TOP ACTIVATIONS
MAX = 13.746

quickly checked for a fire extingu isher , but there wasn
. She grabbed the fire extingu isher and put out the
dolls and pretend they were mer maid s or pirates .
. The strong mer maid thought about the promise
They both skipped and jumped mer rily as they made their
, and she wanted the mer maid to come too .
she was finished , the mer maid thanked her for coming
They had never seen a mer maid before .
S ki pping mer rily along , Hawk came
castle so much . The mer maid said , " I
" And I 'm a mer maid !" Lily said .
passport belonged to a magical mer maid who had been visiting
. The more , the mer rier . Come to my
it was time for the mer maid to return home .
Jack asked the mer maid why the waves were
. " I am a mer maid . Do you want
so happy and thanked the mer maid many times . With
bed . She dreamed of mer maid s and pirates ,
Let 's pretend we are mer maid s and swim in
many more adventures with the mer maid . The

MIN ACTIVATIONS
MIN = -15.681

her hair in a pony tail so she could look pretty
, Emma decided a pony tail wasn 't so important after
with glasses and a pony tail . She is reading a
cars and the cr ay ons and make something nice ."
. The melted cr ay ons have made a beautiful pattern
day , the cr ay ons wanted to know which one
. We used cr ay ons and markers to draw pictures
his paper and cr ay ons back . He wants his
are papers and cr ay ons and stickers and glue .
line with the cr ay ons . Then , they drew
her diary and cr ay ons . She put them in
took out some cr ay ons and paper , and she
. She used cr ay ons of different colors . She
would spend their after no ons in the shade together .
car with his cr ay ons , but he didn 't
many colors of cr ay ons . She likes red and
a box of cr ay ons and a sketch book .
job organizing your cr ay ons by color ," she said
a box of cr ay ons and some paper . Tim
new box of cr ay ons . She was so excited

INTERVAL 6.389 - 13.746
CONTAINS 1.406%

bar ks . He scares them . " Go
coin . " Hey , that 's our coin
and encouraged him to never stop being creative .
She decided to pull it out of the grass and it
! Can 't we keep them all ?" Her

INTERVAL -0.968 - 6.389
CONTAINS 66.687%

to Lily and asked , " What 's wrong , Lily
played together all day long . And they never had to
, " Sure , Anna . He likes that . His
. They rushed off , eager to find the treasure .
look for you ." Tim my ran to

INTERVAL -8.324 - -0.968
CONTAINS 31.740%

again , you can have some toast , â € said
a ball for him . Her dog was very fast and
back to his dad . He started to cry .
Lily and hugs her . She is bleeding and hurt .
wanted to make her feel better . So , he brought

INTERVAL -15.681 - -8.324
CONTAINS 0.168%

on the floor and the pages got torn .
can reveal a solution . From that day on , Benny
flips . Every day he practiced his moves . One day
of old papers and envelop es . They take turns to
She loved to play with puzzles . One day , she
Token quickly
Token ID2952
Feature activation-4.72e+00

Pos logit contributions
ons+0.154
bes+0.122
ages+0.115
on+0.110
con+0.109
Neg logit contributions
ksh-0.099
 flood-0.098
rant-0.097
 dolphin-0.095
 whale-0.093
Token checked
Token ID10667
Feature activation+1.94e+00

Pos logit contributions
ons+0.370
bes+0.293
ages+0.277
on+0.263
con+0.260
Neg logit contributions
ksh-0.249
 flood-0.248
rant-0.248
 dolphin-0.239
 whale-0.235
Token for
Token ID329
Feature activation+2.25e+00

Pos logit contributions
rant+0.099
 coming+0.097
 flood+0.094
 dolphin+0.093
 whale+0.093
Neg logit contributions
ons-0.150
bes-0.129
ages-0.122
seek-0.114
con-0.111
Token a
Token ID257
Feature activation-8.58e-01

Pos logit contributions
 flood+0.126
 coming+0.122
rant+0.121
 dolphin+0.118
 whale+0.118
Neg logit contributions
ons-0.168
bes-0.136
ages-0.131
con-0.121
seek-0.119
Token fire
Token ID2046
Feature activation+6.25e+00

Pos logit contributions
ons+0.063
ages+0.047
bes+0.047
on+0.047
con+0.046
Neg logit contributions
ksh-0.051
rant-0.049
iet-0.046
 dolphin-0.043
 flood-0.043
Token extingu
Token ID24995
Feature activation+1.29e+01

Pos logit contributions
ksh+0.408
rant+0.402
iet+0.393
ackers+0.372
ust+0.372
Neg logit contributions
ons-0.396
ages-0.316
con-0.290
es-0.289
bes-0.282
Tokenisher
Token ID4828
Feature activation+1.90e-01

Pos logit contributions
ksh+0.684
 flood+0.659
 dolphin+0.659
 ending+0.644
rant+0.643
Neg logit contributions
ons-1.038
aid-0.768
on-0.733
ages-0.730
bes-0.727
Token,
Token ID11
Feature activation+1.17e-01

Pos logit contributions
ksh+0.012
rant+0.011
 flood+0.011
 dolphin+0.011
 whale+0.011
Neg logit contributions
ons-0.014
bes-0.010
ages-0.010
on-0.009
es-0.009
Token but
Token ID475
Feature activation+5.49e+00

Pos logit contributions
ksh+0.005
rant+0.004
 flood+0.004
 dolphin+0.004
iet+0.004
Neg logit contributions
ons-0.011
bes-0.009
ages-0.009
on-0.008
con-0.008
Token there
Token ID612
Feature activation+1.48e+00

Pos logit contributions
 flood+0.334
rant+0.327
ksh+0.324
 dolphin+0.322
 coming+0.322
Neg logit contributions
ons-0.388
bes-0.308
ages-0.285
con-0.266
seek-0.263
Token wasn
Token ID2492
Feature activation+3.75e+00

Pos logit contributions
ksh+0.079
 flood+0.077
rant+0.077
 dolphin+0.075
 whale+0.074
Neg logit contributions
ons-0.115
bes-0.091
ages-0.087
on-0.082
con-0.081
Token.
Token ID13
Feature activation+3.37e-01

Pos logit contributions
ksh+0.059
rant+0.058
 flood+0.057
 whale+0.055
 dolphin+0.055
Neg logit contributions
ons-0.068
bes-0.053
ages-0.050
es-0.047
on-0.047
Token She
Token ID1375
Feature activation-1.72e+00

Pos logit contributions
ksh+0.018
rant+0.017
 ending+0.017
 flood+0.017
 beginning+0.017
Neg logit contributions
ons-0.027
bes-0.021
ages-0.019
aid-0.019
on-0.019
Token grabbed
Token ID13176
Feature activation+8.96e-01

Pos logit contributions
ons+0.141
bes+0.112
ages+0.107
on+0.102
con+0.100
Neg logit contributions
ksh-0.086
rant-0.085
 flood-0.085
 dolphin-0.083
 whale-0.081
Token the
Token ID262
Feature activation-9.73e-01

Pos logit contributions
rant+0.048
 flood+0.047
ksh+0.046
 dolphin+0.046
 coming+0.045
Neg logit contributions
ons-0.069
bes-0.056
ages-0.055
seek-0.052
con-0.050
Token fire
Token ID2046
Feature activation+6.04e+00

Pos logit contributions
ons+0.085
bes+0.068
ages+0.066
on+0.064
con+0.062
Neg logit contributions
ksh-0.044
rant-0.042
iet-0.039
 dolphin-0.039
 flood-0.038
Token extingu
Token ID24995
Feature activation+1.27e+01

Pos logit contributions
ksh+0.324
rant+0.320
 flood+0.314
 dolphin+0.307
 whale+0.298
Neg logit contributions
ons-0.467
bes-0.367
ages-0.359
on-0.335
es-0.333
Tokenisher
Token ID4828
Feature activation-2.37e-02

Pos logit contributions
ksh+0.570
 flood+0.566
rant+0.558
 dolphin+0.545
 whale+0.528
Neg logit contributions
ons-1.106
bes-0.880
ages-0.853
on-0.813
aid-0.807
Token and
Token ID290
Feature activation-2.81e-02

Pos logit contributions
ons+0.002
bes+0.002
ages+0.002
aid+0.001
con+0.001
Neg logit contributions
 flood-0.001
ksh-0.001
rant-0.001
 coming-0.001
 dolphin-0.001
Token put
Token ID1234
Feature activation+1.17e+00

Pos logit contributions
ons+0.002
bes+0.002
seek+0.002
ages+0.002
con+0.002
Neg logit contributions
 flood-0.001
 dolphin-0.001
 coming-0.001
ksh-0.001
 whale-0.001
Token out
Token ID503
Feature activation+6.83e+00

Pos logit contributions
rant+0.062
ksh+0.061
 flood+0.060
 coming+0.060
 dolphin+0.058
Neg logit contributions
ons-0.088
bes-0.071
ages-0.070
seek-0.066
con-0.064
Token the
Token ID262
Feature activation-9.34e-01

Pos logit contributions
 flood+0.372
rant+0.372
 coming+0.366
ksh+0.364
 dolphin+0.360
Neg logit contributions
ons-0.506
bes-0.410
ages-0.400
con-0.369
seek-0.366
Token dolls
Token ID36062
Feature activation-6.51e+00

Pos logit contributions
ons+0.067
bes+0.052
ages+0.050
on+0.047
con+0.047
Neg logit contributions
ksh-0.051
 flood-0.050
rant-0.050
 dolphin-0.049
 whale-0.048
Token and
Token ID290
Feature activation+2.14e-01

Pos logit contributions
ons+0.534
bes+0.415
ages+0.406
con+0.387
aid+0.379
Neg logit contributions
rant-0.324
ksh-0.324
 flood-0.319
 dolphin-0.310
 coming-0.306
Token pretend
Token ID16614
Feature activation+1.89e+00

Pos logit contributions
 flood+0.010
ksh+0.010
rant+0.010
 dolphin+0.009
 whale+0.009
Neg logit contributions
ons-0.018
bes-0.015
ages-0.014
on-0.014
con-0.013
Token they
Token ID484
Feature activation+3.31e+00

Pos logit contributions
ksh+0.126
rant+0.123
 flood+0.121
 dolphin+0.117
 whale+0.116
Neg logit contributions
ons-0.128
bes-0.095
ages-0.089
on-0.084
es-0.082
Token were
Token ID547
Feature activation+1.27e+00

Pos logit contributions
ksh+0.192
rant+0.179
 flood+0.179
 dolphin+0.176
 whale+0.174
Neg logit contributions
ons-0.256
bes-0.198
ages-0.187
es-0.187
on-0.178
Token mer
Token ID4017
Feature activation+1.26e+01

Pos logit contributions
ksh+0.073
rant+0.070
 flood+0.067
 whale+0.064
 dolphin+0.064
Neg logit contributions
ons-0.096
bes-0.075
ages-0.072
es-0.069
on-0.068
Tokenmaid
Token ID23151
Feature activation+8.06e+00

Pos logit contributions
 ending+0.533
 flood+0.532
 storm+0.499
 coming+0.464
Why+0.462
Neg logit contributions
ons-1.014
bes-0.950
es-0.910
ages-0.895
aged-0.850
Tokens
Token ID82
Feature activation-3.01e+00

Pos logit contributions
 flood+0.569
rant+0.565
ksh+0.551
 ending+0.544
 tide+0.532
Neg logit contributions
ons-0.503
ages-0.358
bes-0.357
es-0.354
on-0.318
Token or
Token ID393
Feature activation+3.72e+00

Pos logit contributions
ons+0.199
bes+0.152
ages+0.144
es+0.141
on+0.135
Neg logit contributions
ksh-0.196
rant-0.191
 flood-0.190
 dolphin-0.182
 whale-0.180
Token pirates
Token ID27516
Feature activation+4.37e+00

Pos logit contributions
ksh+0.202
rant+0.198
 flood+0.195
 dolphin+0.186
 whale+0.184
Neg logit contributions
ons-0.290
bes-0.229
ages-0.219
on-0.206
con-0.203
Token.
Token ID13
Feature activation+6.96e-01

Pos logit contributions
ksh+0.240
rant+0.236
 flood+0.235
 dolphin+0.228
 whale+0.224
Neg logit contributions
ons-0.334
bes-0.262
ages-0.251
on-0.235
con-0.232
Token.
Token ID13
Feature activation+6.09e-01

Pos logit contributions
ksh+0.019
rant+0.019
 flood+0.019
 dolphin+0.018
 whale+0.018
Neg logit contributions
ons-0.022
bes-0.017
ages-0.017
on-0.016
es-0.015
Token
Token ID220
Feature activation-3.59e+00

Pos logit contributions
ksh+0.032
 dolphin+0.029
rant+0.029
 flood+0.029
Why+0.029
Neg logit contributions
ons-0.048
bes-0.039
ages-0.037
aid-0.035
igs-0.034
Token
Token ID198
Feature activation+2.14e-01

Pos logit contributions
ons+0.267
bes+0.213
ages+0.206
con+0.192
seek+0.189
Neg logit contributions
ksh-0.191
rant-0.186
 flood-0.179
 coming-0.179
 dolphin-0.176
TokenThe
Token ID464
Feature activation-1.12e+00

Pos logit contributions
Why+0.009
 dolphin+0.009
rant+0.009
iet+0.009
 coming+0.009
Neg logit contributions
ons-0.017
ages-0.015
bes-0.014
aces-0.013
igs-0.013
Token strong
Token ID1913
Feature activation-2.81e+00

Pos logit contributions
ons+0.103
bes+0.088
on+0.082
aid+0.081
seek+0.078
Neg logit contributions
ksh-0.047
 extingu-0.038
rant-0.037
OO-0.033
king-0.032
Token mer
Token ID4017
Feature activation+1.26e+01

Pos logit contributions
ons+0.209
bes+0.162
on+0.152
es+0.144
 exclaimed+0.144
Neg logit contributions
ksh-0.174
 extingu-0.147
rant-0.140
 flood-0.137
ISE-0.134
Tokenmaid
Token ID23151
Feature activation+8.03e+00

Pos logit contributions
 flood+0.468
ksh+0.449
 extingu+0.386
rant+0.377
 coming+0.377
Neg logit contributions
ons-1.153
bes-1.020
es-0.971
ages-0.961
aged-0.924
Token thought
Token ID1807
Feature activation-1.19e+00

Pos logit contributions
ksh+0.411
 dolphin+0.407
rant+0.407
 flood+0.407
 whale+0.402
Neg logit contributions
ons-0.636
bes-0.509
ages-0.480
on-0.456
con-0.453
Token about
Token ID546
Feature activation+2.87e+00

Pos logit contributions
ons+0.092
bes+0.073
ages+0.070
on+0.065
con+0.064
Neg logit contributions
ksh-0.065
rant-0.064
 flood-0.064
 dolphin-0.062
 whale-0.061
Token the
Token ID262
Feature activation-6.75e-01

Pos logit contributions
ksh+0.148
 flood+0.147
rant+0.146
 dolphin+0.145
 whale+0.142
Neg logit contributions
ons-0.227
bes-0.181
ages-0.176
on-0.162
con-0.161
Token promise
Token ID6991
Feature activation-1.24e+00

Pos logit contributions
ons+0.046
 skills+0.037
bes+0.036
powers+0.035
 friends+0.035
Neg logit contributions
ksh-0.038
rant-0.036
 extingu-0.034
ount-0.031
OO-0.031
TokenThey
Token ID2990
Feature activation+1.58e+00

Pos logit contributions
 dolphin+0.010
Why+0.010
iet+0.010
Can+0.010
 whale+0.009
Neg logit contributions
ons-0.016
aces-0.013
bes-0.013
con-0.013
ages-0.012
Token both
Token ID1111
Feature activation+7.03e-01

Pos logit contributions
ksh+0.079
rant+0.079
 flood+0.078
 dolphin+0.076
 whale+0.074
Neg logit contributions
ons-0.128
bes-0.104
ages-0.098
con-0.093
seek-0.092
Token skipped
Token ID26684
Feature activation-4.13e+00

Pos logit contributions
ksh+0.042
rant+0.041
 flood+0.041
 dolphin+0.039
 whale+0.039
Neg logit contributions
ons-0.051
bes-0.039
ages-0.038
on-0.035
con-0.035
Token and
Token ID290
Feature activation+2.33e-01

Pos logit contributions
ons+0.351
bes+0.281
ages+0.270
on+0.254
con+0.251
Neg logit contributions
ksh-0.197
 flood-0.195
rant-0.194
 dolphin-0.191
 mate-0.183
Token jumped
Token ID11687
Feature activation+1.45e+00

Pos logit contributions
 flood+0.010
 dolphin+0.010
ksh+0.010
rant+0.009
 coming+0.009
Neg logit contributions
ons-0.019
bes-0.016
ages-0.016
powers-0.015
aid-0.015
Token mer
Token ID4017
Feature activation+1.26e+01

Pos logit contributions
ksh+0.083
rant+0.081
 flood+0.080
 dolphin+0.078
 whale+0.077
Neg logit contributions
ons-0.109
bes-0.085
ages-0.081
on-0.076
con-0.076
Tokenrily
Token ID28904
Feature activation+2.39e+00

Pos logit contributions
 flood+0.619
ksh+0.584
 ending+0.583
rant+0.573
 coming+0.559
Neg logit contributions
ons-1.002
bes-0.869
ages-0.822
es-0.796
aged-0.755
Token as
Token ID355
Feature activation-2.20e-01

Pos logit contributions
ksh+0.131
rant+0.128
 flood+0.128
 dolphin+0.124
 whale+0.122
Neg logit contributions
ons-0.183
bes-0.144
ages-0.138
on-0.130
con-0.128
Token they
Token ID484
Feature activation+3.33e+00

Pos logit contributions
ons+0.017
bes+0.014
ages+0.013
con+0.012
seek+0.012
Neg logit contributions
 flood-0.012
 whale-0.012
 dolphin-0.012
rant-0.012
 tide-0.012
Token made
Token ID925
Feature activation+4.22e+00

Pos logit contributions
ksh+0.167
rant+0.164
 flood+0.163
 dolphin+0.157
 whale+0.155
Neg logit contributions
ons-0.271
bes-0.217
ages-0.208
on-0.196
con-0.194
Token their
Token ID511
Feature activation+6.56e+00

Pos logit contributions
ksh+0.213
rant+0.210
 flood+0.206
 dolphin+0.197
 whale+0.194
Neg logit contributions
ons-0.346
bes-0.273
ages-0.264
on-0.250
con-0.246
Token,
Token ID11
Feature activation+8.35e-02

Pos logit contributions
rant+0.121
ksh+0.120
 flood+0.119
 coming+0.116
 dolphin+0.115
Neg logit contributions
ons-0.190
bes-0.152
ages-0.147
aid-0.140
on-0.135
Token and
Token ID290
Feature activation+1.47e-01

Pos logit contributions
ksh+0.004
rant+0.004
 flood+0.004
iet+0.004
 dolphin+0.004
Neg logit contributions
ons-0.007
bes-0.005
ages-0.005
on-0.005
con-0.005
Token she
Token ID673
Feature activation-2.69e+00

Pos logit contributions
 flood+0.008
rant+0.008
ksh+0.008
 dolphin+0.008
 coming+0.008
Neg logit contributions
ons-0.011
bes-0.008
ages-0.008
on-0.008
aid-0.007
Token wanted
Token ID2227
Feature activation+1.56e+00

Pos logit contributions
ons+0.230
bes+0.185
ages+0.178
on+0.169
con+0.167
Neg logit contributions
ksh-0.125
rant-0.123
 flood-0.122
 dolphin-0.118
 whale-0.116
Token the
Token ID262
Feature activation-7.58e-01

Pos logit contributions
ksh+0.100
rant+0.097
 flood+0.097
 dolphin+0.091
 whale+0.091
Neg logit contributions
ons-0.110
bes-0.081
ages-0.078
on-0.074
seek-0.073
Token mer
Token ID4017
Feature activation+1.25e+01

Pos logit contributions
ons+0.054
 skills+0.043
bes+0.042
on+0.041
powers+0.040
Neg logit contributions
ksh-0.042
rant-0.040
 extingu-0.036
ount-0.035
OO-0.034
Tokenmaid
Token ID23151
Feature activation+7.99e+00

Pos logit contributions
 flood+0.460
ksh+0.436
 extingu+0.400
Why+0.398
 coming+0.373
Neg logit contributions
ons-1.143
bes-1.016
ages-0.948
es-0.939
seek-0.896
Token to
Token ID284
Feature activation-2.18e-01

Pos logit contributions
ksh+0.414
rant+0.408
 flood+0.402
 dolphin+0.401
 whale+0.390
Neg logit contributions
ons-0.632
bes-0.505
ages-0.473
on-0.451
con-0.450
Token come
Token ID1282
Feature activation+7.62e+00

Pos logit contributions
ons+0.018
bes+0.015
ages+0.014
on+0.014
seek+0.013
Neg logit contributions
ksh-0.011
rant-0.010
 flood-0.010
 whale-0.009
 dolphin-0.009
Token too
Token ID1165
Feature activation+3.16e-01

Pos logit contributions
ksh+0.442
 flood+0.439
rant+0.424
 whale+0.416
 dolphin+0.403
Neg logit contributions
ons-0.538
bes-0.423
ages-0.403
es-0.401
on-0.387
Token.
Token ID13
Feature activation+6.09e-01

Pos logit contributions
ksh+0.019
rant+0.019
 flood+0.019
 dolphin+0.018
 whale+0.018
Neg logit contributions
ons-0.022
bes-0.017
ages-0.017
on-0.016
es-0.015
Token she
Token ID673
Feature activation-2.73e+00

Pos logit contributions
ons+0.149
bes+0.128
ages+0.127
aid+0.115
seek+0.109
Neg logit contributions
 flood-0.115
 ending-0.115
 dolphin-0.114
 coming-0.113
 tide-0.109
Token was
Token ID373
Feature activation+1.98e-01

Pos logit contributions
ons+0.196
bes+0.146
on+0.140
es+0.134
ages+0.133
Neg logit contributions
ksh-0.174
rant-0.159
 flood-0.159
 extingu-0.151
 mate-0.150
Token finished
Token ID5201
Feature activation-5.90e-01

Pos logit contributions
ksh+0.014
rant+0.013
 flood+0.013
 extingu+0.013
 dolphin+0.013
Neg logit contributions
ons-0.012
bes-0.009
on-0.009
ages-0.009
es-0.008
Token,
Token ID11
Feature activation+8.35e-02

Pos logit contributions
ons+0.039
bes+0.030
ages+0.029
on+0.026
con+0.026
Neg logit contributions
ksh-0.038
 flood-0.037
rant-0.037
 dolphin-0.037
 whale-0.036
Token the
Token ID262
Feature activation-7.74e-01

Pos logit contributions
 dolphin+0.005
 coming+0.005
 ending+0.005
 beginning+0.005
 flood+0.005
Neg logit contributions
ons-0.006
bes-0.005
ages-0.005
aid-0.004
ittens-0.004
Token mer
Token ID4017
Feature activation+1.25e+01

Pos logit contributions
ons+0.067
bes+0.056
ages+0.052
on+0.051
aid+0.050
Neg logit contributions
ksh-0.037
rant-0.032
 extingu-0.029
OO-0.027
 flood-0.027
Tokenmaid
Token ID23151
Feature activation+7.96e+00

Pos logit contributions
ksh+0.482
 flood+0.481
Why+0.443
 coming+0.432
 beginning+0.415
Neg logit contributions
ons-1.057
bes-0.948
ages-0.908
es-0.886
aged-0.865
Token thanked
Token ID26280
Feature activation-4.09e+00

