+0.178
cake+0.170
cakes+0.167
 amusement+0.149
board+0.149
Neg logit contributions
emo-0.137
cker-0.114
eer-0.113
 sailor-0.106
fish-0.105
Token to
Token ID284
Feature activation+3.62e-01

Pos logit contributions
oph+0.036
cake+0.035
cakes+0.034
board+0.031
 amusement+0.029
Neg logit contributions
emo-0.035
cker-0.030
eer-0.029
 sailor-0.028
ba-0.028
Token share
Token ID2648
Feature activation-8.36e-01

Pos logit contributions
cake+0.028
oph+0.028
cakes+0.028
board+0.025
uct+0.023
Neg logit contributions
emo-0.026
cker-0.022
eer-0.021
 sailor-0.021
ba-0.020
Token the
Token ID262
Feature activation+3.18e-01

Pos logit contributions
emo+0.064
cker+0.054
eer+0.053
 sailor+0.051
ba+0.050
Neg logit contributions
oph-0.061
cake-0.061
cakes-0.060
board-0.054
uct-0.051
Token Tom
Token ID4186
Feature activation+4.49e+00

Pos logit contributions
oph+0.009
cake+0.009
cakes+0.009
board+0.008
uct+0.007
Neg logit contributions
emo-0.013
cker-0.011
eer-0.011
 sailor-0.011
rito-0.011
Token and
Token ID290
Feature activation+4.73e-01

Pos logit contributions
oph+0.275
cake+0.274
cakes+0.267
board+0.230
uct+0.219
Neg logit contributions
emo-0.395
cker-0.345
eer-0.342
 sailor-0.331
ba-0.325
Token Mia
Token ID32189
Feature activation+2.68e+00

Pos logit contributions
oph+0.028
cake+0.027
cakes+0.026
board+0.022
 amusement+0.021
Neg logit contributions
emo-0.044
cker-0.039
eer-0.038
 sailor-0.037
ba-0.037
Token stop
Token ID2245
Feature activation+3.79e+00

Pos logit contributions
cake+0.173
oph+0.172
cakes+0.168
board+0.150
 amusement+0.140
Neg logit contributions
emo-0.226
cker-0.195
eer-0.192
 sailor-0.185
rito-0.183
Token qu
Token ID627
Feature activation+5.78e-01

Pos logit contributions
cake+0.227
oph+0.225
cakes+0.219
board+0.195
 amusement+0.185
Neg logit contributions
emo-0.334
cker-0.293
eer-0.287
rito-0.277
 sailor-0.276
Tokenarre
Token ID9624
Feature activation+1.27e+01

Pos logit contributions
cake+0.042
oph+0.042
cakes+0.041
 amusement+0.035
 Rebecca+0.035
Neg logit contributions
emo-0.047
cker-0.038
eer-0.038
ba-0.036
ery-0.035
Tokenling
Token ID1359
Feature activation-4.26e+00

Pos logit contributions
cake+1.156
oph+1.142
cakes+1.139
board+1.055
uct+1.000
Neg logit contributions
emo-0.728
cker-0.581
eer-0.554
 sailor-0.540
rito-0.530
Token.
Token ID13
Feature activation+1.52e-01

Pos logit contributions
emo+0.241
eer+0.205
cker+0.199
 sailor+0.194
fish+0.185
Neg logit contributions
oph-0.409
cake-0.379
cakes-0.378
uct-0.339
liv-0.337
Token They
Token ID1119
Feature activation+3.26e-01

Pos logit contributions
oph+0.012
cake+0.012
cakes+0.011
board+0.010
uct+0.010
Neg logit contributions
emo-0.011
cker-0.009
eer-0.009
 sailor-0.008
 Albert-0.008
Token see
Token ID766
Feature activation-1.93e+00

Pos logit contributions
oph+0.024
cake+0.024
cakes+0.024
board+0.021
uct+0.020
Neg logit contributions
emo-0.024
cker-0.021
eer-0.021
 sailor-0.020
ba-0.020
Token the
Token ID262
Feature activation+3.14e-01

Pos logit contributions
emo+0.147
cker+0.124
eer+0.123
 sailor+0.120
 crew+0.116
Neg logit contributions
oph-0.147
cake-0.145
cakes-0.140
board-0.127
uct-0.122
Token friends
Token ID2460
Feature activation-1.85e+00

Pos logit contributions
cker+0.223
emo+0.219
rito+0.214
Albert+0.207
eer+0.206
Neg logit contributions
board-0.135
 amusement-0.129
cakes-0.128
cake-0.128
oph-0.125
Token.
Token ID13
Feature activation-2.36e-01

Pos logit contributions
emo+0.126
cker+0.108
eer+0.108
 sailor+0.106
ba+0.101
Neg logit contributions
oph-0.147
cakes-0.146
cake-0.145
board-0.124
uct-0.120
Token
Token ID198
Feature activation-2.27e+00

Pos logit contributions
emo+0.019
cker+0.017
eer+0.017
rito+0.016
 sailor+0.016
Neg logit contributions
oph-0.016
cake-0.016
cakes-0.015
board-0.014
uct-0.013
Token
Token ID198
Feature activation-2.29e+00

Pos logit contributions
emo+0.203
cker+0.203
eer+0.197
 sailor+0.191
rito+0.189
Neg logit contributions
oph-0.116
cake-0.113
cakes-0.109
That-0.100
board-0.098
TokenN
Token ID45
Feature activation-3.51e+00

Pos logit contributions
emo+0.206
cker+0.178
eer+0.175
 sailor+0.171
ba+0.169
Neg logit contributions
cake-0.138
oph-0.137
cakes-0.134
board-0.117
 amusement-0.109
Tokenemo
Token ID41903
Feature activation-1.46e+01

Pos logit contributions
 Albert+0.045
Albert+0.042
cker+0.042
rito+0.032
 wax+0.027
Neg logit contributions
oph-0.427
board-0.409
cake-0.398
aw-0.383
cakes-0.379
Token tried
Token ID3088
Feature activation-2.84e+00

Pos logit contributions
emo+1.330
cker+1.167
eer+1.136
 sailor+1.112
ba+1.101
Neg logit contributions
cake-0.863
oph-0.847
cakes-0.841
board-0.719
 amusement-0.676
Token to
Token ID284
Feature activation-7.10e-02

Pos logit contributions
emo+0.232
cker+0.202
eer+0.199
 sailor+0.191
rito+0.189
Neg logit contributions
cake-0.189
oph-0.188
cakes-0.183
board-0.164
 amusement-0.155
Token swim
Token ID9422
Feature activation-6.69e+00

Pos logit contributions
emo+0.006
eer+0.005
cker+0.005
rito+0.004
 sailor+0.004
Neg logit contributions
oph-0.005
cake-0.005
cakes-0.004
 amusement-0.004
board-0.004
Token away
Token ID1497
Feature activation+1.27e+00

Pos logit contributions
emo+0.544
cker+0.468
eer+0.459
 sailor+0.445
ba+0.438
Neg logit contributions
cake-0.453
oph-0.453
cakes-0.441
board-0.393
uct-0.370
Token,
Token ID11
Feature activation-8.76e-01

Pos logit contributions
cake+0.073
oph+0.072
cakes+0.070
board+0.063
 amusement+0.058
Neg logit contributions
emo-0.114
cker-0.101
eer-0.099
rito-0.095
 sailor-0.094
Token it
Token ID340
Feature activation-2.14e+00

Pos logit contributions
emo+0.136
cker+0.132
oster+0.124
rito+0.123
eer+0.120
Neg logit contributions
 course-0.049
aw-0.048
oph-0.048
That-0.046
cake-0.043
Token.
Token ID13
Feature activation-2.02e-01

Pos logit contributions
emo+0.180
cker+0.156
eer+0.153
 sailor+0.148
rito+0.146
Neg logit contributions
cake-0.139
oph-0.137
cakes-0.134
board-0.121
uct-0.113
Token
Token ID198
Feature activation-2.26e+00

Pos logit contributions
emo+0.018
cker+0.018
eer+0.017
rito+0.017
 sailor+0.016
Neg logit contributions
oph-0.011
cake-0.011
cakes-0.011
board-0.010
That-0.009
Token
Token ID198
Feature activation-2.26e+00

Pos logit contributions
cker+0.207
emo+0.207
eer+0.198
rito+0.191
 sailor+0.189
Neg logit contributions
oph-0.115
cake-0.110
cakes-0.107
That-0.096
board-0.095
TokenN
Token ID45
Feature activation-3.47e+00

Pos logit contributions
emo+0.168
cker+0.141
eer+0.138
 sailor+0.133
ba+0.131
Neg logit contributions
cake-0.172
oph-0.172
cakes-0.168
board-0.152
 amusement-0.144
Tokenemo
Token ID41903
Feature activation-1.46e+01

Pos logit contributions
 Albert+0.049
Albert+0.049
cker+0.049
 crew+0.035
rito+0.032
Neg logit contributions
oph-0.423
board-0.407
cake-0.396
cakes-0.372
aw-0.369
Token's
Token ID338
Feature activation+2.17e+00

Pos logit contributions
emo+1.291
eer+1.151
rito+1.149
cker+1.114
 sailor+1.104
Neg logit contributions
oph-0.813
cake-0.761
cakes-0.727
board-0.691
That-0.642
Token friend
Token ID1545
Feature activation-2.37e+00

Pos logit contributions
oph+0.138
cake+0.135
cakes+0.133
board+0.129
 amusement+0.121
Neg logit contributions
emo-0.156
cker-0.153
rito-0.148
eer-0.143
Albert-0.133
Token,
Token ID11
Feature activation-8.17e-01

Pos logit contributions
emo+0.202
cker+0.176
eer+0.172
 sailor+0.167
rito+0.165
Neg logit contributions
oph-0.151
cake-0.151
cakes-0.147
board-0.130
 amusement-0.121
Token D
Token ID360
Feature activation-2.30e+00

Pos logit contributions
emo+0.071
cker+0.061
eer+0.060
 sailor+0.058
rito+0.058
Neg logit contributions
cake-0.051
oph-0.051
cakes-0.050
board-0.044
uct-0.041
Tokenory
Token ID652
Feature activation-5.08e+00

Pos logit contributions
cker+0.178
emo+0.174
rito+0.166
eer+0.165
 crew+0.165
Neg logit contributions
oph-0.156
cake-0.142
board-0.136
cakes-0.132
ue-0.110
Token.
Token ID13
Feature activation-1.64e-01

Pos logit contributions
emo+0.042
cker+0.036
eer+0.035
rito+0.035
ba+0.033
Neg logit contributions
cake-0.032
cakes-0.031
oph-0.031
board-0.028
 amusement-0.027
Token
Token ID220
Feature activation+2.21e+00

Pos logit contributions
emo+0.014
cker+0.014
eer+0.013
rito+0.013
ba+0.012
Neg logit contributions
oph-0.009
cake-0.009
cakes-0.009
board-0.008
That-0.008
Token
Token ID198
Feature activation-2.21e+00

Pos logit contributions
cake+0.109
cakes+0.107
oph+0.105
That+0.092
board+0.089
Neg logit contributions
cker-0.198
emo-0.198
eer-0.190
 sailor-0.190
rito-0.184
Token
Token ID198
Feature activation-2.21e+00

Pos logit contributions
emo+0.196
cker+0.190
eer+0.182
 sailor+0.175
rito+0.174
Neg logit contributions
oph-0.124
cake-0.121
cakes-0.117
board-0.104
That-0.102
TokenN
Token ID45
Feature activation-3.43e+00

Pos logit contributions
emo+0.193
cker+0.167
eer+0.163
 sailor+0.159
ba+0.157
Neg logit contributions
cake-0.141
oph-0.140
cakes-0.137
board-0.120
uct-0.112
Tokenemo
Token ID41903
Feature activation-1.45e+01

Pos logit contributions
Albert+0.049
cker+0.049
 Albert+0.047
 crew+0.034
rito+0.033
Neg logit contributions
oph-0.410
board-0.396
cake-0.384
aw-0.369
cakes-0.364
Token saw
Token ID2497
Feature activation+9.59e-02

Pos logit contributions
emo+1.431
rito+1.296
eer+1.282
cker+1.258
 sailor+1.230
Neg logit contributions
oph-0.675
cake-0.613
cakes-0.579
board-0.557
That-0.482
Token a
Token ID257
Feature activation-5.33e-01

Pos logit contributions
oph+0.006
cake+0.006
cakes+0.005
 amusement+0.005
board+0.005
Neg logit contributions
emo-0.008
cker-0.008
rito-0.007
eer-0.007
ba-0.007
Token big
Token ID1263
Feature activation+6.98e-01

Pos logit contributions
emo+0.041
eer+0.038
cker+0.038
rito+0.037
eers+0.034
Neg logit contributions
oph-0.034
cake-0.033
cakes-0.031
 amusement-0.030
board-0.030
Token jet
Token ID12644
Feature activation-3.11e-01

Pos logit contributions
oph+0.060
cake+0.060
cakes+0.058
board+0.055
 amusement+0.054
Neg logit contributions
emo-0.043
cker-0.035
eer-0.033
rito-0.033
ba-0.032
Token flying
Token ID7348
Feature activation-5.73e+00

Pos logit contributions
emo+0.021
cker+0.018
eer+0.018
 sailor+0.017
fish+0.017
Neg logit contributions
oph-0.026
cake-0.025
cakes-0.025
board-0.022
uct-0.021
Token He
Token ID679
Feature activation-1.85e+00

Pos logit contributions
emo+0.013
cker+0.011
eer+0.011
 sailor+0.011
rito+0.011
Neg logit contributions
cake-0.010
oph-0.010
cakes-0.009
board-0.008
uct-0.008
Token said
Token ID531
Feature activation+2.10e+00

Pos logit contributions
emo+0.162
cker+0.141
eer+0.141
rito+0.140
 sailor+0.133
Neg logit contributions
oph-0.110
cake-0.108
cakes-0.105
board-0.093
 amusement-0.087
Token,
Token ID11
Feature activation-7.36e-01

Pos logit contributions
cake+0.124
cakes+0.121
oph+0.118
board+0.102
That+0.094
Neg logit contributions
emo-0.190
cker-0.171
eer-0.166
rito-0.164
ba-0.159
Token "
Token ID366
Feature activation+2.05e+00

Pos logit contributions
emo+0.073
cker+0.065
eer+0.064
rito+0.062
 sailor+0.061
Neg logit contributions
cake-0.037
cakes-0.035
oph-0.034
board-0.030
That-0.029
TokenN
Token ID45
Feature activation-3.42e+00

Pos logit contributions
cake+0.104
oph+0.104
cakes+0.100
board+0.085
uct+0.078
Neg logit contributions
emo-0.202
cker-0.179
eer-0.176
 sailor-0.171
rito-0.170
Tokenemo
Token ID41903
Feature activation-1.45e+01

Pos logit contributions
emo+0.146
cker+0.139
 sailor+0.133
 Albert+0.132
Albert+0.131
Neg logit contributions
oph-0.328
cake-0.323
cakes-0.307
board-0.305
aw-0.283
Token,
Token ID11
Feature activation-7.50e-01

Pos logit contributions
emo+1.341
cker+1.162
rito+1.151
eer+1.140
 sailor+1.127
Neg logit contributions
oph-0.775
cake-0.772
cakes-0.725
board-0.690
That-0.602
Token you
Token ID345
Feature activation-1.64e+00

Pos logit contributions
emo+0.061
cker+0.054
eer+0.052
rito+0.051
ba+0.049
Neg logit contributions
cake-0.050
oph-0.049
cakes-0.048
board-0.044
That-0.041
Token must
Token ID1276
Feature activation+2.23e-01

Pos logit contributions
emo+0.152
cker+0.136
rito+0.131
eer+0.128
ba+0.123
Neg logit contributions
cake-0.082
oph-0.081
cakes-0.079
board-0.074
 amusement-0.068
Token keep
Token ID1394
Feature activation-3.90e+00

