TOP ACTIVATIONS
MAX = 13.265

" You have to show people how they are expected
m here to show it to you :
tackle this ," Amir H oss ain , chief forest official
We have to show that we are leading the
after former Finance Minister Jim Fla herty tightened the country 's
[ CO 2 ] are displayed on figure 4 - A
re just trying to show appreciation for the things that
in the Australian Journal of Zo ology . This
on another flight . It appears that none of that was
by Sean Penn ) is shown photograp hing snow le op
has been creating a disp oss essed section of society ,
why , it appears no other thing to me
Batman and Robin was unfor g ivable well , I
ins ic . Research has shown time and again that intrinsic
of this overview is to show that the truly objectionable features
- year - old Faith show the lasting power of what
life . Previous studies have shown that men with younger wives
ock , Germany , has shown that this is not the
by teacher pensions . It appears that their main concern is
on unexpected market shifts never seems to damp en their determination

MIN ACTIVATIONS
MIN = -13.612

acts could not change the minds of Trump supporters . The
with traces of the a Cyr ill ic found in their
. It could be a tweet you sent that insulted a
OV and the n v me storage driver . Amer has
come and go on their minds all the time :
tested and deployed this as well , and shared some results
deliver on other maps as well . Key d
people make up their own minds . 5 .
worked the film into the meditation on relationships and life that
will drop AMC , as well as the AMC - owned
. In a tweet to his 1 . 6
ren ounce them immediately as well , given that even if
including an image falsely suggesting Kurt Cob ain had predicted Donald
have to target him as well and make the damage drop
, or join in the conversation on our Forum . <|endoftext|>
guy . Patrick sings as well . Not to put words
will have a stall as well , so pop by and
team that was playing as well as anyone in football and
the demands by Kentucky Fried Chicken that the EU lift
the film are true as well , and a potential battle

INTERVAL 6.546 - 13.265
CONTAINS 0.461%

nation favors , as we see far too many people lie
that doesn t show female comic book characters do
And the Congress may by general Laws prescribe the Man ner
Raw l inson , John O ' K ane , J
woman , their love making often ve ers into far ce

INTERVAL -0.174 - 6.546
CONTAINS 52.631%

Castro The coaches stride off , important men on
, some quite disson ant seems to stem from
- capt ain Brian G ion ta , heart - and
custody of ICE whilst she waits for her trial . Thompson
to fly yourself . You really need your engine to

INTERVAL -6.893 - -0.174
CONTAINS 46.627%

. Moreno , meanwhile , served as vice president under Rafael
ka for was named Atlantic Coast Conference Men 's Basketball Player
uh " on the other end of the phone . This
she says , there were very few of
idea as to which is the main contributor of R FI

INTERVAL -13.612 - -6.893
CONTAINS 0.282%

struction in Pre y as well . But where Bio Shock
it s a deliberate sense of al oof ness
iness and confusion to the minds of readers .
ren ounce them immediately as well , given that even if
Her ok iller was big enough that you could see his
Token
Token ID198
Feature activation-7.13e-01

Pos logit contributions
istered+0.118
herty+0.113
earance+0.109
 chimpanzees+0.103
eman+0.103
Neg logit contributions
lake-0.169
ール-0.166
dit-0.165
roller-0.157
storms-0.153
Token"
Token ID1
Feature activation+1.64e+00

Pos logit contributions
lake+0.588
ール+0.576
dit+0.573
roller+0.542
storms+0.528
Neg logit contributions
istered-0.500
herty-0.480
earance-0.469
 chimpanzees-0.449
 presumption-0.444
TokenYou
Token ID1639
Feature activation+2.39e+00

Pos logit contributions
istered+1.108
herty+1.058
earance+1.029
 chimpanzees+0.979
eman+0.978
Neg logit contributions
lake-1.389
ール-1.365
dit-1.358
roller-1.283
storms-1.252
Token have
Token ID423
Feature activation+1.09e-02

Pos logit contributions
istered+1.772
herty+1.706
earance+1.659
 chimpanzees+1.598
eman+1.588
Neg logit contributions
lake-1.863
ール-1.836
dit-1.809
roller-1.701
storms-1.662
Token to
Token ID284
Feature activation+3.89e+00

Pos logit contributions
istered+0.008
herty+0.007
earance+0.007
 chimpanzees+0.007
 presumption+0.007
Neg logit contributions
lake-0.009
ール-0.009
dit-0.009
roller-0.008
storms-0.008
Token show
Token ID905
Feature activation+1.33e+01

Pos logit contributions
istered+2.753
herty+2.653
earance+2.568
 chimpanzees+2.493
 presumption+2.480
Neg logit contributions
lake-3.134
ール-3.105
dit-3.044
roller-2.873
storms-2.822
Token people
Token ID661
Feature activation+1.05e+00

Pos logit contributions
istered+8.320
herty+8.077
earance+8.003
 chimpanzees+7.992
 presumption+7.971
Neg logit contributions
ール-10.251
lake-10.214
dit-9.739
roller-9.289
storms-9.124
Token how
Token ID703
Feature activation+4.62e+00

Pos logit contributions
istered+0.714
herty+0.681
earance+0.664
 chimpanzees+0.630
eman+0.628
Neg logit contributions
lake-0.881
ール-0.864
dit-0.860
roller-0.814
storms-0.794
Token they
Token ID484
Feature activation+3.57e-01

Pos logit contributions
istered+3.105
herty+3.001
earance+2.884
 chimpanzees+2.855
 presumption+2.781
Neg logit contributions
lake-3.794
ール-3.793
dit-3.759
roller-3.503
storms-3.407
Token are
Token ID389
Feature activation-3.17e-01

Pos logit contributions
istered+0.265
herty+0.254
earance+0.248
 chimpanzees+0.236
eman+0.235
Neg logit contributions
lake-0.279
ール-0.272
dit-0.272
roller-0.256
storms-0.249
Token expected
Token ID2938
Feature activation+3.14e+00

Pos logit contributions
lake+0.263
ール+0.257
dit+0.256
roller+0.242
storms+0.236
Neg logit contributions
istered-0.220
herty-0.211
earance-0.206
 chimpanzees-0.195
eman-0.194
Token
Token ID447
Feature activation+2.77e+00

Pos logit contributions
istered+0.553
herty+0.530
earance+0.518
 chimpanzees+0.494
eman+0.492
Neg logit contributions
lake-0.583
ール-0.571
dit-0.568
roller-0.535
storms-0.520
Token
Token ID247
Feature activation+1.40e+00

Pos logit contributions
istered+2.064
herty+1.993
earance+1.924
eman+1.845
 presumption+1.838
Neg logit contributions
lake-2.137
dit-2.090
ール-2.084
roller-1.963
storms-1.925
Tokenm
Token ID76
Feature activation+1.96e+00

Pos logit contributions
istered+1.027
herty+0.984
earance+0.960
 chimpanzees+0.916
eman+0.915
Neg logit contributions
lake-1.097
ール-1.075
dit-1.068
roller-1.008
storms-0.982
Token here
Token ID994
Feature activation+2.57e+00

Pos logit contributions
istered+1.412
herty+1.354
earance+1.319
 chimpanzees+1.267
eman+1.260
Neg logit contributions
lake-1.557
ール-1.526
dit-1.522
roller-1.436
storms-1.397
Token to
Token ID284
Feature activation+1.21e+00

Pos logit contributions
istered+1.761
herty+1.688
earance+1.635
 chimpanzees+1.563
 presumption+1.557
Neg logit contributions
lake-2.143
ール-2.096
dit-2.091
roller-1.974
storms-1.923
Token show
Token ID905
Feature activation+1.30e+01