Pos logit contributions
ksh+0.494
rant+0.486
 flood+0.484
 dolphin+0.468
 whale+0.462
Neg logit contributions
ons-0.554
bes-0.422
ages-0.402
on-0.375
con-0.369
Token her
Token ID607
Feature activation-9.38e-01

Pos logit contributions
ons+0.300
bes+0.241
ages+0.235
con+0.210
aid+0.209
Neg logit contributions
rant-0.228
ksh-0.225
 dolphin-0.225
 flood-0.221
 whale-0.218
Token for
Token ID329
Feature activation+2.27e+00

Pos logit contributions
ons+0.081
bes+0.065
ages+0.063
on+0.059
seek+0.058
Neg logit contributions
ksh-0.043
rant-0.042
 flood-0.042
 dolphin-0.042
 whale-0.041
Token coming
Token ID2406
Feature activation+1.12e+01

Pos logit contributions
 flood+0.121
 dolphin+0.121
 coming+0.121
rant+0.119
 whale+0.117
Neg logit contributions
ons-0.173
bes-0.139
ages-0.135
con-0.125
seek-0.122
Token They
Token ID1119
Feature activation+1.84e+00

Pos logit contributions
rant+0.030
 flood+0.030
ksh+0.029
 dolphin+0.029
 whale+0.028
Neg logit contributions
ons-0.038
bes-0.031
ages-0.030
con-0.028
seek-0.028
Token had
Token ID550
Feature activation+7.30e-01

Pos logit contributions
ksh+0.114
rant+0.106
 flood+0.106
 extingu+0.102
 ending+0.100
Neg logit contributions
ons-0.127
bes-0.095
ages-0.094
on-0.089
aid-0.089
Token never
Token ID1239
Feature activation-4.42e-01

Pos logit contributions
ksh+0.045
rant+0.044
 flood+0.042
 dolphin+0.041
 whale+0.040
Neg logit contributions
ons-0.053
bes-0.040
ages-0.039
seek-0.036
on-0.035
Token seen
Token ID1775
Feature activation+7.42e-01

Pos logit contributions
ons+0.035
ages+0.027
bes+0.027
seek+0.025
on+0.025
Neg logit contributions
ksh-0.024
rant-0.023
 flood-0.023
 dolphin-0.022
 whale-0.022
Token a
Token ID257
Feature activation-8.58e-01

Pos logit contributions
ksh+0.046
 flood+0.045
rant+0.044
 ending+0.042
iet+0.042
Neg logit contributions
ons-0.054
on-0.039
bes-0.038
con-0.037
es-0.036
Token mer
Token ID4017
Feature activation+1.25e+01

Pos logit contributions
ons+0.060
on+0.049
con+0.046
bes+0.045
powers+0.044
Neg logit contributions
ksh-0.053
rant-0.044
ount-0.041
 extingu-0.041
latable-0.037
Tokenmaid
Token ID23151
Feature activation+7.97e+00

Pos logit contributions
ksh+0.552
Why+0.538
 flood+0.531
 ending+0.490
rant+0.478
Neg logit contributions
ons-0.931
bes-0.851
es-0.781
ages-0.764
powers-0.758
Token before
Token ID878
Feature activation+5.32e-01

Pos logit contributions
ksh+0.437
 flood+0.428
rant+0.421
 dolphin+0.396
iet+0.393
Neg logit contributions
ons-0.615
bes-0.480
ages-0.464
on-0.454
es-0.444
Token.
Token ID13
Feature activation+5.93e-01

Pos logit contributions
ksh+0.033
rant+0.032
 flood+0.032
 dolphin+0.030
 mate+0.030
Neg logit contributions
ons-0.038
bes-0.029
ages-0.027
on-0.026
es-0.026
Token
Token ID198
Feature activation+1.83e-01

Pos logit contributions
ksh+0.034
rant+0.034
 flood+0.034
 dolphin+0.033
 whale+0.033
Neg logit contributions
ons-0.043
bes-0.034
ages-0.032
on-0.030
con-0.030
Token
Token ID198
Feature activation+1.83e-01

Pos logit contributions
 dolphin+0.009
 whale+0.008
 flood+0.008
rant+0.008
ksh+0.008
Neg logit contributions
ons-0.015
bes-0.012
ages-0.012
aces-0.011
con-0.011
Token
Token ID198
Feature activation+9.89e-02

Pos logit contributions
ons+0.294
bes+0.245
ages+0.231
seek+0.220
tail+0.219
Neg logit contributions
ksh-0.165
rant-0.157
 coming-0.155
 mate-0.151
 flood-0.149
Token
Token ID198
Feature activation+1.17e-01

Pos logit contributions
 dolphin+0.003
Why+0.003
rant+0.003
ksh+0.003
 coming+0.003
Neg logit contributions
ons-0.009
bes-0.007
ages-0.007
aces-0.007
 elbow-0.007
TokenS
Token ID50
Feature activation+1.80e+00

Pos logit contributions
 dolphin+0.006
ksh+0.006
 flood+0.006
iet+0.006
Why+0.006
Neg logit contributions
ons-0.009
bes-0.007
ages-0.006
on-0.006
aces-0.006
Tokenki
Token ID4106
Feature activation-1.60e+00

Pos logit contributions
ksh+0.100
rant+0.098
 flood+0.098
 dolphin+0.095
 whale+0.093
Neg logit contributions
ons-0.138
bes-0.107
ages-0.103
on-0.097
con-0.096
Tokenpping
Token ID2105
Feature activation+1.50e+00

Pos logit contributions
ons+0.126
bes+0.106
ages+0.105
powers+0.102
aid+0.099
Neg logit contributions
rant-0.078
iet-0.071
 whale-0.071
 coming-0.070
 dolphin-0.070
Token mer
Token ID4017
Feature activation+1.25e+01

Pos logit contributions
 coming+0.069
 dolphin+0.068
 flood+0.067
rant+0.067
 whale+0.064
Neg logit contributions
ons-0.122
bes-0.106
ages-0.096
seek-0.093
aid-0.092
Tokenrily
Token ID28904
Feature activation+2.29e+00

Pos logit contributions
 flood+0.775
ksh+0.765
rant+0.750
 dolphin+0.726
 ending+0.726
Neg logit contributions
ons-0.872
bes-0.678
ages-0.647
es-0.607
on-0.582
Token along
Token ID1863
Feature activation-1.36e+00

Pos logit contributions
 flood+0.107
 dolphin+0.107
rant+0.106
 coming+0.105
 ending+0.104
Neg logit contributions
ons-0.188
bes-0.148
ages-0.143
aid-0.138
on-0.136
Token,
Token ID11
Feature activation+8.98e-02

Pos logit contributions
ons+0.104
bes+0.081
ages+0.080
aid+0.075
on+0.072
Neg logit contributions
 coming-0.075
 flood-0.074
rant-0.073
 dolphin-0.072
 whale-0.071
Token Hawk
Token ID26698
Feature activation-9.52e-01

Pos logit contributions
ksh+0.005
rant+0.005
 flood+0.005
 dolphin+0.005
 whale+0.004
Neg logit contributions
ons-0.007
bes-0.005
ages-0.005
on-0.005
con-0.005
Token came
Token ID1625
Feature activation+6.20e+00

Pos logit contributions
ons+0.076
bes+0.061
ages+0.058
on+0.054
aid+0.054
Neg logit contributions
rant-0.048
ksh-0.048
 flood-0.048
 dolphin-0.046
 whale-0.046
Token castle
Token ID16669
Feature activation+9.44e-01

Pos logit contributions
ons+0.105
bes+0.084
ages+0.080
on+0.075
con+0.074
Neg logit contributions
ksh-0.074
rant-0.071
 flood-0.070
 dolphin-0.066
 whale-0.065
Token so
Token ID523
Feature activation-4.22e-01

Pos logit contributions
 flood+0.046
rant+0.045
ksh+0.045
 coming+0.044
 ending+0.043
Neg logit contributions
ons-0.077
bes-0.062
ages-0.060
con-0.056
aid-0.056
Token much
Token ID881
Feature activation-2.17e+00

Pos logit contributions
ons+0.030
bes+0.022
ages+0.021
on+0.021
es+0.020
Neg logit contributions
ksh-0.026
rant-0.024
 extingu-0.023
 flood-0.023
 mate-0.023
Token.
Token ID13
Feature activation+5.30e-01

Pos logit contributions
ons+0.142
bes+0.099
con+0.097
ages+0.094
on+0.092
Neg logit contributions
ksh-0.154
rant-0.142
 flood-0.138
iet-0.137
 mate-0.135
Token The
Token ID383
Feature activation-1.07e+00

Pos logit contributions
ksh+0.032
rant+0.031
 flood+0.031
 dolphin+0.030
 whale+0.030
Neg logit contributions
ons-0.039
bes-0.030
ages-0.028
on-0.026
con-0.026
Token mer
Token ID4017
Feature activation+1.25e+01

Pos logit contributions
ons+0.108
bes+0.092
on+0.087
aid+0.085
ages+0.085
Neg logit contributions
ksh-0.036
rant-0.027
 extingu-0.027
 flood-0.024
OO-0.022
Tokenmaid
Token ID23151
Feature activation+7.95e+00

Pos logit contributions
 flood+0.436
ksh+0.421
 coming+0.353
 extingu+0.352
Why+0.349
Neg logit contributions
ons-1.188
bes-1.032
ages-0.984
es-0.983
aged-0.946
Token said
Token ID531
Feature activation-2.59e+00

Pos logit contributions
ksh+0.540
rant+0.534
 flood+0.532
 dolphin+0.523
 whale+0.516
Neg logit contributions
ons-0.501
bes-0.372
ages-0.352
on-0.322
con-0.319
Token,
Token ID11
Feature activation+8.98e-02

Pos logit contributions
ons+0.168
bes+0.124
ages+0.118
on+0.110
es+0.107
Neg logit contributions
ksh-0.176
rant-0.173
 flood-0.172
 dolphin-0.166
 whale-0.164
Token "
Token ID366
Feature activation+3.05e+00

Pos logit contributions
 flood+0.004
ksh+0.004
rant+0.004
 dolphin+0.004
iet+0.004
Neg logit contributions
ons-0.007
bes-0.006
ages-0.006
on-0.006
es-0.005
TokenI
Token ID40
Feature activation+3.70e+00

Pos logit contributions
 flood+0.165
rant+0.159
ksh+0.158
 ending+0.152
 mate+0.150
Neg logit contributions
ons-0.246
bes-0.189
ages-0.182
on-0.181
aid-0.172
Token"
Token ID1
Feature activation-2.37e+00

Pos logit contributions
ksh+0.005
 flood+0.005
 dolphin+0.005
rant+0.005
 mate+0.005
Neg logit contributions
ons-0.006
bes-0.005
con-0.005
ages-0.005
seek-0.004
TokenAnd
Token ID1870
Feature activation+1.54e+00

Pos logit contributions
ons+0.182
bes+0.151
aid+0.145
ages+0.141
on+0.138
Neg logit contributions
rant-0.126
 flood-0.118
ksh-0.117
 ending-0.112
iet-0.111
Token I
Token ID314
Feature activation+1.28e+00

Pos logit contributions
 flood+0.082
 dolphin+0.082
ksh+0.082
 whale+0.081
rant+0.081
Neg logit contributions
ons-0.119
bes-0.094
ages-0.089
con-0.084
seek-0.083
Token'm
Token ID1101
Feature activation+2.61e-01

Pos logit contributions
ksh+0.082
rant+0.078
 whale+0.075
 dolphin+0.074
 flood+0.073
Neg logit contributions
ons-0.085
bes-0.066
ages-0.066
on-0.062
aid-0.060
Token a
Token ID257
Feature activation-8.97e-01

Pos logit contributions
ksh+0.017
rant+0.017
 flood+0.017
 dolphin+0.016
 whale+0.016
Neg logit contributions
ons-0.017
bes-0.013
ages-0.012
on-0.012
es-0.011
Token mer
Token ID4017
Feature activation+1.25e+01

Pos logit contributions
ons+0.040
on+0.032
bes+0.031
ages+0.030
powers+0.029
Neg logit contributions
rant-0.067
ksh-0.065
ount-0.064
 appearance-0.060
ility-0.060
Tokenmaid
Token ID23151
Feature activation+7.93e+00

Pos logit contributions
 flood+0.524
ksh+0.519
Why+0.510
rant+0.509
 beginning+0.506
Neg logit contributions
ons-0.916
bes-0.874
es-0.830
ages-0.820
aps-0.812
Token!"
Token ID2474
Feature activation-3.37e+00

Pos logit contributions
ksh+0.447
 mate+0.444
 dolphin+0.443
 whale+0.437
rant+0.429
Neg logit contributions
ons-0.586
bes-0.470
ages-0.421
seek-0.396
aid-0.394
Token Lily
Token ID20037
Feature activation+1.06e+00

Pos logit contributions
ons+0.340
bes+0.290
ages+0.278
seek+0.266
con+0.265
Neg logit contributions
 flood-0.113
 dolphin-0.107
 ending-0.103
 mate-0.102
 whale-0.099
Token said
Token ID531
Feature activation-2.58e+00

Pos logit contributions
ksh+0.067
 dolphin+0.065
 whale+0.064
rant+0.063
 mate+0.062
Neg logit contributions
ons-0.074
bes-0.055
ages-0.051
igs-0.050
con-0.049
Token.
Token ID13
Feature activation+5.69e-01

Pos logit contributions
ons+0.224
bes+0.180
ages+0.168
con+0.166
rob+0.162
Neg logit contributions
ksh-0.119
 coming-0.114
rant-0.113
 dolphin-0.111
 flood-0.110
Token passport
Token ID17981
Feature activation+2.72e-01

Pos logit contributions
ons+0.041
bes+0.033
ages+0.032
on+0.030
con+0.030
Neg logit contributions
ksh-0.024
rant-0.023
 flood-0.022
 dolphin-0.021
 whale-0.021
Token belonged
Token ID19611
Feature activation+2.67e+00

Pos logit contributions
 flood+0.012
 coming+0.011
 whale+0.011
 ending+0.011
 wake+0.011
Neg logit contributions
ons-0.022
bes-0.019
ages-0.019
ittens-0.018
seek-0.018
Token to
Token ID284
Feature activation-8.13e-02

Pos logit contributions
rant+0.127
ksh+0.126
 mate+0.125
 coming+0.124
 flood+0.124
Neg logit contributions
ons-0.217
bes-0.177
ages-0.168
aid-0.159
con-0.157
Token a
Token ID257
Feature activation-7.87e-01

Pos logit contributions
ons+0.006
bes+0.004
ages+0.004
on+0.004
es+0.004
Neg logit contributions
ksh-0.005
rant-0.005
 flood-0.005
 dolphin-0.005
 whale-0.004
Token magical
Token ID10883
Feature activation+4.63e+00

Pos logit contributions
ons+0.058
bes+0.045
ages+0.044
con+0.042
on+0.042
Neg logit contributions
ksh-0.045
rant-0.045
iet-0.039
 extingu-0.038
 flood-0.037
Token mer
Token ID4017
Feature activation+1.24e+01

Pos logit contributions
ksh+0.224
rant+0.212
 flood+0.202
 dolphin+0.190
iet+0.186
Neg logit contributions
ons-0.394
bes-0.316
ages-0.301
on-0.291
con-0.290
Tokenmaid
Token ID23151
Feature activation+7.87e+00

Pos logit contributions
 flood+0.460
ksh+0.451
Why+0.408
rant+0.406
 ending+0.399
Neg logit contributions
ons-1.121
bes-0.975
ages-0.932
es-0.912
powers-0.871
Token who
Token ID508
Feature activation+3.98e+00

Pos logit contributions
rant+0.382
ksh+0.380
 dolphin+0.378
 flood+0.373
 whale+0.370
Neg logit contributions
ons-0.637
bes-0.515
ages-0.489
aid-0.462
con-0.458
Token had
Token ID550
Feature activation+5.78e-01

Pos logit contributions
rant+0.181
 flood+0.178
 dolphin+0.177
 whale+0.175
ksh+0.170
Neg logit contributions
ons-0.331
bes-0.276
ages-0.266
con-0.249
seek-0.246
Token been
Token ID587
Feature activation+9.56e-01

Pos logit contributions
rant+0.027
 flood+0.027
ksh+0.027
 dolphin+0.027
 whale+0.026
Neg logit contributions
ons-0.048
bes-0.039
ages-0.037
on-0.035
con-0.035
Token visiting
Token ID10013
Feature activation+2.87e-01

Pos logit contributions
ksh+0.049
rant+0.048
 flood+0.048
 dolphin+0.046
 whale+0.045
Neg logit contributions
ons-0.077
bes-0.061
ages-0.059
on-0.055
con-0.055
Token.
Token ID13
Feature activation+9.60e-01

Pos logit contributions
ons+0.157
bes+0.121
ages+0.116
on+0.107
con+0.106
Neg logit contributions
ksh-0.133
 flood-0.131
rant-0.131
 dolphin-0.128
 whale-0.126
Token The
Token ID383
Feature activation-7.84e-01

Pos logit contributions
ksh+0.047
 mate+0.044
rant+0.043
 flood+0.043
 dolphin+0.043
Neg logit contributions
ons-0.081
bes-0.065
ages-0.063
con-0.059
seek-0.058
Token more
Token ID517
Feature activation-1.35e+00

Pos logit contributions
ons+0.066
bes+0.053
ages+0.050
on+0.048
con+0.048
Neg logit contributions
ksh-0.038
rant-0.037
 flood-0.035
 dolphin-0.033
 whale-0.032
Token,
Token ID11
Feature activation+1.67e-01

Pos logit contributions
ons+0.099
bes+0.080
ages+0.077
seek+0.074
aid+0.072
Neg logit contributions
 flood-0.075
 whale-0.073
 dolphin-0.072
 mate-0.072
 ending-0.070
Token the
Token ID262
Feature activation-7.55e-01

Pos logit contributions
ksh+0.009
rant+0.009
 flood+0.009
 dolphin+0.009
 whale+0.008
Neg logit contributions
ons-0.013
bes-0.010
ages-0.009
on-0.009
con-0.009
Token mer
Token ID4017
Feature activation+1.24e+01

Pos logit contributions
ons+0.062
bes+0.049
ages+0.047
on+0.045
con+0.045
Neg logit contributions
ksh-0.038
rant-0.037
 flood-0.035
 dolphin-0.034
 whale-0.033
Tokenrier
Token ID5277
Feature activation+3.28e+00

Pos logit contributions
 flood+0.387
ksh+0.384
rant+0.341
Why+0.330
 coming+0.326
Neg logit contributions
ons-1.220
bes-1.046
ages-1.018
es-0.990
con-0.948
Token.
Token ID13
Feature activation+4.29e-01

Pos logit contributions
ksh+0.181
rant+0.179
 flood+0.178
 dolphin+0.174
 whale+0.172
Neg logit contributions
ons-0.248
bes-0.195
ages-0.185
on-0.174
con-0.173
Token Come
Token ID7911
Feature activation+3.64e+00

Pos logit contributions
ksh+0.023
rant+0.023
 flood+0.023
 dolphin+0.022
 whale+0.022
Neg logit contributions
ons-0.033
bes-0.026
ages-0.025
on-0.023
con-0.023
Token to
Token ID284
Feature activation-4.48e-01

Pos logit contributions
ksh+0.242
rant+0.238
 flood+0.237
 dolphin+0.231
 whale+0.228
Neg logit contributions
ons-0.238
bes-0.178
ages-0.169
on-0.157
con-0.153
Token my
Token ID616
Feature activation-1.26e+00

Pos logit contributions
ons+0.033
bes+0.025
ages+0.024
on+0.023
con+0.023
Neg logit contributions
ksh-0.026
rant-0.026
 flood-0.026
 dolphin-0.025
 whale-0.024
Token it
Token ID340
Feature activation-6.36e-01

Pos logit contributions
ons+0.028
bes+0.021
ages+0.019
on+0.019
con+0.018
Neg logit contributions
ksh-0.029
rant-0.028
 flood-0.027
 dolphin-0.027
 whale-0.026
Token was
Token ID373
Feature activation+1.30e-01

Pos logit contributions
ons+0.037
bes+0.027
es+0.026
ages+0.025
ves+0.024
Neg logit contributions
ksh-0.047
 extingu-0.044
 whale-0.043
rant-0.043
 dolphin-0.043
Token time
Token ID640
Feature activation+5.38e+00

Pos logit contributions
ksh+0.007
 dolphin+0.006
 whale+0.006
 extingu+0.006
rant+0.006
Neg logit contributions
ons-0.010
bes-0.008
on-0.008
igs-0.007
 onwards-0.007
Token for
Token ID329
Feature activation+2.17e+00

Pos logit contributions
ksh+0.322
 flood+0.317
rant+0.308
 dolphin+0.304
 whale+0.300
Neg logit contributions
ons-0.387
ages-0.290
bes-0.290
on-0.271
con-0.260
Token the
Token ID262
Feature activation-8.46e-01

Pos logit contributions
ksh+0.121
 flood+0.121
rant+0.120
 dolphin+0.118
 whale+0.115
Neg logit contributions
ons-0.163
bes-0.128
ages-0.124
on-0.115
con-0.114
Token mer
Token ID4017
Feature activation+1.24e+01

Pos logit contributions
ons+0.061
bes+0.047
on+0.044
con+0.044
ages+0.043
Neg logit contributions
ksh-0.051
rant-0.048
 flood-0.043
 extingu-0.043
iet-0.042
Tokenmaid
Token ID23151
Feature activation+7.89e+00

Pos logit contributions
 flood+0.521
Why+0.473
ksh+0.461
 coming+0.429
 beginning+0.427
Neg logit contributions
ons-1.044
bes-0.959
ages-0.892
es-0.867
powers-0.860
Token to
Token ID284
Feature activation-2.87e-01

Pos logit contributions
ksh+0.437
rant+0.429
 flood+0.427
 dolphin+0.414
 whale+0.407
Neg logit contributions
ons-0.601
bes-0.471
ages-0.450
on-0.423
con-0.418
Token return
Token ID1441
Feature activation+1.07e+00

Pos logit contributions
ons+0.027
bes+0.022
on+0.021
ages+0.021
aid+0.020
Neg logit contributions
ksh-0.012
rant-0.010
 flood-0.009
 whale-0.009
 dolphin-0.009
Token home
Token ID1363
Feature activation-1.91e+00

Pos logit contributions
ksh+0.059
rant+0.058
 flood+0.058
 dolphin+0.056
 whale+0.055
Neg logit contributions
ons-0.081
bes-0.064
ages-0.061
on-0.057
con-0.056
Token.
Token ID13
Feature activation+5.16e-01

Pos logit contributions
ons+0.163
bes+0.130
ages+0.124
con+0.122
aid+0.122
Neg logit contributions
 coming-0.083
rant-0.083
 flood-0.082
ksh-0.081
 dolphin-0.081
Token
Token ID198
Feature activation+3.73e-02

Pos logit contributions
ksh+0.014
rant+0.013
 flood+0.013
 dolphin+0.013
 whale+0.012
Neg logit contributions
ons-0.042
bes-0.036
ages-0.034
aid-0.033
con-0.032
Token
Token ID198
Feature activation+4.03e-02

Pos logit contributions
 dolphin+0.002
rant+0.002
 whale+0.002
iet+0.002
ksh+0.002
Neg logit contributions
ons-0.003
bes-0.003
ages-0.002
tail-0.002
aces-0.002
TokenJack
Token ID14295
Feature activation+3.03e+00

Pos logit contributions
ksh+0.002
rant+0.002
 flood+0.002
 dolphin+0.002
 whale+0.002
Neg logit contributions
ons-0.003
bes-0.003
ages-0.002
con-0.002
es-0.002
Token asked
Token ID1965
Feature activation-1.77e+00