Pos logit contributions
oph+0.014
cake+0.014
cakes+0.013
board+0.013
 amusement+0.012
Neg logit contributions
emo-0.017
eer-0.015
cker-0.015
 sailor-0.014
rito-0.014
Token swimming
Token ID14899
Feature activation-4.29e+00

Pos logit contributions
emo+0.365
rito+0.330
fish+0.318
cker+0.317
oster+0.317
Neg logit contributions
 course-0.171
 amusement-0.149
uct-0.144
oph-0.141
That-0.140
Token first
Token ID717
Feature activation+2.15e+00

Pos logit contributions
emo+0.010
cker+0.009
eer+0.009
 sailor+0.008
rito+0.008
Neg logit contributions
cake-0.008
oph-0.008
cakes-0.007
board-0.007
 amusement-0.006
Token."
Token ID526
Feature activation-3.67e+00

Pos logit contributions
cake+0.149
oph+0.149
cakes+0.146
board+0.129
uct+0.122
Neg logit contributions
emo-0.169
cker-0.146
eer-0.142
 sailor-0.140
ba-0.136
Token
Token ID198
Feature activation-2.18e+00

Pos logit contributions
emo+0.293
cker+0.247
eer+0.243
 sailor+0.237
ba+0.232
Neg logit contributions
cake-0.251
oph-0.251
cakes-0.246
board-0.220
 amusement-0.209
Token
Token ID198
Feature activation-2.20e+00

Pos logit contributions
emo+0.170
cker+0.148
eer+0.145
 sailor+0.140
rito+0.138
Neg logit contributions
cake-0.152
oph-0.152
cakes-0.147
board-0.132
uct-0.125
TokenN
Token ID45
Feature activation-3.43e+00

Pos logit contributions
emo+0.204
cker+0.175
ba+0.171
 sailor+0.169
eer+0.167
Neg logit contributions
cake-0.124
cakes-0.123
oph-0.123
board-0.107
 amusement-0.096
Tokenemo
Token ID41903
Feature activation-1.45e+01

Pos logit contributions
emo+0.233
cker+0.217
 crew+0.212
eer+0.210
 sailor+0.209
Neg logit contributions
oph-0.260
cake-0.255
cakes-0.234
board-0.233
uct-0.200
Token asked
Token ID1965
Feature activation-3.51e+00

Pos logit contributions
emo+1.288
cker+1.124
eer+1.105
 sailor+1.072
rito+1.062
Neg logit contributions
cake-0.867
oph-0.867
cakes-0.840
board-0.741
uct-0.687
Token,
Token ID11
Feature activation-7.05e-01

Pos logit contributions
emo+0.291
cker+0.266
eer+0.250
rito+0.243
ba+0.237
Neg logit contributions
oph-0.225
cake-0.223
cakes-0.215
board-0.194
 amusement-0.182
Token "
Token ID366
Feature activation+2.10e+00

Pos logit contributions
emo+0.075
eer+0.070
cker+0.069
rito+0.065
 sailor+0.063
Neg logit contributions
cake-0.030
oph-0.026
cakes-0.025
That-0.021
board-0.020
TokenWhat
Token ID2061
Feature activation+2.26e+00

Pos logit contributions
cake+0.118
oph+0.116
cakes+0.112
board+0.098
That+0.092
Neg logit contributions
emo-0.196
cker-0.173
eer-0.171
 sailor-0.164
rito-0.164
Token do
Token ID466
Feature activation+3.12e+00

Pos logit contributions
cake+0.119
oph+0.118
cakes+0.116
board+0.104
 amusement+0.094
Neg logit contributions
emo-0.213
cker-0.192
rito-0.190
eer-0.183
ba-0.181
Token far
Token ID1290
Feature activation-2.75e+00

Pos logit contributions
cakes+0.234
cake+0.230
oph+0.219
That+0.216
board+0.209
Neg logit contributions
cker-0.281
emo-0.278
rito-0.273
eer-0.267
ba-0.239
Token?"
Token ID1701
Feature activation-4.33e+00

Pos logit contributions
emo+0.168
cker+0.141
eer+0.133
rito+0.128
ba+0.125
Neg logit contributions
oph-0.232
cake-0.226
cakes-0.216
board-0.212
 amusement-0.205
Token
Token ID198
Feature activation-2.19e+00

Pos logit contributions
cker+0.329
emo+0.328
eer+0.319
rito+0.312
 sailor+0.288
Neg logit contributions
oph-0.290
cake-0.275
cakes-0.266
board-0.246
That-0.241
Token
Token ID198
Feature activation-2.19e+00

Pos logit contributions
cker+0.216
eer+0.209
emo+0.201
rito+0.200
 sailor+0.193
Neg logit contributions
oph-0.104
cake-0.093
cakes-0.089
That-0.083
board-0.076
TokenN
Token ID45
Feature activation-3.42e+00

Pos logit contributions
emo+0.153
cker+0.135
eer+0.133
rito+0.124
 sailor+0.124
Neg logit contributions
oph-0.171
cake-0.169
cakes-0.164
board-0.150
That-0.144
Tokenemo
Token ID41903
Feature activation-1.45e+01

Pos logit contributions
cker+0.024
rito+0.009
 crew+0.009
 sailor+0.007
eer+0.006
Neg logit contributions
oph-0.462
cake-0.440
board-0.426
cakes-0.422
That-0.394
Token replied
Token ID8712
Feature activation+5.04e+00

Pos logit contributions
emo+1.380
cker+1.216
eer+1.205
 sailor+1.172
rito+1.169
Neg logit contributions
oph-0.771
cake-0.760
cakes-0.730
board-0.640
uct-0.586
Token,
Token ID11
Feature activation-7.43e-01

Pos logit contributions
cake+0.303
oph+0.295
cakes+0.293
board+0.258
That+0.232
Neg logit contributions
emo-0.447
cker-0.400
eer-0.391
rito-0.378
 sailor-0.373
Token "
Token ID366
Feature activation+2.02e+00

Pos logit contributions
emo+0.068
cker+0.060
eer+0.059
 sailor+0.057
rito+0.057
Neg logit contributions
cake-0.043
oph-0.042
cakes-0.041
board-0.036
uct-0.033
TokenI
Token ID40
Feature activation+6.65e-01

Pos logit contributions
cake+0.100
oph+0.099
cakes+0.096
board+0.083
That+0.079
Neg logit contributions
emo-0.199
cker-0.179
eer-0.177
rito-0.172
 sailor-0.171
Token want
Token ID765
Feature activation+1.32e+00

Pos logit contributions
oph+0.031
�+0.030
cake+0.029
board+0.029
 amusement+0.027
Neg logit contributions
emo-0.056
cker-0.051
eer-0.049
 crew-0.049
rito-0.049
Token you
Token ID345
Feature activation-1.55e+00

Pos logit contributions
emo+0.125
cker+0.111
eer+0.104
ba+0.103
rito+0.102
Neg logit contributions
oph-0.091
cakes-0.089
cake-0.088
 amusement-0.077
board-0.076
Token."
Token ID526
Feature activation-3.70e+00

Pos logit contributions
emo+0.138
cker+0.120
eer+0.118
rito+0.116
oster+0.115
Neg logit contributions
cake-0.079
cakes-0.076
oph-0.073
board-0.067
 amusement-0.065
Token
Token ID198
Feature activation-2.20e+00

Pos logit contributions
emo+0.293
cker+0.243
eer+0.240
 sailor+0.236
ba+0.228
Neg logit contributions
cake-0.257
oph-0.256
cakes-0.252
board-0.225
 amusement-0.214
Token
Token ID198
Feature activation-2.22e+00

Pos logit contributions
emo+0.169
cker+0.145
eer+0.142
 sailor+0.137
rito+0.135
Neg logit contributions
cake-0.157
oph-0.157
cakes-0.153
board-0.138
uct-0.130
TokenN
Token ID45
Feature activation-3.42e+00

Pos logit contributions
emo+0.199
cker+0.172
ba+0.168
 sailor+0.166
Albert+0.163
Neg logit contributions
cake-0.133
cakes-0.132
oph-0.131
board-0.116
uct-0.103
Tokenemo
Token ID41903
Feature activation-1.45e+01

Pos logit contributions
emo+0.235
cker+0.222
 crew+0.216
 sailor+0.213
rito+0.212
Neg logit contributions
oph-0.250
cake-0.246
cakes-0.229
board-0.229
aw-0.194
Token was
Token ID373
Feature activation+3.79e-01

Pos logit contributions
emo+1.280
cker+1.113
eer+1.095
 sailor+1.063
rito+1.057
Neg logit contributions
oph-0.873
cake-0.871
cakes-0.846
board-0.751
uct-0.692
Token grateful
Token ID14066
Feature activation-2.68e+00

Pos logit contributions
cake+0.023
oph+0.023
cakes+0.022
uct+0.020
 amusement+0.019
Neg logit contributions
emo-0.033
cker-0.029
eer-0.028
 sailor-0.027
rito-0.027
Token for
Token ID329
Feature activation+2.23e+00

Pos logit contributions
emo+0.220
cker+0.190
eer+0.186
 sailor+0.182
rito+0.177
Neg logit contributions
oph-0.181
cake-0.180
cakes-0.177
board-0.155
uct-0.149
Token Tim
Token ID5045
Feature activation+2.52e+00

Pos logit contributions
cake+0.169
oph+0.168
cakes+0.164
board+0.147
 amusement+0.146
Neg logit contributions
emo-0.160
cker-0.142
eer-0.135
rito-0.128
 sailor-0.126
Tokenmy
Token ID1820
Feature activation-2.11e-01

Pos logit contributions
cake+0.148
oph+0.147
cakes+0.146
board+0.123
 amusement+0.116
Neg logit contributions
emo-0.227
cker-0.201
eer-0.201
 sailor-0.192
ba-0.189
Token.
Token ID13
Feature activation-5.47e-02

Pos logit contributions
emo+0.434
cker+0.379
eer+0.374
 sailor+0.362
ba+0.358
Neg logit contributions
cake-0.294
oph-0.293
cakes-0.287
board-0.248
 amusement-0.237
Token
Token ID220
Feature activation+2.30e+00

Pos logit contributions
emo+0.005
cker+0.004
eer+0.004
 sailor+0.004
rito+0.004
Neg logit contributions
oph-0.003
cake-0.003
cakes-0.003
board-0.003
uct-0.003
Token
Token ID198
Feature activation-2.11e+00

Pos logit contributions
cake+0.114
cakes+0.111
oph+0.109
That+0.096
uct+0.090
Neg logit contributions
cker-0.212
eer-0.207
 sailor-0.206
emo-0.205
rito-0.196
Token
Token ID198
Feature activation-2.12e+00

Pos logit contributions
cker+0.185
eer+0.181
emo+0.181
 sailor+0.170
rito+0.168
Neg logit contributions
oph-0.117
cake-0.114
cakes-0.112
That-0.103
board-0.095
TokenN
Token ID45
Feature activation-3.34e+00

Pos logit contributions
emo+0.161
cker+0.134
eer+0.130
 sailor+0.128
ba+0.127
Neg logit contributions
cake-0.157
oph-0.156
cakes-0.153
board-0.138
 amusement-0.130
Tokenemo
Token ID41903
Feature activation-1.44e+01

Pos logit contributions
cker+0.029
rito+0.014
emo+0.013
eer+0.011
 Albert+0.011
Neg logit contributions
oph-0.444
cake-0.419
board-0.405
cakes-0.403
That-0.379
Token said
Token ID531
Feature activation+2.15e+00

Pos logit contributions
emo+1.273
cker+1.113
eer+1.084
 sailor+1.055
ba+1.046
Neg logit contributions
cake-0.885
oph-0.871
cakes-0.865
board-0.749
 amusement-0.707
Token,
Token ID11
Feature activation-6.68e-01

Pos logit contributions
cake+0.118
cakes+0.113
oph+0.112
board+0.097
That+0.089
Neg logit contributions
emo-0.199
cker-0.183
eer-0.178
rito-0.173
ba-0.169
Token "
Token ID366
Feature activation+2.10e+00

Pos logit contributions
emo+0.064
cker+0.057
eer+0.056
rito+0.054
 sailor+0.053
Neg logit contributions
cake-0.036
oph-0.034
cakes-0.034
board-0.030
That-0.028
TokenPlease
Token ID5492
Feature activation+6.94e-01

Pos logit contributions
oph+0.103
cake+0.101
cakes+0.094
That+0.084
board+0.081
Neg logit contributions
emo-0.206
cker-0.185
eer-0.184
rito-0.177
 sailor-0.177
Token give
Token ID1577
Feature activation+7.53e-03

Pos logit contributions
cake+0.039
oph+0.037
cakes+0.036
board+0.035
ue+0.033
Neg logit contributions
emo-0.061
cker-0.055
eer-0.053
rito-0.050
 sailor-0.048
Token dangerous
Token ID4923
Feature activation-1.49e+00

Pos logit contributions
cake+0.011
cakes+0.011
oph+0.011
 amusement+0.010
uct+0.010
Neg logit contributions
emo-0.013
eer-0.011
cker-0.010
rito-0.010
ba-0.010
Token."
Token ID526
Feature activation-3.74e+00

Pos logit contributions
emo+0.127
cker+0.108
eer+0.103
 sailor+0.103
ba+0.102
Neg logit contributions
cake-0.094
cakes-0.092
oph-0.092
board-0.083
 amusement-0.078
Token
Token ID198
Feature activation-2.20e+00

Pos logit contributions
emo+0.307
cker+0.261
eer+0.255
 sailor+0.250
ba+0.243
Neg logit contributions
cake-0.251
oph-0.248
cakes-0.246
board-0.217
 amusement-0.206
Token
Token ID198
Feature activation-2.18e+00

Pos logit contributions
emo+0.174
cker+0.152
eer+0.149
 sailor+0.144
rito+0.142
Neg logit contributions
oph-0.151
cake-0.151
cakes-0.146
board-0.131
uct-0.124
TokenN
Token ID45
Feature activation-3.35e+00

Pos logit contributions
emo+0.206
cker+0.179
 sailor+0.172
ba+0.171
eer+0.171
Neg logit contributions
cake-0.121
cakes-0.121
oph-0.119
board-0.103
 amusement-0.092
Tokenemo
Token ID41903
Feature activation-1.44e+01

Pos logit contributions
emo+0.192
cker+0.188
 crew+0.183
rito+0.181
eer+0.176
Neg logit contributions
oph-0.279
cake-0.268
board-0.250
cakes-0.245
aw-0.216
Token was
Token ID373
Feature activation+4.47e-01

Pos logit contributions
emo+1.278
cker+1.110
eer+1.095
 sailor+1.061
rito+1.060
Neg logit contributions
oph-0.866
cake-0.859
cakes-0.831
board-0.742
uct-0.687
Token sad
Token ID6507
Feature activation-8.38e-01

Pos logit contributions
cake+0.031
oph+0.031
cakes+0.030
uct+0.026
board+0.026
Neg logit contributions
emo-0.035
cker-0.030
eer-0.030
 sailor-0.029
rito-0.028
Token because
Token ID780
Feature activation+7.80e-01

Pos logit contributions
emo+0.076
cker+0.066
eer+0.065
 sailor+0.063
rito+0.062
Neg logit contributions
cake-0.050
oph-0.049
cakes-0.048
board-0.042
 amusement-0.039
Token he
Token ID339
Feature activation-2.28e+00

Pos logit contributions
cake+0.062
oph+0.062
cakes+0.061
board+0.055
 amusement+0.054
Neg logit contributions
emo-0.052
cker-0.044
eer-0.043
rito-0.042
ba-0.041
Token wanted
Token ID2227
Feature activation+6.42e-01

Pos logit contributions
emo+0.204
cker+0.173
eer+0.173
rito+0.169
 sailor+0.169
Neg logit contributions
cake-0.129
oph-0.129
cakes-0.120
That-0.116
board-0.114
Token.
Token ID13
Feature activation-1.69e-01