Pos logit contributions
istered+0.846
herty+0.809
earance+0.790
 chimpanzees+0.751
eman+0.747
Neg logit contributions
lake-0.994
ール-0.974
dit-0.969
roller-0.916
storms-0.892
Token it
Token ID340
Feature activation+3.87e+00

Pos logit contributions
istered+6.421
herty+6.421
earance+6.044
 chimpanzees+5.956
 comparative+5.897
Neg logit contributions
lake-11.943
ール-11.536
dit-11.405
roller-10.757
storms-10.576
Token to
Token ID284
Feature activation+2.87e+00

Pos logit contributions
istered+2.701
herty+2.610
earance+2.524
eman+2.407
 chimpanzees+2.401
Neg logit contributions
lake-3.173
ール-3.089
dit-3.073
roller-2.898
storms-2.817
Token you
Token ID345
Feature activation+1.29e+00

Pos logit contributions
istered+1.897
herty+1.823
earance+1.769
 chimpanzees+1.694
 presumption+1.681
Neg logit contributions
lake-2.459
ール-2.397
dit-2.387
roller-2.259
storms-2.206
Token:
Token ID25
Feature activation+1.93e+00

Pos logit contributions
istered+0.961
herty+0.923
earance+0.900
 chimpanzees+0.861
eman+0.857
Neg logit contributions
lake-1.011
ール-0.990
dit-0.983
roller-0.926
storms-0.901
Token
Token ID198
Feature activation+3.72e+00

Pos logit contributions
istered+1.328
herty+1.271
earance+1.238
 chimpanzees+1.181
 presumption+1.175
Neg logit contributions
lake-1.613
ール-1.581
dit-1.572
roller-1.486
storms-1.449
Token tackle
Token ID9761
Feature activation-1.92e+00

Pos logit contributions
lake+0.282
ール+0.275
dit+0.273
roller+0.259
storms+0.252
Neg logit contributions
istered-0.264
herty-0.252
earance-0.247
eman-0.234
 chimpanzees-0.233
Token this
Token ID428
Feature activation-3.23e-01

Pos logit contributions
lake+1.411
dit+1.365
ール+1.363
roller+1.276
storms+1.252
Neg logit contributions
istered-1.517
herty-1.454
earance-1.426
eman-1.352
 presumption-1.348
Token,"
Token ID553
Feature activation-2.91e-01

Pos logit contributions
lake+0.259
ール+0.254
dit+0.252
roller+0.238
storms+0.232
Neg logit contributions
istered-0.233
herty-0.223
earance-0.218
 chimpanzees-0.208
eman-0.207
Token Amir
Token ID43931
Feature activation+1.20e+00

Pos logit contributions
lake+0.258
dit+0.252
ール+0.252
roller+0.239
storms+0.234
Neg logit contributions
istered-0.186
herty-0.177
earance-0.173
 chimpanzees-0.163
 presumption-0.162
Token H
Token ID367
Feature activation-1.74e+00

Pos logit contributions
istered+0.918
herty+0.881
earance+0.862
 chimpanzees+0.825
 presumption+0.821
Neg logit contributions
lake-0.908
ール-0.888
dit-0.884
roller-0.830
storms-0.807
Tokenoss
Token ID793
Feature activation+1.25e+01

Pos logit contributions
lake+1.405
dit+1.373
ール+1.351
roller+1.303
storms+1.248
Neg logit contributions
istered-1.229
herty-1.175
earance-1.146
 chimpanzees-1.114
 presumption-1.112
Tokenain
Token ID391
Feature activation+1.42e+00

Pos logit contributions
istered+6.972
herty+6.881
eman+6.538
earance+6.399
phan+6.156
Neg logit contributions
ール-11.000
lake-10.831
dit-10.546
storms-10.137
roller-10.076
Token,
Token ID11
Feature activation+1.78e+00

Pos logit contributions
istered+1.074
herty+1.030
earance+1.007
 chimpanzees+0.962
eman+0.958
Neg logit contributions
lake-1.088
ール-1.066
dit-1.059
roller-0.996
storms-0.969
Token chief
Token ID4039
Feature activation+1.64e+00

Pos logit contributions
istered+1.222
herty+1.175
earance+1.137
 chimpanzees+1.091
eman+1.086
Neg logit contributions
lake-1.476
ール-1.453
dit-1.443
roller-1.368
storms-1.331
Token forest
Token ID8222
Feature activation+1.19e+00

Pos logit contributions
istered+1.089
herty+1.040
earance+1.011
 chimpanzees+0.968
 presumption+0.961
Neg logit contributions
lake-1.408
ール-1.387
dit-1.379
roller-1.304
storms-1.271
Token official
Token ID1743
Feature activation-2.67e+00

Pos logit contributions
istered+0.853
herty+0.818
earance+0.797
 chimpanzees+0.761
eman+0.758
Neg logit contributions
lake-0.959
ール-0.942
dit-0.936
roller-0.882
storms-0.859
Token
Token ID564
Feature activation+1.78e-02

Pos logit contributions
istered+0.787
herty+0.749
earance+0.731
 chimpanzees+0.695
 presumption+0.690
Neg logit contributions
lake-0.996
ール-0.978
dit-0.972
roller-0.920
storms-0.897
Token
Token ID250
Feature activation-5.28e-01

Pos logit contributions
istered+0.014
herty+0.013
earance+0.013
 chimpanzees+0.012
eman+0.012
Neg logit contributions
lake-0.013
ール-0.013
dit-0.013
roller-0.012
storms-0.012
TokenWe
Token ID1135
Feature activation+4.33e+00

Pos logit contributions
lake+0.448
ール+0.437
dit+0.435
roller+0.413
storms+0.402
Neg logit contributions
istered-0.359
herty-0.341
earance-0.334
 chimpanzees-0.319
 presumption-0.315
Token have
Token ID423
Feature activation-1.11e+00

Pos logit contributions
istered+3.021
herty+2.928
earance+2.828
 chimpanzees+2.720
eman+2.719
Neg logit contributions
lake-3.526
ール-3.468
dit-3.429
roller-3.235
storms-3.180
Token to
Token ID284
Feature activation+2.00e+00

Pos logit contributions
lake+0.868
ール+0.849
dit+0.847
roller+0.794
storms+0.775
Neg logit contributions
istered-0.823
herty-0.784
earance-0.769
eman-0.726
 chimpanzees-0.725
Token show
Token ID905
Feature activation+1.22e+01

Pos logit contributions
istered+1.529
herty+1.472
earance+1.436
 chimpanzees+1.379
 presumption+1.373
Neg logit contributions
lake-1.510
ール-1.479
dit-1.468
roller-1.381
storms-1.343
Token that
Token ID326
Feature activation+5.43e+00

Pos logit contributions
istered+7.077
herty+6.840
earance+6.760
 comparative+6.664
 chimpanzees+6.645
Neg logit contributions
lake-10.443
ール-10.333
dit-10.043
roller-9.693
storms-9.185
Token we
Token ID356
Feature activation+2.76e+00

Pos logit contributions
istered+3.742
herty+3.629
earance+3.517
 chimpanzees+3.417
 presumption+3.395
Neg logit contributions
lake-4.386
ール-4.356
dit-4.316
roller-4.053
storms-3.937
Token are
Token ID389
Feature activation+1.42e+00

Pos logit contributions
istered+1.996
herty+1.916
earance+1.862
 chimpanzees+1.788
eman+1.781
Neg logit contributions
lake-2.202
ール-2.162
dit-2.142
roller-2.021
storms-1.970
Token leading
Token ID3756
Feature activation-2.65e+00