Pos logit contributions
ksh+0.155
rant+0.154
 flood+0.151
 dolphin+0.150
 whale+0.147
Neg logit contributions
ons-0.242
bes-0.193
ages-0.185
con-0.173
on-0.173
Token the
Token ID262
Feature activation-8.70e-01

Pos logit contributions
ons+0.127
bes+0.102
ages+0.097
con+0.088
on+0.087
Neg logit contributions
rant-0.103
 flood-0.103
ksh-0.102
 dolphin-0.101
 whale-0.100
Token mer
Token ID4017
Feature activation+1.24e+01

Pos logit contributions
ons+0.077
bes+0.066
 exclaimed+0.063
on+0.062
aid+0.062
Neg logit contributions
ksh-0.038
rant-0.029
 extingu-0.028
OO-0.027
 flood-0.026
Tokenmaid
Token ID23151
Feature activation+7.86e+00

Pos logit contributions
 flood+0.539
ksh+0.478
 ending+0.447
 storm+0.445
Why+0.443
Neg logit contributions
ons-1.069
bes-0.925
es-0.916
ages-0.882
aged-0.840
Token why
Token ID1521
Feature activation+8.54e+00

Pos logit contributions
ksh+0.441
 flood+0.431
rant+0.422
 dolphin+0.401
 whale+0.394
Neg logit contributions
ons-0.606
bes-0.460
ages-0.450
es-0.434
on-0.433
Token the
Token ID262
Feature activation-8.47e-01

Pos logit contributions
ksh+0.645
rant+0.628
 flood+0.621
 dolphin+0.604
 whale+0.598
Neg logit contributions
ons-0.496
bes-0.347
ages-0.323
on-0.303
es-0.294
Token waves
Token ID9813
Feature activation+4.07e+00

Pos logit contributions
ons+0.079
bes+0.067
powers+0.063
ages+0.062
on+0.061
Neg logit contributions
ksh-0.034
rant-0.028
 extingu-0.025
latable-0.022
 flood-0.022
Token were
Token ID547
Feature activation+1.11e+00

Pos logit contributions
ksh+0.229
rant+0.212
 flood+0.205
 mate+0.200
 dolphin+0.197
Neg logit contributions
ons-0.323
bes-0.243
ages-0.235
on-0.233
es-0.225
Token.
Token ID13
Feature activation+4.04e-01

Pos logit contributions
ons+0.193
bes+0.149
ages+0.144
on+0.136
es+0.135
Neg logit contributions
ksh-0.166
rant-0.165
 flood-0.164
 dolphin-0.157
iet-0.157
Token "
Token ID366
Feature activation+2.89e+00

Pos logit contributions
ksh+0.018
rant+0.018
 flood+0.017
 dolphin+0.017
 whale+0.016
Neg logit contributions
ons-0.035
bes-0.029
ages-0.028
on-0.026
con-0.026
TokenI
Token ID40
Feature activation+3.54e+00

Pos logit contributions
 flood+0.136
rant+0.125
ksh+0.125
 ending+0.120
 dolphin+0.119
Neg logit contributions
ons-0.246
bes-0.204
on-0.193
ages-0.192
aid-0.190
Token am
Token ID716
Feature activation-2.61e+00

Pos logit contributions
ksh+0.219
rant+0.196
 flood+0.193
iet+0.191
 dolphin+0.189
Neg logit contributions
ons-0.251
bes-0.192
ages-0.187
on-0.185
aid-0.181
Token a
Token ID257
Feature activation-1.01e+00

Pos logit contributions
ons+0.175
on+0.128
bes+0.128
ages+0.122
es+0.115
Neg logit contributions
ksh-0.171
rant-0.160
iet-0.156
 flood-0.154
 ending-0.151
Token mer
Token ID4017
Feature activation+1.24e+01

Pos logit contributions
ons+0.055
on+0.047
powers+0.045
bes+0.044
ages+0.044
Neg logit contributions
ksh-0.066
rant-0.065
ount-0.059
iet-0.056
ains-0.056
Tokenmaid
Token ID23151
Feature activation+7.82e+00

Pos logit contributions
ksh+0.531
Why+0.526
 flood+0.518
rant+0.497
 beginning+0.479
Neg logit contributions
ons-0.900
bes-0.843
ages-0.801
aged-0.790
es-0.787
Token.
Token ID13
Feature activation+4.45e-01

Pos logit contributions
ksh+0.429
 dolphin+0.427
rant+0.421
 whale+0.421
 mate+0.420
Neg logit contributions
ons-0.596
bes-0.479
ages-0.437
con-0.413
seek-0.411
Token Do
Token ID2141
Feature activation+4.19e-01

Pos logit contributions
 flood+0.024
ksh+0.024
rant+0.023
iet+0.022
 dolphin+0.022
Neg logit contributions
ons-0.033
bes-0.026
ages-0.025
on-0.025
es-0.024
Token you
Token ID345
Feature activation-1.99e+00

Pos logit contributions
 dolphin+0.026
 mate+0.026
 flood+0.025
ksh+0.025
 whale+0.025
Neg logit contributions
ons-0.028
bes-0.022
ages-0.021
con-0.019
aid-0.019
Token want
Token ID765
Feature activation+3.18e+00

Pos logit contributions
ons+0.190
bes+0.152
on+0.149
ages+0.149
aid+0.145
Neg logit contributions
ksh-0.077
 flood-0.067
rant-0.066
 dolphin-0.064
 extingu-0.064
Token so
Token ID523
Feature activation-5.43e-01

Pos logit contributions
ksh+0.003
rant+0.003
 flood+0.003
 dolphin+0.003
 whale+0.003
Neg logit contributions
ons-0.005
bes-0.004
ages-0.004
con-0.003
on-0.003
Token happy
Token ID3772
Feature activation-1.15e+00

Pos logit contributions
ons+0.044
bes+0.035
con+0.032
ages+0.032
seek+0.031
Neg logit contributions
 flood-0.028
rant-0.027
 dolphin-0.027
 whale-0.027
ksh-0.027
Token and
Token ID290
Feature activation+3.39e-05

Pos logit contributions
ons+0.084
bes+0.065
ages+0.062
on+0.058
con+0.057
Neg logit contributions
ksh-0.067
rant-0.066
 flood-0.065
 dolphin-0.064
 whale-0.063
Token thanked
Token ID26280
Feature activation-4.24e+00

Pos logit contributions
 dolphin+0.000
 mer+0.000
 whale+0.000
 coming+0.000
 flood+0.000
Neg logit contributions
ons-0.000
bes-0.000
orns-0.000
aid-0.000
rob-0.000
Token the
Token ID262
Feature activation-9.06e-01

Pos logit contributions
ons+0.307
bes+0.240
ages+0.232
on+0.211
con+0.208
Neg logit contributions
ksh-0.249
rant-0.247
 flood-0.246
 dolphin-0.242
 whale-0.239
Token mer
Token ID4017
Feature activation+1.24e+01

Pos logit contributions
ons+0.074
bes+0.061
aid+0.059
on+0.059
ages+0.057
Neg logit contributions
ksh-0.048
rant-0.041
 extingu-0.036
 flood-0.035
iet-0.034
Tokenmaid
Token ID23151
Feature activation+7.84e+00

Pos logit contributions
 flood+0.472
ksh+0.467
 coming+0.410
 beginning+0.401
rant+0.400
Neg logit contributions
ons-1.095
bes-0.951
ages-0.932
es-0.901
aged-0.882
Token many
Token ID867
Feature activation-7.28e+00

Pos logit contributions
ksh+0.333
rant+0.323
 mate+0.323
 dolphin+0.322
 whale+0.316
Neg logit contributions
ons-0.693
bes-0.585
aid-0.523
ages-0.520
rob-0.517
Token times
Token ID1661
Feature activation-4.64e+00

Pos logit contributions
ons+0.532
bes+0.417
ages+0.399
on+0.371
con+0.365
Neg logit contributions
ksh-0.423
rant-0.422
 flood-0.419
 dolphin-0.414
 whale-0.409
Token.
Token ID13
Feature activation+4.57e-01

Pos logit contributions
ons+0.388
bes+0.321
ages+0.304
aid+0.287
con+0.283
Neg logit contributions
rant-0.211
 coming-0.210
ksh-0.207
 mate-0.205
 dolphin-0.205
Token With
Token ID2080
Feature activation-4.80e+00

Pos logit contributions
ksh+0.026
rant+0.025
 dolphin+0.025
 whale+0.024
 flood+0.024
Neg logit contributions
ons-0.035
bes-0.027
ages-0.026
aid-0.025
on-0.024
Token bed
Token ID3996
Feature activation-5.91e+00

Pos logit contributions
ons+0.033
ages+0.027
bes+0.026
aid+0.024
aces+0.024
Neg logit contributions
 flood-0.024
 wake-0.024
 coming-0.023
 dolphin-0.022
 ending-0.022
Token.
Token ID13
Feature activation+3.95e-01

Pos logit contributions
ons+0.495
bes+0.363
ages+0.361
aid+0.361
on+0.358
Neg logit contributions
 coming-0.294
 wake-0.269
rant-0.267
 flood-0.267
 ending-0.264
Token She
Token ID1375
Feature activation-1.66e+00

Pos logit contributions
ksh+0.020
rant+0.019
Why+0.019
 ending+0.019
 wake+0.019
Neg logit contributions
ons-0.032
bes-0.025
ages-0.024
on-0.023
con-0.023
Token dreamed
Token ID27947
Feature activation-1.14e+00

Pos logit contributions
ons+0.150
bes+0.120
ages+0.118
con+0.114
on+0.112
Neg logit contributions
rant-0.066
ksh-0.066
 dolphin-0.066
 flood-0.065
 whale-0.064
Token of
Token ID286
Feature activation-1.34e+00

Pos logit contributions
ons+0.085
bes+0.072
ages+0.068
con+0.060
tail+0.060
Neg logit contributions
rant-0.061
 coming-0.061
 flood-0.060
 ending-0.060
 dolphin-0.059
Token mer
Token ID4017
Feature activation+1.23e+01

Pos logit contributions
ons+0.103
bes+0.081
ages+0.081
seek+0.073
on+0.073
Neg logit contributions
 flood-0.072
 coming-0.070
 dolphin-0.070
 whale-0.069
rant-0.068
Tokenmaid
Token ID23151
Feature activation+7.81e+00

Pos logit contributions
 flood+0.542
ksh+0.486
 ending+0.470
 storm+0.455
rant+0.452
Neg logit contributions
ons-1.084
bes-0.952
es-0.912
ages-0.886
aged-0.847
Tokens
Token ID82
Feature activation-3.24e+00

Pos logit contributions
ksh+0.524
rant+0.517
 flood+0.514
 dolphin+0.506
 whale+0.498
Neg logit contributions
ons-0.501
bes-0.374
ages-0.352
on-0.326
con-0.320
Token and
Token ID290
Feature activation+8.40e-03

Pos logit contributions
ons+0.261
bes+0.207
ages+0.202
con+0.190
on+0.188
Neg logit contributions
 flood-0.159
rant-0.158
 dolphin-0.156
ksh-0.154
 coming-0.154
Token pirates
Token ID27516
Feature activation+4.13e+00

Pos logit contributions
 dolphin+0.000
 flood+0.000
 ending+0.000
 whale+0.000
 mate+0.000
Neg logit contributions
ons-0.001
bes-0.001
ages-0.001
on-0.000
con-0.000
Token,
Token ID11
Feature activation-2.56e-02

Pos logit contributions
rant+0.198
 dolphin+0.196
 flood+0.194
ksh+0.194
 coming+0.192
Neg logit contributions
ons-0.333
bes-0.266
ages-0.257
on-0.242
con-0.241
TokenLet
Token ID5756
Feature activation+2.99e+00

Pos logit contributions
 flood+0.172
 mate+0.162
rant+0.161
arter+0.159
 ending+0.159
Neg logit contributions
ons-0.196
bes-0.163
ages-0.156
seek-0.155
tail-0.150
Token's
Token ID338
Feature activation+3.41e+00

Pos logit contributions
rant+0.219
ksh+0.216
 flood+0.206
 extingu+0.205
 mate+0.204
Neg logit contributions
ons-0.194
bes-0.127
ages-0.126
on-0.123
 exclaimed-0.115
Token pretend
Token ID16614
Feature activation+1.65e+00

Pos logit contributions
ksh+0.213
rant+0.192
 ending+0.186
king+0.173
 whale+0.172
Neg logit contributions
ons-0.245
bes-0.192
on-0.180
igs-0.170
tail-0.170
Token we
Token ID356
Feature activation+2.04e+00

Pos logit contributions
ksh+0.108
rant+0.107
 flood+0.100
iet+0.098
 extingu+0.097
Neg logit contributions
ons-0.114
bes-0.083
ages-0.080
on-0.077
es-0.074
Token are
Token ID389
Feature activation+1.08e+00

Pos logit contributions
ksh+0.108
rant+0.103
 ending+0.101
iet+0.100
 dolphin+0.099
Neg logit contributions
ons-0.161
on-0.118
bes-0.116
es-0.115
ages-0.114
Token mer
Token ID4017
Feature activation+1.23e+01

Pos logit contributions
ksh+0.062
rant+0.061
iet+0.057
 ending+0.056
 flood+0.056
Neg logit contributions
ons-0.079
bes-0.060
ages-0.059
on-0.058
es-0.057
Tokenmaid
Token ID23151
Feature activation+7.81e+00

Pos logit contributions
 flood+0.507
 ending+0.503
 storm+0.470
rant+0.443
Why+0.441
Neg logit contributions
ons-1.014
bes-0.957
es-0.913
ages-0.911
aged-0.848
Tokens
Token ID82
Feature activation-3.24e+00

Pos logit contributions
rant+0.568
 flood+0.568
ksh+0.567
 ending+0.540
 dolphin+0.538
Neg logit contributions
ons-0.461
bes-0.323
ages-0.317
es-0.291
on-0.286
Token and
Token ID290
Feature activation+8.40e-03

Pos logit contributions
ons+0.177
bes+0.125
ages+0.120
es+0.113
on+0.109
Neg logit contributions
ksh-0.243
rant-0.239
 flood-0.237
 dolphin-0.231
iet-0.228
Token swim
Token ID9422
Feature activation+5.59e+00

Pos logit contributions
 flood+0.000
ksh+0.000
 dolphin+0.000
rant+0.000
 whale+0.000
Neg logit contributions
ons-0.001
bes-0.001
ages-0.001
on-0.000
con-0.000
Token in
Token ID287
Feature activation+1.89e+00

Pos logit contributions
ksh+0.355
 flood+0.354
rant+0.350
 ending+0.349
 extingu+0.334
Neg logit contributions
ons-0.352
bes-0.272
ages-0.268
es-0.256
seek-0.234
Token many
Token ID867
Feature activation-7.09e+00

Pos logit contributions
ons+0.232
bes+0.186
ages+0.177
con+0.165
on+0.164
Neg logit contributions
ksh-0.164
rant-0.162
 flood-0.161
 dolphin-0.158
 coming-0.156
Token more
Token ID517
Feature activation-1.49e+00

Pos logit contributions
ons+0.546
ages+0.473
bes+0.472
seek+0.433
on+0.426
Neg logit contributions
 coming-0.342
 flood-0.333
 whale-0.328
 dolphin-0.327
rant-0.321
Token adventures
Token ID17545
Feature activation-2.88e+00

Pos logit contributions
ons+0.119
bes+0.098
ages+0.094
es+0.088
seek+0.088
Neg logit contributions
 flood-0.073
 dolphin-0.071
 coming-0.071
 whale-0.071
rant-0.070
Token with
Token ID351
Feature activation-1.24e+00

Pos logit contributions
ons+0.231
bes+0.192
ages+0.183
aid+0.176
con+0.170
Neg logit contributions
 coming-0.133
rant-0.126
ksh-0.125
 flood-0.125
 dolphin-0.121
Token the
Token ID262
Feature activation-9.08e-01

Pos logit contributions
ons+0.093
bes+0.076
ages+0.075
seek+0.070
aid+0.069
Neg logit contributions
 flood-0.064
 coming-0.063
rant-0.063
 dolphin-0.063
 whale-0.062
Token mer
Token ID4017
Feature activation+1.23e+01

Pos logit contributions
ons+0.071
bes+0.056
ages+0.053
con+0.051
on+0.051
Neg logit contributions
ksh-0.049
rant-0.048
 flood-0.046
 dolphin-0.044
 whale-0.043
Tokenmaid
Token ID23151
Feature activation+7.75e+00

Pos logit contributions
 flood+0.417
ksh+0.410
Why+0.383
 coming+0.363
 ending+0.360
Neg logit contributions
ons-1.173
bes-1.009
ages-0.971
es-0.935
powers-0.914
Token.
Token ID13
Feature activation+3.23e-01

Pos logit contributions
 dolphin+0.409
ksh+0.402
rant+0.401
 whale+0.399
 flood+0.392
Neg logit contributions
ons-0.593
bes-0.479
ages-0.442
aid-0.421
seek-0.421
Token
Token ID198
Feature activation-1.06e-01

Pos logit contributions
ksh+0.019
 dolphin+0.018
rant+0.018
 flood+0.018
 mate+0.018
Neg logit contributions
ons-0.024
bes-0.018
ages-0.018
aid-0.017
igs-0.016
Token
Token ID198
Feature activation-1.33e-01

Pos logit contributions
ons+0.008
ages+0.007
bes+0.007
aces+0.007
seek+0.006
Neg logit contributions
 dolphin-0.005
 whale-0.005
iet-0.005
rant-0.004
 flood-0.004
TokenThe
Token ID464
Feature activation-1.49e+00

Pos logit contributions
ons+0.010
bes+0.007
ages+0.007
con+0.007
aces+0.007
Neg logit contributions
 dolphin-0.008
ksh-0.007
iet-0.007
 flood-0.007
 mate-0.007
Token her
Token ID607
Feature activation-1.50e+00

Pos logit contributions
rant+0.045
ksh+0.044
 dolphin+0.043
 coming+0.043
 flood+0.043
Neg logit contributions
ons-0.057
bes-0.046
ages-0.045
seek-0.044
powers-0.041
Token hair
Token ID4190
Feature activation-5.82e+00

Pos logit contributions
ons+0.114
bes+0.089
ages+0.086
seek+0.082
on+0.080
Neg logit contributions
ksh-0.081
rant-0.080
 dolphin-0.078
 flood-0.078
 whale-0.077
Token in
Token ID287
Feature activation+1.46e+00

Pos logit contributions
ons+0.436
bes+0.338
ages+0.323
con+0.305
seek+0.301
Neg logit contributions
ksh-0.327
rant-0.327
 flood-0.314
 dolphin-0.306
 coming-0.303
Token a
Token ID257
Feature activation-1.41e+00

Pos logit contributions
 flood+0.083
ksh+0.082
rant+0.082
 dolphin+0.080
 coming+0.079
Neg logit contributions
ons-0.107
bes-0.083
ages-0.083
con-0.076
seek-0.075
Token pony
Token ID26902
Feature activation-1.42e+00

Pos logit contributions
ons+0.109
bes+0.085
ages+0.081
on+0.077
con+0.076
Neg logit contributions
ksh-0.078
rant-0.077
 flood-0.075
 dolphin-0.073
 whale-0.072
Tokentail
Token ID13199
Feature activation-1.57e+01

Pos logit contributions
ons+0.113
bes+0.091
ages+0.088
aid+0.085
seek+0.081
Neg logit contributions
ksh-0.069
 coming-0.069
rant-0.069
 dolphin-0.068
 flood-0.067
Token so
Token ID523
Feature activation-9.20e-01

Pos logit contributions
ons+1.261
bes+1.004
ages+0.977
aid+0.909
con+0.908
Neg logit contributions
rant-0.771
 flood-0.768
ksh-0.754
 dolphin-0.739
 mate-0.735
Token she
Token ID673
Feature activation-3.24e+00

Pos logit contributions
ons+0.059
bes+0.047
ages+0.043
rob+0.041
seek+0.041
Neg logit contributions
 dolphin-0.058
 flood-0.058
 ending-0.058
rant-0.057
ksh-0.056
Token could
Token ID714
Feature activation-2.18e+00

Pos logit contributions
ons+0.271
bes+0.224
ages+0.211
seek+0.205
con+0.200
Neg logit contributions
ksh-0.150
rant-0.149
 dolphin-0.146
 flood-0.143
 whale-0.142
Token look
Token ID804
Feature activation+3.79e+00

Pos logit contributions
ons+0.199
bes+0.163
ages+0.162
rob+0.152
con+0.152
Neg logit contributions
 wake-0.087
 flood-0.085
rant-0.081
 dolphin-0.080
 coming-0.079
Token pretty
Token ID2495
Feature activation+1.31e+00

Pos logit contributions
ksh+0.182
 flood+0.178
rant+0.174
 dolphin+0.170
 whale+0.167
Neg logit contributions
ons-0.317
bes-0.251
ages-0.242
on-0.233
es-0.228
Token,
Token ID11
Feature activation-3.47e-01

Pos logit contributions
 flood+0.040
ksh+0.040
rant+0.040
 dolphin+0.039
 ending+0.039
Neg logit contributions
ons-0.047
bes-0.036
ages-0.035
on-0.032
con-0.032
Token Emma
Token ID18966
Feature activation+1.31e+00

Pos logit contributions
ons+0.030
bes+0.024
ages+0.024
con+0.022
aid+0.022
Neg logit contributions
ksh-0.016
 flood-0.016
rant-0.015
 dolphin-0.015
 ending-0.015
Token decided
Token ID3066
Feature activation-4.70e-01

Pos logit contributions
ksh+0.067
rant+0.066
 flood+0.065
 dolphin+0.063
 whale+0.062
Neg logit contributions
ons-0.106
bes-0.084
ages-0.080
on-0.076
con-0.076
Token a
Token ID257
Feature activation-1.29e+00

Pos logit contributions
ons+0.036
bes+0.029
ages+0.027
on+0.026
con+0.025
Neg logit contributions
ksh-0.025
 flood-0.025
rant-0.025
 dolphin-0.024
 coming-0.024
Token pony
Token ID26902
Feature activation-1.30e+00

Pos logit contributions
ons+0.103
bes+0.081
ages+0.079
on+0.075
con+0.075
Neg logit contributions
ksh-0.066
rant-0.066
 flood-0.061
 dolphin-0.059
 mate-0.058
Tokentail
Token ID13199
Feature activation-1.56e+01

Pos logit contributions
ons+0.106
bes+0.087
ages+0.082
aid+0.076
on+0.076
Neg logit contributions
 flood-0.063
rant-0.062
ksh-0.062
 dolphin-0.061
 coming-0.060
Token wasn
Token ID2492
Feature activation+3.30e+00

Pos logit contributions
ons+1.338
bes+1.059
ages+1.022
on+0.989
es+0.974
Neg logit contributions
ksh-0.772
rant-0.722
 flood-0.698
 dolphin-0.678
 whale-0.662
Token't
Token ID470
Feature activation-4.49e+00

Pos logit contributions
 flood+0.230
rant+0.225
ksh+0.224
 coming+0.224
 dolphin+0.218
Neg logit contributions
ons-0.200
bes-0.152
ages-0.147
con-0.131
es-0.126
Token so
Token ID523
Feature activation-7.80e-01

Pos logit contributions
ons+0.360
bes+0.287
ages+0.274
on+0.258
con+0.256
Neg logit contributions
ksh-0.231
 flood-0.228
rant-0.227
 dolphin-0.219
 whale-0.215
Token important
Token ID1593
Feature activation-9.11e-01

Pos logit contributions
ons+0.066
bes+0.054
ages+0.051
on+0.048
con+0.048
Neg logit contributions
 flood-0.036
ksh-0.036
rant-0.036
 dolphin-0.035
 whale-0.034
Token after
Token ID706
Feature activation+1.29e+00