Pos logit contributions
cake+0.073
cakes+0.070
oph+0.069
board+0.063
That+0.057
Neg logit contributions
emo-0.097
cker-0.084
eer-0.080
 sailor-0.079
rito-0.078
Token
Token ID220
Feature activation+2.22e+00

Pos logit contributions
emo+0.015
cker+0.013
eer+0.013
rito+0.013
 sailor+0.012
Neg logit contributions
oph-0.010
cake-0.010
cakes-0.010
board-0.008
uct-0.008
Token
Token ID198
Feature activation-2.18e+00

Pos logit contributions
cake+0.107
cakes+0.106
oph+0.100
board+0.086
That+0.086
Neg logit contributions
cker-0.201
emo-0.198
 sailor-0.198
eer-0.193
 crew-0.188
Token
Token ID198
Feature activation-2.14e+00

Pos logit contributions
emo+0.177
cker+0.161
eer+0.159
 sailor+0.153
rito+0.150
Neg logit contributions
oph-0.140
cake-0.140
cakes-0.134
board-0.119
That-0.119
TokenN
Token ID45
Feature activation-3.34e+00

Pos logit contributions
emo+0.190
cker+0.162
eer+0.157
 sailor+0.155
ba+0.154
Neg logit contributions
cake-0.132
oph-0.131
cakes-0.130
board-0.114
 amusement-0.104
Tokenemo
Token ID41903
Feature activation-1.44e+01

Pos logit contributions
cker+0.045
 crew+0.041
 sword+0.036
Albert+0.036
igs+0.035
Neg logit contributions
oph-0.405
cake-0.389
board-0.384
cakes-0.360
aw-0.355
Token's
Token ID338
Feature activation+2.36e+00

Pos logit contributions
emo+1.283
cker+1.107
eer+1.101
rito+1.081
 sailor+1.062
Neg logit contributions
oph-0.854
cake-0.821
cakes-0.787
board-0.725
uct-0.675
Token friend
Token ID1545
Feature activation-2.18e+00

Pos logit contributions
oph+0.166
cake+0.166
cakes+0.160
board+0.152
 amusement+0.147
Neg logit contributions
emo-0.178
cker-0.153
eer-0.148
rito-0.145
ba-0.143
Token,
Token ID11
Feature activation-5.89e-01

Pos logit contributions
emo+0.187
cker+0.163
eer+0.160
rito+0.155
 sailor+0.154
Neg logit contributions
oph-0.138
cake-0.136
cakes-0.132
board-0.118
 amusement-0.110
Token Sammy
Token ID44067
Feature activation+1.37e+00

Pos logit contributions
emo+0.051
cker+0.045
eer+0.044
rito+0.043
 sailor+0.042
Neg logit contributions
oph-0.036
cake-0.036
cakes-0.034
board-0.030
 amusement-0.029
Token the
Token ID262
Feature activation+1.64e-01

Pos logit contributions
oph+0.069
cake+0.066
cakes+0.060
board+0.057
That+0.052
Neg logit contributions
emo-0.133
rito-0.114
eer-0.114
cker-0.113
 sailor-0.108
Token.
Token ID13
Feature activation-1.44e-02

Pos logit contributions
emo+0.064
cker+0.054
eer+0.053
 sailor+0.052
fish+0.050
Neg logit contributions
oph-0.071
cake-0.069
cakes-0.069
board-0.060
uct-0.060
Token
Token ID220
Feature activation+2.35e+00

Pos logit contributions
emo+0.001
cker+0.001
eer+0.001
ba+0.001
rito+0.001
Neg logit contributions
cake-0.001
oph-0.001
cakes-0.001
board-0.001
That-0.001
Token
Token ID198
Feature activation-2.06e+00

Pos logit contributions
cake+0.123
cakes+0.120
oph+0.113
That+0.100
uct+0.098
Neg logit contributions
emo-0.211
cker-0.209
 sailor-0.205
eer-0.202
rito-0.194
Token
Token ID198
Feature activation-2.06e+00

Pos logit contributions
cker+0.176
emo+0.176
eer+0.170
 sailor+0.160
 crew+0.159
Neg logit contributions
oph-0.119
cake-0.119
cakes-0.115
board-0.101
That-0.100
TokenN
Token ID45
Feature activation-3.29e+00

Pos logit contributions
emo+0.152
cker+0.125
eer+0.121
 sailor+0.120
ba+0.117
Neg logit contributions
cake-0.158
oph-0.157
cakes-0.155
board-0.140
 amusement-0.133
Tokenemo
Token ID41903
Feature activation-1.44e+01

Pos logit contributions
 Albert+0.039
Albert+0.035
cker+0.035
rito+0.022
 wax+0.021
Neg logit contributions
oph-0.406
board-0.395
cake-0.388
aw-0.370
cakes-0.365
Token was
Token ID373
Feature activation+4.74e-01

Pos logit contributions
emo+1.241
cker+1.081
eer+1.067
 sailor+1.033
rito+1.029
Neg logit contributions
oph-0.886
cake-0.884
cakes-0.855
board-0.766
uct-0.701
Token so
Token ID523
Feature activation+3.87e+00

Pos logit contributions
cake+0.031
oph+0.030
cakes+0.029
 amusement+0.025
uct+0.025
Neg logit contributions
emo-0.039
cker-0.035
eer-0.034
 sailor-0.033
rito-0.032
Token happy
Token ID3772
Feature activation-1.59e+00

Pos logit contributions
cake+0.262
oph+0.245
cakes+0.244
That+0.241
board+0.213
Neg logit contributions
emo-0.284
cker-0.265
eer-0.262
rito-0.255
 sailor-0.242
Token to
Token ID284
Feature activation+1.34e-01

Pos logit contributions
emo+0.142
cker+0.125
eer+0.122
 sailor+0.119
rito+0.118
Neg logit contributions
cake-0.095
oph-0.095
cakes-0.092
board-0.081
 amusement-0.075
Token be
Token ID307
Feature activation-6.12e-01

Pos logit contributions
cake+0.008
cakes+0.007
oph+0.007
board+0.006
 amusement+0.006
Neg logit contributions
emo-0.011
eer-0.010
cker-0.010
rito-0.010
Albert-0.010
Token anxious
Token ID18116
Feature activation-1.56e+00

Pos logit contributions
emo+0.080
cker+0.076
ba+0.072
Albert+0.070
eer+0.070
Neg logit contributions
That-0.040
cake-0.036
 so-0.036
vious-0.035
aw-0.035
Token.
Token ID13
Feature activation+2.62e-02

Pos logit contributions
emo+0.139
cker+0.123
eer+0.117
 sailor+0.116
rito+0.115
Neg logit contributions
cake-0.093
cakes-0.089
oph-0.088
board-0.082
 amusement-0.074
Token
Token ID198
Feature activation-2.01e+00

Pos logit contributions
oph+0.001
cake+0.001
cakes+0.001
board+0.001
uct+0.001
Neg logit contributions
emo-0.002
cker-0.002
eer-0.002
rito-0.002
 sailor-0.002
Token
Token ID198
Feature activation-2.02e+00

Pos logit contributions
cker+0.189
emo+0.185
eer+0.180
rito+0.174
 sailor+0.172
Neg logit contributions
oph-0.099
cake-0.092
cakes-0.089
That-0.082
board-0.080
TokenN
Token ID45
Feature activation-3.24e+00

Pos logit contributions
emo+0.158
cker+0.139
eer+0.137
 sailor+0.130
rito+0.129
Neg logit contributions
oph-0.142
cake-0.141
cakes-0.137
board-0.125
That-0.118
Tokenemo
Token ID41903
Feature activation-1.43e+01

Pos logit contributions
cker+0.050
 Albert+0.048
Albert+0.047
 crew+0.035
rito+0.033
Neg logit contributions
oph-0.388
board-0.373
cake-0.358
aw-0.345
cakes-0.335
Token sw
Token ID1509
Feature activation-5.83e-01

Pos logit contributions
emo+1.293
eer+1.141
rito+1.133
cker+1.122
 sailor+1.099
Neg logit contributions
oph-0.796
cake-0.758
cakes-0.723
board-0.680
That-0.629
Tokenam
Token ID321
Feature activation-4.45e+00

Pos logit contributions
emo+0.044
 sailor+0.040
eer+0.040
rito+0.039
cker+0.039
Neg logit contributions
oph-0.038
cakes-0.035
cake-0.035
board-0.034
aw-0.032
Token away
Token ID1497
Feature activation+1.56e+00

Pos logit contributions
emo+0.360
cker+0.306
eer+0.300
 sailor+0.291
ba+0.288
Neg logit contributions
oph-0.310
cake-0.310
cakes-0.302
board-0.269
uct-0.254
Token from
Token ID422
Feature activation+1.13e+00

Pos logit contributions
cake+0.083
oph+0.078
cakes+0.075
board+0.068
That+0.063
Neg logit contributions
emo-0.143
eer-0.130
cker-0.129
rito-0.123
 sailor-0.122
Token the
Token ID262
Feature activation+1.42e-01

Pos logit contributions
 amusement+0.041
 Tom+0.038
 course+0.036
oph+0.032
 Meg+0.032
Neg logit contributions
emo-0.103
cker-0.102
rito-0.101
oster-0.100
Albert-0.099
Token.
Token ID13
Feature activation+2.10e-02

Pos logit contributions
emo+0.115
cker+0.096
eer+0.095
 sailor+0.092
ba+0.090
Neg logit contributions
cake-0.125
oph-0.125
cakes-0.122
board-0.108
uct-0.103
Token
Token ID220
Feature activation+2.38e+00

Pos logit contributions
oph+0.001
cake+0.001
cakes+0.001
board+0.001
That+0.001
Neg logit contributions
emo-0.002
cker-0.002
eer-0.002
rito-0.002
 sailor-0.002
Token
Token ID198
Feature activation-2.05e+00

Pos logit contributions
cake+0.123
cakes+0.120
oph+0.119
That+0.104
board+0.101
Neg logit contributions
emo-0.212
cker-0.209
eer-0.201
 sailor-0.200
rito-0.196
Token
Token ID198
Feature activation-2.04e+00

Pos logit contributions
emo+0.184
cker+0.181
eer+0.172
rito+0.166
 sailor+0.165
Neg logit contributions
oph-0.112
cake-0.107
cakes-0.105
That-0.093
board-0.092
TokenN
Token ID45
Feature activation-3.25e+00

Pos logit contributions
emo+0.145
cker+0.123
eer+0.120
 sailor+0.115
rito+0.113
Neg logit contributions
cake-0.160
oph-0.159
cakes-0.156
board-0.142
 amusement-0.134
Tokenemo
Token ID41903
Feature activation-1.43e+01

Pos logit contributions
Albert+0.052
 Albert+0.052
cker+0.048
 crew+0.044
rito+0.037
Neg logit contributions
oph-0.380
board-0.366
cake-0.350
aw-0.344
cakes-0.328
Token sw
Token ID1509
Feature activation-5.82e-01

Pos logit contributions
emo+1.285
eer+1.128
cker+1.121
rito+1.113
 sailor+1.088
Neg logit contributions
oph-0.822
cake-0.793
cakes-0.760
board-0.701
That-0.642
Tokenam
Token ID321
Feature activation-4.47e+00

Pos logit contributions
emo+0.044
 sailor+0.040
rito+0.040
eer+0.040
cker+0.039
Neg logit contributions
oph-0.038
cakes-0.035
cake-0.035
board-0.034
aw-0.031
Token up
Token ID510
Feature activation-1.80e+00

Pos logit contributions
emo+0.363
cker+0.308
eer+0.302
 sailor+0.294
ba+0.292
Neg logit contributions
oph-0.311
cake-0.310
cakes-0.302
board-0.269
 amusement-0.255
Token to
Token ID284
Feature activation+1.84e-01

Pos logit contributions
emo+0.149
cker+0.130
eer+0.129
 sailor+0.124
rito+0.124
Neg logit contributions
cake-0.117
oph-0.115
cakes-0.114
board-0.102
 amusement-0.094
Token his
Token ID465
Feature activation-2.66e+00

Pos logit contributions
oph+0.007
 Tom+0.006
 amusement+0.006
 Sophia+0.006
cake+0.006
Neg logit contributions
cker-0.018
rito-0.018
eer-0.017
emo-0.017
oster-0.017
Token caught
Token ID4978
Feature activation+7.75e-01

Pos logit contributions
cake+0.044
oph+0.043
cakes+0.043
board+0.038
uct+0.036
Neg logit contributions
emo-0.043
cker-0.036
eer-0.036
 sailor-0.034
rito-0.034
Token!
Token ID0
Feature activation+5.34e+00

Pos logit contributions
oph+0.063
cake+0.062
cakes+0.061
board+0.054
 amusement+0.052
Neg logit contributions
emo-0.054
cker-0.044
eer-0.044
 sailor-0.042
ba-0.042
Token
Token ID198
Feature activation-2.06e+00

Pos logit contributions
cake+0.351
oph+0.348
cakes+0.340
board+0.303
uct+0.283
Neg logit contributions
emo-0.443
cker-0.390
eer-0.381
 sailor-0.369
ba-0.363
Token
Token ID198
Feature activation-2.05e+00

Pos logit contributions
emo+0.173
cker+0.162
eer+0.159
 sailor+0.153
 crew+0.148
Neg logit contributions
cake-0.127
oph-0.126
cakes-0.121
board-0.110
That-0.106
TokenN
Token ID45
Feature activation-3.25e+00

Pos logit contributions
emo+0.181
cker+0.153
ba+0.148
 sailor+0.148
eer+0.147
Neg logit contributions
oph-0.127
cake-0.127
cakes-0.126
board-0.107
 amusement-0.101
Tokenemo
Token ID41903
Feature activation-1.43e+01

Pos logit contributions
emo+0.172
cker+0.169
 crew+0.166
 sailor+0.162
rito+0.160
Neg logit contributions
oph-0.282
cake-0.265
board-0.258
cakes-0.245
aw-0.228
Token was
Token ID373
Feature activation+5.28e-01

Pos logit contributions
emo+1.117
cker+0.977
eer+0.931
ba+0.911
 sailor+0.896
Neg logit contributions
cake-1.021
oph-1.007
cakes-1.007
board-0.869
 amusement-0.855
Token scared
Token ID12008
Feature activation-1.09e+00

Pos logit contributions
cake+0.036
oph+0.036
cakes+0.035
board+0.031
 amusement+0.029
Neg logit contributions
emo-0.043
cker-0.037
eer-0.036
 sailor-0.035
rito-0.034
Token and
Token ID290
Feature activation+3.36e-01

Pos logit contributions
emo+0.082
eer+0.070
cker+0.069
 sailor+0.069
ba+0.066
Neg logit contributions
oph-0.081
cakes-0.080
cake-0.080
board-0.069
uct-0.066
Token didn
Token ID1422
Feature activation+8.15e-01

Pos logit contributions
cake+0.020
oph+0.019
cakes+0.019
board+0.017
uct+0.017
Neg logit contributions
emo-0.029
eer-0.025
cker-0.025
rito-0.024
 sailor-0.024
Token't
Token ID470
Feature activation-1.27e+00

Pos logit contributions
cake+0.054
oph+0.054
cakes+0.053
board+0.047
uct+0.044
Neg logit contributions
emo-0.067
cker-0.058
eer-0.057
 sailor-0.055
rito-0.054
Token water
Token ID1660
Feature activation-8.65e-01

Pos logit contributions
cake+0.014
oph+0.014
cakes+0.014
board+0.013
 amusement+0.012
Neg logit contributions
emo-0.015
cker-0.013
eer-0.012
rito-0.012
ba-0.012
Token.
Token ID13
Feature activation+2.48e-02

Pos logit contributions
emo+0.055
cker+0.048
eer+0.047
fish+0.045
 sailor+0.044
Neg logit contributions
oph-0.075
cake-0.071
cakes-0.071
uct-0.063
Sarah-0.062
Token
Token ID198
Feature activation-2.02e+00