Pos logit contributions
istered+1.015
herty+0.970
earance+0.945
 chimpanzees+0.906
eman+0.902
Neg logit contributions
lake-1.155
ール-1.134
dit-1.129
roller-1.064
storms-1.035
Token the
Token ID262
Feature activation-3.28e+00

Pos logit contributions
lake+2.146
ール+2.093
dit+2.082
roller+1.960
storms+1.932
Neg logit contributions
istered-1.880
herty-1.797
earance-1.767
eman-1.651
 chimpanzees-1.646
Token after
Token ID706
Feature activation-1.68e+00

Pos logit contributions
istered+0.450
herty+0.431
earance+0.420
 chimpanzees+0.401
eman+0.399
Neg logit contributions
lake-0.497
ール-0.488
dit-0.485
roller-0.457
storms-0.444
Token former
Token ID1966
Feature activation+9.39e-01

Pos logit contributions
lake+1.403
dit+1.370
ール+1.358
roller+1.298
storms+1.276
Neg logit contributions
istered-1.149
herty-1.088
earance-1.072
 chimpanzees-1.010
 presumption-1.005
Token Finance
Token ID15007
Feature activation-3.37e-01

Pos logit contributions
istered+0.602
herty+0.577
earance+0.557
 chimpanzees+0.531
 presumption+0.528
Neg logit contributions
lake-0.825
ール-0.813
dit-0.807
roller-0.766
storms-0.747
Token Minister
Token ID4139
Feature activation+9.63e-01

Pos logit contributions
lake+0.276
ール+0.269
dit+0.269
roller+0.254
storms+0.247
Neg logit contributions
istered-0.239
herty-0.228
earance-0.223
 chimpanzees-0.212
 presumption-0.211
Token Jim
Token ID5395
Feature activation-2.57e+00

Pos logit contributions
istered+0.754
herty+0.725
earance+0.708
 chimpanzees+0.679
eman+0.677
Neg logit contributions
lake-0.711
ール-0.697
dit-0.690
roller-0.650
storms-0.631
Token Fla
Token ID22026
Feature activation+1.21e+01

Pos logit contributions
lake+1.616
dit+1.556
ール+1.494
storms+1.394
roller+1.390
Neg logit contributions
istered-2.314
earance-2.160
herty-2.136
 chimpanzees-2.100
 presumption-2.068
Tokenherty
Token ID29029
Feature activation+3.63e+00

Pos logit contributions
herty+0.022
istered-1.277
earance-1.799
eman-2.115
phan-2.299
Neg logit contributions
ール-19.311
dit-18.916
lake-18.803
storms-18.359
starter-18.177
Token tightened
Token ID37257
Feature activation+5.32e+00

Pos logit contributions
istered+2.512
herty+2.426
earance+2.346
 chimpanzees+2.245
eman+2.239
Neg logit contributions
lake-2.982
ール-2.954
dit-2.914
roller-2.775
storms-2.678
Token the
Token ID262
Feature activation-8.15e-02

Pos logit contributions
istered+3.391
herty+3.283
earance+3.161
 presumption+3.008
 comparative+3.001
Neg logit contributions
lake-4.599
ール-4.518
dit-4.484
roller-4.221
storms-4.166
Token country
Token ID1499
Feature activation-2.71e+00

Pos logit contributions
lake+0.068
ール+0.067
dit+0.067
roller+0.063
storms+0.061
Neg logit contributions
istered-0.056
herty-0.053
earance-0.052
 chimpanzees-0.049
eman-0.049
Token's
Token ID338
Feature activation-1.68e+00

Pos logit contributions
lake+1.914
dit+1.872
ール+1.859
roller+1.747
storms+1.684
Neg logit contributions
istered-2.200
herty-2.104
earance-2.077
 chimpanzees-1.991
eman-1.986
Token [
Token ID685
Feature activation-2.29e+00

Pos logit contributions
lake+0.422
dit+0.410
ール+0.410
roller+0.385
storms+0.381
Neg logit contributions
istered-0.346
herty-0.329
earance-0.324
 chimpanzees-0.303
eman-0.303
TokenCO
Token ID8220
Feature activation+6.86e-01

Pos logit contributions
lake+1.511
dit+1.444
ール+1.440
roller+1.333
storms+1.303
Neg logit contributions
istered-1.993
herty-1.909
earance-1.888
 chimpanzees-1.820
 presumption-1.818
Token 2
Token ID362
Feature activation-6.00e-01

Pos logit contributions
istered+0.523
herty+0.502
earance+0.490
 chimpanzees+0.469
eman+0.467
Neg logit contributions
lake-0.521
ール-0.510
dit-0.507
roller-0.478
storms-0.465
Token ]
Token ID2361
Feature activation-1.89e+00

Pos logit contributions
lake+0.486
ール+0.476
dit+0.474
roller+0.445
storms+0.435
Neg logit contributions
istered-0.428
herty-0.410
earance-0.399
 chimpanzees-0.381
eman-0.379
Token are
Token ID389
Feature activation+5.13e+00

Pos logit contributions
lake+1.584
dit+1.531
ール+1.530
roller+1.442
storms+1.421
Neg logit contributions
istered-1.304
herty-1.254
earance-1.212
 chimpanzees-1.157
eman-1.145
Token displayed
Token ID9066
Feature activation+1.21e+01

Pos logit contributions
istered+3.548
herty+3.401
earance+3.284
 chimpanzees+3.185
 presumption+3.170
Neg logit contributions
lake-4.188
ール-4.153
dit-4.090
roller-3.893
storms-3.759
Token on
Token ID319
Feature activation+7.19e+00

Pos logit contributions
istered+7.166
herty+6.855
 comparative+6.565
earance+6.519
eman+6.450
Neg logit contributions
ール-10.182
lake-10.077
dit-9.820
roller-9.450
storms-9.107
Token figure
Token ID3785
Feature activation+4.87e+00

Pos logit contributions
istered+4.503
herty+4.284
earance+4.145
eman+4.000
 presumption+3.988
Neg logit contributions
lake-6.232
ール-6.186
dit-6.046
roller-5.856
storms-5.622
Token 4
Token ID604
Feature activation+4.69e+00

Pos logit contributions
istered+3.483
herty+3.328
earance+3.239
 presumption+3.116
eman+3.112
Neg logit contributions
lake-3.842
ール-3.820
dit-3.781
roller-3.571
storms-3.456
Token-
Token ID12
Feature activation+2.78e+00

Pos logit contributions
istered+3.397
herty+3.253
earance+3.176
eman+3.045
 chimpanzees+3.038
Neg logit contributions
lake-3.676
ール-3.638
dit-3.580
roller-3.393
storms-3.296
TokenA
Token ID32
Feature activation+4.73e+00

Pos logit contributions
istered+1.853
herty+1.773
earance+1.719
eman+1.642
 chimpanzees+1.630
Neg logit contributions
lake-2.346
ール-2.318
dit-2.293
roller-2.178
storms-2.126
Token
Token ID247
Feature activation+3.04e-01

Pos logit contributions
lake+0.162
ール+0.158
dit+0.156
roller+0.147
storms+0.142
Neg logit contributions
istered-0.176
herty-0.168
earance-0.166
 chimpanzees-0.158
 presumption-0.157
Tokenre
Token ID260
Feature activation+1.10e+00

Pos logit contributions
istered+0.250
herty+0.240
earance+0.236
 chimpanzees+0.226
 presumption+0.225
Neg logit contributions
lake-0.214
ール-0.208
dit-0.208
roller-0.194
storms-0.187
Token just
Token ID655
Feature activation+1.77e+00