Pos logit contributions
ons+0.077
bes+0.062
ages+0.059
on+0.057
aid+0.057
Neg logit contributions
ksh-0.042
 coming-0.041
rant-0.041
 flood-0.040
 dolphin-0.040
Token with
Token ID351
Feature activation-1.14e+00

Pos logit contributions
ksh+0.086
rant+0.084
 flood+0.083
 dolphin+0.081
 whale+0.079
Neg logit contributions
ons-0.099
bes-0.076
ages-0.072
on-0.069
es-0.067
Token glasses
Token ID15232
Feature activation-3.94e+00

Pos logit contributions
ons+0.086
bes+0.068
ages+0.065
on+0.060
con+0.060
Neg logit contributions
ksh-0.063
 flood-0.062
rant-0.062
 dolphin-0.061
 whale-0.060
Token and
Token ID290
Feature activation+1.62e-01

Pos logit contributions
ons+0.298
bes+0.235
ages+0.225
con+0.208
on+0.207
Neg logit contributions
ksh-0.217
rant-0.215
 flood-0.213
 dolphin-0.208
 whale-0.204
Token a
Token ID257
Feature activation-8.34e-01

Pos logit contributions
 dolphin+0.008
 flood+0.008
 whale+0.008
ksh+0.008
 mate+0.008
Neg logit contributions
ons-0.013
bes-0.010
ages-0.010
on-0.009
seek-0.009
Token pony
Token ID26902
Feature activation-8.59e-01

Pos logit contributions
ons+0.067
bes+0.053
ages+0.051
on+0.048
con+0.047
Neg logit contributions
ksh-0.043
 flood-0.042
rant-0.042
 dolphin-0.041
 whale-0.040
Tokentail
Token ID13199
Feature activation-1.51e+01

Pos logit contributions
ons+0.066
bes+0.052
ages+0.050
aid+0.047
on+0.046
Neg logit contributions
ksh-0.046
 flood-0.045
rant-0.045
 dolphin-0.044
 coming-0.044
Token.
Token ID13
Feature activation+6.00e-01

Pos logit contributions
ons+1.127
bes+0.882
ages+0.840
on+0.788
es+0.779
Neg logit contributions
ksh-0.875
rant-0.851
 flood-0.847
 dolphin-0.824
 whale-0.810
Token She
Token ID1375
Feature activation-1.46e+00

Pos logit contributions
rant+0.038
ksh+0.038
 flood+0.038
 whale+0.036
 mate+0.036
Neg logit contributions
ons-0.040
bes-0.030
ages-0.029
on-0.027
con-0.027
Token is
Token ID318
Feature activation-1.14e-01

Pos logit contributions
ons+0.103
bes+0.079
ages+0.074
on+0.070
es+0.070
Neg logit contributions
ksh-0.090
 flood-0.088
rant-0.088
 dolphin-0.084
 whale-0.083
Token reading
Token ID3555
Feature activation-8.83e+00

Pos logit contributions
ons+0.008
bes+0.006
ages+0.006
on+0.005
es+0.005
Neg logit contributions
ksh-0.007
 flood-0.007
rant-0.007
 dolphin-0.007
 ending-0.007
Token a
Token ID257
Feature activation-7.99e-01

Pos logit contributions
ons+0.641
bes+0.496
ages+0.476
on+0.442
con+0.437
Neg logit contributions
ksh-0.519
rant-0.511
 flood-0.507
 dolphin-0.495
 whale-0.486
Token cars
Token ID5006
Feature activation-6.50e+00

Pos logit contributions
ons+0.096
bes+0.073
ages+0.070
con+0.067
on+0.067
Neg logit contributions
ksh-0.078
rant-0.076
 flood-0.072
iet-0.070
 dolphin-0.070
Token and
Token ID290
Feature activation-3.96e-01

Pos logit contributions
ons+0.539
bes+0.443
ages+0.421
con+0.395
on+0.391
Neg logit contributions
 flood-0.303
rant-0.303
ksh-0.302
 dolphin-0.287
 mate-0.287
Token the
Token ID262
Feature activation-1.31e+00

Pos logit contributions
ons+0.030
bes+0.025
ages+0.024
seek+0.022
on+0.022
Neg logit contributions
 flood-0.021
 coming-0.020
 dolphin-0.020
 mate-0.020
ksh-0.020
Token cr
Token ID1067
Feature activation-3.50e+00

Pos logit contributions
ons+0.092
bes+0.071
ages+0.067
con+0.063
on+0.063
Neg logit contributions
ksh-0.080
rant-0.080
 flood-0.075
 dolphin-0.075
iet-0.074
Tokenay
Token ID323
Feature activation-1.72e+00

Pos logit contributions
ons+0.269
bes+0.221
ages+0.210
con+0.200
seek+0.196
Neg logit contributions
ksh-0.181
rant-0.180
 flood-0.171
iet-0.167
 mate-0.165
Tokenons
Token ID684
Feature activation-1.44e+01

Pos logit contributions
bes+0.005
ons+0.003
seek-0.002
ages-0.003
con-0.005
Neg logit contributions
 coming-0.190
 whale-0.185
rant-0.184
iet-0.181
ksh-0.180
Token and
Token ID290
Feature activation-4.01e-01

Pos logit contributions
ons+1.153
bes+0.929
ages+0.885
con+0.834
seek+0.823
Neg logit contributions
rant-0.724
ksh-0.724
 flood-0.714
 dolphin-0.692
 mate-0.681
Token make
Token ID787
Feature activation+4.13e-01

Pos logit contributions
ons+0.031
bes+0.025
ages+0.024
seek+0.023
on+0.022
Neg logit contributions
 flood-0.021
 coming-0.020
 dolphin-0.020
ksh-0.020
 mate-0.020
Token something
Token ID1223
Feature activation+1.82e+00

Pos logit contributions
ksh+0.019
 flood+0.018
rant+0.018
 dolphin+0.018
 whale+0.018
Neg logit contributions
ons-0.035
bes-0.029
ages-0.028
seek-0.026
on-0.026
Token nice
Token ID3621
Feature activation+3.25e+00

Pos logit contributions
ksh+0.099
rant+0.098
 flood+0.097
 dolphin+0.094
 whale+0.092
Neg logit contributions
ons-0.140
bes-0.110
ages-0.105
on-0.099
con-0.098
Token."
Token ID526
Feature activation-4.54e+00

Pos logit contributions
ksh+0.185
rant+0.181
 flood+0.181
 dolphin+0.175
 whale+0.172
Neg logit contributions
ons-0.243
bes-0.189
ages-0.182
on-0.171
es-0.168
Token.
Token ID13
Feature activation+2.92e-02

Pos logit contributions
ksh+0.049
rant+0.048
 flood+0.047
 dolphin+0.046
 whale+0.045
Neg logit contributions
ons-0.068
bes-0.053
ages-0.051
on-0.048
con-0.047
Token The
Token ID383
Feature activation-1.58e+00

Pos logit contributions
rant+0.002
ksh+0.002
 flood+0.002
 dolphin+0.002
 mate+0.002
Neg logit contributions
ons-0.002
bes-0.001
ages-0.001
on-0.001
con-0.001
Token melted
Token ID24178
Feature activation+2.63e+00

Pos logit contributions
ons+0.120
bes+0.091
ages+0.088
on+0.084
con+0.080
Neg logit contributions
ksh-0.095
rant-0.089
 mate-0.085
ust-0.084
iet-0.084
Token cr
Token ID1067
Feature activation-3.50e+00

Pos logit contributions
ksh+0.157
rant+0.155
 flood+0.155
 dolphin+0.150
 whale+0.148
Neg logit contributions
ons-0.189
bes-0.146
ages-0.139
on-0.129
con-0.128
Tokenay
Token ID323
Feature activation-1.72e+00

Pos logit contributions
ons+0.265
bes+0.216
ages+0.205
con+0.196
seek+0.192
Neg logit contributions
rant-0.186
ksh-0.184
 flood-0.175
iet-0.171
 coming-0.168
Tokenons
Token ID684
Feature activation-1.44e+01

Pos logit contributions
bes+0.010
ons+0.010
seek+0.009
powers+0.002
ages+0.001
Neg logit contributions
rant-0.182
 coming-0.180
 whale-0.177
iet-0.176
 dolphin-0.173
Token have
Token ID423
Feature activation-3.75e+00

Pos logit contributions
ons+1.143
bes+0.924
ages+0.885
con+0.830
seek+0.827
Neg logit contributions
 flood-0.732
rant-0.731
ksh-0.720
 dolphin-0.699
 coming-0.693
Token made
Token ID925
Feature activation+3.56e+00

Pos logit contributions
ons+0.279
bes+0.220
ages+0.210
on+0.196
con+0.194
Neg logit contributions
ksh-0.211
rant-0.209
 flood-0.207
 dolphin-0.200
 whale-0.198
Token a
Token ID257
Feature activation-1.41e+00

Pos logit contributions
ksh+0.200
rant+0.196
 flood+0.196
 dolphin+0.190
 whale+0.186
Neg logit contributions
ons-0.268
bes-0.210
ages-0.201
on-0.188
con-0.186
Token beautiful
Token ID4950
Feature activation+3.49e+00

Pos logit contributions
ons+0.096
bes+0.071
ages+0.070
on+0.068
con+0.066
Neg logit contributions
rant-0.089
ksh-0.088
iet-0.079
 mate-0.079
 dolphin-0.077
Token pattern
Token ID3912
Feature activation-8.87e-01

Pos logit contributions
ksh+0.218
rant+0.212
 flood+0.205
 dolphin+0.201
 mate+0.198
Neg logit contributions
ons-0.249
bes-0.190
ages-0.178
on-0.173
con-0.166
Token day
Token ID1110
Feature activation-1.44e+00

Pos logit contributions
ksh+0.097
rant+0.093
 flood+0.091
 dolphin+0.087
 mate+0.086
Neg logit contributions
ons-0.122
bes-0.091
ages-0.089
on-0.088
es-0.081
Token,
Token ID11
Feature activation-4.53e-01

Pos logit contributions
ons+0.102
bes+0.083
ages+0.077
con+0.072
aid+0.072
Neg logit contributions
 flood-0.084
 dolphin-0.083
 whale-0.082
ksh-0.082
rant-0.082
Token the
Token ID262
Feature activation-1.31e+00

Pos logit contributions
ons+0.037
bes+0.030
ages+0.029
seek+0.027
con+0.027
Neg logit contributions
 flood-0.023
 dolphin-0.022
ksh-0.022
 whale-0.022
rant-0.022
Token cr
Token ID1067
Feature activation-3.50e+00

Pos logit contributions
ons+0.105
bes+0.082
ages+0.078
on+0.077
con+0.073
Neg logit contributions
ksh-0.070
rant-0.069
 flood-0.067
 dolphin-0.063
iet-0.062
Tokenay
Token ID323
Feature activation-1.72e+00

Pos logit contributions
ons+0.261
bes+0.219
ages+0.206
con+0.196
seek+0.195
Neg logit contributions
rant-0.187
ksh-0.181
 flood-0.175
iet-0.172
 whale-0.168
Tokenons
Token ID684
Feature activation-1.44e+01

Pos logit contributions
ons+0.013
bes+0.012
seek+0.009
ages+0.008
powers+0.003
Neg logit contributions
rant-0.184
 whale-0.184
 dolphin-0.177
 coming-0.177
 dot-0.176
Token wanted
Token ID2227
Feature activation+1.00e+00

Pos logit contributions
ons+1.214
bes+0.978
ages+0.942
on+0.889
con+0.882
Neg logit contributions
ksh-0.680
rant-0.668
 flood-0.666
 dolphin-0.640
 whale-0.628
Token to
Token ID284
Feature activation-7.96e-01

Pos logit contributions
ksh+0.056
rant+0.055
 flood+0.055
 dolphin+0.054
 whale+0.053
Neg logit contributions
ons-0.076
bes-0.060
ages-0.057
on-0.053
con-0.053
Token know
Token ID760
Feature activation-5.74e+00

Pos logit contributions
ons+0.071
bes+0.060
ages+0.059
es+0.056
con+0.055
Neg logit contributions
 flood-0.034
 wake-0.031
 dolphin-0.031
 whale-0.031
rant-0.030
Token which
Token ID543
Feature activation+2.75e+00

Pos logit contributions
ons+0.472
bes+0.370
ages+0.356
on+0.342
es+0.336
Neg logit contributions
ksh-0.291
rant-0.282
 flood-0.282
 dolphin-0.269
 whale-0.263
Token one
Token ID530
Feature activation+4.22e+00

Pos logit contributions
ksh+0.118
rant+0.115
 flood+0.115
 dolphin+0.110
 whale+0.108
Neg logit contributions
ons-0.245
bes-0.200
ages-0.193
on-0.182
con-0.181
Token.
Token ID13
Feature activation+2.92e-02

Pos logit contributions
ons+0.222
bes+0.180
ages+0.170
aid+0.160
on+0.159
Neg logit contributions
 coming-0.175
rant-0.170
ksh-0.169
 mate-0.168
 dolphin-0.167
Token We
Token ID775
Feature activation+2.40e+00

Pos logit contributions
ksh+0.001
rant+0.001
 flood+0.001
 dolphin+0.001
 mate+0.001
Neg logit contributions
ons-0.002
bes-0.002
ages-0.002
on-0.002
con-0.002
Token used
Token ID973
Feature activation-4.69e+00

Pos logit contributions
ksh+0.108
rant+0.104
 flood+0.104
 dolphin+0.100
 whale+0.098
Neg logit contributions
ons-0.210
bes-0.169
ages-0.164
on-0.156
es-0.153
Token cr
Token ID1067
Feature activation-3.50e+00

Pos logit contributions
ons+0.348
bes+0.291
ages+0.279
seek+0.264
es+0.254
Neg logit contributions
rant-0.246
 flood-0.244
ksh-0.242
 dolphin-0.240
 whale-0.238
Tokenay
Token ID323
Feature activation-1.72e+00

Pos logit contributions
ons+0.270
bes+0.237
ages+0.219
seek+0.212
con+0.209
Neg logit contributions
rant-0.165
ksh-0.164
iet-0.154
 mate-0.147
 dolphin-0.143
Tokenons
Token ID684
Feature activation-1.44e+01

Pos logit contributions
bes+0.002
ons+0.001
seek-0.005
tail-0.008
ages-0.011
Neg logit contributions
 coming-0.188
iet-0.188
 whale-0.188
rant-0.187
 dolphin-0.185
Token and
Token ID290
Feature activation-4.01e-01

Pos logit contributions
ons+1.210
bes+1.038
seek+0.935
ages+0.928
rob+0.915
Neg logit contributions
 mate-0.611
rant-0.611
ksh-0.603
 dolphin-0.586
 whale-0.579
Token markers
Token ID19736
Feature activation-5.15e+00

Pos logit contributions
ons+0.029
bes+0.024
ages+0.022
seek+0.021
on+0.021
Neg logit contributions
rant-0.022
ksh-0.021
 flood-0.021
 whale-0.021
 dolphin-0.021
Token to
Token ID284
Feature activation-7.93e-01

Pos logit contributions
ons+0.420
bes+0.354
ages+0.322
seek+0.318
on+0.313
Neg logit contributions
rant-0.233
ksh-0.228
 mate-0.225
 coming-0.212
 dolphin-0.211
Token draw
Token ID3197
Feature activation-2.16e+00

Pos logit contributions
ons+0.067
bes+0.055
ages+0.054
seek+0.050
con+0.050
Neg logit contributions
rant-0.036
 flood-0.036
ksh-0.035
 dolphin-0.034
 whale-0.034
Token pictures
Token ID5986
Feature activation-7.02e+00

Pos logit contributions
ons+0.143
bes+0.114
ages+0.111
seek+0.105
aid+0.103
Neg logit contributions
ksh-0.130
rant-0.130
 coming-0.125
 dolphin-0.123
 flood-0.122
Token his
Token ID465
Feature activation-1.86e+00

Pos logit contributions
ons+0.108
bes+0.074
ages+0.073
on+0.072
con+0.068
Neg logit contributions
ksh-0.109
rant-0.103
 flood-0.100
iet-0.097
 dolphin-0.095
Token paper
Token ID3348
Feature activation-3.70e+00

Pos logit contributions
ons+0.131
bes+0.100
ages+0.095
on+0.089
con+0.087
Neg logit contributions
ksh-0.115
rant-0.113
 flood-0.113
 dolphin-0.109
 whale-0.108
Token and
Token ID290
Feature activation-4.00e-01

Pos logit contributions
ons+0.300
bes+0.238
ages+0.229
on+0.218
es+0.214
Neg logit contributions
ksh-0.188
rant-0.184
 flood-0.183
 dolphin-0.175
 whale-0.172
Token cr
Token ID1067
Feature activation-3.49e+00

Pos logit contributions
ons+0.029
bes+0.024
ages+0.023
seek+0.023
ops+0.022
Neg logit contributions
 dolphin-0.022
 mate-0.022
 whale-0.022
 flood-0.021
 wake-0.021
Tokenay
Token ID323
Feature activation-1.72e+00

Pos logit contributions
ons+0.271
bes+0.226
ages+0.213
con+0.206
seek+0.201
Neg logit contributions
rant-0.177
ksh-0.177
iet-0.164
 flood-0.162
 mate-0.160
Tokenons
Token ID684
Feature activation-1.44e+01

Pos logit contributions
bes+0.001
ons+0.001
seek-0.001
ages-0.007
con-0.008
Neg logit contributions
rant-0.191
 coming-0.189
 whale-0.189
iet-0.186
ksh-0.185
Token back
Token ID736
Feature activation+4.86e+00

Pos logit contributions
ons+1.134
bes+0.903
ages+0.860
con+0.804
on+0.802
Neg logit contributions
ksh-0.762
rant-0.751
 flood-0.745
 dolphin-0.723
 whale-0.708
Token.
Token ID13
Feature activation+1.23e-02

Pos logit contributions
rant+0.214
 coming+0.208
ksh+0.206
 flood+0.205
 mate+0.199
Neg logit contributions
ons-0.420
bes-0.345
ages-0.334
aid-0.313
con-0.313
Token He
Token ID679
Feature activation-1.61e+00

Pos logit contributions
ksh+0.001
 flood+0.001
rant+0.001
 dolphin+0.001
 whale+0.001
Neg logit contributions
ons-0.001
bes-0.001
ages-0.001
on-0.001
con-0.001
Token wants
Token ID3382
Feature activation-1.57e+00

Pos logit contributions
ons+0.118
bes+0.091
ages+0.087
on+0.082
con+0.080
Neg logit contributions
ksh-0.095
rant-0.093
 flood-0.093
 dolphin-0.090
 whale-0.089
Token his
Token ID465
Feature activation-1.85e+00

Pos logit contributions
ons+0.106
bes+0.074
ages+0.071
on+0.071
aid+0.066
Neg logit contributions
ksh-0.109
rant-0.104
 flood-0.103
 dolphin-0.098
iet-0.098
Token are
Token ID389
Feature activation+6.86e-01

Pos logit contributions
 flood+0.182
 ending+0.171
 whale+0.167
 dolphin+0.165
 coming+0.164
Neg logit contributions
ons-0.314
bes-0.280
ages-0.267
aid-0.257
con-0.253
Token papers
Token ID9473
Feature activation-8.98e+00

Pos logit contributions
 flood+0.039
ksh+0.038
rant+0.037
 whale+0.037
 dolphin+0.037
Neg logit contributions
ons-0.051
bes-0.041
ages-0.039
con-0.037
seek-0.036
Token and
Token ID290
Feature activation-4.00e-01

Pos logit contributions
ons+0.703
bes+0.559
ages+0.541
con+0.506
seek+0.501
Neg logit contributions
 flood-0.462
rant-0.458
ksh-0.454
 dolphin-0.438
 coming-0.437
Token cr
Token ID1067
Feature activation-3.49e+00

Pos logit contributions
ons+0.025
bes+0.019
ages+0.018
seek+0.017
con+0.016
Neg logit contributions
 flood-0.027
ksh-0.026
 dolphin-0.026
 whale-0.026
rant-0.026
Tokenay
Token ID323
Feature activation-1.72e+00

Pos logit contributions
ons+0.260
bes+0.208
ages+0.197
con+0.186
seek+0.183
Neg logit contributions
ksh-0.194
rant-0.193
 flood-0.186
 dolphin-0.178
iet-0.177
Tokenons
Token ID684
Feature activation-1.44e+01

Pos logit contributions
ons+0.001
bes-0.004
seek-0.009
tail-0.010
ages-0.013
Neg logit contributions
 coming-0.195
rant-0.194
ksh-0.192
 whale-0.188
iet-0.186
Token and
Token ID290
Feature activation-4.01e-01

Pos logit contributions
ons+1.131
bes+0.909
ages+0.867
con+0.815
seek+0.812
Neg logit contributions
rant-0.737
ksh-0.735
 flood-0.731
 dolphin-0.701
 coming-0.698
Token stickers
Token ID28568
Feature activation-7.57e+00

Pos logit contributions
ons+0.025
bes+0.019
ages+0.018
seek+0.017
on+0.017
Neg logit contributions
 flood-0.026
ksh-0.026
 dolphin-0.025
 whale-0.025
rant-0.025
Token and
Token ID290
Feature activation-3.90e-01

Pos logit contributions
ons+0.595
bes+0.481
ages+0.456
con+0.428
seek+0.426
Neg logit contributions
rant-0.388
ksh-0.385
 flood-0.376
 dolphin-0.364
 coming-0.363
Token glue
Token ID22749
Feature activation-4.19e+00

Pos logit contributions
ons+0.026
bes+0.020
ages+0.019
on+0.018
seek+0.018
Neg logit contributions
ksh-0.024
 flood-0.023
 mate-0.023
 dolphin-0.023
rant-0.023
Token.
Token ID13
Feature activation+2.66e-02

Pos logit contributions
ons+0.321
bes+0.253
ages+0.242
on+0.227
con+0.225
Neg logit contributions
ksh-0.228
rant-0.226
 flood-0.223
 dolphin-0.216
 whale-0.213
Token line
Token ID1627
Feature activation-3.00e+00

Pos logit contributions
ons+0.256
bes+0.207
ages+0.203
aid+0.193
seek+0.192
Neg logit contributions
 flood-0.136
ksh-0.134
rant-0.133
 whale-0.129
 dolphin-0.129
Token with
Token ID351
Feature activation-1.70e+00

Pos logit contributions
ons+0.226
bes+0.185
ages+0.176
aid+0.164
con+0.164
Neg logit contributions
rant-0.156
 coming-0.156
 flood-0.154
ksh-0.151
 mate-0.146
Token the
Token ID262
Feature activation-1.32e+00

Pos logit contributions
ons+0.119
bes+0.089
ages+0.085
on+0.080
con+0.078
Neg logit contributions
ksh-0.107
rant-0.104
 flood-0.104
 dolphin-0.101
 whale-0.099
Token cr
Token ID1067
Feature activation-3.49e+00

Pos logit contributions
ons+0.095
bes+0.072
ages+0.069
on+0.065
con+0.064
Neg logit contributions
ksh-0.081
rant-0.079
 flood-0.078
 dolphin-0.076
 whale-0.074
Tokenay
Token ID323
Feature activation-1.72e+00

Pos logit contributions
ons+0.265
bes+0.215
ages+0.204
con+0.191
seek+0.190
Neg logit contributions
ksh-0.187
rant-0.186
 flood-0.178
 dolphin-0.173
iet-0.171
Tokenons
Token ID684
Feature activation-1.44e+01

Pos logit contributions
ons+0.007
bes-0.002
seek-0.008
ages-0.008
tail-0.013
Neg logit contributions
rant-0.196
 whale-0.193
 coming-0.193
ksh-0.191
iet-0.190
Token.
Token ID13
Feature activation+1.55e-02