Pos logit contributions
oph+0.002
cake+0.002
cakes+0.002
board+0.001
That+0.001
Neg logit contributions
emo-0.002
cker-0.002
eer-0.002
rito-0.002
ba-0.002
Token
Token ID198
Feature activation-2.01e+00

Pos logit contributions
cker+0.186
emo+0.182
eer+0.177
rito+0.172
 sailor+0.167
Neg logit contributions
oph-0.104
cake-0.098
cakes-0.095
That-0.086
board-0.084
TokenN
Token ID45
Feature activation-3.23e+00

Pos logit contributions
emo+0.142
cker+0.126
eer+0.124
rito+0.117
 sailor+0.116
Neg logit contributions
oph-0.154
cake-0.152
cakes-0.148
board-0.135
That-0.131
Tokenemo
Token ID41903
Feature activation-1.43e+01

Pos logit contributions
cker+0.042
Albert+0.039
 Albert+0.038
rito+0.028
 crew+0.025
Neg logit contributions
oph-0.400
board-0.383
cake-0.373
cakes-0.355
aw-0.353
Token's
Token ID338
Feature activation+2.40e+00

Pos logit contributions
emo+1.294
cker+1.133
eer+1.118
 sailor+1.085
rito+1.076
Neg logit contributions
oph-0.833
cake-0.832
cakes-0.804
board-0.708
uct-0.652
Token friends
Token ID2460
Feature activation-1.63e+00

Pos logit contributions
cakes+0.151
cake+0.149
oph+0.149
board+0.147
 amusement+0.135
Neg logit contributions
emo-0.172
cker-0.167
rito-0.165
eer-0.157
ba-0.150
Token warned
Token ID7728
Feature activation+2.14e+00

Pos logit contributions
emo+0.113
cker+0.097
 sailor+0.096
ba+0.094
 crew+0.093
Neg logit contributions
cake-0.128
cakes-0.128
oph-0.123
board-0.108
uct-0.104
Token him
Token ID683
Feature activation-2.79e+00

Pos logit contributions
oph+0.151
cake+0.146
cakes+0.143
board+0.129
 amusement+0.123
Neg logit contributions
emo-0.167
cker-0.149
eer-0.144
rito-0.140
 sailor-0.137
Token not
Token ID407
Feature activation-1.22e+00

Pos logit contributions
emo+0.228
cker+0.196
eer+0.193
 sailor+0.187
ba+0.183
Neg logit contributions
cake-0.189
oph-0.189
cakes-0.183
board-0.163
uct-0.154
Token.
Token ID13
Feature activation+4.61e-02

Pos logit contributions
oph+0.497
cake+0.486
cakes+0.477
board+0.415
uct+0.413
Neg logit contributions
emo-0.390
cker-0.335
eer-0.332
 sailor-0.311
fish-0.306
Token
Token ID220
Feature activation+2.42e+00

Pos logit contributions
oph+0.003
cake+0.003
cakes+0.003
board+0.003
uct+0.003
Neg logit contributions
emo-0.004
cker-0.003
eer-0.003
rito-0.003
ba-0.003
Token
Token ID198
Feature activation-2.00e+00

Pos logit contributions
cake+0.113
cakes+0.111
oph+0.105
That+0.097
uct+0.090
Neg logit contributions
cker-0.223
emo-0.223
 sailor-0.218
eer-0.213
rito-0.208
Token
Token ID198
Feature activation-2.00e+00

Pos logit contributions
cker+0.193
emo+0.186
eer+0.185
 crew+0.174
rito+0.173
Neg logit contributions
oph-0.096
cake-0.092
cakes-0.089
That-0.081
board-0.075
TokenN
Token ID45
Feature activation-3.22e+00

Pos logit contributions
emo+0.153
cker+0.135
eer+0.133
rito+0.125
 sailor+0.125
Neg logit contributions
cake-0.142
oph-0.142
cakes-0.138
board-0.125
That-0.119
Tokenemo
Token ID41903
Feature activation-1.43e+01

Pos logit contributions
Albert+0.038
 Albert+0.035
cker+0.035
rito+0.025
 crew+0.025
Neg logit contributions
oph-0.391
board-0.381
cake-0.372
cakes-0.358
aw-0.352
Token asked
Token ID1965
Feature activation-3.33e+00

Pos logit contributions
emo+1.260
cker+1.100
eer+1.099
rito+1.076
 sailor+1.056
Neg logit contributions
oph-0.850
cake-0.831
cakes-0.801
board-0.723
That-0.671
Token the
Token ID262
Feature activation+1.86e-01

Pos logit contributions
emo+0.302
cker+0.296
rito+0.279
eer+0.265
ba+0.262
Neg logit contributions
oph-0.167
cake-0.162
cakes-0.160
board-0.142
 Meg-0.138
Token dolphins
Token ID36798
Feature activation-2.67e+00

Pos logit contributions
cake+0.016
oph+0.016
cakes+0.016
board+0.015
 amusement+0.014
Neg logit contributions
emo-0.011
cker-0.010
eer-0.009
rito-0.009
ba-0.008
Token for
Token ID329
Feature activation+2.33e+00

Pos logit contributions
emo+0.237
cker+0.210
rito+0.204
eer+0.202
 sailor+0.189
Neg logit contributions
cake-0.150
cakes-0.148
oph-0.145
board-0.133
 amusement-0.124
Token help
Token ID1037
Feature activation-2.54e+00

Pos logit contributions
cakes+0.156
cake+0.154
oph+0.150
 amusement+0.145
 course+0.135
Neg logit contributions
emo-0.181
cker-0.160
eer-0.154
rito-0.150
ba-0.143
Tokeno
Token ID78
Feature activation-4.37e+00

Pos logit contributions
emo+0.482
 sailor+0.406
cker+0.406
eer+0.399
 crew+0.384
Neg logit contributions
cake-0.471
oph-0.449
cakes-0.443
board-0.409
That-0.372
Token.
Token ID13
Feature activation+4.23e-02

Pos logit contributions
emo+0.359
cker+0.306
eer+0.303
 sailor+0.295
rito+0.286
Neg logit contributions
cake-0.293
oph-0.284
cakes-0.281
board-0.253
uct-0.235
Token
Token ID198
Feature activation-2.00e+00

Pos logit contributions
cake+0.002
cakes+0.002
oph+0.002
board+0.002
That+0.002
Neg logit contributions
emo-0.004
cker-0.004
eer-0.004
ba-0.003
 sailor-0.003
Token
Token ID198
Feature activation-2.01e+00

Pos logit contributions
emo+0.175
cker+0.173
eer+0.169
rito+0.162
 sailor+0.162
Neg logit contributions
oph-0.108
cake-0.108
cakes-0.105
board-0.094
That-0.090
TokenN
Token ID45
Feature activation-3.23e+00

Pos logit contributions
emo+0.180
cker+0.155
eer+0.150
 sailor+0.149
ba+0.147
Neg logit contributions
cake-0.123
oph-0.122
cakes-0.120
board-0.104
 amusement-0.098
Tokenemo
Token ID41903
Feature activation-1.43e+01

Pos logit contributions
 Albert+0.033
Albert+0.030
 crew+0.029
cker+0.028
 sailor+0.026
Neg logit contributions
oph-0.404
cake-0.395
board-0.392
cakes-0.369
aw-0.361
Token sw
Token ID1509
Feature activation-5.57e-01

Pos logit contributions
emo+1.221
cker+1.050
eer+1.049
 sailor+1.015
rito+1.009
Neg logit contributions
cake-0.884
oph-0.881
cakes-0.851
board-0.780
That-0.705
Tokenam
Token ID321
Feature activation-4.43e+00

Pos logit contributions
emo+0.040
cker+0.035
eer+0.035
 sailor+0.035
rito+0.034
Neg logit contributions
oph-0.041
cake-0.039
cakes-0.039
board-0.036
uct-0.033
Token under
Token ID739
Feature activation-3.23e+00

Pos logit contributions
emo+0.363
cker+0.307
eer+0.301
 sailor+0.293
ba+0.292
Neg logit contributions
oph-0.312
cake-0.307
cakes-0.299
board-0.266
uct-0.254
Token the
Token ID262
Feature activation+1.51e-01

Pos logit contributions
emo+0.330
cker+0.328
eer+0.311
ba+0.310
rito+0.304
Neg logit contributions
oph-0.114
cake-0.113
 amusement-0.104
cakes-0.103
board-0.096
Token blanket
Token ID18447
Feature activation+8.24e-01

Pos logit contributions
cake+0.014
oph+0.014
cakes+0.013
board+0.012
 amusement+0.012
Neg logit contributions
emo-0.009
cker-0.007
eer-0.007
 sailor-0.007
rito-0.006
Token mouths
Token ID28552
Feature activation-1.20e+00

Pos logit contributions
emo+0.248
cker+0.216
ba+0.206
rito+0.203
eer+0.201
Neg logit contributions
oph-0.222
cake-0.221
cakes-0.218
board-0.208
 amusement-0.199
Token!"
Token ID2474
Feature activation+1.87e+00

Pos logit contributions
emo+0.077
cker+0.063
eer+0.062
 sailor+0.059
ba+0.058
Neg logit contributions
oph-0.101
cake-0.100
cakes-0.099
board-0.090
uct-0.086
Token
Token ID198
Feature activation-2.00e+00

Pos logit contributions
cake+0.130
oph+0.129
cakes+0.127
board+0.115
uct+0.106
Neg logit contributions
emo-0.148
cker-0.131
eer-0.127
 sailor-0.122
rito-0.121
Token
Token ID198
Feature activation-2.01e+00

Pos logit contributions
emo+0.165
cker+0.157
eer+0.151
rito+0.145
 sailor+0.143
Neg logit contributions
cake-0.125
oph-0.124
cakes-0.123
board-0.110
That-0.104
TokenN
Token ID45
Feature activation-3.23e+00

Pos logit contributions
emo+0.183
cker+0.153
ba+0.151
 sailor+0.150
eer+0.147
Neg logit contributions
cake-0.122
oph-0.121
cakes-0.118
board-0.103
uct-0.097
Tokenemo
Token ID41903
Feature activation-1.43e+01

Pos logit contributions
cker+0.063
 crew+0.047
 Albert+0.045
 sailor+0.045
emo+0.043
Neg logit contributions
oph-0.386
cake-0.373
board-0.370
cakes-0.354
That-0.347
Token tried
Token ID3088
Feature activation-2.54e+00

Pos logit contributions
emo+1.180
cker+1.016
eer+0.989
 sailor+0.959
ba+0.957
Neg logit contributions
cake-0.963
oph-0.957
cakes-0.939
board-0.821
 amusement-0.788
Token his
Token ID465
Feature activation-2.62e+00

Pos logit contributions
emo+0.223
cker+0.196
eer+0.193
 sailor+0.185
rito+0.184
Neg logit contributions
cake-0.155
oph-0.155
cakes-0.150
board-0.132
 amusement-0.125
Token best
Token ID1266
Feature activation-2.05e+00

Pos logit contributions
emo+0.214
cker+0.208
rito+0.196
eer+0.189
 sailor+0.177
Neg logit contributions
oph-0.151
cake-0.148
cakes-0.148
board-0.136
oga-0.135
Token,
Token ID11
Feature activation-5.77e-01

Pos logit contributions
emo+0.186
cker+0.175
eer+0.165
rito+0.165
oster+0.163
Neg logit contributions
oph-0.099
cake-0.096
board-0.090
cakes-0.088
 amusement-0.080
Token but
Token ID475
Feature activation-6.07e-01

Pos logit contributions
emo+0.050
cker+0.044
eer+0.043
 sailor+0.041
rito+0.041
Neg logit contributions
cake-0.036
oph-0.036
cakes-0.035
board-0.031
 amusement-0.029
Token.
Token ID13
Feature activation+4.23e-02

Pos logit contributions
emo+0.050
cker+0.042
eer+0.042
rito+0.040
 sailor+0.039
Neg logit contributions
oph-0.053
cake-0.051
cakes-0.051
board-0.045
 amusement-0.044
Token
Token ID220
Feature activation+2.41e+00

Pos logit contributions
oph+0.002
cake+0.002
cakes+0.002
board+0.002
That+0.002
Neg logit contributions
cker-0.004
emo-0.004
eer-0.004
rito-0.003
ba-0.003
Token
Token ID198
Feature activation-2.01e+00

Pos logit contributions
cake+0.127
cakes+0.124
oph+0.121
That+0.105
board+0.104
Neg logit contributions
emo-0.215
cker-0.215
 sailor-0.208
eer-0.207
 crew-0.198
Token
Token ID198
Feature activation-2.02e+00

Pos logit contributions
cker+0.188
emo+0.184
eer+0.181
 sailor+0.174
rito+0.172
Neg logit contributions
oph-0.101
cake-0.096
cakes-0.093
That-0.084
board-0.080
TokenN
Token ID45
Feature activation-3.23e+00

Pos logit contributions
emo+0.155
cker+0.141
eer+0.140
rito+0.132
 sailor+0.131
Neg logit contributions
oph-0.140
cake-0.139
cakes-0.134
board-0.122
That-0.120
Tokenemo
Token ID41903
Feature activation-1.43e+01

Pos logit contributions
cker+0.043
 Albert+0.042
Albert+0.042
 crew+0.029
rito+0.028
Neg logit contributions
oph-0.394
board-0.381
cake-0.371
aw-0.355
cakes-0.350
Token's
Token ID338
Feature activation+2.42e+00

Pos logit contributions
emo+1.271
cker+1.111
eer+1.089
 sailor+1.057
ba+1.044
Neg logit contributions
cake-0.867
oph-0.861
cakes-0.842
board-0.735
 amusement-0.685
Token mom
Token ID1995
Feature activation-3.20e-01

Pos logit contributions
oph+0.156
cake+0.150
cakes+0.146
board+0.143
 amusement+0.139
Neg logit contributions
emo-0.185
cker-0.169
rito-0.167
eer-0.161
ba-0.157
Token saw
Token ID2497
Feature activation+2.89e-01

Pos logit contributions
emo+0.023
cker+0.021
eer+0.019
ba+0.019
 sailor+0.019
Neg logit contributions
cake-0.024
oph-0.024
cakes-0.024
board-0.021
 amusement-0.020
Token him
Token ID683
Feature activation-2.79e+00

Pos logit contributions
oph+0.016
cake+0.015
cakes+0.015
board+0.013
That+0.013
Neg logit contributions
emo-0.026
cker-0.025
eer-0.024
rito-0.023
 crew-0.023
Token and
Token ID290
Feature activation+3.20e-01

Pos logit contributions
emo+0.201
cker+0.178
eer+0.173
 sailor+0.168
ba+0.164
Neg logit contributions
oph-0.215
cakes-0.211
cake-0.209
board-0.179
uct-0.166
Token ocean
Token ID9151
Feature activation-2.37e-01

Pos logit contributions
cake+0.011
oph+0.011
cakes+0.011
board+0.009
 amusement+0.009
Neg logit contributions
emo-0.014
cker-0.012
eer-0.011
 sailor-0.011
ba-0.011
Token."
Token ID526
Feature activation-3.56e+00

Pos logit contributions
emo+0.017
cker+0.015
eer+0.015
 sailor+0.014
ba+0.014
Neg logit contributions
oph-0.018
cake-0.018
cakes-0.017
board-0.015
uct-0.015
Token
Token ID198
Feature activation-2.02e+00

Pos logit contributions
emo+0.267
cker+0.223
eer+0.218
 sailor+0.214
ba+0.208
Neg logit contributions
cake-0.263
oph-0.260
cakes-0.258
board-0.232
 amusement-0.219
Token
Token ID198
Feature activation-2.02e+00

Pos logit contributions
emo+0.158
cker+0.137
eer+0.134
 sailor+0.129
rito+0.128
Neg logit contributions
oph-0.142
cake-0.142
cakes-0.138
board-0.124
uct-0.117
TokenN
Token ID45
Feature activation-3.22e+00