Pos logit contributions
istered+0.789
herty+0.754
earance+0.738
 chimpanzees+0.701
 presumption+0.698
Neg logit contributions
lake-0.890
ール-0.871
dit-0.866
roller-0.819
storms-0.797
Token trying
Token ID2111
Feature activation+1.38e+00

Pos logit contributions
istered+1.253
herty+1.199
earance+1.170
 chimpanzees+1.115
eman+1.109
Neg logit contributions
lake-1.436
ール-1.408
dit-1.400
roller-1.322
storms-1.288
Token to
Token ID284
Feature activation+1.49e+00

Pos logit contributions
istered+0.953
herty+0.911
earance+0.887
 chimpanzees+0.846
eman+0.843
Neg logit contributions
lake-1.144
ール-1.120
dit-1.115
roller-1.055
storms-1.028
Token show
Token ID905
Feature activation+1.20e+01

Pos logit contributions
istered+1.078
herty+1.032
earance+1.008
 chimpanzees+0.960
eman+0.956
Neg logit contributions
lake-1.190
ール-1.165
dit-1.160
roller-1.094
storms-1.065
Token appreciation
Token ID19163
Feature activation+2.53e+00

Pos logit contributions
herty+7.111
istered+7.091
earance+6.837
 chimpanzees+6.781
 presumption+6.599
Neg logit contributions
lake-10.006
ール-9.894
dit-9.490
roller-9.036
storms-8.744
Token for
Token ID329
Feature activation+2.70e+00

Pos logit contributions
istered+1.868
herty+1.794
earance+1.753
 chimpanzees+1.676
eman+1.668
Neg logit contributions
lake-1.981
ール-1.944
dit-1.928
roller-1.821
storms-1.767
Token the
Token ID262
Feature activation+1.73e+00

Pos logit contributions
istered+1.772
herty+1.699
earance+1.649
 chimpanzees+1.583
eman+1.565
Neg logit contributions
lake-2.327
ール-2.289
dit-2.269
roller-2.154
storms-2.092
Token things
Token ID1243
Feature activation-7.67e-01

Pos logit contributions
istered+1.153
herty+1.100
earance+1.072
 chimpanzees+1.015
eman+1.011
Neg logit contributions
lake-1.481
ール-1.453
dit-1.446
roller-1.369
storms-1.336
Token that
Token ID326
Feature activation-1.50e+00

Pos logit contributions
lake+0.631
ール+0.617
dit+0.615
roller+0.582
storms+0.571
Neg logit contributions
istered-0.538
herty-0.509
earance-0.500
 presumption-0.472
eman-0.469
Token in
Token ID287
Feature activation+2.08e+00

Pos logit contributions
istered+1.319
herty+1.266
earance+1.232
 chimpanzees+1.174
eman+1.167
Neg logit contributions
lake-1.620
ール-1.597
dit-1.589
roller-1.500
storms-1.461
Token the
Token ID262
Feature activation+1.42e+00

Pos logit contributions
istered+1.295
herty+1.239
earance+1.200
 chimpanzees+1.143
 presumption+1.131
Neg logit contributions
lake-1.867
ール-1.839
dit-1.825
roller-1.734
storms-1.695
Token Australian
Token ID6638
Feature activation-4.47e-01

Pos logit contributions
istered+0.965
herty+0.920
earance+0.899
 chimpanzees+0.852
eman+0.848
Neg logit contributions
lake-1.193
ール-1.169
dit-1.164
roller-1.102
storms-1.073
Token Journal
Token ID4913
Feature activation+1.45e+00

Pos logit contributions
lake+0.364
dit+0.356
ール+0.353
roller+0.333
storms+0.325
Neg logit contributions
istered-0.317
herty-0.301
earance-0.298
eman-0.279
 presumption-0.278
Token of
Token ID286
Feature activation+1.35e+00

Pos logit contributions
istered+1.013
herty+0.970
earance+0.944
 chimpanzees+0.907
eman+0.902
Neg logit contributions
lake-1.184
ール-1.164
dit-1.151
roller-1.095
storms-1.073
Token Zo
Token ID31645
Feature activation+1.20e+01

Pos logit contributions
istered+0.993
herty+0.950
earance+0.930
 chimpanzees+0.885
eman+0.883
Neg logit contributions
lake-1.057
ール-1.035
dit-1.031
roller-0.970
storms-0.944
Tokenology
Token ID1435
Feature activation+3.03e+00

Pos logit contributions
herty+5.865
istered+5.740
eman+5.421
earance+5.195
ocyte+5.114
Neg logit contributions
ール-11.571
dit-11.562
lake-11.428
roller-11.002
storms-10.619
Token.
Token ID13
Feature activation-5.51e-02

Pos logit contributions
istered+2.184
herty+2.123
earance+2.052
 chimpanzees+1.975
eman+1.970
Neg logit contributions
lake-2.367
ール-2.353
dit-2.323
roller-2.194
storms-2.137
Token
Token ID198
Feature activation+5.02e-01

Pos logit contributions
lake+0.048
ール+0.047
dit+0.046
roller+0.044
storms+0.043
Neg logit contributions
istered-0.036
herty-0.035
earance-0.034
 chimpanzees-0.032
 presumption-0.032
Token
Token ID198
Feature activation-2.09e-01

Pos logit contributions
istered+0.312
herty+0.298
earance+0.288
 chimpanzees+0.272
eman+0.272
Neg logit contributions
lake-0.451
ール-0.444
dit-0.441
roller-0.419
storms-0.409
TokenThis
Token ID1212
Feature activation+2.44e+00

Pos logit contributions
lake+0.181
ール+0.177
dit+0.176
roller+0.167
storms+0.163
Neg logit contributions
istered-0.139
herty-0.132
earance-0.129
 chimpanzees-0.122
 presumption-0.122
Token on
Token ID319
Feature activation+9.24e-01

Pos logit contributions
lake+2.673
dit+2.619
ール+2.616
roller+2.460
storms+2.394
Neg logit contributions
istered-2.579
herty-2.493
earance-2.413
 chimpanzees-2.296
eman-2.283
Token another
Token ID1194
Feature activation-1.12e+00

Pos logit contributions
istered+0.640
herty+0.611
earance+0.598
 chimpanzees+0.569
 presumption+0.567
Neg logit contributions
lake-0.767
ール-0.753
dit-0.746
roller-0.707
storms-0.689
Token flight
Token ID5474
Feature activation-2.71e+00

Pos logit contributions
lake+1.011
dit+0.986
ール+0.986
roller+0.939
storms+0.913
Neg logit contributions
istered-0.696
herty-0.663
earance-0.642
 chimpanzees-0.608
eman-0.603
Token.
Token ID13
Feature activation-5.04e-01

Pos logit contributions
lake+2.038
dit+1.992
ール+1.987
roller+1.880
storms+1.816
Neg logit contributions
istered-2.079
herty-1.998
earance-1.946
 chimpanzees-1.864
eman-1.845
TokenIt
Token ID1026
Feature activation+1.84e+00

Pos logit contributions
lake+0.418
ール+0.411
dit+0.408
roller+0.385
storms+0.376
Neg logit contributions
istered-0.350
herty-0.334
earance-0.328
 chimpanzees-0.312
 presumption-0.308
Token appears
Token ID3568
Feature activation+1.19e+01

Pos logit contributions
istered+1.294
herty+1.245
earance+1.210
eman+1.151
 chimpanzees+1.148
Neg logit contributions
lake-1.512
ール-1.480
dit-1.474
roller-1.392
storms-1.351
Token that
Token ID326
Feature activation+1.83e+00

Pos logit contributions
istered+6.286
herty+6.042
earance+5.818
 presumption+5.807
 chimpanzees+5.749
Neg logit contributions
lake-10.627
ール-10.534
dit-10.357
roller-9.992
storms-9.481
Token none
Token ID4844
Feature activation-1.44e+00