Pos logit contributions
ons+1.062
bes+0.815
ages+0.786
on+0.745
es+0.731
Neg logit contributions
ksh-0.848
rant-0.824
 flood-0.823
 dolphin-0.795
 whale-0.781
Token Then
Token ID3244
Feature activation-5.91e+00

Pos logit contributions
ksh+0.001
rant+0.001
 flood+0.001
 dolphin+0.001
 whale+0.001
Neg logit contributions
ons-0.001
bes-0.001
ages-0.001
on-0.001
aid-0.001
Token,
Token ID11
Feature activation-4.48e-01

Pos logit contributions
ons+0.472
bes+0.380
ages+0.362
on+0.342
con+0.341
Neg logit contributions
 flood-0.304
ksh-0.294
 dolphin-0.290
rant-0.289
 ending-0.285
Token they
Token ID484
Feature activation+2.69e+00

Pos logit contributions
ons+0.036
bes+0.028
ages+0.027
on+0.025
con+0.025
Neg logit contributions
ksh-0.023
 flood-0.023
rant-0.023
 dolphin-0.022
 whale-0.022
Token drew
Token ID9859
Feature activation-2.39e+00

Pos logit contributions
ksh+0.135
rant+0.135
 flood+0.133
 dolphin+0.129
 whale+0.127
Neg logit contributions
ons-0.216
bes-0.176
ages-0.168
con-0.157
seek-0.156
Token her
Token ID607
Feature activation-1.49e+00

Pos logit contributions
 flood+0.010
 coming+0.010
rant+0.009
ksh+0.009
 dolphin+0.009
Neg logit contributions
ons-0.018
bes-0.016
ages-0.015
con-0.015
seek-0.014
Token diary
Token ID26339
Feature activation-6.33e+00

Pos logit contributions
ons+0.112
ages+0.092
seek+0.091
bes+0.090
rob+0.086
Neg logit contributions
 dolphin-0.077
 flood-0.075
 coming-0.074
 whale-0.074
 harbor-0.072
Token and
Token ID290
Feature activation-3.98e-01

Pos logit contributions
ons+0.547
bes+0.431
ages+0.417
rob+0.403
con+0.402
Neg logit contributions
 coming-0.274
 flood-0.272
rant-0.271
ksh-0.269
 mate-0.263
Token cr
Token ID1067
Feature activation-3.51e+00

Pos logit contributions
ons+0.033
rob+0.029
ages+0.029
seek+0.029
bes+0.028
Neg logit contributions
 coming-0.016
 wake-0.015
 flood-0.015
 dolphin-0.015
 spr-0.014
Tokenay
Token ID323
Feature activation-1.72e+00

Pos logit contributions
ons+0.274
bes+0.229
ages+0.217
con+0.207
seek+0.203
Neg logit contributions
rant-0.174
ksh-0.173
iet-0.161
 flood-0.158
 mate-0.157
Tokenons
Token ID684
Feature activation-1.44e+01

Pos logit contributions
seek+0.011
bes+0.011
ages+0.004
ons+0.001
tail+0.000
Neg logit contributions
 coming-0.179
 them-0.176
rant-0.174
 us-0.170
iet-0.169
Token.
Token ID13
Feature activation+1.55e-02

Pos logit contributions
ons+1.140
bes+0.913
ages+0.870
con+0.811
seek+0.804
Neg logit contributions
ksh-0.745
rant-0.739
 flood-0.727
 dolphin-0.711
 coming-0.694
Token She
Token ID1375
Feature activation-2.05e+00

Pos logit contributions
ksh+0.001
rant+0.001
 dolphin+0.001
 flood+0.001
 coming+0.001
Neg logit contributions
ons-0.001
ages-0.001
bes-0.001
aid-0.001
on-0.001
Token put
Token ID1234
Feature activation+7.97e-01

Pos logit contributions
ons+0.177
ages+0.143
bes+0.143
seek+0.139
con+0.139
Neg logit contributions
rant-0.080
 dolphin-0.080
ksh-0.078
 whale-0.078
 coming-0.076
Token them
Token ID606
Feature activation+8.46e+00

Pos logit contributions
rant+0.041
ksh+0.040
 flood+0.039
 dolphin+0.039
 whale+0.038
Neg logit contributions
ons-0.062
bes-0.051
ages-0.050
seek-0.047
con-0.045
Token in
Token ID287
Feature activation+1.46e+00

Pos logit contributions
rant+0.446
ksh+0.441
 flood+0.435
 coming+0.434
 dolphin+0.426
Neg logit contributions
ons-0.636
bes-0.511
ages-0.498
con-0.484
seek-0.479
Token took
Token ID1718
Feature activation+9.77e-01

Pos logit contributions
ons+0.173
bes+0.148
ages+0.145
seek+0.140
con+0.139
Neg logit contributions
rant-0.083
 whale-0.080
 wake-0.079
 rum-0.079
 coming-0.078
Token out
Token ID503
Feature activation+6.45e+00

Pos logit contributions
 coming+0.038
rant+0.037
 wake+0.035
 like+0.034
 them+0.034
Neg logit contributions
ons-0.081
bes-0.077
ages-0.073
rob-0.071
seek-0.069
Token some
Token ID617
Feature activation-2.06e+00

Pos logit contributions
 coming+0.293
 dolphin+0.293
iet+0.279
 mate+0.279
 whale+0.278
Neg logit contributions
ons-0.498
bes-0.455
ages-0.438
rob-0.421
seek-0.417
Token cr
Token ID1067
Feature activation-3.51e+00

Pos logit contributions
ons+0.145
bes+0.136
ages+0.129
seek+0.129
rob+0.116
Neg logit contributions
 coming-0.106
 dolphin-0.105
 whale-0.104
rant-0.102
 flood-0.100
Tokenay
Token ID323
Feature activation-1.72e+00

Pos logit contributions
ons+0.269
bes+0.229
ages+0.214
con+0.206
seek+0.204
Neg logit contributions
rant-0.175
ksh-0.174
iet-0.162
 dolphin-0.155
 mate-0.155
Tokenons
Token ID684
Feature activation-1.44e+01

Pos logit contributions
bes+0.011
seek+0.007
ons+0.001
tail+0.000
ages-0.001
Neg logit contributions
 coming-0.181
rant-0.180
iet-0.177
 whale-0.177
 dolphin-0.176
Token and
Token ID290
Feature activation-4.01e-01

Pos logit contributions
ons+1.178
bes+0.966
ages+0.910
con+0.856
seek+0.854
Neg logit contributions
ksh-0.686
rant-0.684
 dolphin-0.667
 flood-0.664
 whale-0.649
Token paper
Token ID3348
Feature activation-3.69e+00

Pos logit contributions
ons+0.031
bes+0.028
seek+0.026
ages+0.026
ittens+0.026
Neg logit contributions
 coming-0.017
rant-0.017
 dolphin-0.017
 whale-0.017
 wake-0.016
Token,
Token ID11
Feature activation-4.58e-01

Pos logit contributions
ons+0.285
bes+0.229
ages+0.218
seek+0.206
aid+0.205
Neg logit contributions
rant-0.189
ksh-0.187
 dolphin-0.183
 flood-0.181
 coming-0.180
Token and
Token ID290
Feature activation-4.02e-01

Pos logit contributions
ons+0.037
bes+0.031
ages+0.030
seek+0.028
con+0.027
Neg logit contributions
rant-0.021
 coming-0.021
ksh-0.021
 dolphin-0.020
 flood-0.020
Token she
Token ID673
Feature activation-3.25e+00

Pos logit contributions
ons+0.032
bes+0.027
ages+0.025
seek+0.024
con+0.023
Neg logit contributions
rant-0.019
 coming-0.019
 dolphin-0.019
 flood-0.019
 whale-0.019
Token.
Token ID13
Feature activation+2.61e-02

Pos logit contributions
rant+0.212
ksh+0.208
 coming+0.206
 flood+0.202
 dolphin+0.201
Neg logit contributions
ons-0.319
bes-0.263
ages-0.251
con-0.234
aid-0.233
Token She
Token ID1375
Feature activation-2.05e+00

Pos logit contributions
ksh+0.001
rant+0.001
 flood+0.001
 dolphin+0.001
 whale+0.001
Neg logit contributions
ons-0.002
bes-0.002
ages-0.001
on-0.001
con-0.001
Token used
Token ID973
Feature activation-4.69e+00

Pos logit contributions
ons+0.171
bes+0.143
ages+0.139
con+0.131
seek+0.129
Neg logit contributions
 whale-0.091
rant-0.091
 dolphin-0.090
ksh-0.086
 flood-0.086
Token cr
Token ID1067
Feature activation-3.51e+00

Pos logit contributions
ons+0.346
bes+0.296
ages+0.287
seek+0.268
rob+0.258
Neg logit contributions
rant-0.242
 coming-0.239
 dolphin-0.237
 mate-0.234
 flood-0.234
Tokenay
Token ID323
Feature activation-1.72e+00

Pos logit contributions
ons+0.269
bes+0.238
ages+0.220
seek+0.209
con+0.209
Neg logit contributions
rant-0.169
ksh-0.162
iet-0.154
 mate-0.149
 coming-0.146
Tokenons
Token ID684
Feature activation-1.44e+01

Pos logit contributions
bes+0.005
ons+0.000
seek-0.003
tail-0.004
ages-0.007
Neg logit contributions
 coming-0.186
rant-0.185
iet-0.185
 whale-0.180
 mate-0.178
Token of
Token ID286
Feature activation-1.73e+00

Pos logit contributions
ons+1.128
bes+0.927
ages+0.866
con+0.810
seek+0.808
Neg logit contributions
rant-0.735
ksh-0.729
 flood-0.707
 dolphin-0.704
 coming-0.690
Token different
Token ID1180
Feature activation+3.84e+00

Pos logit contributions
ons+0.122
bes+0.103
ages+0.099
seek+0.093
aid+0.088
Neg logit contributions
rant-0.096
 dolphin-0.094
 whale-0.093
ksh-0.092
 flood-0.092
Token colors
Token ID7577
Feature activation-8.88e-01

Pos logit contributions
rant+0.199
ksh+0.190
 coming+0.188
 appearance+0.183
 mate+0.182
Neg logit contributions
ons-0.274
bes-0.240
ages-0.222
aid-0.217
seek-0.211
Token.
Token ID13
Feature activation+1.44e-02

Pos logit contributions
ons+0.067
bes+0.054
ages+0.052
seek+0.048
con+0.048
Neg logit contributions
rant-0.048
ksh-0.047
 flood-0.046
 dolphin-0.045
 whale-0.045
Token She
Token ID1375
Feature activation-2.05e+00

Pos logit contributions
ksh+0.001
rant+0.001
 flood+0.001
 dolphin+0.001
 whale+0.001
Neg logit contributions
ons-0.001
bes-0.001
ages-0.001
on-0.001
con-0.001
Token would
Token ID561
Feature activation+1.29e+00

Pos logit contributions
ksh+0.132
 flood+0.132
rant+0.131
 dolphin+0.127
 whale+0.125
Neg logit contributions
ons-0.220
bes-0.178
ages-0.169
on-0.159
con-0.158
Token spend
Token ID4341
Feature activation-2.12e+00

Pos logit contributions
ksh+0.072
rant+0.068
 flood+0.063
 dolphin+0.062
 whale+0.062
Neg logit contributions
ons-0.099
bes-0.079
ages-0.075
on-0.072
seek-0.071
Token their
Token ID511
Feature activation+5.89e+00

Pos logit contributions
ons+0.174
bes+0.141
ages+0.138
on+0.132
con+0.130
Neg logit contributions
 flood-0.094
rant-0.091
ksh-0.091
 dolphin-0.089
 coming-0.089
Token after
Token ID706
Feature activation+1.14e+00

Pos logit contributions
ksh+0.318
 flood+0.316
rant+0.308
 dolphin+0.304
 whale+0.299
Neg logit contributions
ons-0.454
bes-0.356
ages-0.339
on-0.324
es-0.319
Tokenno
Token ID3919
Feature activation-5.29e+00

Pos logit contributions
 coming+0.058
 flood+0.056
 dolphin+0.054
 whale+0.052
 harbor+0.049
Neg logit contributions
ons-0.088
bes-0.076
ages-0.072
aid-0.071
aces-0.068
Tokenons
Token ID684
Feature activation-1.44e+01

Pos logit contributions
bes+0.206
ons+0.199
con+0.185
ages+0.162
seek+0.153
Neg logit contributions
 coming-0.409
 flood-0.384
 ending-0.379
 storm-0.371
 whale-0.363
Token in
Token ID287
Feature activation+1.47e+00

Pos logit contributions
ons+1.079
bes+0.864
ages+0.802
on+0.760
con+0.752
Neg logit contributions
ksh-0.777
 flood-0.775
 dolphin-0.752
 coming-0.750
rant-0.750
Token the
Token ID262
Feature activation-1.32e+00

Pos logit contributions
ksh+0.086
 flood+0.085
rant+0.085
 dolphin+0.082
 whale+0.081
Neg logit contributions
ons-0.107
bes-0.083
ages-0.080
on-0.074
con-0.073
Token shade
Token ID17979
Feature activation-4.94e-01

Pos logit contributions
ons+0.089
bes+0.064
ages+0.064
con+0.062
on+0.061
Neg logit contributions
rant-0.085
ksh-0.082
 mate-0.076
 extingu-0.075
 dolphin-0.073
Token together
Token ID1978
Feature activation-4.15e+00

Pos logit contributions
ons+0.039
bes+0.033
ages+0.030
aid+0.029
con+0.029
Neg logit contributions
 flood-0.025
rant-0.025
ksh-0.024
 coming-0.023
 whale-0.023
Token.
Token ID13
Feature activation+3.43e-02

Pos logit contributions
ons+0.292
bes+0.219
ages+0.209
es+0.200
on+0.199
Neg logit contributions
ksh-0.261
rant-0.253
 flood-0.252
 dolphin-0.243
 whale-0.240
Token car
Token ID1097
Feature activation-3.33e+00

Pos logit contributions
ons+0.157
bes+0.123
ages+0.120
es+0.115
on+0.113
Neg logit contributions
 flood-0.093
ksh-0.088
 dolphin-0.088
 whale-0.087
 ending-0.086
Token with
Token ID351
Feature activation-1.69e+00

Pos logit contributions
ons+0.270
bes+0.222
ages+0.211
aid+0.193
con+0.193
Neg logit contributions
 flood-0.167
 coming-0.166
rant-0.160
ksh-0.157
 ending-0.157
Token his
Token ID465
Feature activation-1.86e+00

Pos logit contributions
ons+0.112
bes+0.088
ages+0.085
con+0.077
es+0.075
Neg logit contributions
 flood-0.108
rant-0.108
ksh-0.106
 coming-0.104
 dolphin-0.104
Token cr
Token ID1067
Feature activation-3.50e+00

Pos logit contributions
ons+0.161
bes+0.130
ages+0.126
seek+0.123
es+0.119
Neg logit contributions
 flood-0.083
 dolphin-0.081
ksh-0.080
 whale-0.080
 mate-0.079
Tokenay
Token ID323
Feature activation-1.72e+00

Pos logit contributions
ons+0.274
bes+0.230
ages+0.218
con+0.208
seek+0.203
Neg logit contributions
ksh-0.171
rant-0.169
 flood-0.159
iet-0.158
 mate-0.157
Tokenons
Token ID684
Feature activation-1.44e+01

Pos logit contributions
bes+0.006
seek+0.005
ons+0.004
ages+0.003
tail+0.003
Neg logit contributions
 coming-0.185
rant-0.181
iet-0.178
 mate-0.177
 whale-0.177
Token,
Token ID11
Feature activation-4.48e-01

Pos logit contributions
ons+1.049
bes+0.810
ages+0.775
on+0.725
con+0.714
Neg logit contributions
ksh-0.851
rant-0.836
 flood-0.834
 dolphin-0.808
 whale-0.797
Token but
Token ID475
Feature activation+4.92e+00

Pos logit contributions
ons+0.044
bes+0.037
ages+0.036
on+0.034
con+0.034
Neg logit contributions
ksh-0.015
rant-0.015
 flood-0.014
 dolphin-0.014
 whale-0.013
Token he
Token ID339
Feature activation-2.44e+00

Pos logit contributions
 flood+0.328
 dolphin+0.321
 coming+0.319
 mate+0.318
 ending+0.317
Neg logit contributions
ons-0.314
bes-0.243
ages-0.232
con-0.213
seek-0.211
Token didn
Token ID1422
Feature activation-1.24e+00

Pos logit contributions
ons+0.209
bes+0.169
ages+0.162
con+0.153
on+0.152
Neg logit contributions
ksh-0.112
rant-0.110
 flood-0.110
 dolphin-0.107
 whale-0.104
Token't
Token ID470
Feature activation-4.62e+00

Pos logit contributions
ons+0.084
ages+0.069
bes+0.068
aid+0.063
con+0.062
Neg logit contributions
 flood-0.073
 coming-0.072
rant-0.069
 wake-0.069
ksh-0.067
Token many
Token ID867
Feature activation-7.71e+00

Pos logit contributions
ons+0.138
bes+0.110
ages+0.105
con+0.098
on+0.098
Neg logit contributions
ksh-0.101
rant-0.099
 flood-0.097
 dolphin-0.097
 coming-0.096
Token colors
Token ID7577
Feature activation-8.86e-01

Pos logit contributions
ons+0.534
bes+0.460
seek+0.451
ages+0.448
aid+0.425
Neg logit contributions
 dolphin-0.395
 coming-0.393
iet-0.389
 whale-0.385
rant-0.378
Token of
Token ID286
Feature activation-1.73e+00

Pos logit contributions
ons+0.068
bes+0.054
ages+0.052
con+0.048
on+0.048
Neg logit contributions
rant-0.048
ksh-0.048
 flood-0.047
 dolphin-0.046
 whale-0.045
Token cr
Token ID1067
Feature activation-3.50e+00

Pos logit contributions
ons+0.129
bes+0.101
ages+0.098
on+0.090
seek+0.089
Neg logit contributions
ksh-0.097
rant-0.096
 flood-0.096
 dolphin-0.094
 whale-0.092
Tokenay
Token ID323
Feature activation-1.72e+00

Pos logit contributions
ons+0.267
bes+0.232
ages+0.219
con+0.207
seek+0.207
Neg logit contributions
rant-0.169
ksh-0.164
iet-0.159
 coming-0.148
 mate-0.147
Tokenons
Token ID684
Feature activation-1.44e+01

Pos logit contributions
bes+0.003
seek+0.001
ons+0.000
ages-0.003
tail-0.004
Neg logit contributions
 coming-0.185
rant-0.183
iet-0.182
 whale-0.177
 them-0.176
Token.
Token ID13
Feature activation+2.59e-02

Pos logit contributions
ons+1.108
bes+0.889
ages+0.844
con+0.786
seek+0.781
Neg logit contributions
rant-0.765
ksh-0.755
 flood-0.745
 dolphin-0.731
 coming-0.722
Token She
Token ID1375
Feature activation-2.05e+00

Pos logit contributions
ksh+0.002
 flood+0.002
rant+0.002
 dolphin+0.002
 whale+0.001
Neg logit contributions
ons-0.002
bes-0.001
ages-0.001
on-0.001
con-0.001
Token likes
Token ID7832
Feature activation-6.01e-01

Pos logit contributions
ons+0.159
bes+0.125
ages+0.121
on+0.112
con+0.112
Neg logit contributions
ksh-0.110
rant-0.109
 flood-0.107
 dolphin-0.105
 whale-0.103
Token red
Token ID2266
Feature activation+1.97e+00

Pos logit contributions
ons+0.046
bes+0.036
ages+0.035
on+0.032
con+0.032
Neg logit contributions
ksh-0.033
rant-0.033
 flood-0.032
 dolphin-0.032
 whale-0.031
Token and
Token ID290
Feature activation-3.82e-01

Pos logit contributions
ksh+0.097
rant+0.095
 dolphin+0.094
 coming+0.093
 dot+0.091
Neg logit contributions
ons-0.143
bes-0.123
ages-0.119
aid-0.114
seek-0.112
Token a
Token ID257
Feature activation-1.41e+00

Pos logit contributions
ksh+0.156
rant+0.151
 flood+0.150
 dolphin+0.143
 whale+0.141
Neg logit contributions
ons-0.167
bes-0.123
ages-0.119
on-0.113
es-0.111
Token box
Token ID3091
Feature activation-2.65e+00

Pos logit contributions
ons+0.099
bes+0.076
ages+0.071
on+0.070
con+0.069
Neg logit contributions
ksh-0.090
rant-0.087
 flood-0.080
iet-0.077
 ending-0.075
Token of
Token ID286
Feature activation-1.73e+00

Pos logit contributions
ons+0.185
bes+0.139
ages+0.132
on+0.127
es+0.122
Neg logit contributions
ksh-0.170
 flood-0.163
rant-0.162
 dolphin-0.158
 whale-0.155
Token cr
Token ID1067
Feature activation-3.49e+00

Pos logit contributions
ons+0.116
bes+0.092
ages+0.089
seek+0.083
es+0.080
Neg logit contributions
 flood-0.107
 dolphin-0.106
rant-0.104
 whale-0.104
ksh-0.104
Tokenay
Token ID323
Feature activation-1.72e+00

Pos logit contributions
ons+0.263
bes+0.216
ages+0.206
con+0.193
seek+0.191
Neg logit contributions
rant-0.185
ksh-0.182
 flood-0.173
iet-0.170
 dolphin-0.168
Tokenons
Token ID684
Feature activation-1.44e+01

Pos logit contributions
ons+0.001
bes-0.003
seek-0.006
ages-0.008
tail-0.012
Neg logit contributions
 coming-0.193
rant-0.193
 whale-0.189
iet-0.187
 dolphin-0.186
Token and
Token ID290
Feature activation-4.00e-01

Pos logit contributions
ons+1.137
bes+0.905
ages+0.868
on+0.809
con+0.806
Neg logit contributions
ksh-0.744
rant-0.740
 flood-0.732
 dolphin-0.713
 whale-0.701
Token a
Token ID257
Feature activation-1.41e+00

Pos logit contributions
ons+0.030
bes+0.025
ages+0.023
seek+0.022
aid+0.022
Neg logit contributions
 dolphin-0.021
 whale-0.021
 mate-0.020
rant-0.020
 coming-0.020
Token sketch
Token ID17548
Feature activation+1.15e+00

Pos logit contributions
ons+0.104
bes+0.081
ages+0.077
on+0.073
con+0.072
Neg logit contributions
ksh-0.081
rant-0.080
 flood-0.079
 dolphin-0.077
 whale-0.076
Tokenbook
Token ID2070
Feature activation-5.16e+00

Pos logit contributions
ksh+0.087
 flood+0.086
rant+0.086
 dolphin+0.084
 whale+0.083
Neg logit contributions
ons-0.065
bes-0.046
ages-0.043
on-0.039
con-0.038
Token.
Token ID13
Feature activation+1.55e-02

Pos logit contributions
ons+0.376
bes+0.292
ages+0.279
on+0.263
es+0.258
Neg logit contributions
ksh-0.309
 flood-0.301
rant-0.299
 dolphin-0.289
 whale-0.284
Token job
Token ID1693
Feature activation-6.59e+00

Pos logit contributions
 flood+0.160
ksh+0.159
 dolphin+0.154
rant+0.154
 ending+0.154
Neg logit contributions
ons-0.160
bes-0.120
ages-0.113
aid-0.105
es-0.105
Token organizing
Token ID16924
Feature activation+4.11e-01