Pos logit contributions
emo+0.187
cker+0.161
ba+0.157
 sailor+0.156
Albert+0.153
Neg logit contributions
cakes-0.116
cake-0.115
oph-0.112
board-0.100
uct-0.088
Tokenemo
Token ID41903
Feature activation-1.43e+01

Pos logit contributions
emo+0.201
cker+0.194
 crew+0.194
 sailor+0.187
 sword+0.184
Neg logit contributions
oph-0.253
cake-0.242
board-0.226
cakes-0.222
aw-0.197
Token was
Token ID373
Feature activation+5.56e-01

Pos logit contributions
emo+1.255
cker+1.084
eer+1.071
rito+1.041
 sailor+1.039
Neg logit contributions
oph-0.867
cake-0.861
cakes-0.833
board-0.748
uct-0.691
Token curious
Token ID11040
Feature activation-5.89e-01

Pos logit contributions
cake+0.035
oph+0.034
cakes+0.032
uct+0.030
 amusement+0.029
Neg logit contributions
emo-0.047
cker-0.041
eer-0.040
 sailor-0.039
fish-0.039
Token and
Token ID290
Feature activation+3.81e-01

Pos logit contributions
emo+0.041
eer+0.038
 sailor+0.036
cker+0.036
fish+0.034
Neg logit contributions
oph-0.043
cakes-0.043
cake-0.043
liv-0.037
Tam-0.037
Token wanted
Token ID2227
Feature activation+6.99e-01

Pos logit contributions
cake+0.021
cakes+0.020
oph+0.020
That+0.018
uct+0.018
Neg logit contributions
emo-0.034
eer-0.029
rito-0.029
cker-0.028
ba-0.027
Token to
Token ID284
Feature activation+2.69e-01

Pos logit contributions
cake+0.040
cakes+0.040
oph+0.038
board+0.034
 amusement+0.033
Neg logit contributions
emo-0.063
cker-0.056
eer-0.055
rito-0.053
ba-0.053
Token head
Token ID1182
Feature activation-1.66e+00

Pos logit contributions
oph+0.084
cake+0.084
cakes+0.083
board+0.075
 amusement+0.071
Neg logit contributions
emo-0.064
cker-0.054
eer-0.053
 sailor-0.050
rito-0.049
Token and
Token ID290
Feature activation+4.39e-01

Pos logit contributions
emo+0.116
cker+0.102
eer+0.099
ba+0.096
 sailor+0.095
Neg logit contributions
oph-0.128
cakes-0.122
cake-0.121
board-0.108
 amusement-0.107
Token said
Token ID531
Feature activation+2.37e+00

Pos logit contributions
cake+0.030
cakes+0.030
oph+0.029
board+0.027
 amusement+0.025
Neg logit contributions
emo-0.032
cker-0.029
 sailor-0.029
ba-0.028
 crew-0.027
Token,
Token ID11
Feature activation-4.51e-01

Pos logit contributions
cake+0.148
oph+0.145
cakes+0.144
board+0.126
uct+0.115
Neg logit contributions
emo-0.206
cker-0.181
eer-0.177
 sailor-0.170
rito-0.169
Token "
Token ID366
Feature activation+2.32e+00

Pos logit contributions
emo+0.037
cker+0.031
eer+0.031
 sailor+0.030
ba+0.030
Neg logit contributions
oph-0.030
cake-0.030
cakes-0.029
board-0.026
 amusement-0.025
TokenThat
Token ID2504
Feature activation+9.08e+00

Pos logit contributions
oph+0.121
cake+0.120
cakes+0.119
board+0.106
 amusement+0.100
Neg logit contributions
emo-0.226
cker-0.193
ba-0.187
eer-0.183
 sailor-0.179
Token was
Token ID373
Feature activation+6.25e-01

Pos logit contributions
oph+0.516
cake+0.512
cakes+0.491
uct+0.414
board+0.412
Neg logit contributions
emo-0.843
cker-0.747
eer-0.743
 sailor-0.724
ba-0.701
Token a
Token ID257
Feature activation-2.18e-01

Pos logit contributions
cake+0.043
oph+0.042
cakes+0.042
board+0.037
uct+0.036
Neg logit contributions
emo-0.050
cker-0.043
eer-0.042
 sailor-0.041
ba-0.040
Token terrible
Token ID7818
Feature activation+3.00e+00

Pos logit contributions
emo+0.017
cker+0.014
eer+0.014
ba+0.013
rito+0.013
Neg logit contributions
cake-0.016
oph-0.016
cakes-0.015
board-0.014
 amusement-0.013
Token joke
Token ID9707
Feature activation+3.20e+00

Pos logit contributions
cake+0.208
oph+0.205
cakes+0.200
board+0.186
 amusement+0.172
Neg logit contributions
emo-0.238
cker-0.205
eer-0.197
ba-0.192
rito-0.192
Token!"
Token ID2474
Feature activation+1.92e+00

Pos logit contributions
oph+0.238
cake+0.222
cakes+0.217
uct+0.201
 amusement+0.197
Neg logit contributions
emo-0.240
eer-0.210
cker-0.203
 sailor-0.198
fish-0.195
Token there
Token ID612
Feature activation-1.17e+00

Pos logit contributions
emo+0.038
cker+0.034
eer+0.033
rito+0.032
 sailor+0.031
Neg logit contributions
cake-0.025
cakes-0.025
oph-0.025
board-0.021
That-0.020
Token was
Token ID373
Feature activation+6.46e-01

Pos logit contributions
emo+0.090
cker+0.076
eer+0.076
 sailor+0.074
ba+0.073
Neg logit contributions
oph-0.082
cake-0.081
cakes-0.078
board-0.070
uct-0.068
Token a
Token ID257
Feature activation-2.08e-01

Pos logit contributions
oph+0.055
cake+0.053
cakes+0.050
uct+0.048
board+0.048
Neg logit contributions
emo-0.039
eer-0.032
cker-0.032
 sailor-0.030
rito-0.030
Token big
Token ID1263
Feature activation+1.05e+00

Pos logit contributions
emo+0.015
cker+0.013
eer+0.012
rito+0.012
ba+0.011
Neg logit contributions
cake-0.016
oph-0.016
cakes-0.016
board-0.015
 amusement-0.014
Token books
Token ID3835
Feature activation+2.95e+00

Pos logit contributions
oph+0.082
cake+0.080
cakes+0.079
uct+0.073
That+0.068
Neg logit contributions
emo-0.070
 sailor-0.064
cker-0.062
eer-0.062
 crew-0.058
Tokenhe
Token ID258
Feature activation+7.39e+00

Pos logit contributions
oph+0.196
cakes+0.164
cake+0.152
 amusement+0.145
uki+0.144
Neg logit contributions
emo-0.210
cker-0.202
fish-0.201
 sailor-0.197
eer-0.194
Tokenlf
Token ID1652
Feature activation+1.69e+00

Pos logit contributions
oph+0.518
cake+0.515
cakes+0.501
board+0.445
 amusement+0.425
Neg logit contributions
emo-0.584
cker-0.503
eer-0.493
 sailor-0.478
ba-0.468
Token with
Token ID351
Feature activation+1.16e+00

Pos logit contributions
oph+0.153
cake+0.143
cakes+0.142
uct+0.127
 amusement+0.126
Neg logit contributions
emo-0.097
cker-0.089
eer-0.084
fish-0.080
 sailor-0.078
Token many
Token ID867
Feature activation+2.02e+00

Pos logit contributions
oph+0.088
cake+0.084
cakes+0.079
uct+0.076
board+0.074
Neg logit contributions
emo-0.082
eer-0.073
cker-0.069
 sailor-0.068
 crew-0.067
Token books
Token ID3835
Feature activation+2.94e+00

Pos logit contributions
oph+0.146
cake+0.143
cakes+0.135
uct+0.121
board+0.121
Neg logit contributions
emo-0.149
eer-0.132
cker-0.129
 sailor-0.126
rito-0.123
Token.
Token ID13
Feature activation+1.13e-01

Pos logit contributions
oph+0.273
cake+0.243
cakes+0.242
 amusement+0.227
uct+0.225
Neg logit contributions
emo-0.150
cker-0.134
eer-0.129
fish-0.127
 sailor-0.120
Token makes
Token ID1838
Feature activation-5.74e-01

Pos logit contributions
cake+0.105
cakes+0.101
oph+0.101
board+0.092
That+0.087
Neg logit contributions
emo-0.110
cker-0.093
eer-0.088
rito-0.086
 sailor-0.085
Token mistakes
Token ID10135
Feature activation+5.38e+00

Pos logit contributions
emo+0.042
 sailor+0.034
eer+0.033
cker+0.033
 crew+0.033
Neg logit contributions
cake-0.044
cakes-0.042
oph-0.042
board-0.039
 amusement-0.035
Token!".
Token ID48220
Feature activation+2.71e+00

Pos logit contributions
oph+0.427
cake+0.425
cakes+0.416
board+0.378
uct+0.360
Neg logit contributions
emo-0.370
cker-0.310
eer-0.305
 sailor-0.294
ba-0.287
Token
Token ID198
Feature activation-1.89e+00

Pos logit contributions
oph+0.184
cake+0.183
cakes+0.180
board+0.161
 amusement+0.152
Neg logit contributions
emo-0.213
cker-0.179
eer-0.178
 Albert-0.173
 sailor-0.171
Token
Token ID198
Feature activation-1.88e+00

Pos logit contributions
emo+0.151
cker+0.132
eer+0.129
 sailor+0.123
rito+0.122
Neg logit contributions
cake-0.131
oph-0.130
cakes-0.127
board-0.113
uct-0.107
TokenThis
Token ID1212
Feature activation+7.07e+00

Pos logit contributions
emo+0.147
ba+0.129
Albert+0.126
 sailor+0.120
cker+0.118
Neg logit contributions
oph-0.127
cake-0.126
cakes-0.126
board-0.118
 Meg-0.101
Token made
Token ID925
Feature activation+2.88e+00

Pos logit contributions
cake+0.639
cakes+0.635
oph+0.611
uct+0.561
Tam+0.543
Neg logit contributions
emo-0.373
 sailor-0.333
eer-0.315
cker-0.306
fish-0.303
Token Rob
Token ID3851
Feature activation-4.37e+00

Pos logit contributions
cake+0.199
cakes+0.188
oph+0.185
board+0.178
uct+0.153
Neg logit contributions
emo-0.229
eer-0.192
cker-0.191
ba-0.190
 Albert-0.189
Token the
Token ID262
Feature activation+3.46e-01

Pos logit contributions
emo+0.239
cker+0.186
eer+0.179
 sailor+0.171
rito+0.169
Neg logit contributions
cake-0.414
oph-0.412
cakes-0.405
board-0.377
 amusement-0.356
Token happiest
Token ID49414
Feature activation+5.42e-01

Pos logit contributions
oph+0.030
cakes+0.030
cake+0.030
uct+0.026
board+0.025
Neg logit contributions
emo-0.020
 sailor-0.017
 crew-0.017
cker-0.016
 sword-0.016
Token robot
Token ID9379
Feature activation-1.93e-01

Pos logit contributions
cake+0.041
oph+0.041
cakes+0.040
board+0.036
 amusement+0.034
Neg logit contributions
emo-0.040
cker-0.034
eer-0.033
 sailor-0.032
rito-0.031
Token When
Token ID1649
Feature activation-1.16e+00

Pos logit contributions
emo+0.001
cker+0.001
eer+0.001
 sailor+0.001
ba+0.001
Neg logit contributions
cake-0.001
oph-0.001
cakes-0.001
board-0.001
 amusement-0.001
Token they
Token ID484
Feature activation-7.80e-01

Pos logit contributions
emo+0.085
cker+0.071
 sailor+0.069
eer+0.069
ba+0.066
Neg logit contributions
cake-0.089
oph-0.088
cakes-0.086
board-0.078
uct-0.074
Token reached
Token ID4251
Feature activation-6.62e-01

Pos logit contributions
emo+0.050
ba+0.044
 sailor+0.044
fish+0.041
 crew+0.038
Neg logit contributions
cakes-0.063
cake-0.062
oph-0.057
oga-0.055
board-0.053
Token the
Token ID262
Feature activation+1.73e-01

Pos logit contributions
emo+0.059
cker+0.052
eer+0.051
rito+0.050
ba+0.049
Neg logit contributions
oph-0.039
cake-0.038
cakes-0.037
board-0.033
 amusement-0.032
Token finish
Token ID5461
Feature activation+3.66e+00

Pos logit contributions
oph+0.012
cakes+0.011
cake+0.011
uct+0.010
board+0.010
Neg logit contributions
emo-0.013
 sailor-0.012
cker-0.012
eer-0.012
 crew-0.011
Token line
Token ID1627
Feature activation+7.06e+00

Pos logit contributions
cake+0.247
oph+0.247
cakes+0.239
board+0.209
uct+0.205
Neg logit contributions
emo-0.294
cker-0.254
eer-0.247
 sailor-0.246
 crew-0.236
Token,
Token ID11
Feature activation-5.40e-01

Pos logit contributions
oph+0.548
cake+0.537
cakes+0.521
uct+0.475
That+0.468
Neg logit contributions
emo-0.483
cker-0.399
 sailor-0.385
eer-0.383
ba-0.381
Token the
Token ID262
Feature activation+1.97e-01

Pos logit contributions
emo+0.041
cker+0.034
 sailor+0.033
eer+0.033
ba+0.032
Neg logit contributions
oph-0.040
cake-0.040
cakes-0.039
board-0.035
uct-0.033
Token teacher
Token ID4701
Feature activation+5.95e+00

Pos logit contributions
oph+0.014
cake+0.014
cakes+0.014
board+0.012
uct+0.012
Neg logit contributions
emo-0.015
cker-0.013
eer-0.013
 sailor-0.013
ba-0.012
Token said
Token ID531
Feature activation+2.29e+00

Pos logit contributions
oph+0.400
cake+0.388
cakes+0.382
 amusement+0.334
uct+0.333
Neg logit contributions
emo-0.424
cker-0.398
 sailor-0.386
eer-0.381
fish-0.375
Token,
Token ID11
Feature activation-5.08e-01

Pos logit contributions
oph+0.163
cake+0.162
cakes+0.158
board+0.143
uct+0.135
Neg logit contributions
emo-0.177
cker-0.149
eer-0.147
 sailor-0.145
ba-0.140
Token her
Token ID607
Feature activation+7.73e-01

Pos logit contributions
cakes+0.103
cake+0.103
oph+0.102
board+0.092
uct+0.088
Neg logit contributions
emo-0.082
cker-0.066
 sailor-0.065
eer-0.065
 Albert-0.061
Token face
Token ID1986
Feature activation+3.47e+00

Pos logit contributions
cake+0.038
oph+0.037
cakes+0.036
board+0.033
 amusement+0.028
Neg logit contributions
emo-0.077
cker-0.068
eer-0.066
ba-0.066
rito-0.066
Token,
Token ID11
Feature activation-7.26e-01

Pos logit contributions
oph+0.271
cake+0.262
cakes+0.260
board+0.233
uct+0.227
Neg logit contributions
emo-0.239
cker-0.204
eer-0.199
 sailor-0.195
ba-0.191
Token dreaming
Token ID28368
Feature activation-3.85e+00

Pos logit contributions
emo+0.062
cker+0.054
eer+0.053
 sailor+0.051
ba+0.050
Neg logit contributions
cake-0.046
oph-0.046
cakes-0.045
board-0.040
 amusement-0.037
Token about
Token ID546
Feature activation+1.94e+00

Pos logit contributions
emo+0.369
cker+0.325
eer+0.321
 sailor+0.313
rito+0.309
Neg logit contributions
oph-0.203
cake-0.202
cakes-0.196
board-0.168
 amusement-0.155
Token all
Token ID477
Feature activation+6.43e+00