Pos logit contributions
istered+1.263
herty+1.211
earance+1.174
 presumption+1.128
 chimpanzees+1.126
Neg logit contributions
lake-1.515
ール-1.491
dit-1.476
roller-1.398
storms-1.358
Token of
Token ID286
Feature activation+4.73e-01

Pos logit contributions
lake+1.118
ール+1.093
dit+1.088
roller+1.025
storms+0.996
Neg logit contributions
istered-1.077
herty-1.034
earance-1.006
 chimpanzees-0.964
 presumption-0.959
Token that
Token ID326
Feature activation-1.06e+00

Pos logit contributions
istered+0.319
herty+0.305
earance+0.298
 chimpanzees+0.282
eman+0.280
Neg logit contributions
lake-0.400
ール-0.392
dit-0.390
roller-0.368
storms-0.361
Token was
Token ID373
Feature activation-2.16e+00

Pos logit contributions
lake+0.831
ール+0.812
dit+0.808
roller+0.760
storms+0.742
Neg logit contributions
istered-0.780
herty-0.748
earance-0.728
 chimpanzees-0.694
eman-0.693
Token by
Token ID416
Feature activation+2.79e+00

Pos logit contributions
istered+3.060
herty+2.930
earance+2.876
 chimpanzees+2.796
eman+2.761
Neg logit contributions
lake-2.459
ール-2.420
dit-2.380
roller-2.245
storms-2.169
Token Sean
Token ID11465
Feature activation+1.82e+00

Pos logit contributions
istered+2.161
herty+2.076
earance+2.025
 chimpanzees+1.950
eman+1.937
Neg logit contributions
lake-2.079
ール-2.043
dit-2.016
roller-1.905
storms-1.851
Token Penn
Token ID6595
Feature activation+4.97e+00

Pos logit contributions
istered+1.463
herty+1.408
earance+1.378
 chimpanzees+1.322
 presumption+1.315
Neg logit contributions
lake-1.314
ール-1.284
dit-1.277
roller-1.197
storms-1.160
Token)
Token ID8
Feature activation+1.79e+00

Pos logit contributions
istered+3.655
herty+3.554
earance+3.427
eman+3.336
 chimpanzees+3.259
Neg logit contributions
lake-3.792
ール-3.773
dit-3.762
roller-3.513
storms-3.414
Token is
Token ID318
Feature activation+3.17e+00

Pos logit contributions
istered+1.224
herty+1.169
earance+1.139
 chimpanzees+1.082
 presumption+1.077
Neg logit contributions
lake-1.510
ール-1.480
dit-1.473
roller-1.393
storms-1.360
Token shown
Token ID3402
Feature activation+1.19e+01

Pos logit contributions
istered+2.220
herty+2.122
earance+2.068
 chimpanzees+1.986
eman+1.966
Neg logit contributions
lake-2.594
ール-2.550
dit-2.532
roller-2.396
storms-2.330
Token photograp
Token ID10079
Feature activation+5.11e+00

Pos logit contributions
istered+7.144
 chimpanzees+6.883
herty+6.761
 comparative+6.607
earance+6.596
Neg logit contributions
ール-9.844
lake-9.728
dit-9.512
roller-9.146
starter-8.771
Tokenhing
Token ID722
Feature activation+4.15e+00

Pos logit contributions
istered+3.428
herty+3.269
earance+3.137
eman+3.017
 chimpanzees+2.964
Neg logit contributions
ール-4.327
lake-4.320
dit-4.259
roller-3.997
storms-3.888
Token snow
Token ID6729
Feature activation+2.45e-01

Pos logit contributions
istered+2.997
herty+2.861
earance+2.787
 chimpanzees+2.738
 presumption+2.667
Neg logit contributions
lake-3.294
ール-3.246
dit-3.198
roller-3.039
storms-2.920
Token le
Token ID443
Feature activation+3.06e+00

Pos logit contributions
istered+0.165
herty+0.158
earance+0.154
 presumption+0.145
 chimpanzees+0.145
Neg logit contributions
lake-0.209
ール-0.204
dit-0.203
roller-0.192
storms-0.189
Tokenop
Token ID404
Feature activation+5.46e+00

Pos logit contributions
istered+1.627
herty+1.524
earance+1.478
 chimpanzees+1.383
eman+1.379
Neg logit contributions
lake-3.027
ール-2.983
dit-2.962
roller-2.824
storms-2.768
Token has
Token ID468
Feature activation-2.67e+00

Pos logit contributions
lake+0.040
ール+0.039
dit+0.039
roller+0.037
storms+0.036
Neg logit contributions
istered-0.036
herty-0.035
earance-0.034
 chimpanzees-0.032
 presumption-0.032
Token been
Token ID587
Feature activation+7.44e-01

Pos logit contributions
lake+2.004
dit+1.962
ール+1.945
roller+1.829
storms+1.793
Neg logit contributions
istered-2.048
herty-1.944
earance-1.940
 presumption-1.825
eman-1.813
Token creating
Token ID4441
Feature activation-8.79e-01

Pos logit contributions
istered+0.518
herty+0.493
earance+0.484
 chimpanzees+0.457
 presumption+0.455
Neg logit contributions
lake-0.616
ール-0.601
dit-0.601
roller-0.569
storms-0.555
Token a
Token ID257
Feature activation-1.56e+00

Pos logit contributions
lake+0.731
dit+0.712
ール+0.708
roller+0.672
storms+0.661
Neg logit contributions
istered-0.606
herty-0.576
earance-0.570
 chimpanzees-0.533
eman-0.532
Token disp
Token ID4596
Feature activation-7.70e-01

Pos logit contributions
lake+1.280
ール+1.239
dit+1.235
roller+1.183
storms+1.146
Neg logit contributions
istered-1.095
herty-1.031
earance-1.030
 chimpanzees-0.965
eman-0.962
Tokenoss
Token ID793
Feature activation+1.19e+01

Pos logit contributions
lake+0.650
dit+0.626
ール+0.621
roller+0.601
storms+0.579
Neg logit contributions
istered-0.521
herty-0.500
earance-0.481
 chimpanzees-0.477
 presumption-0.468
Tokenessed
Token ID6676
Feature activation-6.60e-01

Pos logit contributions
istered+5.990
herty+5.786
earance+5.743
eman+5.138
phan+4.886
Neg logit contributions
ール-11.386
lake-11.322
dit-10.918
roller-10.546
storms-10.476
Token section
Token ID2665
Feature activation-1.05e+00

Pos logit contributions
lake+0.546
dit+0.535
ール+0.533
roller+0.504
storms+0.490
Neg logit contributions
istered-0.458
herty-0.437
earance-0.429
 chimpanzees-0.405
eman-0.403
Token of
Token ID286
Feature activation-6.54e-01

Pos logit contributions
lake+0.815
ール+0.797
dit+0.793
roller+0.748
storms+0.726
Neg logit contributions
istered-0.780
herty-0.749
earance-0.731
 chimpanzees-0.699
 presumption-0.694
Token society
Token ID3592
Feature activation-5.01e-01

Pos logit contributions
lake+0.567
dit+0.556
ール+0.555
roller+0.524
storms+0.513
Neg logit contributions
istered-0.427
herty-0.406
earance-0.400
 chimpanzees-0.375
eman-0.373
Token,
Token ID11
Feature activation-4.23e-01

Pos logit contributions
lake+0.386
ール+0.377
dit+0.376
roller+0.354
storms+0.345
Neg logit contributions
istered-0.378
herty-0.362
earance-0.355
 chimpanzees-0.337
eman-0.336
Tokenwhy
Token ID22850
Feature activation+2.80e+00