Pos logit contributions
ons+0.470
bes+0.367
ages+0.348
aid+0.328
con+0.326
Neg logit contributions
 flood-0.385
ksh-0.383
rant-0.378
 coming-0.371
 dolphin-0.368
Token your
Token ID534
Feature activation-3.44e+00

Pos logit contributions
rant+0.023
ksh+0.023
 flood+0.022
 dolphin+0.022
 coming+0.022
Neg logit contributions
ons-0.029
ages-0.023
bes-0.023
aid-0.022
seek-0.022
Token cr
Token ID1067
Feature activation-3.50e+00

Pos logit contributions
ons+0.246
bes+0.192
ages+0.188
aid+0.181
seek+0.178
Neg logit contributions
 flood-0.194
ksh-0.194
 whale-0.187
rant-0.186
 ending-0.185
Tokenay
Token ID323
Feature activation-1.72e+00

Pos logit contributions
ons+0.286
bes+0.258
ages+0.243
rob+0.239
aid+0.238
Neg logit contributions
ksh-0.132
rant-0.125
iet-0.125
 mate-0.111
 dot-0.109
Tokenons
Token ID684
Feature activation-1.44e+01

Pos logit contributions
seek+0.013
bes+0.012
aid+0.008
tail+0.008
con+0.008
Neg logit contributions
 coming-0.167
iet-0.164
rant-0.159
 whale-0.159
y-0.159
Token by
Token ID416
Feature activation-3.48e-01

Pos logit contributions
ons+1.078
bes+0.894
ages+0.822
aid+0.817
con+0.804
Neg logit contributions
ksh-0.714
rant-0.708
 coming-0.708
 flood-0.707
 like-0.701
Token color
Token ID3124
Feature activation+1.47e+00

Pos logit contributions
ons+0.028
bes+0.022
ages+0.022
aid+0.021
con+0.020
Neg logit contributions
 flood-0.017
rant-0.017
ksh-0.017
 dolphin-0.017
 whale-0.017
Token,"
Token ID553
Feature activation-7.87e+00

Pos logit contributions
ksh+0.082
rant+0.081
 flood+0.079
 coming+0.078
 dolphin+0.077
Neg logit contributions
ons-0.097
bes-0.082
seek-0.076
ages-0.075
aid-0.074
Token she
Token ID673
Feature activation-3.24e+00

Pos logit contributions
ons+0.589
bes+0.503
seek+0.498
ages+0.487
powers+0.470
Neg logit contributions
 dolphin-0.400
Why-0.393
 coming-0.388
 why-0.388
 whale-0.383
Token said
Token ID531
Feature activation-3.13e+00

Pos logit contributions
ons+0.259
orns+0.226
bes+0.223
igs+0.210
seek+0.206
Neg logit contributions
 dolphin-0.151
ksh-0.145
 mer-0.144
 whale-0.143
 rum-0.139
Token a
Token ID257
Feature activation-1.41e+00

Pos logit contributions
ksh+0.132
rant+0.129
 dolphin+0.127
 flood+0.126
 whale+0.124
Neg logit contributions
ons-0.180
bes-0.146
ages-0.135
con-0.128
on-0.126
Token box
Token ID3091
Feature activation-2.64e+00

Pos logit contributions
ons+0.103
bes+0.076
on+0.074
ages+0.074
con+0.071
Neg logit contributions
ksh-0.085
rant-0.083
 flood-0.078
iet-0.075
 dolphin-0.074
Token of
Token ID286
Feature activation-1.73e+00

Pos logit contributions
ons+0.188
bes+0.145
ages+0.137
on+0.128
con+0.127
Neg logit contributions
ksh-0.160
rant-0.157
 flood-0.157
 dolphin-0.152
 whale-0.150
Token cr
Token ID1067
Feature activation-3.50e+00

Pos logit contributions
ons+0.120
bes+0.105
ages+0.105
seek+0.101
es+0.095
Neg logit contributions
 flood-0.099
 dolphin-0.097
 whale-0.095
 coming-0.091
 tide-0.091
Tokenay
Token ID323
Feature activation-1.72e+00

Pos logit contributions
ons+0.270
bes+0.232
ages+0.219
con+0.212
seek+0.206
Neg logit contributions
rant-0.168
ksh-0.167
iet-0.157
 flood-0.151
 mate-0.150
Tokenons
Token ID684
Feature activation-1.44e+01

Pos logit contributions
bes+0.018
seek+0.016
ages+0.007
tail+0.006
powers+0.006
Neg logit contributions
 coming-0.176
iet-0.166
rant-0.166
 whale-0.166
 dolphin-0.163
Token and
Token ID290
Feature activation-4.06e-01

Pos logit contributions
ons+1.199
bes+1.008
ages+0.921
seek+0.891
con+0.889
Neg logit contributions
rant-0.656
ksh-0.652
 dolphin-0.632
 coming-0.630
 flood-0.618
Token some
Token ID617
Feature activation-2.06e+00

Pos logit contributions
ons+0.030
bes+0.028
seek+0.025
ages+0.024
tail+0.023
Neg logit contributions
 dolphin-0.020
 whale-0.020
 coming-0.019
 flood-0.019
 mate-0.019
Token paper
Token ID3348
Feature activation-3.70e+00

Pos logit contributions
ons+0.147
bes+0.120
ages+0.112
seek+0.107
es+0.103
Neg logit contributions
 flood-0.118
ksh-0.117
rant-0.117
 dolphin-0.116
 whale-0.114
Token.
Token ID13
Feature activation+2.59e-02

Pos logit contributions
ons+0.289
bes+0.232
ages+0.219
seek+0.208
on+0.205
Neg logit contributions
ksh-0.189
rant-0.188
 flood-0.184
 dolphin-0.183
 whale-0.180
Token Tim
Token ID5045
Feature activation+1.94e+00

Pos logit contributions
ksh+0.001
 flood+0.001
rant+0.001
 dolphin+0.001
 coming+0.001
Neg logit contributions
ons-0.002
bes-0.002
ages-0.002
es-0.002
aid-0.002
Token new
Token ID649
Feature activation-1.07e-01

Pos logit contributions
ons+0.101
bes+0.074
on+0.072
ages+0.071
aid+0.069
Neg logit contributions
rant-0.089
ksh-0.088
 flood-0.078
 mate-0.077
iet-0.076
Token box
Token ID3091
Feature activation-2.64e+00

Pos logit contributions
ons+0.008
bes+0.007
ages+0.006
on+0.006
con+0.006
Neg logit contributions
ksh-0.006
rant-0.006
 flood-0.005
 dolphin-0.005
 mate-0.005
Token of
Token ID286
Feature activation-1.73e+00

Pos logit contributions
ons+0.200
bes+0.158
ages+0.151
con+0.141
on+0.140
Neg logit contributions
ksh-0.145
rant-0.144
 flood-0.142
 dolphin-0.138
 whale-0.136
Token cr
Token ID1067
Feature activation-3.50e+00

Pos logit contributions
ons+0.118
ages+0.099
bes+0.099
seek+0.093
es+0.089
Neg logit contributions
 flood-0.103
 dolphin-0.103
 whale-0.100
 coming-0.097
rant-0.097
Tokenay
Token ID323
Feature activation-1.72e+00

Pos logit contributions
ons+0.273
bes+0.236
ages+0.226
con+0.218
seek+0.209
Neg logit contributions
rant-0.161
ksh-0.160
iet-0.153
 mate-0.143
 coming-0.143
Tokenons
Token ID684
Feature activation-1.44e+01

Pos logit contributions
seek+0.022
bes+0.019
powers+0.012
ages+0.010
tail+0.008
Neg logit contributions
 coming-0.172
rant-0.161
 whale-0.161
iet-0.160
 them-0.160
Token.
Token ID13
Feature activation+1.00e-02

Pos logit contributions
ons+1.194
bes+0.993
ages+0.924
con+0.885
aid+0.877
Neg logit contributions
rant-0.664
ksh-0.661
 coming-0.642
 dolphin-0.633
 flood-0.630
Token She
Token ID1375
Feature activation-2.05e+00

Pos logit contributions
rant+0.001
ksh+0.001
 dolphin+0.001
 whale+0.001
 flood+0.001
Neg logit contributions
ons-0.001
bes-0.001
ages-0.000
on-0.000
seek-0.000
Token was
Token ID373
Feature activation-3.28e-01

Pos logit contributions
ons+0.173
bes+0.147
ages+0.142
seek+0.138
con+0.136
Neg logit contributions
 dolphin-0.085
 whale-0.085
rant-0.082
 flood-0.080
ksh-0.080
Token so
Token ID523
Feature activation-9.21e-01

Pos logit contributions
ons+0.027
bes+0.022
ages+0.020
con+0.020
seek+0.019
Neg logit contributions
 flood-0.016
ksh-0.016
 coming-0.016
rant-0.016
 dolphin-0.016
Token excited
Token ID6568
Feature activation-2.37e+00

Pos logit contributions
ons+0.074
bes+0.061
ages+0.056
con+0.056
seek+0.056
Neg logit contributions
 flood-0.046
ksh-0.045
rant-0.045
 dolphin-0.045
 whale-0.044
Token bar
Token ID2318
Feature activation-1.59e+00

Pos logit contributions
ons+0.027
bes+0.021
ages+0.020
con+0.019
on+0.019
Neg logit contributions
ksh-0.020
rant-0.019
 flood-0.019
 dolphin-0.018
 ending-0.018
Tokenks
Token ID591
Feature activation-1.76e+00

Pos logit contributions
ons+0.106
bes+0.077
ages+0.076
es+0.072
on+0.071
Neg logit contributions
ksh-0.106
 flood-0.102
rant-0.101
 dolphin-0.098
 ending-0.096
Token.
Token ID13
Feature activation+7.47e-02

Pos logit contributions
ons+0.118
bes+0.088
es+0.086
ages+0.084
on+0.081
Neg logit contributions
ksh-0.115
rant-0.113
 flood-0.112
 whale-0.105
 dolphin-0.104
Token He
Token ID679
Feature activation-1.57e+00

Pos logit contributions
ksh+0.005
rant+0.005
 flood+0.005
 dolphin+0.005
 whale+0.005
Neg logit contributions
ons-0.005
bes-0.003
ages-0.003
on-0.003
con-0.003
Token scares
Token ID44462
Feature activation+5.20e-01

Pos logit contributions
ons+0.119
bes+0.092
ages+0.090
on+0.084
aid+0.082
Neg logit contributions
ksh-0.087
 flood-0.086
rant-0.085
 dolphin-0.084
 whale-0.083
Token them
Token ID606
Feature activation+8.53e+00

Pos logit contributions
ksh+0.032
rant+0.030
 ending+0.029
 flood+0.028
 mate+0.028
Neg logit contributions
ons-0.039
on-0.027
bes-0.027
es-0.027
ages-0.026
Token.
Token ID13
Feature activation+8.20e-02

Pos logit contributions
 coming+0.377
 flood+0.373
 dolphin+0.352
 wake+0.347
 mate+0.346
Neg logit contributions
ons-0.744
bes-0.608
ages-0.577
con-0.563
rob-0.553
Token
Token ID198
Feature activation-3.18e-01

Pos logit contributions
ksh+0.005
 flood+0.005
rant+0.005
 dolphin+0.005
 whale+0.005
Neg logit contributions
ons-0.006
bes-0.004
ages-0.004
on-0.004
con-0.004
Token
Token ID198
Feature activation-3.17e-01

Pos logit contributions
ons+0.025
bes+0.021
ages+0.020
aces+0.019
con+0.019
Neg logit contributions
 flood-0.015
 dolphin-0.015
rant-0.015
 whale-0.015
 coming-0.014
Token"
Token ID1
Feature activation-2.79e+00

Pos logit contributions
ons+0.023
bes+0.018
ages+0.018
aces+0.017
con+0.017
Neg logit contributions
Why-0.018
 flood-0.017
 dolphin-0.017
 whale-0.017
rant-0.017
TokenGo
Token ID5247
Feature activation+3.62e+00

Pos logit contributions
ons+0.219
aid+0.176
bes+0.173
ages+0.160
on+0.158
Neg logit contributions
rant-0.155
ksh-0.143
 ending-0.140
 harbor-0.136
 mate-0.136
Token coin
Token ID10752
Feature activation-3.09e+00

Pos logit contributions
ons+0.050
bes+0.038
ages+0.036
es+0.034
seek+0.034
Neg logit contributions
 flood-0.049
 whale-0.048
 dolphin-0.048
 mate-0.047
 ending-0.046
Token.
Token ID13
Feature activation+6.09e-01

Pos logit contributions
ons+0.229
bes+0.179
ages+0.170
aid+0.157
con+0.157
Neg logit contributions
rant-0.174
ksh-0.174
 flood-0.174
 dolphin-0.169
 whale-0.168
Token
Token ID198
Feature activation+2.08e-01

Pos logit contributions
ksh+0.032
 flood+0.031
rant+0.031
 dolphin+0.031
 whale+0.030
Neg logit contributions
ons-0.048
bes-0.039
ages-0.037
seek-0.034
aid-0.034
Token
Token ID198
Feature activation+2.14e-01

Pos logit contributions
 dolphin+0.010
 flood+0.010
 whale+0.009
rant+0.009
iet+0.009
Neg logit contributions
ons-0.016
bes-0.014
ages-0.013
aces-0.012
seek-0.012
Token"
Token ID1
Feature activation-2.27e+00

Pos logit contributions
 flood+0.008
ksh+0.008
rant+0.008
 dolphin+0.008
iet+0.008
Neg logit contributions
ons-0.019
bes-0.016
ages-0.016
con-0.015
seek-0.015
TokenHey
Token ID10814
Feature activation+7.29e+00

Pos logit contributions
ons+0.165
aid+0.133
bes+0.132
on+0.125
rob+0.119
Neg logit contributions
rant-0.129
ksh-0.120
ashing-0.119
 flood-0.118
 appearance-0.117
Token,
Token ID11
Feature activation+1.75e-01

Pos logit contributions
ksh+0.674
rant+0.663
iet+0.591
 flood+0.586
 extingu+0.582
Neg logit contributions
ons-0.339
on-0.213
es-0.188
ages-0.172
con-0.165
Token that
Token ID326
Feature activation+1.19e+00

Pos logit contributions
ksh+0.013
rant+0.012
ashing+0.010
iet+0.010
 horizon+0.010
Neg logit contributions
ons-0.012
on-0.009
aid-0.008
con-0.008
es-0.008
Token's
Token ID338
Feature activation+3.66e+00

Pos logit contributions
ksh+0.065
 flood+0.064
rant+0.063
 dolphin+0.062
 whale+0.061
Neg logit contributions
ons-0.091
bes-0.072
ages-0.069
on-0.064
con-0.064
Token our
Token ID674
Feature activation+3.04e+00

Pos logit contributions
rant+0.279
ksh+0.275
 dolphin+0.266
 extingu+0.264
 flood+0.259
Neg logit contributions
ons-0.199
bes-0.133
ages-0.126
on-0.125
 myself-0.114
Token coin
Token ID10752
Feature activation-3.03e+00

Pos logit contributions
ksh+0.214
rant+0.211
 flood+0.209
 dolphin+0.204
 whale+0.201
Neg logit contributions
ons-0.188
bes-0.138
ages-0.130
on-0.119
con-0.117
Token and
Token ID290
Feature activation-4.00e-01

Pos logit contributions
ons+0.184
bes+0.115
ages+0.112
on+0.111
es+0.107
Neg logit contributions
ksh-0.266
rant-0.264
 flood-0.256
iet-0.246
 extingu-0.235
Token encouraged
Token ID10085
Feature activation-1.20e+00

Pos logit contributions
ons+0.034
bes+0.027
orns+0.025
con+0.025
ops+0.025
Neg logit contributions
 dolphin-0.019
 flood-0.019
 coming-0.019
 ending-0.019
 wake-0.019
Token him
Token ID683
Feature activation+2.39e+00

Pos logit contributions
ons+0.099
bes+0.081
ages+0.077
on+0.072
aid+0.071
Neg logit contributions
ksh-0.059
rant-0.057
 dolphin-0.056
 flood-0.056
 coming-0.054
Token to
Token ID284
Feature activation-7.98e-01

Pos logit contributions
 coming+0.104
 mate+0.104
 wake+0.100
 dolphin+0.099
 ending+0.098
Neg logit contributions
ons-0.209
bes-0.168
rob-0.156
ages-0.154
aid-0.153
Token never
Token ID1239
Feature activation-9.84e-01

Pos logit contributions
ons+0.074
bes+0.061
ages+0.059
con+0.056
on+0.055
Neg logit contributions
 flood-0.031
rant-0.030
ksh-0.030
 dolphin-0.030
 whale-0.029
Token stop
Token ID2245
Feature activation+6.45e+00

Pos logit contributions
ons+0.071
seek+0.056
tail+0.053
ages+0.052
on+0.052
Neg logit contributions
ksh-0.059
rant-0.055
iet-0.051
 dolphin-0.049
 extingu-0.049
Token being
Token ID852
Feature activation+1.40e+00

Pos logit contributions
ksh+0.404
rant+0.392
 flood+0.381
iet+0.369
 dolphin+0.358
Neg logit contributions
ons-0.453
bes-0.340
ages-0.322
on-0.313
es-0.307
Token creative
Token ID7325
Feature activation-1.25e+00

Pos logit contributions
ksh+0.071
rant+0.070
 flood+0.069
 dolphin+0.066
 whale+0.065
Neg logit contributions
ons-0.114
bes-0.090
ages-0.087
on-0.082
es-0.081
Token.
Token ID13
Feature activation+2.66e-02

Pos logit contributions
ons+0.096
bes+0.075
ages+0.073
es+0.069
on+0.068
Neg logit contributions
ksh-0.068
 flood-0.067
rant-0.067
 dolphin-0.064
 whale-0.063
Token
Token ID198
Feature activation-3.87e-01

Pos logit contributions
ksh+0.001
 dolphin+0.001
 whale+0.001
 flood+0.001
 mate+0.001
Neg logit contributions
ons-0.002
bes-0.002
ages-0.002
aches-0.002
aid-0.002
Token
Token ID198
Feature activation-3.73e-01

Pos logit contributions
ons+0.032
ages+0.027
bes+0.027
aces+0.026
seek+0.025
Neg logit contributions
 dolphin-0.016
iet-0.015
 whale-0.015
 flood-0.014
 coming-0.014
Token She
Token ID1375
Feature activation-2.02e+00

Pos logit contributions
ksh+0.003
rant+0.003
 flood+0.003
 dolphin+0.003
 whale+0.003
Neg logit contributions
ons-0.004
bes-0.003
ages-0.003
on-0.003
con-0.003
Token decided
Token ID3066
Feature activation-5.45e-01

Pos logit contributions
ons+0.174
bes+0.140
ages+0.134
on+0.129
es+0.127
Neg logit contributions
ksh-0.094
rant-0.091
 flood-0.090
 dolphin-0.085
 whale-0.084
Token to
Token ID284
Feature activation-7.45e-01

Pos logit contributions
ons+0.040
bes+0.031
ages+0.030
on+0.028
con+0.027
Neg logit contributions
ksh-0.032
rant-0.031
 flood-0.031
 dolphin-0.030
 whale-0.030
Token pull
Token ID2834
Feature activation-7.00e-02

Pos logit contributions
ons+0.067
bes+0.054
ages+0.053
con+0.050
on+0.050
Neg logit contributions
 flood-0.031
ksh-0.030
rant-0.030
 dolphin-0.029
 whale-0.029
Token it
Token ID340
Feature activation-1.02e+00

Pos logit contributions
ons+0.005
bes+0.004
ages+0.004
seek+0.004
con+0.004
Neg logit contributions
rant-0.004
ksh-0.004
 flood-0.004
 dolphin-0.004
 whale-0.004
Token out
Token ID503
Feature activation+6.51e+00

Pos logit contributions
ons+0.096
bes+0.080
ages+0.077
on+0.072
con+0.072
Neg logit contributions
 flood-0.038
rant-0.038
ksh-0.038
 coming-0.035
 dolphin-0.035
Token of
Token ID286
Feature activation-1.67e+00

Pos logit contributions
 coming+0.327
rant+0.325
 flood+0.315
 dolphin+0.306
ksh+0.302
Neg logit contributions
ons-0.508
bes-0.426
ages-0.415
seek-0.381
rob-0.379
Token the
Token ID262
Feature activation-1.26e+00

Pos logit contributions
ons+0.119
bes+0.091
ages+0.090
es+0.081
con+0.081
Neg logit contributions
 flood-0.101
rant-0.100
ksh-0.099
 dolphin-0.097
 whale-0.095
Token grass
Token ID8701
Feature activation-2.59e+00

Pos logit contributions
ons+0.097
bes+0.076
ages+0.072
on+0.068
con+0.068
Neg logit contributions
ksh-0.070
rant-0.068
 flood-0.068
 dolphin-0.066
 whale-0.064
Token and
Token ID290
Feature activation-3.34e-01

Pos logit contributions
ons+0.194
bes+0.150
ages+0.144
on+0.137
es+0.136
Neg logit contributions
ksh-0.148
 flood-0.143
rant-0.143
 dolphin-0.139
 whale-0.136
Token it
Token ID340
Feature activation-1.01e+00

Pos logit contributions
ons+0.029
bes+0.023
ages+0.023
on+0.021
seek+0.021
Neg logit contributions
 flood-0.015
rant-0.014
 dolphin-0.014
ksh-0.014
 coming-0.014
Token!
Token ID0
Feature activation+1.63e+00

Pos logit contributions
ons+0.152
bes+0.121
ages+0.114
con+0.110
on+0.107
Neg logit contributions
ksh-0.097
rant-0.095
 flood-0.093
 dolphin-0.091
 coming-0.089
Token Can
Token ID1680
Feature activation+1.72e+00

Pos logit contributions
ksh+0.087
rant+0.086
 flood+0.085
 dolphin+0.082
 whale+0.081
Neg logit contributions
ons-0.126
bes-0.100
ages-0.096
on-0.090
con-0.089
Token't
Token ID470
Feature activation-4.55e+00

Pos logit contributions
 flood+0.069
ksh+0.069
 dolphin+0.068
 mate+0.067
Why+0.067
Neg logit contributions
ons-0.150
ages-0.126
bes-0.123
con-0.116
seek-0.114
Token we
Token ID356
Feature activation+1.72e+00

Pos logit contributions
ons+0.333
bes+0.253
ages+0.238
on+0.236
es+0.222
Neg logit contributions
ksh-0.275
rant-0.270
 flood-0.256
 dolphin-0.248
 whale-0.248
Token keep
Token ID1394
Feature activation+1.88e-01

Pos logit contributions
ksh+0.088
rant+0.083
 flood+0.081
 dolphin+0.079
 whale+0.079
Neg logit contributions
ons-0.142
bes-0.112
ages-0.107
on-0.105
aid-0.102
Token them
Token ID606
Feature activation+8.51e+00

Pos logit contributions
ksh+0.006
rant+0.005
 flood+0.005
 dolphin+0.005
 whale+0.005
Neg logit contributions
ons-0.019
bes-0.016
ages-0.016
on-0.015
con-0.015
Token all
Token ID477
Feature activation-1.04e+00

Pos logit contributions
ksh+0.439
 flood+0.434
rant+0.432
 dolphin+0.418
 whale+0.407
Neg logit contributions
ons-0.678
bes-0.539
ages-0.518
con-0.488
on-0.485
Token?"
Token ID1701
Feature activation-3.02e+00

Pos logit contributions
ons+0.081
bes+0.065
ages+0.063
es+0.058
con+0.058
Neg logit contributions
 flood-0.056
rant-0.056
ksh-0.055
 coming-0.053
 dolphin-0.053
Token
Token ID198
Feature activation-3.50e-01