Pos logit contributions
cake+0.116
oph+0.115
cakes+0.113
board+0.097
 amusement+0.097
Neg logit contributions
emo-0.171
cker-0.151
eer-0.147
rito-0.144
ba-0.140
Token the
Token ID262
Feature activation+2.35e-02

Pos logit contributions
oph+0.464
cake+0.460
cakes+0.447
board+0.403
uct+0.372
Neg logit contributions
emo-0.488
eer-0.423
cker-0.420
 sailor-0.406
rito-0.392
Token cards
Token ID4116
Feature activation+9.36e-01

Pos logit contributions
oph+0.002
cake+0.002
cakes+0.002
board+0.001
 amusement+0.001
Neg logit contributions
emo-0.002
cker-0.002
eer-0.001
rito-0.001
ba-0.001
Token she
Token ID673
Feature activation+5.66e-01

Pos logit contributions
oph+0.063
cake+0.061
cakes+0.059
board+0.053
uct+0.051
Neg logit contributions
emo-0.076
cker-0.066
eer-0.065
 sailor-0.063
fish-0.062
Token would
Token ID561
Feature activation-3.45e+00

Pos logit contributions
cake+0.035
oph+0.035
cakes+0.034
board+0.030
That+0.028
Neg logit contributions
emo-0.050
cker-0.043
eer-0.042
rito-0.041
 sailor-0.040
Token find
Token ID1064
Feature activation-1.48e+00

Pos logit contributions
emo+0.249
cker+0.211
eer+0.206
 sailor+0.198
rito+0.194
Neg logit contributions
cake-0.264
oph-0.264
cakes-0.258
board-0.233
uct-0.221
Token't
Token ID470
Feature activation-1.16e+00

Pos logit contributions
emo+0.168
cker+0.140
eer+0.136
 sailor+0.135
ba+0.134
Neg logit contributions
oph-0.179
cake-0.173
cakes-0.169
board-0.154
 amusement-0.148
Token know
Token ID760
Feature activation-1.35e+00

Pos logit contributions
emo+0.084
cker+0.072
eer+0.069
 sailor+0.065
rito+0.065
Neg logit contributions
cake-0.088
oph-0.088
cakes-0.083
board-0.078
 amusement-0.074
Token,
Token ID11
Feature activation-4.19e-01

Pos logit contributions
emo+0.119
cker+0.102
eer+0.099
rito+0.096
 sailor+0.096
Neg logit contributions
cake-0.084
oph-0.082
cakes-0.082
board-0.072
uct-0.068
Token Lily
Token ID20037
Feature activation+1.39e+00

Pos logit contributions
emo+0.034
 sailor+0.030
eer+0.029
cker+0.028
 crew+0.028
Neg logit contributions
oph-0.028
cake-0.027
cakes-0.027
board-0.024
uct-0.022
Token.
Token ID13
Feature activation+1.65e-01

Pos logit contributions
cake+0.100
oph+0.099
cakes+0.097
board+0.087
 amusement+0.082
Neg logit contributions
emo-0.108
cker-0.092
eer-0.090
 sailor-0.087
rito-0.085
Token Maybe
Token ID6674
Feature activation-3.05e-01

Pos logit contributions
cake+0.009
oph+0.009
cakes+0.009
board+0.008
 amusement+0.007
Neg logit contributions
emo-0.015
cker-0.013
eer-0.013
 sailor-0.013
ba-0.013
Token it
Token ID340
Feature activation-1.78e+00

Pos logit contributions
emo+0.028
rito+0.024
eer+0.024
cker+0.024
oster+0.023
Neg logit contributions
cake-0.017
oph-0.017
cakes-0.017
 amusement-0.015
board-0.014
Token is
Token ID318
Feature activation-3.48e-01

Pos logit contributions
emo+0.157
cker+0.130
 sailor+0.129
eer+0.129
rito+0.126
Neg logit contributions
cake-0.114
cakes-0.112
oph-0.107
board-0.098
uct-0.090
Token under
Token ID739
Feature activation-3.07e+00

Pos logit contributions
emo+0.030
eer+0.027
ba+0.026
cker+0.026
oster+0.025
Neg logit contributions
cake-0.020
oph-0.019
cakes-0.018
uct-0.016
 amusement-0.016
Token the
Token ID262
Feature activation+3.22e-01

Pos logit contributions
emo+0.237
cker+0.202
eer+0.199
 sailor+0.195
rito+0.187
Neg logit contributions
cake-0.220
oph-0.219
cakes-0.215
board-0.192
uct-0.182
Token sofa
Token ID34902
Feature activation+3.84e-01

Pos logit contributions
oph+0.025
cakes+0.023
cake+0.023
uct+0.022
liv+0.021
Neg logit contributions
emo-0.022
 sailor-0.020
eer-0.019
cker-0.019
 lung-0.018
Token to
Token ID284
Feature activation+3.18e-01

Pos logit contributions
cakes+0.136
cake+0.136
oph+0.131
board+0.120
 amusement+0.112
Neg logit contributions
emo-0.210
cker-0.185
eer-0.177
 sailor-0.174
rito-0.172
Token Tim
Token ID5045
Feature activation+2.70e+00

Pos logit contributions
oph+0.020
cake+0.020
cakes+0.019
board+0.017
 amusement+0.017
Neg logit contributions
emo-0.027
cker-0.024
eer-0.024
rito-0.023
ba-0.023
Tokenmy
Token ID1820
Feature activation-6.23e-02

Pos logit contributions
cakes+0.177
cake+0.176
oph+0.170
That+0.137
board+0.137
Neg logit contributions
emo-0.218
cker-0.204
eer-0.199
ba-0.193
 sailor-0.191
Token's
Token ID338
Feature activation+2.51e+00

Pos logit contributions
emo+0.005
cker+0.005
eer+0.005
 sailor+0.004
ba+0.004
Neg logit contributions
oph-0.004
cake-0.004
cakes-0.004
board-0.003
uct-0.003
Token house
Token ID2156
Feature activation+3.42e+00

Pos logit contributions
oph+0.190
cake+0.188
cakes+0.182
board+0.160
uct+0.159
Neg logit contributions
emo-0.187
cker-0.159
eer-0.157
 sailor-0.156
 crew-0.150
Token and
Token ID290
Feature activation+4.38e-01

Pos logit contributions
oph+0.277
cake+0.262
cakes+0.259
uct+0.229
board+0.225
Neg logit contributions
emo-0.227
cker-0.203
eer-0.197
 sailor-0.191
 crew-0.188
Token got
Token ID1392
Feature activation+7.68e-01

Pos logit contributions
oph+0.031
cake+0.031
cakes+0.030
board+0.027
uct+0.026
Neg logit contributions
emo-0.034
cker-0.030
eer-0.029
 sailor-0.028
ba-0.028
Token his
Token ID465
Feature activation-2.51e+00

Pos logit contributions
cakes+0.048
cake+0.048
oph+0.045
board+0.040
 amusement+0.038
Neg logit contributions
emo-0.066
cker-0.059
eer-0.057
rito-0.055
fish-0.054
Token homework
Token ID26131
Feature activation+1.53e+00

Pos logit contributions
emo+0.207
cker+0.175
ba+0.172
eer+0.170
rito+0.169
Neg logit contributions
cakes-0.169
cake-0.167
oph-0.156
board-0.153
 amusement-0.137
Token.
Token ID13
Feature activation+1.40e-01

Pos logit contributions
oph+0.130
cake+0.121
cakes+0.120
uct+0.109
 amusement+0.108
Neg logit contributions
emo-0.097
eer-0.082
cker-0.081
 sailor-0.079
ba-0.077
Token On
Token ID1550
Feature activation-2.51e-01

Pos logit contributions
oph+0.009
cake+0.009
cakes+0.008
board+0.008
 amusement+0.007
Neg logit contributions
emo-0.012
cker-0.010
eer-0.010
 sailor-0.009
rito-0.009
Token.
Token ID13
Feature activation+1.10e-01

Pos logit contributions
oph+0.270
cakes+0.261
cake+0.257
liv+0.236
Aud+0.234
Neg logit contributions
emo-0.128
cker-0.123
fish-0.121
 sailor-0.113
 sail-0.110
Token Inside
Token ID14384
Feature activation-1.66e+00

Pos logit contributions
oph+0.007
cake+0.007
cakes+0.007
board+0.006
 amusement+0.006
Neg logit contributions
emo-0.009
 Albert-0.008
cker-0.008
eer-0.008
 sailor-0.007
Token was
Token ID373
Feature activation+6.32e-01

Pos logit contributions
emo+0.126
cker+0.107
eer+0.104
 sailor+0.103
fish+0.101
Neg logit contributions
cake-0.119
oph-0.116
cakes-0.115
board-0.102
 amusement-0.099
Token a
Token ID257
Feature activation-2.07e-01

Pos logit contributions
cake+0.052
oph+0.051
cakes+0.050
board+0.046
uct+0.045
Neg logit contributions
emo-0.041
cker-0.033
eer-0.033
 sailor-0.033
 crew-0.032
Token small
Token ID1402
Feature activation-3.28e+00

Pos logit contributions
emo+0.015
cker+0.012
eer+0.012
rito+0.011
ba+0.011
Neg logit contributions
cake-0.016
oph-0.016
cakes-0.016
board-0.014
 amusement-0.014
Token,
Token ID11
Feature activation-4.43e-01

Pos logit contributions
emo+0.241
cker+0.208
eer+0.203
 sailor+0.200
rito+0.192
Neg logit contributions
oph-0.242
cake-0.241
cakes-0.238
board-0.210
uct-0.206
Token cute
Token ID13779
Feature activation-2.60e+00

Pos logit contributions
emo+0.028
cker+0.023
eer+0.022
 sailor+0.022
rito+0.021
Neg logit contributions
oph-0.038
cake-0.038
cakes-0.037
board-0.034
uct-0.032
Token puppy
Token ID26188
Feature activation+7.00e-01

Pos logit contributions
emo+0.184
cker+0.155
eer+0.149
ba+0.143
rito+0.143
Neg logit contributions
oph-0.204
cake-0.204
cakes-0.196
board-0.183
 amusement-0.173
Token.
Token ID13
Feature activation+1.45e-01

Pos logit contributions
oph+0.049
cake+0.048
cakes+0.048
board+0.042
uct+0.041
Neg logit contributions
emo-0.055
cker-0.048
eer-0.047
 sailor-0.046
ba-0.045
Token The
Token ID383
Feature activation-1.40e-01

Pos logit contributions
oph+0.009
cake+0.009
cakes+0.009
board+0.008
 amusement+0.008
Neg logit contributions
emo-0.012
 Albert-0.010
eer-0.010
 sailor-0.010
cker-0.010
Token puppy
Token ID26188
Feature activation+7.10e-01

Pos logit contributions
emo+0.010
 sailor+0.008
eer+0.008
cker+0.008
 crew+0.008
Neg logit contributions
oph-0.011
cake-0.011
cakes-0.011
board-0.010
uct-0.010
Token of
Token ID286
Feature activation+2.56e+00

Pos logit contributions
oph+0.348
cake+0.294
cakes+0.290
uct+0.275
Aud+0.275
Neg logit contributions
emo-0.266
fish-0.237
cker-0.236
eer-0.223
 sailor-0.213
Token wood
Token ID4898
Feature activation-6.13e+00

Pos logit contributions
oph+0.208
cake+0.203
cakes+0.193
uct+0.175
board+0.171
Neg logit contributions
emo-0.178
eer-0.150
cker-0.149
 sailor-0.142
rito-0.140
Token near
Token ID1474
Feature activation-2.81e+00

Pos logit contributions
emo+0.391
cker+0.368
eer+0.343
fish+0.338
 sailor+0.315
Neg logit contributions
oph-0.541
cake-0.493
cakes-0.484
uct-0.440
Sarah-0.423
Token the
Token ID262
Feature activation+6.48e-02

Pos logit contributions
emo+0.193
cker+0.165
eer+0.154
ba+0.150
 sailor+0.147
Neg logit contributions
cake-0.237
oph-0.230
cakes-0.229
board-0.208
uct-0.191
Token trees
Token ID7150
Feature activation-7.18e-01

Pos logit contributions
oph+0.005
cake+0.005
cakes+0.005
uct+0.004
liv+0.004
Neg logit contributions
emo-0.005
cker-0.004
eer-0.004
 sailor-0.004
 crew-0.004
Token.
Token ID13
Feature activation-9.69e-02

Pos logit contributions
emo+0.038
cker+0.035
eer+0.031
fish+0.031
ba+0.030
Neg logit contributions
oph-0.070
cakes-0.064
cake-0.064
uct-0.057
board-0.057
Token They
Token ID1119
Feature activation+5.91e-02

Pos logit contributions
emo+0.007
 sailor+0.004
cker+0.004
eer+0.004
 Albert+0.004
Neg logit contributions
oph-0.008
cake-0.008
cakes-0.007
board-0.007
uct-0.007
Token wanted
Token ID2227
Feature activation+5.41e-01

Pos logit contributions
cake+0.005
cakes+0.005
oph+0.005
board+0.005
oga+0.005
Neg logit contributions
emo-0.003
cker-0.003
 sailor-0.003
ba-0.003
 exc-0.003
Token to
Token ID284
Feature activation+7.19e-02

Pos logit contributions
cake+0.035
cakes+0.034
oph+0.034
board+0.030
 amusement+0.028
Neg logit contributions
emo-0.046
cker-0.040
eer-0.039
 sailor-0.038
ba-0.038
Token build
Token ID1382
Feature activation-1.58e+00

Pos logit contributions
oph+0.006
cake+0.006
cakes+0.006
board+0.005
uct+0.005
Neg logit contributions
emo-0.005
cker-0.004
eer-0.004
 sailor-0.004
ba-0.004
Token a
Token ID257
Feature activation-4.58e-01

Pos logit contributions
emo+0.115
cker+0.098
eer+0.094
 sailor+0.091
rito+0.089
Neg logit contributions
oph-0.122
cake-0.121
cakes-0.117
board-0.106
uct-0.100
Token
Token ID198
Feature activation-2.04e+00

Pos logit contributions
emo+0.239
eer+0.177
cker+0.175
 sailor+0.168
ba+0.166
Neg logit contributions
oph-0.295
cake-0.290
cakes-0.280
 amusement-0.265
board-0.254
Token
Token ID198
Feature activation-2.04e+00

Pos logit contributions
emo+0.162
cker+0.143
eer+0.139
 sailor+0.134
rito+0.132
Neg logit contributions
cake-0.141
oph-0.140
cakes-0.138
board-0.123
uct-0.115
TokenL
Token ID43
Feature activation+3.20e+00

Pos logit contributions
emo+0.162
ba+0.139
oster+0.138
cker+0.131
Ar+0.131
Neg logit contributions
oph-0.142
cake-0.134
cakes-0.131
board-0.116
 amusement-0.113
Tokenily
Token ID813
Feature activation+5.46e-01

Pos logit contributions
oph+0.204
cake+0.201
cakes+0.198
 amusement+0.177
board+0.162
Neg logit contributions
emo-0.280
eer-0.233
ba-0.225
cker-0.220
rito-0.217
Token was
Token ID373
Feature activation+4.92e-01

Pos logit contributions
cakes+0.041
cake+0.040
oph+0.039
 amusement+0.036
oga+0.035
Neg logit contributions
emo-0.038
cker-0.034
 sailor-0.031
ba-0.031
eer-0.030
Token disappointed
Token ID11679
Feature activation+2.30e+00

Pos logit contributions
cake+0.036
oph+0.036
cakes+0.035
board+0.031
uct+0.030
Neg logit contributions
emo-0.038
cker-0.032
eer-0.032
 sailor-0.030
rito-0.030
Token but
Token ID475
Feature activation-6.32e-01

Pos logit contributions
cakes+0.162
cake+0.162
oph+0.162
board+0.139
uct+0.134
Neg logit contributions
emo-0.180
cker-0.151
eer-0.149
 sailor-0.149
ba-0.144
Token she
Token ID673
Feature activation+6.20e-01