Pos logit contributions
istered+1.453
herty+1.387
earance+1.350
 chimpanzees+1.281
eman+1.276
Neg logit contributions
lake-1.878
ール-1.845
dit-1.834
roller-1.737
storms-1.694
Token,
Token ID11
Feature activation+3.30e+00

Pos logit contributions
istered+2.024
herty+1.943
earance+1.895
 chimpanzees+1.815
 presumption+1.810
Neg logit contributions
lake-2.214
ール-2.194
dit-2.162
roller-2.043
storms-1.977
Token
Token ID198
Feature activation+2.03e+00

Pos logit contributions
istered+2.314
herty+2.218
earance+2.156
 chimpanzees+2.073
 presumption+2.064
Neg logit contributions
lake-2.689
ール-2.657
dit-2.630
roller-2.487
storms-2.410
Token
Token ID198
Feature activation+1.81e+00

Pos logit contributions
istered+1.207
herty+1.156
earance+1.107
eman+1.056
 presumption+1.049
Neg logit contributions
lake-1.859
ール-1.840
dit-1.822
roller-1.734
storms-1.694
Tokenit
Token ID270
Feature activation+4.02e+00

Pos logit contributions
istered+1.263
herty+1.209
earance+1.178
 chimpanzees+1.122
eman+1.117
Neg logit contributions
lake-1.489
ール-1.462
dit-1.453
roller-1.373
storms-1.337
Token appears
Token ID3568
Feature activation+1.18e+01

Pos logit contributions
istered+2.713
herty+2.595
earance+2.520
eman+2.405
 chimpanzees+2.402
Neg logit contributions
lake-3.382
ール-3.342
dit-3.309
roller-3.139
storms-3.023
Token no
Token ID645
Feature activation+2.14e+00

Pos logit contributions
istered+7.162
herty+6.780
earance+6.626
 presumption+6.564
 comparative+6.497
Neg logit contributions
ール-9.874
lake-9.639
dit-9.592
roller-9.168
starter-8.621
Token other
Token ID584
Feature activation+1.93e+00

Pos logit contributions
istered+1.502
herty+1.436
earance+1.402
 chimpanzees+1.340
 presumption+1.335
Neg logit contributions
lake-1.745
ール-1.719
dit-1.702
roller-1.611
storms-1.565
Token thing
Token ID1517
Feature activation+2.49e+00

Pos logit contributions
istered+1.350
herty+1.292
earance+1.261
 chimpanzees+1.205
 presumption+1.201
Neg logit contributions
lake-1.585
ール-1.563
dit-1.550
roller-1.464
storms-1.424
Token to
Token ID284
Feature activation+2.10e+00

Pos logit contributions
istered+1.854
herty+1.779
earance+1.738
 chimpanzees+1.662
eman+1.653
Neg logit contributions
lake-1.933
ール-1.898
dit-1.884
roller-1.774
storms-1.722
Token me
Token ID502
Feature activation+3.49e-01

Pos logit contributions
istered+1.484
herty+1.420
earance+1.386
 chimpanzees+1.322
 presumption+1.315
Neg logit contributions
lake-1.705
ール-1.675
dit-1.662
roller-1.571
storms-1.529
Token Batman
Token ID9827
Feature activation+1.02e+00

Pos logit contributions
istered+1.363
herty+1.312
earance+1.271
 chimpanzees+1.220
 presumption+1.214
Neg logit contributions
lake-1.611
ール-1.588
dit-1.573
roller-1.479
storms-1.443
Token and
Token ID290
Feature activation+2.37e-01

Pos logit contributions
istered+0.773
herty+0.742
earance+0.725
 chimpanzees+0.693
eman+0.691
Neg logit contributions
lake-0.775
ール-0.760
dit-0.755
roller-0.710
storms-0.690
Token Robin
Token ID12325
Feature activation+1.09e-01

Pos logit contributions
istered+0.184
herty+0.176
earance+0.172
 chimpanzees+0.165
 presumption+0.164
Neg logit contributions
lake-0.178
ール-0.174
dit-0.172
roller-0.163
storms-0.158
Token was
Token ID373
Feature activation-1.90e+00

Pos logit contributions
istered+0.082
herty+0.079
earance+0.077
 chimpanzees+0.074
eman+0.074
Neg logit contributions
lake-0.084
ール-0.082
dit-0.082
roller-0.077
storms-0.075
Token unfor
Token ID28371
Feature activation-3.62e+00

Pos logit contributions
lake+1.503
ール+1.459
dit+1.459
roller+1.385
storms+1.343
Neg logit contributions
istered-1.401
herty-1.330
earance-1.312
 chimpanzees-1.246
 presumption-1.235
Tokeng
Token ID70
Feature activation+1.18e+01

Pos logit contributions
lake+2.375
dit+2.261
ール+2.206
roller+2.093
storms+2.009
Neg logit contributions
istered-3.175
herty-3.025
earance-2.981
 chimpanzees-2.907
 presumption-2.883
Tokenivable
Token ID21911
Feature activation-1.87e+00

Pos logit contributions
istered+7.362
herty+6.763
earance+6.753
eman+6.668
phan+6.294
Neg logit contributions
lake-10.074
ール-9.946
dit-9.862
roller-9.273
storms-9.150
Token
Token ID1399
Feature activation+2.25e+00

Pos logit contributions
lake+1.448
ール+1.410
dit+1.408
roller+1.323
storms+1.293
Neg logit contributions
istered-1.413
herty-1.343
earance-1.321
 chimpanzees-1.249
eman-1.247
Token well
Token ID880
Feature activation-2.91e+00

Pos logit contributions
istered+1.558
herty+1.496
earance+1.451
 chimpanzees+1.385
 presumption+1.380
Neg logit contributions
lake-1.863
ール-1.833
dit-1.821
roller-1.714
storms-1.675
Token,
Token ID11
Feature activation+1.32e+00

Pos logit contributions
lake+2.269
ール+2.218
dit+2.206
roller+2.103
storms+2.027
Neg logit contributions
istered-2.161
herty-2.050
earance-2.042
 chimpanzees-1.928
eman-1.919
Token I
Token ID314
Feature activation-1.75e-01

Pos logit contributions
istered+0.953
herty+0.915
earance+0.891
 chimpanzees+0.852
 presumption+0.848
Neg logit contributions
lake-1.048
ール-1.028
dit-1.022
roller-0.963
storms-0.938
Tokenins
Token ID1040
Feature activation+3.03e+00

Pos logit contributions
istered+2.028
herty+1.947
earance+1.900
eman+1.813
 chimpanzees+1.809
Neg logit contributions
lake-2.064
ール-2.029
dit-2.005
roller-1.891
storms-1.846
Tokenic
Token ID291
Feature activation+2.01e+00

Pos logit contributions
istered+1.705
herty+1.601
earance+1.549
eman+1.467
 chimpanzees+1.448
Neg logit contributions
lake-2.905
ール-2.875
dit-2.822
roller-2.719
storms-2.647
Token.
Token ID13
Feature activation+4.49e-01

Pos logit contributions
istered+1.305
herty+1.245
earance+1.211
 chimpanzees+1.145
eman+1.141
Neg logit contributions
lake-1.757
ール-1.725
dit-1.719
roller-1.628
storms-1.590
Token Research
Token ID4992
Feature activation+3.29e-02

Pos logit contributions
istered+0.310
herty+0.295
earance+0.290
 chimpanzees+0.275
 presumption+0.273
Neg logit contributions
lake-0.376
ール-0.369
dit-0.366
roller-0.347
storms-0.337
Token has
Token ID468
Feature activation+1.27e-01