Pos logit contributions
ons+0.231
bes+0.187
ages+0.185
seek+0.168
igs+0.166
Neg logit contributions
ksh-0.154
 dolphin-0.151
Why-0.147
 coming-0.145
 whale-0.144
Token
Token ID198
Feature activation-3.56e-01

Pos logit contributions
ons+0.028
ages+0.023
bes+0.023
aces+0.021
seek+0.021
Neg logit contributions
 dolphin-0.016
ksh-0.015
iet-0.015
 whale-0.015
Why-0.015
TokenHer
Token ID9360
Feature activation-2.87e+00

Pos logit contributions
ons+0.028
ages+0.022
con+0.022
bes+0.022
aces+0.021
Neg logit contributions
 dolphin-0.018
iet-0.017
ksh-0.017
Why-0.017
 mate-0.016
Token to
Token ID284
Feature activation-2.84e-01

Pos logit contributions
 coming+0.048
 flood+0.047
 dolphin+0.047
 whale+0.046
rant+0.045
Neg logit contributions
ons-0.100
bes-0.085
ages-0.083
aid-0.076
aces-0.075
Token Lily
Token ID20037
Feature activation+1.02e+00

Pos logit contributions
ons+0.021
bes+0.016
on+0.015
ages+0.015
es+0.014
Neg logit contributions
ksh-0.017
rant-0.016
 flood-0.016
 whale-0.015
 dolphin-0.015
Token and
Token ID290
Feature activation+1.14e-01

Pos logit contributions
 coming+0.040
ksh+0.037
 wake+0.036
 dolphin+0.036
rant+0.036
Neg logit contributions
ons-0.093
bes-0.077
ages-0.075
aid-0.074
rob-0.072
Token asked
Token ID1965
Feature activation-1.69e+00

Pos logit contributions
 dolphin+0.007
 flood+0.007
ksh+0.007
 whale+0.006
rant+0.006
Neg logit contributions
ons-0.008
bes-0.006
ages-0.006
aces-0.006
on-0.006
Token,
Token ID11
Feature activation+6.48e-02

Pos logit contributions
ons+0.122
bes+0.095
ages+0.091
on+0.084
con+0.083
Neg logit contributions
ksh-0.099
rant-0.098
 flood-0.098
 dolphin-0.096
 whale-0.094
Token "
Token ID366
Feature activation+3.04e+00

Pos logit contributions
rant+0.004
ksh+0.004
iet+0.004
 flood+0.004
 appearance+0.004
Neg logit contributions
ons-0.004
on-0.003
bes-0.003
ner-0.003
es-0.003
TokenWhat
Token ID2061
Feature activation+7.20e+00

Pos logit contributions
 flood+0.151
ksh+0.149
sing+0.148
rant+0.146
 ending+0.142
Neg logit contributions
ons-0.254
on-0.198
bes-0.192
aid-0.189
rob-0.182
Token's
Token ID338
Feature activation+3.58e+00

Pos logit contributions
ksh+0.358
 flood+0.354
rant+0.349
 dolphin+0.348
 whale+0.342
Neg logit contributions
ons-0.574
bes-0.469
ages-0.444
con-0.420
aid-0.411
Token wrong
Token ID2642
Feature activation+3.79e-01

Pos logit contributions
ksh+0.227
rant+0.220
 flood+0.215
 dolphin+0.208
 whale+0.207
Neg logit contributions
ons-0.253
bes-0.191
ages-0.181
on-0.173
con-0.169
Token,
Token ID11
Feature activation+9.50e-02

Pos logit contributions
ksh+0.031
rant+0.031
 flood+0.027
 beginning+0.027
 whale+0.026
Neg logit contributions
ons-0.019
bes-0.013
ages-0.013
es-0.012
on-0.011
Token Lily
Token ID20037
Feature activation+1.08e+00

Pos logit contributions
ksh+0.006
rant+0.006
 flood+0.005
 extingu+0.005
 beginning+0.005
Neg logit contributions
ons-0.007
bes-0.005
on-0.005
aid-0.005
con-0.004
Token played
Token ID2826
Feature activation-3.49e+00

Pos logit contributions
ons+0.018
bes+0.015
ages+0.014
aid+0.013
con+0.013
Neg logit contributions
 flood-0.010
rant-0.010
ksh-0.009
 dolphin-0.009
 whale-0.009
Token together
Token ID1978
Feature activation-3.95e+00

Pos logit contributions
ons+0.250
ages+0.185
bes+0.184
con+0.171
aid+0.170
Neg logit contributions
 flood-0.208
ksh-0.203
rant-0.201
 dolphin-0.200
 coming-0.199
Token all
Token ID477
Feature activation-8.83e-01

Pos logit contributions
ons+0.291
bes+0.226
ages+0.215
on+0.203
es+0.199
Neg logit contributions
ksh-0.233
rant-0.228
 flood-0.227
 dolphin-0.220
 whale-0.216
Token day
Token ID1110
Feature activation-1.25e+00

Pos logit contributions
ons+0.072
bes+0.057
ages+0.055
con+0.052
on+0.052
Neg logit contributions
ksh-0.045
rant-0.045
 flood-0.044
 dolphin-0.043
 whale-0.042
Token long
Token ID890
Feature activation-2.80e+00

Pos logit contributions
ons+0.102
aid+0.080
bes+0.079
ages+0.076
con+0.072
Neg logit contributions
 flood-0.060
ksh-0.060
 coming-0.059
rant-0.058
 dolphin-0.058
Token.
Token ID13
Feature activation+2.32e-01

Pos logit contributions
ons+0.217
bes+0.171
ages+0.165
on+0.154
aid+0.154
Neg logit contributions
ksh-0.149
rant-0.148
 flood-0.147
 dolphin-0.142
 whale-0.140
Token And
Token ID843
Feature activation-2.82e+00

Pos logit contributions
ksh+0.015
 flood+0.015
rant+0.015
 dolphin+0.014
 whale+0.014
Neg logit contributions
ons-0.016
bes-0.012
ages-0.011
on-0.010
con-0.010
Token they
Token ID484
Feature activation+2.91e+00

Pos logit contributions
ons+0.232
bes+0.188
ages+0.178
on+0.167
con+0.166
Neg logit contributions
ksh-0.139
 flood-0.137
rant-0.135
 dolphin-0.135
 whale-0.131
Token never
Token ID1239
Feature activation-7.39e-01

Pos logit contributions
 flood+0.142
rant+0.141
ksh+0.138
 dolphin+0.136
 whale+0.134
Neg logit contributions
ons-0.239
bes-0.196
ages-0.188
con-0.178
seek-0.174
Token had
Token ID550
Feature activation+4.28e-01

Pos logit contributions
ons+0.054
ages+0.041
seek+0.039
bes+0.039
con+0.038
Neg logit contributions
ksh-0.042
rant-0.042
 dolphin-0.041
iet-0.040
 whale-0.039
Token to
Token ID284
Feature activation-5.48e-01

Pos logit contributions
ksh+0.024
 flood+0.024
rant+0.024
 dolphin+0.023
 whale+0.023
Neg logit contributions
ons-0.032
bes-0.025
ages-0.024
on-0.023
con-0.022
Token,
Token ID11
Feature activation+1.57e-01

Pos logit contributions
ons+0.148
bes+0.119
ages+0.111
con+0.104
seek+0.100
Neg logit contributions
 flood-0.111
 mate-0.110
 dolphin-0.110
ksh-0.110
rant-0.110
Token "
Token ID366
Feature activation+3.13e+00

Pos logit contributions
ksh+0.008
rant+0.008
 flood+0.008
iet+0.008
 dolphin+0.007
Neg logit contributions
ons-0.012
bes-0.010
ages-0.009
on-0.009
es-0.009
TokenSure
Token ID19457
Feature activation+3.91e-01

Pos logit contributions
ksh+0.154
rant+0.147
 flood+0.147
 dolphin+0.145
 whale+0.141
Neg logit contributions
ons-0.264
bes-0.211
ages-0.201
on-0.191
es-0.188
Token,
Token ID11
Feature activation+1.73e-01

Pos logit contributions
ksh+0.026
rant+0.026
 flood+0.026
 dolphin+0.025
 whale+0.025
Neg logit contributions
ons-0.026
bes-0.019
ages-0.018
on-0.017
con-0.016
Token Anna
Token ID11735
Feature activation+6.42e-01

Pos logit contributions
ksh+0.012
rant+0.012
 flood+0.012
iet+0.011
 extingu+0.011
Neg logit contributions
ons-0.011
bes-0.007
on-0.007
es-0.007
aid-0.007
Token.
Token ID13
Feature activation+6.62e-01

Pos logit contributions
ksh+0.031
rant+0.031
 flood+0.031
 dolphin+0.030
 whale+0.030
Neg logit contributions
ons-0.052
bes-0.043
ages-0.040
con-0.038
aid-0.038
Token He
Token ID679
Feature activation-9.83e-01

Pos logit contributions
ksh+0.035
rant+0.034
 flood+0.033
 dolphin+0.032
 whale+0.032
Neg logit contributions
ons-0.053
bes-0.042
ages-0.040
on-0.038
con-0.037
Token likes
Token ID7832
Feature activation+4.97e-02

Pos logit contributions
ons+0.078
bes+0.062
ages+0.058
on+0.056
seek+0.055
Neg logit contributions
ksh-0.050
rant-0.050
 flood-0.049
 dolphin-0.048
 whale-0.047
Token that
Token ID326
Feature activation+1.23e+00

Pos logit contributions
 dolphin+0.003
 whale+0.002
 coming+0.002
 flood+0.002
ksh+0.002
Neg logit contributions
ons-0.004
bes-0.003
ages-0.003
on-0.003
es-0.003
Token.
Token ID13
Feature activation+6.96e-01

Pos logit contributions
 flood+0.062
 dolphin+0.061
ksh+0.061
 whale+0.059
 ending+0.058
Neg logit contributions
ons-0.101
bes-0.080
ages-0.077
aid-0.073
on-0.072
Token His
Token ID2399
Feature activation-1.08e+00

Pos logit contributions
 flood+0.044
ksh+0.044
rant+0.044
 dolphin+0.042
 whale+0.042
Neg logit contributions
ons-0.047
bes-0.035
ages-0.034
on-0.032
con-0.031
Token.
Token ID13
Feature activation+5.24e-01

Pos logit contributions
ksh+0.124
rant+0.124
 flood+0.123
 dolphin+0.120
 whale+0.118
Neg logit contributions
ons-0.184
bes-0.146
ages-0.141
on-0.131
aid-0.130
Token They
Token ID1119
Feature activation+1.82e+00

Pos logit contributions
ksh+0.030
rant+0.029
 flood+0.029
 dolphin+0.029
 whale+0.028
Neg logit contributions
ons-0.039
bes-0.030
ages-0.029
seek-0.027
aid-0.027
Token rushed
Token ID13999
Feature activation-1.36e+00

Pos logit contributions
 flood+0.086
rant+0.086
 dolphin+0.085
 whale+0.085
 mate+0.084
Neg logit contributions
ons-0.148
bes-0.124
ages-0.117
con-0.110
seek-0.109
Token off
Token ID572
Feature activation-3.82e+00

Pos logit contributions
ons+0.107
bes+0.084
ages+0.080
on+0.077
es+0.076
Neg logit contributions
ksh-0.073
 flood-0.070
rant-0.070
 dolphin-0.067
 whale-0.067
Token,
Token ID11
Feature activation+6.48e-02

Pos logit contributions
ons+0.326
bes+0.270
ages+0.268
aid+0.252
con+0.240
Neg logit contributions
 coming-0.176
 flood-0.173
 dolphin-0.164
rant-0.163
 mer-0.161
Token eager
Token ID11069
Feature activation+2.09e-01

Pos logit contributions
ksh+0.004
rant+0.003
 flood+0.003
 dolphin+0.003
 whale+0.003
Neg logit contributions
ons-0.005
bes-0.004
ages-0.004
on-0.004
con-0.004
Token to
Token ID284
Feature activation-2.51e-01

Pos logit contributions
ksh+0.015
rant+0.014
 flood+0.014
iet+0.014
 dolphin+0.013
Neg logit contributions
ons-0.013
ages-0.009
bes-0.009
seek-0.008
con-0.008
Token find
Token ID1064
Feature activation+1.01e+00

Pos logit contributions
ons+0.023
bes+0.019
ages+0.018
con+0.017
aid+0.017
Neg logit contributions
 flood-0.011
rant-0.010
 dolphin-0.010
ksh-0.010
 whale-0.010
Token the
Token ID262
Feature activation-7.68e-01

Pos logit contributions
ksh+0.061
 flood+0.056
rant+0.056
 ending+0.052
 dolphin+0.052
Neg logit contributions
ons-0.077
bes-0.057
ages-0.055
es-0.054
on-0.053
Token treasure
Token ID14068
Feature activation+2.43e+00

Pos logit contributions
ons+0.052
bes+0.040
con+0.038
ages+0.037
 puzzles+0.036
Neg logit contributions
ksh-0.050
rant-0.046
 flood-0.043
iet-0.042
 extingu-0.041
Token.
Token ID13
Feature activation+5.80e-01

Pos logit contributions
rant+0.126
 flood+0.126
ksh+0.125
 dolphin+0.122
 whale+0.120
Neg logit contributions
ons-0.189
bes-0.150
ages-0.145
aid-0.135
on-0.134
Token look
Token ID804
Feature activation+4.23e+00

Pos logit contributions
ksh+0.011
rant+0.011
 flood+0.011
 dolphin+0.011
 whale+0.010
Neg logit contributions
ons-0.020
bes-0.016
ages-0.015
on-0.015
con-0.015
Token for
Token ID329
Feature activation+2.15e+00

Pos logit contributions
ksh+0.206
 flood+0.206
rant+0.198
 dolphin+0.198
 whale+0.196
Neg logit contributions
ons-0.342
bes-0.267
ages-0.259
on-0.250
es-0.246
Token you
Token ID345
Feature activation-1.97e+00

Pos logit contributions
ksh+0.116
rant+0.114
 flood+0.114
 dolphin+0.112
 whale+0.110
Neg logit contributions
ons-0.164
bes-0.131
ages-0.127
on-0.116
con-0.116
Token."
Token ID526
Feature activation-4.06e+00

Pos logit contributions
ons+0.154
bes+0.117
ages+0.112
con+0.110
on+0.108
Neg logit contributions
ksh-0.108
rant-0.108
 mate-0.104
 coming-0.101
 flood-0.100
Token
Token ID220
Feature activation-3.72e+00

Pos logit contributions
ons+0.344
bes+0.289
ages+0.283
seek+0.267
aid+0.266
Neg logit contributions
ksh-0.174
 flood-0.165
rant-0.158
 coming-0.157
 extingu-0.150
Token
Token ID198
Feature activation+8.45e-02

Pos logit contributions
ons+0.281
bes+0.228
ages+0.217
seek+0.207
con+0.204
Neg logit contributions
ksh-0.194
rant-0.185
 flood-0.181
 coming-0.179
 mate-0.173
Token
Token ID198
Feature activation+8.91e-02

Pos logit contributions
ksh+0.004
rant+0.004
 coming+0.004
Why+0.003
 flood+0.003
Neg logit contributions
ons-0.007
bes-0.006
ages-0.006
aces-0.005
tail-0.005
TokenTim
Token ID14967
Feature activation-2.02e-01

Pos logit contributions
ksh+0.005
 flood+0.005
rant+0.005
 dolphin+0.005
 whale+0.005
Neg logit contributions
ons-0.007
bes-0.005
ages-0.005
con-0.005
on-0.005
Tokenmy
Token ID1820
Feature activation-3.90e-01

Pos logit contributions
ons+0.020
bes+0.018
ages+0.017
con+0.017
aid+0.016
Neg logit contributions
rant-0.006
ksh-0.005
iet-0.005
y-0.005
 wake-0.005
Token ran
Token ID4966
Feature activation-1.77e+00

Pos logit contributions
ons+0.036
bes+0.028
aid+0.028
con+0.027
rob+0.027
Neg logit contributions
iet-0.014
 dolphin-0.014
ksh-0.014
 wake-0.014
 mate-0.014
Token to
Token ID284
Feature activation-2.93e-01

Pos logit contributions
ons+0.161
bes+0.128
ages+0.125
on+0.119
aid+0.116
Neg logit contributions
rant-0.076
 flood-0.075
ksh-0.073
 coming-0.072
 mate-0.070
Token again
Token ID757
Feature activation+1.02e+00

Pos logit contributions
ons+0.232
bes+0.185
ages+0.178
on+0.165
con+0.163
Neg logit contributions
rant-0.156
ksh-0.155
 flood-0.154
 dolphin-0.151
 coming-0.146
Token,
Token ID11
Feature activation-4.02e-01

Pos logit contributions
 flood+0.055
rant+0.055
ksh+0.054
 dolphin+0.054
 coming+0.053
Neg logit contributions
ons-0.078
bes-0.061
ages-0.058
aid-0.055
on-0.055
Token you
Token ID345
Feature activation-2.37e+00

Pos logit contributions
ons+0.028
bes+0.022
ages+0.020
on+0.019
seek+0.019
Neg logit contributions
 flood-0.025
ksh-0.024
 dolphin-0.024
rant-0.024
 whale-0.023
Token can
Token ID460
Feature activation+1.35e+00

Pos logit contributions
ons+0.230
bes+0.195
ages+0.183
con+0.176
seek+0.176
Neg logit contributions
 flood-0.083
rant-0.079
ksh-0.077
 dolphin-0.077
 mate-0.076
Token have
Token ID423
Feature activation-3.68e+00

Pos logit contributions
 flood+0.066
 dolphin+0.063
rant+0.062
ksh+0.061
 whale+0.061
Neg logit contributions
ons-0.112
bes-0.090
ages-0.087
con-0.081
aid-0.080
Token some
Token ID617
Feature activation-1.99e+00

Pos logit contributions
ons+0.298
bes+0.253
ages+0.236
es+0.229
on+0.222
Neg logit contributions
 coming-0.168
ksh-0.167
 flood-0.166
 dolphin-0.165
 whale-0.160
Token toast
Token ID27805
Feature activation-5.02e+00

Pos logit contributions
ons+0.153
bes+0.131
ages+0.118
seek+0.116
es+0.114
Neg logit contributions
 dolphin-0.100
 whale-0.099
 flood-0.099
 coming-0.098
ksh-0.098
Token,
Token ID11
Feature activation-3.84e-01

Pos logit contributions
ons+0.398
bes+0.315
ages+0.301
on+0.284
con+0.282
Neg logit contributions
ksh-0.260
rant-0.256
 flood-0.253
 dolphin-0.246
 whale-0.241
Tokenâ
Token ID22940
Feature activation+1.14e+00

Pos logit contributions
ons+0.030
bes+0.023
ages+0.022
on+0.021
con+0.021
Neg logit contributions
ksh-0.021
rant-0.021
 flood-0.020
 dolphin-0.020
 whale-0.020
Token€
Token ID26391
Feature activation-1.08e+00

Pos logit contributions
ksh+0.057
rant+0.057
 flood+0.055
 dolphin+0.053
 whale+0.052
Neg logit contributions
ons-0.094
bes-0.075
ages-0.072
es-0.068
on-0.068
Token said
Token ID531
Feature activation-3.04e+00

Pos logit contributions
ons+0.083
bes+0.063
aid+0.062
ages+0.059
on+0.058
Neg logit contributions
ksh-0.058
 flood-0.054
 dolphin-0.054
 whale-0.052
 mate-0.052
Token a
Token ID257
Feature activation-7.87e-01

Pos logit contributions
ksh+0.140
rant+0.136
 flood+0.135
 dolphin+0.134
 whale+0.129
Neg logit contributions
ons-0.219
bes-0.178
ages-0.172
seek-0.161
on-0.157
Token ball
Token ID2613
Feature activation-2.00e+00

Pos logit contributions
ons+0.059
bes+0.046
ages+0.044
on+0.042
con+0.041
Neg logit contributions
ksh-0.045
rant-0.044
 flood-0.043
 dolphin-0.042
 whale-0.041
Token for
Token ID329
Feature activation+2.20e+00

Pos logit contributions
ons+0.158
bes+0.126
ages+0.120
on+0.112
con+0.112
Neg logit contributions
ksh-0.104
rant-0.103
 flood-0.103
 dolphin-0.099
 whale-0.098
Token him
Token ID683
Feature activation+2.85e+00

Pos logit contributions
 coming+0.100
 flood+0.099
 dolphin+0.096
 mate+0.092
 whale+0.090
Neg logit contributions
ons-0.180
ages-0.150
bes-0.149
es-0.135
con-0.134
Token.
Token ID13
Feature activation+4.29e-01

Pos logit contributions
ksh+0.129
 flood+0.128
 coming+0.127
rant+0.126
 mate+0.125
Neg logit contributions
ons-0.237
bes-0.191
ages-0.178
aid-0.173
on-0.172
Token Her
Token ID2332
Feature activation-1.06e+00

Pos logit contributions
ksh+0.022
 flood+0.021
rant+0.021
 dolphin+0.021
 whale+0.020
Neg logit contributions
ons-0.035
bes-0.027
ages-0.027
aid-0.025
on-0.025
Token dog
Token ID3290
Feature activation+1.95e-01

Pos logit contributions
ons+0.092
bes+0.073
ages+0.070
on+0.067
es+0.066
Neg logit contributions
ksh-0.048
 flood-0.048
 dolphin-0.047
rant-0.046
 whale-0.046
Token was
Token ID373
Feature activation-1.82e-02

Pos logit contributions
ksh+0.011
rant+0.011
 flood+0.011
 dolphin+0.011
 whale+0.010
Neg logit contributions
ons-0.014
bes-0.011
ages-0.011
on-0.010
es-0.010
Token very
Token ID845
Feature activation-1.68e+00

Pos logit contributions
ons+0.001
bes+0.001
ages+0.001
on+0.001
con+0.001
Neg logit contributions
ksh-0.001
rant-0.001
 flood-0.001
 dolphin-0.001
 whale-0.001
Token fast
Token ID3049
Feature activation-5.65e+00

Pos logit contributions
ons+0.132
bes+0.105
ages+0.101
on+0.094
con+0.093
Neg logit contributions
ksh-0.090
rant-0.088
 flood-0.087
 dolphin-0.084
 whale-0.083
Token and
Token ID290
Feature activation-1.64e-01

Pos logit contributions
ons+0.451
bes+0.357
ages+0.342
on+0.323
con+0.318
Neg logit contributions
ksh-0.293
 flood-0.288
rant-0.288
 dolphin-0.279
 whale-0.274
Token back
Token ID736
Feature activation+4.89e+00

Pos logit contributions
ksh+0.027
rant+0.026
 flood+0.026
 dolphin+0.025
 whale+0.025
Neg logit contributions
ons-0.041
bes-0.033
ages-0.031
on-0.029
con-0.029
Token to
Token ID284
Feature activation-7.65e-01

Pos logit contributions
 flood+0.234
rant+0.228
ksh+0.224
 coming+0.223
 dolphin+0.219
Neg logit contributions
ons-0.407
bes-0.334
ages-0.320
on-0.300
aid-0.297
Token his
Token ID465
Feature activation-1.83e+00

Pos logit contributions
ons+0.053
bes+0.040
ages+0.038
on+0.036
con+0.036
Neg logit contributions
ksh-0.048
rant-0.047
 flood-0.046
 dolphin-0.045
 whale-0.045
Token dad
Token ID9955
Feature activation+3.99e+00

Pos logit contributions
ons+0.151
bes+0.125
ages+0.119
con+0.112
on+0.111
Neg logit contributions
ksh-0.088
rant-0.087
iet-0.077
 flood-0.077
 dolphin-0.076
Token.
Token ID13
Feature activation+5.61e-02