Pos logit contributions
emo+0.051
cker+0.043
 sailor+0.043
ba+0.042
eer+0.041
Neg logit contributions
cakes-0.043
cake-0.043
oph-0.042
board-0.038
 amusement-0.034
Token remembered
Token ID12086
Feature activation-2.02e+00

Pos logit contributions
cakes+0.045
cake+0.045
oph+0.044
board+0.039
 amusement+0.038
Neg logit contributions
emo-0.047
cker-0.041
 sailor-0.039
ba-0.038
eer-0.038
Token something
Token ID1223
Feature activation+9.94e-01

Pos logit contributions
emo+0.169
cker+0.145
 sailor+0.141
eer+0.141
 crew+0.136
Neg logit contributions
cake-0.134
oph-0.131
cakes-0.131
board-0.116
uct-0.106
Token her
Token ID607
Feature activation+8.13e-01

Pos logit contributions
oph+0.068
cake+0.068
cakes+0.066
board+0.059
 amusement+0.055
Neg logit contributions
emo-0.080
cker-0.069
eer-0.068
 sailor-0.066
rito-0.065
Token to
Token ID284
Feature activation+3.46e-01

Pos logit contributions
cakes+0.095
cake+0.094
oph+0.093
 amusement+0.080
board+0.079
Neg logit contributions
emo-0.151
cker-0.134
rito-0.129
eer-0.128
ba-0.127
Token get
Token ID651
Feature activation-5.69e-01

Pos logit contributions
cake+0.019
oph+0.019
cakes+0.019
 amusement+0.017
ue+0.016
Neg logit contributions
emo-0.031
eer-0.026
cker-0.026
rito-0.026
 crew-0.025
Token lost
Token ID2626
Feature activation-5.85e+00

Pos logit contributions
emo+0.050
cker+0.042
oster+0.042
eer+0.042
rito+0.041
Neg logit contributions
cakes-0.031
cake-0.030
 amusement-0.026
uct-0.025
oph-0.025
Token."
Token ID526
Feature activation-3.43e+00

Pos logit contributions
emo+0.447
cker+0.377
rito+0.348
eer+0.348
ba+0.346
Neg logit contributions
cake-0.409
cakes-0.399
oph-0.395
board-0.366
 amusement-0.352
Token
Token ID198
Feature activation-1.91e+00

Pos logit contributions
emo+0.272
cker+0.235
eer+0.230
 sailor+0.221
rito+0.219
Neg logit contributions
oph-0.241
cake-0.241
cakes-0.235
board-0.210
uct-0.198
Token
Token ID198
Feature activation-1.90e+00

Pos logit contributions
emo+0.169
cker+0.167
eer+0.162
rito+0.156
 sailor+0.154
Neg logit contributions
oph-0.103
cake-0.099
cakes-0.097
That-0.086
board-0.084
TokenThey
Token ID2990
Feature activation+2.25e+00

Pos logit contributions
emo+0.156
cker+0.128
ba+0.127
 sailor+0.126
fish+0.122
Neg logit contributions
cake-0.140
cakes-0.137
oph-0.125
board-0.115
uct-0.111
Token held
Token ID2714
Feature activation-3.60e+00

Pos logit contributions
cake+0.184
cakes+0.179
oph+0.170
board+0.152
oga+0.150
Neg logit contributions
emo-0.147
cker-0.134
ba-0.131
 sailor-0.129
eer-0.124
Token hands
Token ID2832
Feature activation+6.41e-01

Pos logit contributions
emo+0.283
cker+0.244
eer+0.243
 sailor+0.232
rito+0.226
Neg logit contributions
cake-0.258
oph-0.256
cakes-0.248
board-0.222
uct-0.208
Token and
Token ID290
Feature activation+4.51e-01

Pos logit contributions
oph+0.045
cake+0.044
cakes+0.043
board+0.039
uct+0.037
Neg logit contributions
emo-0.050
cker-0.045
eer-0.044
 sailor-0.042
ba-0.041
Token walked
Token ID6807
Feature activation-1.51e+00

Pos logit contributions
cake+0.035
oph+0.034
cakes+0.033
board+0.029
uct+0.028
Neg logit contributions
emo-0.033
cker-0.030
eer-0.028
 sailor-0.028
 crew-0.027
Token he
Token ID339
Feature activation-2.16e+00

Pos logit contributions
cake+0.257
oph+0.256
cakes+0.252
 amusement+0.227
board+0.226
Neg logit contributions
emo-0.294
cker-0.266
eer-0.259
rito-0.258
ba-0.243
Token had
Token ID550
Feature activation+1.57e+00

Pos logit contributions
emo+0.187
cker+0.160
rito+0.154
 sailor+0.153
eer+0.152
Neg logit contributions
cake-0.131
oph-0.128
cakes-0.124
board-0.117
That-0.113
Token a
Token ID257
Feature activation-2.31e-01

Pos logit contributions
oph+0.098
cake+0.096
cakes+0.093
board+0.082
uct+0.078
Neg logit contributions
emo-0.136
cker-0.122
eer-0.119
 sailor-0.114
rito-0.114
Token great
Token ID1049
Feature activation+1.95e-01

Pos logit contributions
emo+0.018
eer+0.016
cker+0.016
ba+0.015
rito+0.015
Neg logit contributions
oph-0.016
cake-0.016
cakes-0.015
 amusement-0.014
board-0.014
Token friend
Token ID1545
Feature activation-2.06e+00

Pos logit contributions
oph+0.015
cake+0.014
cakes+0.014
board+0.013
 amusement+0.012
Neg logit contributions
emo-0.014
cker-0.012
eer-0.012
ba-0.012
rito-0.011
Token in
Token ID287
Feature activation-3.62e+00

Pos logit contributions
emo+0.160
cker+0.138
eer+0.136
 sailor+0.131
ba+0.128
Neg logit contributions
oph-0.146
cake-0.146
cakes-0.143
board-0.127
uct-0.121
Token Billy
Token ID15890
Feature activation+2.64e-01

Pos logit contributions
emo+0.307
cker+0.269
eer+0.259
ba+0.256
rito+0.254
Neg logit contributions
cake-0.223
oph-0.218
cakes-0.212
 amusement-0.196
board-0.196
Token who
Token ID508
Feature activation-4.84e+00

Pos logit contributions
oph+0.012
cake+0.012
cakes+0.011
board+0.010
 amusement+0.009
Neg logit contributions
emo-0.027
cker-0.024
eer-0.023
rito-0.023
 sailor-0.023
Token would
Token ID561
Feature activation-3.31e+00

Pos logit contributions
emo+0.412
cker+0.346
rito+0.340
eer+0.331
 sailor+0.327
Neg logit contributions
cake-0.305
cakes-0.293
oph-0.291
board-0.272
That-0.251
Token always
Token ID1464
Feature activation-5.28e+00

Pos logit contributions
emo+0.241
cker+0.202
eer+0.199
 sailor+0.189
rito+0.187
Neg logit contributions
cake-0.253
oph-0.252
cakes-0.245
board-0.223
 amusement-0.213
Token be
Token ID307
Feature activation-4.80e-01

Pos logit contributions
emo+0.463
eer+0.393
cker+0.383
rito+0.372
ba+0.363
Neg logit contributions
cake-0.314
oph-0.307
cakes-0.288
 amusement-0.279
 course-0.270
Token.
Token ID13
Feature activation+4.04e-02

Pos logit contributions
emo+0.221
cker+0.193
eer+0.182
ba+0.175
rito+0.172
Neg logit contributions
oph-0.266
cake-0.260
cakes-0.257
board-0.237
 amusement-0.227
Token Sue
Token ID26089
Feature activation+3.70e+00

Pos logit contributions
oph+0.003
cake+0.002
cakes+0.002
board+0.002
 amusement+0.002
Neg logit contributions
emo-0.003
cker-0.003
eer-0.003
 sailor-0.003
rito-0.003
Token was
Token ID373
Feature activation+5.48e-01

Pos logit contributions
oph+0.227
cake+0.227
cakes+0.220
board+0.195
uct+0.181
Neg logit contributions
emo-0.324
cker-0.281
eer-0.277
 sailor-0.268
rito-0.265
Token scared
Token ID12008
Feature activation-1.05e+00

Pos logit contributions
cake+0.036
oph+0.036
cakes+0.035
board+0.030
uct+0.030
Neg logit contributions
emo-0.045
cker-0.039
eer-0.038
 sailor-0.036
rito-0.036
Token!
Token ID0
Feature activation+5.43e+00

Pos logit contributions
emo+0.062
eer+0.053
 sailor+0.052
cker+0.051
ba+0.050
Neg logit contributions
oph-0.089
cakes-0.089
cake-0.089
board-0.079
liv-0.077
Token
Token ID198
Feature activation-1.97e+00

Pos logit contributions
oph+0.321
cake+0.311
cakes+0.307
board+0.272
 amusement+0.272
Neg logit contributions
emo-0.479
cker-0.407
eer-0.395
 Albert-0.390
 sailor-0.384
Token
Token ID198
Feature activation-1.96e+00

Pos logit contributions
emo+0.154
cker+0.132
eer+0.130
 sailor+0.125
rito+0.123
Neg logit contributions
cake-0.141
oph-0.140
cakes-0.137
board-0.122
uct-0.116
TokenBut
Token ID1537
Feature activation+3.84e-01

Pos logit contributions
emo+0.129
oster+0.111
cker+0.110
ba+0.103
Albert+0.101
Neg logit contributions
oph-0.154
cakes-0.148
cake-0.144
board-0.139
 amusement-0.132
Token then
Token ID788
Feature activation+2.89e+00

Pos logit contributions
cakes+0.028
cake+0.027
oph+0.027
board+0.026
ives+0.023
Neg logit contributions
emo-0.028
cker-0.026
 sailor-0.024
 Albert-0.024
 crew-0.024
Token,
Token ID11
Feature activation-4.97e-01

Pos logit contributions
cake+0.204
oph+0.199
cakes+0.199
board+0.179
uct+0.167
Neg logit contributions
emo-0.223
cker-0.195
 sailor-0.188
eer-0.186
 crew-0.182
Token the
Token ID262
Feature activation+2.44e-01

Pos logit contributions
emo+0.032
cker+0.028
 sailor+0.027
 Albert+0.027
ba+0.026
Neg logit contributions
oph-0.039
cake-0.039
cakes-0.037
board-0.036
uct-0.032
Token liked
Token ID8288
Feature activation-1.79e+00

Pos logit contributions
emo+0.014
rito+0.013
cker+0.012
 crew+0.012
ba+0.012
Neg logit contributions
cake-0.010
oph-0.009
board-0.009
cakes-0.009
That-0.009
Token to
Token ID284
Feature activation+1.87e-01

Pos logit contributions
emo+0.151
cker+0.133
eer+0.128
rito+0.126
ba+0.125
Neg logit contributions
cake-0.115
cakes-0.114
oph-0.113
board-0.100
 amusement-0.094
Token play
Token ID711
Feature activation+2.24e+00

Pos logit contributions
cake+0.011
cakes+0.011
oph+0.011
board+0.010
 amusement+0.009
Neg logit contributions
emo-0.017
cker-0.014
eer-0.014
rito-0.014
ba-0.014
Token outside
Token ID2354
Feature activation-2.32e+00

Pos logit contributions
cake+0.154
oph+0.153
cakes+0.150
board+0.134
 amusement+0.125
Neg logit contributions
emo-0.180
cker-0.156
eer-0.152
 sailor-0.146
rito-0.145
Token and
Token ID290
Feature activation+2.96e-01

Pos logit contributions
emo+0.179
cker+0.152
eer+0.148
rito+0.143
 sailor+0.142
Neg logit contributions
cake-0.167
oph-0.164
cakes-0.163
board-0.148
 amusement-0.138
Token explore
Token ID7301
Feature activation-9.02e-01

Pos logit contributions
cake+0.018
cakes+0.018
oph+0.017
board+0.016
 amusement+0.015
Neg logit contributions
emo-0.025
rito-0.021
cker-0.021
eer-0.021
ba-0.020
Token.
Token ID13
Feature activation-3.73e-02

Pos logit contributions
emo+0.081
cker+0.072
eer+0.069
rito+0.068
ba+0.067
Neg logit contributions
oph-0.051
cakes-0.051
cake-0.051
board-0.046
 amusement-0.044
Token One
Token ID1881
Feature activation-1.34e-01

Pos logit contributions
emo+0.003
cker+0.003
eer+0.003
 sailor+0.003
ba+0.003
Neg logit contributions
cake-0.002
oph-0.002
cakes-0.002
board-0.002
 amusement-0.002
Token day
Token ID1110
Feature activation-4.56e-02

Pos logit contributions
emo+0.009
cker+0.007
eer+0.007
 sailor+0.007
ba+0.006
Neg logit contributions
cake-0.011
oph-0.011
cakes-0.011
board-0.010
uct-0.010
Token,
Token ID11
Feature activation-6.30e-01

Pos logit contributions
emo+0.004
cker+0.004
eer+0.004
rito+0.004
 sailor+0.004
Neg logit contributions
cake-0.003
oph-0.003
cakes-0.002
board-0.002
That-0.002
Token Tim
Token ID5045
Feature activation+2.52e+00

Pos logit contributions
emo+0.058
cker+0.052
eer+0.051
rito+0.050
 sailor+0.049
Neg logit contributions
cake-0.035
cakes-0.035
oph-0.035
board-0.030
That-0.028
Token he
Token ID339
Feature activation-2.13e+00

Pos logit contributions
emo+0.085
cker+0.071
eer+0.069
rito+0.066
ba+0.065
Neg logit contributions
cake-0.107
oph-0.107
cakes-0.105
board-0.096
 amusement-0.092
Token reached
Token ID4251
Feature activation-5.43e-01

Pos logit contributions
emo+0.185
cker+0.162
eer+0.159
rito+0.153
 sailor+0.152
Neg logit contributions
oph-0.134
cake-0.132
cakes-0.128
board-0.116
 amusement-0.105
Token his
Token ID465
Feature activation-2.50e+00

Pos logit contributions
emo+0.050
cker+0.045
rito+0.043
eer+0.043
ba+0.042
Neg logit contributions
oph-0.031
cake-0.028
cakes-0.027
 amusement-0.026
board-0.025
Token destination
Token ID10965
Feature activation+1.61e+00

Pos logit contributions
emo+0.201
cker+0.173
eer+0.169
 sailor+0.162
rito+0.161
Neg logit contributions
oph-0.173
cake-0.173
cakes-0.168
board-0.151
 amusement-0.143
Token.
Token ID13
Feature activation+1.45e-01

Pos logit contributions
cake+0.116
oph+0.116
cakes+0.114
board+0.102
uct+0.097
Neg logit contributions
emo-0.123
cker-0.105
eer-0.103
 sailor-0.100
ba-0.098
Token He
Token ID679
Feature activation-1.56e+00

Pos logit contributions
cake+0.009
oph+0.009
cakes+0.009
board+0.008
uct+0.008
Neg logit contributions
emo-0.012
cker-0.011
eer-0.010
 sailor-0.010
ba-0.010
Token had
Token ID550
Feature activation+1.63e+00

Pos logit contributions
emo+0.136
cker+0.118
eer+0.116
rito+0.113
 sailor+0.109
Neg logit contributions
oph-0.098
cake-0.095
cakes-0.092
board-0.084
 amusement-0.078
Token a
Token ID257
Feature activation-1.75e-01

Pos logit contributions
cake+0.121
cakes+0.118
oph+0.117
board+0.107
uct+0.098
Neg logit contributions
emo-0.122
eer-0.101
cker-0.101
 sailor-0.100
 crew-0.097
Token great
Token ID1049
Feature activation+2.49e-01

Pos logit contributions
emo+0.013
cker+0.011
eer+0.011
rito+0.010
ba+0.010
Neg logit contributions
oph-0.014
cake-0.013
cakes-0.013
board-0.012
 amusement-0.012
Token visit
Token ID3187
Feature activation-3.94e+00