Pos logit contributions
istered+0.022
herty+0.021
earance+0.020
 chimpanzees+0.019
 presumption+0.019
Neg logit contributions
lake-0.028
ール-0.028
dit-0.028
roller-0.026
storms-0.026
Token shown
Token ID3402
Feature activation+1.17e+01

Pos logit contributions
istered+0.076
herty+0.072
earance+0.070
 chimpanzees+0.066
eman+0.066
Neg logit contributions
lake-0.117
ール-0.115
dit-0.114
roller-0.109
storms-0.106
Token time
Token ID640
Feature activation+6.52e-01

Pos logit contributions
istered+5.764
herty+5.504
 chimpanzees+5.462
earance+5.279
 comparative+5.274
Neg logit contributions
ール-11.106
lake-11.103
dit-10.868
roller-10.291
storms-10.070
Token and
Token ID290
Feature activation+1.64e+00

Pos logit contributions
istered+0.485
herty+0.468
earance+0.455
 chimpanzees+0.433
eman+0.432
Neg logit contributions
lake-0.508
ール-0.497
dit-0.494
roller-0.465
storms-0.454
Token again
Token ID757
Feature activation+5.23e-01

Pos logit contributions
istered+1.219
herty+1.170
earance+1.142
 chimpanzees+1.092
 presumption+1.086
Neg logit contributions
lake-1.285
ール-1.260
dit-1.252
roller-1.179
storms-1.147
Token that
Token ID326
Feature activation+1.96e+00

Pos logit contributions
istered+0.348
herty+0.329
earance+0.322
eman+0.303
 presumption+0.302
Neg logit contributions
lake-0.449
ール-0.440
dit-0.436
roller-0.415
storms-0.407
Token intrinsic
Token ID28327
Feature activation-1.67e+00

Pos logit contributions
istered+1.316
herty+1.257
earance+1.222
 chimpanzees+1.175
 presumption+1.164
Neg logit contributions
lake-1.663
ール-1.637
dit-1.622
roller-1.536
storms-1.498
Token of
Token ID286
Feature activation+1.11e+00

Pos logit contributions
lake+1.952
ール+1.913
dit+1.880
roller+1.783
storms+1.738
Neg logit contributions
istered-2.020
herty-1.942
earance-1.898
 chimpanzees-1.808
 presumption-1.792
Token this
Token ID428
Feature activation+2.87e+00

Pos logit contributions
istered+0.757
herty+0.723
earance+0.705
 chimpanzees+0.669
eman+0.666
Neg logit contributions
lake-0.932
ール-0.914
dit-0.909
roller-0.861
storms-0.840
Token overview
Token ID16700
Feature activation+1.87e+00

Pos logit contributions
istered+1.926
herty+1.846
earance+1.792
 presumption+1.719
 chimpanzees+1.714
Neg logit contributions
lake-2.420
ール-2.389
dit-2.375
roller-2.240
storms-2.184
Token is
Token ID318
Feature activation+2.88e+00

Pos logit contributions
istered+1.295
herty+1.240
earance+1.209
 chimpanzees+1.152
eman+1.149
Neg logit contributions
lake-1.551
ール-1.524
dit-1.515
roller-1.433
storms-1.395
Token to
Token ID284
Feature activation+8.75e-01

Pos logit contributions
istered+1.983
herty+1.902
earance+1.853
 chimpanzees+1.766
 presumption+1.762
Neg logit contributions
lake-2.391
ール-2.351
dit-2.337
roller-2.208
storms-2.150
Token show
Token ID905
Feature activation+1.17e+01

Pos logit contributions
istered+0.604
herty+0.576
earance+0.563
 chimpanzees+0.534
eman+0.531
Neg logit contributions
lake-0.730
ール-0.714
dit-0.713
roller-0.673
storms-0.656
Token that
Token ID326
Feature activation+4.02e+00

Pos logit contributions
herty+5.990
istered+5.837
 comparative+5.701
 chimpanzees+5.615
earance+5.575
Neg logit contributions
ール-10.773
lake-10.684
dit-10.404
roller-9.947
storms-9.539
Token the
Token ID262
Feature activation+1.43e-01

Pos logit contributions
istered+2.699
herty+2.596
earance+2.521
 chimpanzees+2.450
 presumption+2.436
Neg logit contributions
lake-3.379
ール-3.328
dit-3.301
roller-3.124
storms-3.034
Token truly
Token ID4988
Feature activation-2.71e+00

Pos logit contributions
istered+0.094
herty+0.090
earance+0.088
 chimpanzees+0.083
eman+0.082
Neg logit contributions
lake-0.123
ール-0.120
dit-0.120
roller-0.113
storms-0.111
Token objectionable
Token ID48540
Feature activation+8.19e-01

Pos logit contributions
lake+2.253
dit+2.202
ール+2.180
roller+2.073
storms+2.033
Neg logit contributions
istered-1.835
herty-1.764
earance-1.738
 chimpanzees-1.605
eman-1.600
Token features
Token ID3033
Feature activation+2.65e+00

Pos logit contributions
istered+0.626
herty+0.601
earance+0.587
 chimpanzees+0.559
eman+0.558
Neg logit contributions
lake-0.622
ール-0.607
dit-0.605
roller-0.568
storms-0.554
Token-
Token ID12
Feature activation+1.09e+00

Pos logit contributions
istered+2.262
herty+2.182
earance+2.133
 chimpanzees+2.053
eman+2.036
Neg logit contributions
lake-2.054
ール-2.010
dit-1.993
roller-1.868
storms-1.815
Tokenyear
Token ID1941
Feature activation+3.02e+00

Pos logit contributions
istered+0.748
herty+0.714
earance+0.696
 chimpanzees+0.662
 presumption+0.660
Neg logit contributions
lake-0.914
ール-0.895
dit-0.892
roller-0.844
storms-0.821
Token-
Token ID12
Feature activation-2.51e+00

Pos logit contributions
istered+2.396
herty+2.305
earance+2.249
 chimpanzees+2.173
eman+2.155
Neg logit contributions
lake-2.193
ール-2.153
dit-2.137
roller-2.003
storms-1.949
Tokenold
Token ID727
Feature activation+2.08e+00

Pos logit contributions
lake+1.528
dit+1.467
ール+1.457
roller+1.363
storms+1.294
Neg logit contributions
istered-2.308
herty-2.221
earance-2.189
 chimpanzees-2.120
 presumption-2.119
Token Faith
Token ID16463
Feature activation-1.61e+00

Pos logit contributions
istered+1.542
herty+1.478
earance+1.445
 chimpanzees+1.375
 presumption+1.371
Neg logit contributions
lake-1.634
ール-1.599
dit-1.592
roller-1.499
storms-1.458
Token show
Token ID905
Feature activation+1.16e+01

Pos logit contributions
lake+1.240
dit+1.204
ール+1.201
roller+1.138
storms+1.109
Neg logit contributions
istered-1.216
herty-1.153
earance-1.149
 presumption-1.093
 chimpanzees-1.084
Token the
Token ID262
Feature activation+3.46e+00

Pos logit contributions
istered+7.500
herty+7.190
 chimpanzees+7.071
earance+7.051
 comparative+6.754
Neg logit contributions
ール-9.415
lake-9.354
dit-8.994
roller-8.553
storms-8.244
Token lasting
Token ID15727
Feature activation-6.52e-01

Pos logit contributions
istered+2.150
herty+2.044
earance+1.987
 chimpanzees+1.879
eman+1.867
Neg logit contributions
lake-3.127
ール-3.072
dit-3.056
roller-2.903
storms-2.836
Token power
Token ID1176
Feature activation+2.98e+00