Pos logit contributions
ksh+0.225
rant+0.221
 flood+0.220
 dolphin+0.213
 whale+0.210
Neg logit contributions
ons-0.301
bes-0.235
ages-0.225
on-0.212
con-0.208
Token He
Token ID679
Feature activation-1.59e+00

Pos logit contributions
ksh+0.004
 flood+0.003
rant+0.003
 dolphin+0.003
 whale+0.003
Neg logit contributions
ons-0.004
bes-0.003
ages-0.003
aid-0.003
on-0.003
Token started
Token ID2067
Feature activation-2.45e+00

Pos logit contributions
ons+0.119
bes+0.093
ages+0.090
on+0.084
es+0.082
Neg logit contributions
ksh-0.090
rant-0.088
 flood-0.088
 dolphin-0.084
 whale-0.083
Token to
Token ID284
Feature activation-7.45e-01

Pos logit contributions
ons+0.191
bes+0.150
ages+0.143
on+0.135
con+0.134
Neg logit contributions
ksh-0.130
 flood-0.130
rant-0.127
 dolphin-0.125
 coming-0.123
Token cry
Token ID3960
Feature activation-2.74e+00

Pos logit contributions
ons+0.059
bes+0.047
ages+0.045
on+0.042
con+0.042
Neg logit contributions
ksh-0.040
rant-0.039
 flood-0.037
 dolphin-0.037
 whale-0.036
Token.
Token ID13
Feature activation+7.13e-02

Pos logit contributions
ons+0.154
ages+0.124
es+0.121
bes+0.118
on+0.106
Neg logit contributions
rant-0.192
ksh-0.187
 flood-0.185
 whale-0.184
iet-0.176
Token
Token ID198
Feature activation-3.33e-01

Pos logit contributions
ksh+0.004
 flood+0.004
rant+0.004
 dolphin+0.004
 whale+0.004
Neg logit contributions
ons-0.005
bes-0.004
ages-0.004
aid-0.003
es-0.003
Token Lily
Token ID20037
Feature activation+6.35e-01

Pos logit contributions
 dolphin+0.032
 flood+0.031
ksh+0.030
 whale+0.030
 coming+0.030
Neg logit contributions
ons-0.064
bes-0.054
ages-0.052
seek-0.050
con-0.048
Token and
Token ID290
Feature activation-2.75e-01

Pos logit contributions
 coming+0.021
ksh+0.019
rant+0.018
 wake+0.018
 extingu+0.017
Neg logit contributions
ons-0.061
bes-0.051
con-0.050
seek-0.049
ages-0.049
Token hugs
Token ID40657
Feature activation-4.60e+00

Pos logit contributions
ons+0.018
bes+0.013
ages+0.013
on+0.011
seek+0.011
Neg logit contributions
ksh-0.019
 flood-0.018
rant-0.018
 dolphin-0.018
 whale-0.018
Token her
Token ID607
Feature activation-1.37e+00

Pos logit contributions
ons+0.298
bes+0.207
es+0.202
aid+0.202
on+0.197
Neg logit contributions
ksh-0.324
 flood-0.311
rant-0.300
 whale-0.291
 mate-0.290
Token.
Token ID13
Feature activation+1.60e-01

Pos logit contributions
ons+0.127
bes+0.097
con+0.097
seek+0.095
ages+0.094
Neg logit contributions
ksh-0.058
rant-0.052
 dolphin-0.052
 coming-0.052
 extingu-0.051
Token She
Token ID1375
Feature activation-1.91e+00

Pos logit contributions
ksh+0.011
rant+0.010
 flood+0.010
 dolphin+0.010
 whale+0.010
Neg logit contributions
ons-0.011
bes-0.008
ages-0.008
on-0.007
con-0.007
Token is
Token ID318
Feature activation-5.63e-01

Pos logit contributions
ons+0.128
bes+0.098
ages+0.096
on+0.089
seek+0.088
Neg logit contributions
 flood-0.119
 dolphin-0.118
ksh-0.118
rant-0.117
 whale-0.117
Token bleeding
Token ID16832
Feature activation-2.22e+00

Pos logit contributions
ons+0.045
bes+0.036
ages+0.034
con+0.033
ops+0.032
Neg logit contributions
 coming-0.029
 flood-0.029
ksh-0.028
rant-0.028
 dolphin-0.028
Token and
Token ID290
Feature activation-2.58e-01

Pos logit contributions
ons+0.192
bes+0.155
ages+0.144
con+0.141
on+0.139
Neg logit contributions
ksh-0.102
rant-0.100
 flood-0.098
 coming-0.098
 dolphin-0.095
Token hurt
Token ID5938
Feature activation-2.49e+00

Pos logit contributions
ons+0.021
bes+0.017
ages+0.017
seek+0.016
ops+0.016
Neg logit contributions
 coming-0.013
 flood-0.013
Why-0.012
 wake-0.012
 dolphin-0.012
Token.
Token ID13
Feature activation+1.81e-01

Pos logit contributions
ons+0.197
bes+0.157
ages+0.149
con+0.141
on+0.140
Neg logit contributions
ksh-0.131
rant-0.130
 flood-0.129
 dolphin-0.124
 coming-0.124
Token wanted
Token ID2227
Feature activation+1.24e+00

Pos logit contributions
ons+0.013
bes+0.010
ages+0.010
on+0.009
con+0.009
Neg logit contributions
 flood-0.008
 dolphin-0.008
 coming-0.008
 whale-0.008
ksh-0.007
Token to
Token ID284
Feature activation-5.48e-01

Pos logit contributions
 flood+0.056
 coming+0.056
 dolphin+0.056
rant+0.056
ksh+0.055
Neg logit contributions
ons-0.103
bes-0.087
ages-0.082
es-0.076
on-0.075
Token make
Token ID787
Feature activation+6.66e-01

Pos logit contributions
ons+0.049
bes+0.042
ages+0.041
es+0.040
rob+0.039
Neg logit contributions
 wake-0.024
 flood-0.023
 stop-0.021
 dolphin-0.019
 coming-0.019
Token her
Token ID607
Feature activation-1.25e+00

Pos logit contributions
 flood+0.034
ksh+0.034
 dolphin+0.034
 coming+0.033
 whale+0.032
Neg logit contributions
ons-0.051
bes-0.042
ages-0.039
on-0.037
seek-0.036
Token feel
Token ID1254
Feature activation-2.01e+00

Pos logit contributions
ons+0.111
bes+0.087
ages+0.083
con+0.081
rob+0.080
Neg logit contributions
 flood-0.057
 wake-0.055
 ending-0.054
 dolphin-0.053
ksh-0.052
Token better
Token ID1365
Feature activation-1.10e+00

Pos logit contributions
ons+0.151
bes+0.118
ages+0.113
con+0.105
on+0.105
Neg logit contributions
ksh-0.114
 flood-0.113
rant-0.113
 dolphin-0.109
 whale-0.107
Token.
Token ID13
Feature activation+2.89e-01

Pos logit contributions
ons+0.081
bes+0.063
ages+0.061
on+0.057
es+0.056
Neg logit contributions
ksh-0.063
rant-0.062
 flood-0.062
 dolphin-0.060
 whale-0.059
Token So
Token ID1406
Feature activation-6.46e+00

Pos logit contributions
ksh+0.013
Why+0.011
 flood+0.011
 ending+0.010
ashing+0.010
Neg logit contributions
ons-0.026
bes-0.020
on-0.020
odic-0.019
igs-0.018
Token,
Token ID11
Feature activation-1.66e-01

Pos logit contributions
ons+0.527
bes+0.435
ages+0.398
on+0.380
con+0.372
Neg logit contributions
 ending-0.336
 flood-0.332
 coming-0.315
 mate-0.311
 dolphin-0.309
Token he
Token ID339
Feature activation-2.16e+00

Pos logit contributions
ons+0.013
bes+0.011
ages+0.010
on+0.009
igs+0.009
Neg logit contributions
 flood-0.009
Why-0.009
 coming-0.008
 dolphin-0.008
 ending-0.008
Token brought
Token ID3181
Feature activation+1.10e+00

Pos logit contributions
ons+0.182
bes+0.150
ages+0.140
seek+0.135
con+0.132
Neg logit contributions
ksh-0.100
 dolphin-0.100
rant-0.099
 flood-0.097
 whale-0.097
Token on
Token ID319
Feature activation-4.24e+00

Pos logit contributions
ons+0.253
bes+0.204
ages+0.192
on+0.179
con+0.177
Neg logit contributions
ksh-0.167
rant-0.164
 flood-0.164
 coming-0.160
 dolphin-0.153
Token the
Token ID262
Feature activation-7.69e-01

Pos logit contributions
ons+0.280
bes+0.208
ages+0.189
on+0.187
es+0.180
Neg logit contributions
ksh-0.285
rant-0.275
 flood-0.272
 dolphin-0.266
 whale-0.264
Token floor
Token ID4314
Feature activation-1.53e+00

Pos logit contributions
ons+0.065
bes+0.051
ages+0.049
aid+0.047
es+0.046
Neg logit contributions
ksh-0.037
rant-0.036
 flood-0.036
 dolphin-0.035
 whale-0.035
Token and
Token ID290
Feature activation+1.62e-01

Pos logit contributions
ons+0.117
bes+0.092
ages+0.088
on+0.083
con+0.082
Neg logit contributions
ksh-0.084
rant-0.082
 flood-0.082
 dolphin-0.079
 whale-0.078
Token the
Token ID262
Feature activation-7.44e-01

Pos logit contributions
 flood+0.008
 coming+0.008
 rum+0.007
rant+0.007
Why+0.007
Neg logit contributions
ons-0.013
bes-0.011
ages-0.011
seek-0.011
con-0.010
Token pages
Token ID5468
Feature activation-8.42e+00

Pos logit contributions
ons+0.052
bes+0.040
ages+0.039
igs+0.036
aid+0.036
Neg logit contributions
 flood-0.044
 ending-0.044
ksh-0.044
 dolphin-0.044
 coming-0.044
Token got
Token ID1392
Feature activation+7.88e-01

Pos logit contributions
ons+0.591
bes+0.463
ages+0.444
con+0.413
seek+0.406
Neg logit contributions
 flood-0.503
rant-0.497
ksh-0.492
 dolphin-0.478
 coming-0.472
Token torn
Token ID12445
Feature activation+1.96e-01

Pos logit contributions
 flood+0.042
ksh+0.042
rant+0.041
 coming+0.040
 dolphin+0.039
Neg logit contributions
ons-0.062
bes-0.050
ages-0.048
seek-0.044
con-0.044
Token.
Token ID13
Feature activation+6.09e-01

Pos logit contributions
ksh+0.012
 flood+0.012
rant+0.012
 dolphin+0.012
 whale+0.011
Neg logit contributions
ons-0.014
bes-0.011
ages-0.010
es-0.010
on-0.009
Token
Token ID198
Feature activation+2.08e-01

Pos logit contributions
ksh+0.021
 flood+0.020
rant+0.018
 dolphin+0.018
Why+0.018
Neg logit contributions
ons-0.058
bes-0.048
ages-0.048
aid-0.045
seek-0.045
Token
Token ID198
Feature activation+2.14e-01

Pos logit contributions
Why+0.008
rant+0.008
 flood+0.007
iet+0.007
 coming+0.007
Neg logit contributions
ons-0.018
bes-0.015
ages-0.015
aces-0.015
con-0.014
Token can
Token ID460
Feature activation+1.29e+00

Pos logit contributions
 flood+0.154
rant+0.151
 whale+0.150
 dolphin+0.149
 coming+0.143
Neg logit contributions
ons-0.301
bes-0.263
ages-0.243
seek-0.235
con-0.232
Token reveal
Token ID7766
Feature activation+5.18e+00

Pos logit contributions
ksh+0.070
rant+0.068
 flood+0.068
 dolphin+0.066
 whale+0.065
Neg logit contributions
ons-0.100
bes-0.079
ages-0.076
on-0.071
con-0.070
Token a
Token ID257
Feature activation-1.42e+00

Pos logit contributions
ksh+0.265
rant+0.259
 flood+0.258
 dolphin+0.249
 whale+0.245
Neg logit contributions
ons-0.417
bes-0.331
ages-0.318
on-0.300
con-0.297
Token solution
Token ID4610
Feature activation+2.80e+00

Pos logit contributions
ons+0.113
bes+0.088
ages+0.086
on+0.081
con+0.080
Neg logit contributions
ksh-0.076
rant-0.074
 flood-0.072
 dolphin-0.069
iet-0.067
Token.
Token ID13
Feature activation+1.22e-02

Pos logit contributions
rant+0.145
ksh+0.145
 flood+0.143
 dolphin+0.141
 whale+0.138
Neg logit contributions
ons-0.218
bes-0.174
ages-0.166
on-0.156
con-0.155
Token From
Token ID3574
Feature activation-8.35e+00

Pos logit contributions
ksh+0.001
 dolphin+0.001
 mate+0.001
rant+0.001
 flood+0.001
Neg logit contributions
ons-0.001
bes-0.001
ages-0.001
seek-0.001
aches-0.001
Token that
Token ID326
Feature activation+5.65e-01

Pos logit contributions
ons+0.630
bes+0.493
ages+0.475
on+0.441
es+0.434
Neg logit contributions
rant-0.471
ksh-0.467
 flood-0.467
 dolphin-0.459
 whale-0.451
Token day
Token ID1110
Feature activation-1.46e+00

Pos logit contributions
 flood+0.026
rant+0.026
ksh+0.025
 ending+0.025
 dolphin+0.025
Neg logit contributions
ons-0.048
bes-0.040
ages-0.038
aid-0.036
con-0.036
Token on
Token ID319
Feature activation-4.80e+00

Pos logit contributions
ons+0.099
bes+0.085
con+0.076
ages+0.075
seek+0.074
Neg logit contributions
 coming-0.088
rant-0.083
 beginning-0.083
 ending-0.083
 flood-0.083
Token,
Token ID11
Feature activation-4.57e-01

Pos logit contributions
ons+0.375
aid+0.324
ages+0.323
bes+0.310
seek+0.307
Neg logit contributions
 flood-0.228
 dolphin-0.226
 ending-0.221
 coming-0.214
 whale-0.208
Token Benny
Token ID44275
Feature activation+6.63e-01

Pos logit contributions
ons+0.040
bes+0.033
ages+0.032
seek+0.030
aid+0.030
Neg logit contributions
 flood-0.020
 dolphin-0.020
ksh-0.019
 ending-0.019
 mer-0.019
Token flips
Token ID45971
Feature activation-2.57e+00

Pos logit contributions
ons+0.165
bes+0.132
ages+0.130
aid+0.125
on+0.123
Neg logit contributions
 coming-0.111
 flood-0.109
 dolphin-0.107
 mate-0.103
 ending-0.103
Token.
Token ID13
Feature activation+1.72e-01

Pos logit contributions
ons+0.201
bes+0.158
ages+0.152
on+0.143
con+0.141
Neg logit contributions
ksh-0.137
rant-0.135
 flood-0.134
 dolphin-0.130
 whale-0.128
Token Every
Token ID3887
Feature activation-1.30e+00

Pos logit contributions
rant+0.010
ksh+0.010
 flood+0.010
 dolphin+0.010
 whale+0.010
Neg logit contributions
ons-0.012
bes-0.009
ages-0.009
on-0.008
seek-0.008
Token day
Token ID1110
Feature activation-1.29e+00

Pos logit contributions
ons+0.106
bes+0.085
ages+0.082
on+0.077
con+0.076
Neg logit contributions
ksh-0.065
 flood-0.064
rant-0.063
 dolphin-0.062
 whale-0.060
Token he
Token ID339
Feature activation-2.29e+00

Pos logit contributions
ons+0.069
ages+0.045
bes+0.044
on+0.041
es+0.039
Neg logit contributions
ksh-0.103
rant-0.100
 flood-0.098
iet-0.096
 dolphin-0.096
Token practiced
Token ID19893
Feature activation-9.22e+00

Pos logit contributions
ons+0.214
bes+0.175
ages+0.170
on+0.162
con+0.161
Neg logit contributions
ksh-0.088
rant-0.085
 flood-0.085
 dolphin-0.080
 whale-0.078
Token his
Token ID465
Feature activation-1.67e+00

Pos logit contributions
ons+0.699
ages+0.551
bes+0.549
aid+0.520
con+0.492
Neg logit contributions
 coming-0.509
 dolphin-0.471
rant-0.470
 flood-0.466
 crashing-0.458
Token moves
Token ID6100
Feature activation-2.25e+00

Pos logit contributions
ons+0.132
bes+0.098
ages+0.095
aid+0.095
es+0.093
Neg logit contributions
 dolphin-0.092
 flood-0.090
 ending-0.089
 whale-0.088
 tide-0.087
Token.
Token ID13
Feature activation+2.06e-01

Pos logit contributions
ons+0.186
bes+0.150
ages+0.145
aid+0.134
con+0.134
Neg logit contributions
rant-0.104
ksh-0.104
 dolphin-0.103
 coming-0.102
 flood-0.102
Token One
Token ID1881
Feature activation+1.79e+00

Pos logit contributions
ksh+0.013
rant+0.013
 flood+0.013
 dolphin+0.012
 whale+0.012
Neg logit contributions
ons-0.014
bes-0.011
ages-0.010
on-0.009
con-0.009
Token day
Token ID1110
Feature activation-1.26e+00

Pos logit contributions
 flood+0.080
 dolphin+0.078
 ending+0.077
 whale+0.076
ksh+0.075
Neg logit contributions
ons-0.156
bes-0.131
ages-0.124
con-0.116
es-0.116
Token of
Token ID286
Feature activation-1.43e+00

Pos logit contributions
ons+0.257
bes+0.203
ages+0.190
con+0.179
aid+0.175
Neg logit contributions
rant-0.210
 flood-0.209
ksh-0.206
 coming-0.203
 dolphin-0.203
Token old
Token ID1468
Feature activation-1.55e+00

Pos logit contributions
ons+0.100
bes+0.081
ages+0.076
seek+0.075
es+0.072
Neg logit contributions
 dolphin-0.083
 flood-0.083
 whale-0.082
ksh-0.081
rant-0.080
Token papers
Token ID9473
Feature activation-8.65e+00

Pos logit contributions
ons+0.106
bes+0.082
on+0.076
ages+0.076
aid+0.076
Neg logit contributions
 flood-0.093
 whale-0.092
 dolphin-0.092
 mate-0.090
ksh-0.089
Token and
Token ID290
Feature activation-7.19e-02

Pos logit contributions
ons+0.669
bes+0.528
ages+0.507
con+0.471
on+0.471
Neg logit contributions
rant-0.457
ksh-0.454
 flood-0.451
 dolphin-0.441
 mate-0.434
Token envelop
Token ID16441
Feature activation-3.05e+00

Pos logit contributions
ons+0.005
bes+0.004
seek+0.004
on+0.004
ages+0.004
Neg logit contributions
 mate-0.004
 dolphin-0.004
 whale-0.004
 coming-0.004
 flood-0.004
Tokenes
Token ID274
Feature activation-1.00e+01

Pos logit contributions
ons+0.088
bes+0.046
ages+0.035
con+0.029
aid+0.025
Neg logit contributions
rant-0.304
ksh-0.304
 mate-0.301
 dolphin-0.300
 whale-0.296
Token.
Token ID13
Feature activation+3.58e-01

Pos logit contributions
ons+0.750
bes+0.580
ages+0.558
on+0.523
es+0.519
Neg logit contributions
ksh-0.576
 flood-0.564
rant-0.561
 dolphin-0.541
 whale-0.533
Token They
Token ID1119
Feature activation+1.66e+00

Pos logit contributions
rant+0.026
 flood+0.026
ksh+0.025
 ending+0.025
 whale+0.025
Neg logit contributions
ons-0.020
bes-0.015
ages-0.014
on-0.013
con-0.012
Token take
Token ID1011
Feature activation+1.24e+00

Pos logit contributions
ksh+0.077
rant+0.077
 flood+0.077
 dolphin+0.074
 whale+0.072
Neg logit contributions
ons-0.141
bes-0.114
ages-0.110
con-0.103
on-0.103
Token turns
Token ID4962
Feature activation-3.02e+00

Pos logit contributions
ksh+0.068
rant+0.067
 flood+0.066
 dolphin+0.064
 whale+0.063
Neg logit contributions
ons-0.094
bes-0.075
ages-0.071
on-0.067
con-0.066
Token to
Token ID284
Feature activation-4.29e-01

Pos logit contributions
ons+0.229
bes+0.189
ages+0.175
aid+0.172
seek+0.166
Neg logit contributions
 coming-0.157
rant-0.151
 flood-0.149
ksh-0.148
 whale-0.147
Token She
Token ID1375
Feature activation-1.50e+00

Pos logit contributions
ksh+0.036
rant+0.036
 flood+0.036
 dolphin+0.035
 whale+0.034
Neg logit contributions
ons-0.038
bes-0.029
ages-0.028
on-0.026
con-0.025
Token loved
Token ID6151
Feature activation-1.50e-01

Pos logit contributions
ons+0.138
bes+0.114
con+0.112
ages+0.110
aid+0.107
Neg logit contributions
 wake-0.052
 coming-0.051
 dolphin-0.051
 ending-0.050
 flood-0.050
Token to
Token ID284
Feature activation-2.29e-01

Pos logit contributions
ons+0.012
bes+0.011
ages+0.010
es+0.010
aid+0.009
Neg logit contributions
 coming-0.007
ksh-0.007
 flood-0.007
 dolphin-0.007
 whale-0.007
Token play
Token ID711
Feature activation-2.06e+00

Pos logit contributions
ons+0.021
bes+0.017
ages+0.017
es+0.017
con+0.016
Neg logit contributions
 wake-0.009
 flood-0.009
 dolphin-0.009
 whale-0.008
 tide-0.008
Token with
Token ID351
Feature activation-1.12e+00

Pos logit contributions
ons+0.165
bes+0.130
ages+0.128
con+0.119
on+0.118
Neg logit contributions
ksh-0.103
 flood-0.103
 dolphin-0.101
rant-0.101
 whale-0.098
Token puzzles
Token ID24367
Feature activation-1.29e+01

Pos logit contributions
ons+0.082
ages+0.075
seek+0.073
bes+0.071
con+0.068
Neg logit contributions
 dolphin-0.052
 coming-0.052
 flood-0.051
 whale-0.050
iet-0.048
Token.
Token ID13
Feature activation+5.90e-01

Pos logit contributions
ons+1.154
ages+0.966
bes+0.954
con+0.893
aid+0.890
Neg logit contributions
 coming-0.513
rant-0.504
 like-0.499
 flood-0.484
 mate-0.482
Token One
Token ID1881
Feature activation+2.19e+00

Pos logit contributions
 flood+0.034
 dolphin+0.034
 whale+0.034
ksh+0.034
rant+0.033
Neg logit contributions
ons-0.043
bes-0.033
on-0.031
ages-0.030
con-0.030
Token day
Token ID1110
Feature activation-8.62e-01

Pos logit contributions
ksh+0.130
rant+0.128
 flood+0.124
 dolphin+0.120
 mate+0.118
Neg logit contributions
ons-0.161
bes-0.121
ages-0.119
on-0.116
aid-0.108
Token,
Token ID11
Feature activation+1.42e-01

Pos logit contributions
ons+0.062
bes+0.051
ages+0.047
con+0.045
aid+0.044
Neg logit contributions
 flood-0.048
 dolphin-0.047
rant-0.047
ksh-0.047
 coming-0.047
Token she
Token ID673
Feature activation-2.64e+00

Pos logit contributions
ksh+0.010
 flood+0.010
rant+0.010
 dolphin+0.010
 whale+0.010
Neg logit contributions
ons-0.009
bes-0.006
ages-0.006
on-0.005
con-0.005