Pos logit contributions
oph+0.020
cake+0.020
cakes+0.019
board+0.018
 amusement+0.017
Neg logit contributions
emo-0.017
cker-0.014
eer-0.014
ba-0.013
rito-0.013
Token,
Token ID11
Feature activation-4.20e-01

Pos logit contributions
emo+0.317
cker+0.274
eer+0.270
 sailor+0.261
ba+0.256
Neg logit contributions
cake-0.268
oph-0.267
cakes-0.261
board-0.232
uct-0.219
Token day
Token ID1110
Feature activation+1.52e-01

Pos logit contributions
cake+0.054
oph+0.053
cakes+0.053
board+0.049
 amusement+0.045
Neg logit contributions
emo-0.058
cker-0.049
eer-0.047
rito-0.047
ba-0.046
Token,
Token ID11
Feature activation-4.22e-01

Pos logit contributions
oph+0.009
cake+0.009
cakes+0.009
board+0.008
 amusement+0.007
Neg logit contributions
emo-0.013
cker-0.012
eer-0.012
rito-0.011
 sailor-0.011
Token their
Token ID511
Feature activation-1.64e-01

Pos logit contributions
emo+0.032
cker+0.027
eer+0.027
 sailor+0.027
ba+0.026
Neg logit contributions
cake-0.031
oph-0.030
cakes-0.030
board-0.027
uct-0.025
Token mom
Token ID1995
Feature activation-1.75e-01

Pos logit contributions
emo+0.011
cker+0.009
eer+0.009
 sailor+0.009
 crew+0.009
Neg logit contributions
cake-0.013
oph-0.013
cakes-0.013
board-0.012
uct-0.011
Tokenm
Token ID76
Feature activation+1.20e+00

Pos logit contributions
emo+0.012
cker+0.011
ba+0.011
eer+0.011
 sailor+0.010
Neg logit contributions
cake-0.013
oph-0.013
cakes-0.012
 amusement-0.011
uct-0.011
Tokenies
Token ID444
Feature activation-9.24e+00

Pos logit contributions
cake+0.101
oph+0.101
cakes+0.099
board+0.090
 amusement+0.087
Neg logit contributions
emo-0.078
cker-0.065
eer-0.063
 sailor-0.060
ba-0.059
Token and
Token ID290
Feature activation+4.69e-01

Pos logit contributions
emo+0.684
cker+0.597
 sailor+0.582
eer+0.582
ba+0.567
Neg logit contributions
oph-0.655
cake-0.655
cakes-0.639
board-0.565
uct-0.550
Token d
Token ID288
Feature activation-1.16e+00

Pos logit contributions
cake+0.040
oph+0.039
cakes+0.039
board+0.035
uct+0.034
Neg logit contributions
emo-0.030
 sailor-0.025
cker-0.025
eer-0.025
 crew-0.024
Tokenadd
Token ID2860
Feature activation-5.91e+00

Pos logit contributions
emo+0.100
cker+0.087
ba+0.086
eer+0.084
rito+0.082
Neg logit contributions
oph-0.071
cake-0.070
cakes-0.065
 amusement-0.061
board-0.061
Tokenies
Token ID444
Feature activation-9.25e+00

Pos logit contributions
emo+0.363
cker+0.286
 sailor+0.280
eer+0.278
rito+0.267
Neg logit contributions
cake-0.511
oph-0.509
cakes-0.508
board-0.464
uct-0.437
Token said
Token ID531
Feature activation+2.41e+00

Pos logit contributions
emo+0.643
cker+0.567
eer+0.556
 sailor+0.542
ba+0.529
Neg logit contributions
oph-0.712
cake-0.686
cakes-0.667
board-0.603
uct-0.585
Token small
Token ID1402
Feature activation-3.38e+00

Pos logit contributions
emo+0.346
cker+0.346
eer+0.339
oster+0.325
rito+0.318
Neg logit contributions
cake-0.231
cakes-0.230
oph-0.228
 Meg-0.214
That-0.213
Token as
Token ID355
Feature activation-4.36e+00

Pos logit contributions
emo+0.291
cker+0.253
eer+0.245
 sailor+0.240
ba+0.237
Neg logit contributions
cake-0.212
oph-0.210
cakes-0.205
board-0.186
 amusement-0.170
Token a
Token ID257
Feature activation-3.36e-01

Pos logit contributions
emo+0.352
cker+0.328
eer+0.327
rito+0.306
oster+0.299
Neg logit contributions
cake-0.270
cakes-0.269
oph-0.268
 Meg-0.228
 Rebecca-0.228
Token pe
Token ID613
Feature activation-5.30e+00

Pos logit contributions
emo+0.025
cker+0.021
eer+0.021
ba+0.020
rito+0.019
Neg logit contributions
cake-0.025
oph-0.024
cakes-0.023
board-0.022
 amusement-0.021
Tokenb
Token ID65
Feature activation-9.25e+00

Pos logit contributions
emo+0.305
eer+0.210
 sailor+0.210
Ar+0.208
 Albert+0.205
Neg logit contributions
cake-0.455
aw-0.450
board-0.431
uct-0.430
vious-0.424
Tokenble
Token ID903
Feature activation-8.73e+00

Pos logit contributions
emo+0.450
eer+0.333
cker+0.330
 sailor+0.327
Ar+0.313
Neg logit contributions
cake-0.890
board-0.848
cakes-0.843
oph-0.810
oga-0.788
Token can
Token ID460
Feature activation-2.54e+00

Pos logit contributions
emo+0.749
cker+0.642
eer+0.632
 sailor+0.612
rito+0.606
Neg logit contributions
cake-0.555
oph-0.538
cakes-0.536
board-0.484
uct-0.436
Token be
Token ID307
Feature activation-5.71e-01

Pos logit contributions
emo+0.203
eer+0.170
cker+0.170
 sailor+0.164
rito+0.161
Neg logit contributions
cake-0.177
cakes-0.169
oph-0.168
board-0.155
That-0.143
Token valuable
Token ID8119
Feature activation-1.57e-01

Pos logit contributions
emo+0.047
 sailor+0.041
eer+0.041
ba+0.039
Albert+0.039
Neg logit contributions
cake-0.034
cakes-0.033
oph-0.032
board-0.029
aw-0.029
Token and
Token ID290
Feature activation+3.00e-01

Pos logit contributions
emo+0.014
cker+0.013
eer+0.012
 sailor+0.012
ba+0.012
Neg logit contributions
cake-0.009
cakes-0.009
oph-0.008
board-0.008
 amusement-0.007
Token worth
Token ID2861
Feature activation-4.72e+00

Pos logit contributions
cake+0.020
cakes+0.019
oph+0.019
board+0.017
That+0.017
Neg logit contributions
emo-0.025
eer-0.021
cker-0.021
ba-0.020
rito-0.020
Token to
Token ID284
Feature activation+2.78e-01

Pos logit contributions
emo+0.037
cker+0.031
eer+0.030
 sailor+0.030
ba+0.029
Neg logit contributions
oph-0.040
cake-0.039
cakes-0.039
board-0.034
uct-0.033
Token the
Token ID262
Feature activation+2.31e-01

Pos logit contributions
oph+0.014
cake+0.014
 amusement+0.013
cakes+0.013
 Meg+0.013
Neg logit contributions
emo-0.026
cker-0.022
eer-0.022
rito-0.022
ba-0.022
Token edge
Token ID5743
Feature activation+2.08e+00

Pos logit contributions
cakes+0.017
oph+0.017
cake+0.017
board+0.015
uct+0.014
Neg logit contributions
emo-0.017
cker-0.015
 sailor-0.015
eer-0.014
 crew-0.014
Token of
Token ID286
Feature activation+2.73e+00

Pos logit contributions
oph+0.128
cake+0.125
cakes+0.123
board+0.102
uct+0.102
Neg logit contributions
emo-0.182
cker-0.164
eer-0.159
 sailor-0.153
fish-0.150
Token the
Token ID262
Feature activation+2.63e-01

Pos logit contributions
oph+0.162
cake+0.161
cakes+0.154
board+0.137
 amusement+0.136
Neg logit contributions
emo-0.240
cker-0.208
eer-0.204
ba-0.200
rito-0.197
Token Root
Token ID20410
Feature activation-9.30e+00

Pos logit contributions
cake+0.019
oph+0.019
cakes+0.018
board+0.016
uct+0.015
Neg logit contributions
emo-0.021
cker-0.018
eer-0.017
 sailor-0.017
rito-0.016
Token tree
Token ID5509
Feature activation+3.15e+00

Pos logit contributions
emo+0.861
eer+0.693
rito+0.686
cker+0.684
 sailor+0.682
Neg logit contributions
oph-0.544
cake-0.531
cakes-0.497
board-0.480
 amusement-0.426
Token.
Token ID13
Feature activation+1.12e-01

Pos logit contributions
oph+0.236
cake+0.231
cakes+0.230
board+0.199
uct+0.193
Neg logit contributions
emo-0.229
cker-0.207
eer-0.195
 sailor-0.188
fish-0.184
Token The
Token ID383
Feature activation-1.73e-01

Pos logit contributions
cake+0.006
oph+0.006
cakes+0.006
board+0.005
That+0.005
Neg logit contributions
emo-0.010
cker-0.009
eer-0.009
ba-0.009
fish-0.009
Token rabbit
Token ID22746
Feature activation-9.66e-02

Pos logit contributions
emo+0.011
cker+0.009
eer+0.009
 sailor+0.009
rito+0.009
Neg logit contributions
oph-0.015
cake-0.015
cakes-0.014
board-0.013
uct-0.012
Token wanted
Token ID2227
Feature activation+7.58e-01

Pos logit contributions
emo+0.008
cker+0.007
eer+0.006
 sailor+0.006
ba+0.006
Neg logit contributions
cake-0.007
oph-0.007
cakes-0.007
board-0.006
 amusement-0.005
Token me
Token ID502
Feature activation+1.42e+00

Pos logit contributions
oph+0.058
cake+0.055
cakes+0.053
board+0.045
 amusement+0.043
Neg logit contributions
emo-0.124
cker-0.112
eer-0.106
 sailor-0.104
rito-0.103
Token?"
Token ID1701
Feature activation-4.01e+00

Pos logit contributions
cake+0.112
oph+0.111
cakes+0.108
board+0.099
 amusement+0.094
Neg logit contributions
emo-0.101
cker-0.085
eer-0.082
rito-0.077
 sailor-0.076
Token
Token ID198
Feature activation-1.87e+00

Pos logit contributions
emo+0.341
cker+0.306
eer+0.292
 sailor+0.283
rito+0.277
Neg logit contributions
cake-0.260
oph-0.251
cakes-0.251
board-0.222
That-0.210
Token
Token ID198
Feature activation-1.88e+00

Pos logit contributions
emo+0.165
cker+0.156
eer+0.149
 sailor+0.142
rito+0.138
Neg logit contributions
cake-0.111
oph-0.107
cakes-0.106
That-0.096
board-0.090
TokenFl
Token ID7414
Feature activation-4.13e+00

Pos logit contributions
emo+0.148
cker+0.125
eer+0.122
ba+0.121
 sailor+0.120
Neg logit contributions
oph-0.134
cake-0.133
cakes-0.130
board-0.117
 amusement-0.109
Tokenuffy
Token ID15352
Feature activation-7.76e+00

Pos logit contributions
emo+0.260
eer+0.214
 sailor+0.213
cker+0.209
rito+0.200
Neg logit contributions
oph-0.351
cake-0.350
cakes-0.338
board-0.319
ue-0.305
Token was
Token ID373
Feature activation+6.95e-01

Pos logit contributions
emo+0.632
cker+0.551
eer+0.539
 sailor+0.527
ba+0.523
Neg logit contributions
cake-0.510
cakes-0.504
oph-0.500
board-0.434
 amusement-0.417
Token so
Token ID523
Feature activation+4.09e+00

Pos logit contributions
cake+0.036
oph+0.036
cakes+0.035
board+0.030
uct+0.028
Neg logit contributions
emo-0.067
cker-0.059
eer-0.058
 sailor-0.057
rito-0.056
Token happy
Token ID3772
Feature activation-1.35e+00

Pos logit contributions
cake+0.281
oph+0.274
cakes+0.262
That+0.245
uct+0.233
Neg logit contributions
emo-0.321
cker-0.289
eer-0.280
rito-0.271
 crew-0.263
Token.
Token ID13
Feature activation+1.81e-01

Pos logit contributions
emo+0.103
 sailor+0.087
cker+0.087
eer+0.087
fish+0.085
Neg logit contributions
oph-0.096
cake-0.095
cakes-0.094
board-0.082
uct-0.080
Token It
Token ID632
Feature activation+2.90e-01

Pos logit contributions
cake+0.011
oph+0.011
cakes+0.011
board+0.009
uct+0.009
Neg logit contributions
emo-0.016
cker-0.014
eer-0.014
 sailor-0.013
rito-0.013
Token was
Token ID373
Feature activation+6.77e-01

Pos logit contributions
emo+0.098
cker+0.087
eer+0.085
 sailor+0.082
rito+0.082
Neg logit contributions
oph-0.070
cake-0.070
cakes-0.068
board-0.061
uct-0.056
Token a
Token ID257
Feature activation-1.60e-01

Pos logit contributions
oph+0.044
cake+0.043
cakes+0.042
board+0.037
 amusement+0.036
Neg logit contributions
emo-0.056
cker-0.050
eer-0.048
rito-0.047
ba-0.046
Token shy
Token ID15800
Feature activation-3.01e+00

Pos logit contributions
emo+0.012
cker+0.011
eer+0.011
rito+0.011
eers+0.010
Neg logit contributions
oph-0.011
cake-0.011
cakes-0.010
That-0.010
board-0.009
Token little
Token ID1310
Feature activation-2.71e+00

Pos logit contributions
emo+0.225
cker+0.197
rito+0.180
ba+0.179
eer+0.175
Neg logit contributions
cake-0.220
oph-0.220
cakes-0.204
board-0.201
 amusement-0.181
Token tw
Token ID665
Feature activation-2.76e+00

Pos logit contributions
emo+0.221
cker+0.189
eer+0.180
rito+0.180
ba+0.174
Neg logit contributions
cake-0.182
oph-0.181
cakes-0.174
board-0.161
 amusement-0.150
Tokenig
Token ID328
Feature activation-8.23e+00

Pos logit contributions
emo+0.186
eer+0.158
cker+0.151
rito+0.149
 crew+0.146
Neg logit contributions
oph-0.217
cake-0.204
cakes-0.201
board-0.196
aw-0.194
Token.
Token ID13
Feature activation+1.63e-01

Pos logit contributions
emo+0.612
eer+0.497
cker+0.494
rito+0.484
 sailor+0.481
Neg logit contributions
cake-0.611
oph-0.598
cakes-0.595
board-0.554
uct-0.500
Token It
Token ID632
Feature activation+2.86e-01

Pos logit contributions
cake+0.010
oph+0.009
cakes+0.009
board+0.008
 amusement+0.007
Neg logit contributions
emo-0.015
cker-0.013
eer-0.013
 sailor-0.012
rito-0.012
Token wanted
Token ID2227
Feature activation+8.19e-01

Pos logit contributions
cake+0.015
oph+0.014
cakes+0.014
That+0.013
board+0.013
Neg logit contributions
emo-0.027
cker-0.024
eer-0.023
rito-0.023
 crew-0.023
Token to
Token ID284
Feature activation+3.62e-01

Pos logit contributions
cake+0.045
oph+0.044
cakes+0.044
board+0.038
 amusement+0.037
Neg logit contributions
emo-0.076
cker-0.070
eer-0.066
rito-0.065
ba-0.064
Token be
Token ID307
Feature activation-3.84e-01

Pos logit contributions
cake+0.025
oph+0.025
cakes+0.025
board+0.022
 amusement+0.021
Neg logit contributions
emo-0.028
cker-0.024
eer-0.024
rito-0.023
 sailor-0.023