Pos logit contributions
lake+0.623
dit+0.609
ール+0.604
roller+0.581
storms+0.571
Neg logit contributions
istered-0.365
herty-0.348
earance-0.333
eman-0.310
phan-0.304
Token of
Token ID286
Feature activation+1.16e+00

Pos logit contributions
istered+2.173
herty+2.080
earance+2.035
 chimpanzees+1.947
 presumption+1.932
Neg logit contributions
lake-2.366
ール-2.321
dit-2.307
roller-2.173
storms-2.114
Token what
Token ID644
Feature activation-4.15e-01

Pos logit contributions
istered+0.735
herty+0.702
earance+0.681
eman+0.640
 presumption+0.636
Neg logit contributions
lake-1.024
dit-1.001
ール-1.000
roller-0.951
storms-0.927
Token life
Token ID1204
Feature activation-1.88e-01

Pos logit contributions
istered+2.059
herty+1.974
earance+1.931
 chimpanzees+1.844
 presumption+1.838
Neg logit contributions
lake-2.119
ール-2.076
dit-2.065
roller-1.941
storms-1.891
Token.
Token ID13
Feature activation+1.67e+00

Pos logit contributions
lake+0.141
ール+0.138
dit+0.138
roller+0.129
storms+0.126
Neg logit contributions
istered-0.145
herty-0.140
earance-0.136
 chimpanzees-0.130
eman-0.130
Token Previous
Token ID21801
Feature activation+2.75e+00

Pos logit contributions
istered+1.153
herty+1.100
earance+1.074
 chimpanzees+1.021
eman+1.015
Neg logit contributions
lake-1.396
ール-1.370
dit-1.362
roller-1.288
storms-1.256
Token studies
Token ID3640
Feature activation+4.55e+00

Pos logit contributions
istered+1.660
herty+1.575
earance+1.530
 chimpanzees+1.442
eman+1.434
Neg logit contributions
lake-2.536
ール-2.492
dit-2.478
roller-2.358
storms-2.305
Token have
Token ID423
Feature activation+1.83e-01

Pos logit contributions
istered+3.114
herty+3.030
earance+2.938
 chimpanzees+2.817
eman+2.812
Neg logit contributions
lake-3.721
ール-3.715
dit-3.648
roller-3.432
storms-3.370
Token shown
Token ID3402
Feature activation+1.16e+01

Pos logit contributions
istered+0.109
herty+0.103
earance+0.101
 chimpanzees+0.095
 presumption+0.094
Neg logit contributions
lake-0.169
ール-0.166
dit-0.165
roller-0.157
storms-0.153
Token that
Token ID326
Feature activation+3.66e+00

Pos logit contributions
istered+5.881
herty+5.712
 chimpanzees+5.678
earance+5.595
 comparative+5.521
Neg logit contributions
lake-10.813
ール-10.732
dit-10.624
roller-10.179
storms-9.733
Token men
Token ID1450
Feature activation+3.68e-01

Pos logit contributions
istered+2.231
herty+2.124
earance+2.068
 chimpanzees+2.006
 presumption+1.980
Neg logit contributions
lake-3.318
ール-3.272
dit-3.241
roller-3.093
storms-3.004
Token with
Token ID351
Feature activation+1.39e+00

Pos logit contributions
istered+0.271
herty+0.260
earance+0.254
 chimpanzees+0.241
eman+0.240
Neg logit contributions
lake-0.289
ール-0.282
dit-0.282
roller-0.265
storms-0.258
Token younger
Token ID7099
Feature activation+1.88e+00

Pos logit contributions
istered+0.964
herty+0.922
earance+0.899
 chimpanzees+0.855
eman+0.851
Neg logit contributions
lake-1.147
ール-1.125
dit-1.119
roller-1.058
storms-1.031
Token wives
Token ID17743
Feature activation+8.02e-01

Pos logit contributions
istered+0.977
herty+0.920
earance+0.889
 chimpanzees+0.830
eman+0.824
Neg logit contributions
lake-1.891
ール-1.861
dit-1.852
roller-1.769
storms-1.733
Tokenock
Token ID735
Feature activation+6.00e-01

Pos logit contributions
istered+0.294
herty+0.282
earance+0.274
 chimpanzees+0.261
eman+0.261
Neg logit contributions
lake-0.343
ール-0.337
dit-0.336
roller-0.316
storms-0.308
Token,
Token ID11
Feature activation-4.88e-02

Pos logit contributions
istered+0.431
herty+0.411
earance+0.402
 chimpanzees+0.382
 presumption+0.380
Neg logit contributions
lake-0.485
ール-0.474
dit-0.471
roller-0.446
storms-0.435
Token Germany
Token ID4486
Feature activation-1.14e+00

Pos logit contributions
lake+0.039
ール+0.038
dit+0.038
roller+0.036
storms+0.035
Neg logit contributions
istered-0.035
herty-0.034
earance-0.033
 chimpanzees-0.031
 presumption-0.031
Token,
Token ID11
Feature activation+5.43e-02

Pos logit contributions
lake+0.933
ール+0.912
dit+0.908
roller+0.856
storms+0.842
Neg logit contributions
istered-0.801
herty-0.753
earance-0.745
 presumption-0.704
 chimpanzees-0.702
Token has
Token ID468
Feature activation-6.45e-01

Pos logit contributions
istered+0.037
herty+0.035
earance+0.035
 chimpanzees+0.033
 presumption+0.033
Neg logit contributions
lake-0.045
ール-0.045
dit-0.044
roller-0.042
storms-0.041
Token shown
Token ID3402
Feature activation+1.16e+01

Pos logit contributions
lake+0.565
ール+0.555
dit+0.554
roller+0.521
storms+0.510
Neg logit contributions
istered-0.416
herty-0.392
earance-0.386
eman-0.360
 presumption-0.360
Token that
Token ID326
Feature activation+3.70e+00

Pos logit contributions
istered+6.077
herty+5.991
 chimpanzees+5.846
earance+5.829
 comparative+5.658
Neg logit contributions
lake-10.538
ール-10.252
dit-10.178
roller-9.789
storms-9.479
Token this
Token ID428
Feature activation+1.58e+00

Pos logit contributions
istered+2.414
herty+2.317
earance+2.256
 chimpanzees+2.184
 presumption+2.169
Neg logit contributions
lake-3.195
ール-3.131
dit-3.112
roller-2.962
storms-2.873
Token is
Token ID318
Feature activation-7.89e-01

Pos logit contributions
istered+1.040
herty+0.992
earance+0.966
 chimpanzees+0.917
 presumption+0.912
Neg logit contributions
lake-1.371
ール-1.347
dit-1.340
roller-1.269
storms-1.239
Token not
Token ID407
Feature activation-2.39e+00

Pos logit contributions
lake+0.629
ール+0.616
dit+0.612
roller+0.580
storms+0.565
Neg logit contributions
istered-0.571
herty-0.541
earance-0.530
 chimpanzees-0.501
eman-0.501
Token the
Token ID262
Feature activation-1.65e+00

Pos logit contributions
lake+1.959
ール+1.931
dit+1.893
roller+1.802
storms+1.765
Neg logit contributions
istered-1.655
herty-1.556
earance-1.520
 chimpanzees-1.413
eman-1.411
Token by
Token ID416
Feature activation+1.42e+00

Pos logit contributions
istered+0.205
herty+0.197
earance+0.193
 chimpanzees+0.184
 presumption+0.184
Neg logit contributions
lake-0.194
ール-0.190
dit-0.189
roller-0.177
storms-0.172
Token teacher
Token ID4701
Feature activation+1.66e+00

Pos logit contributions
istered+0.979
herty+0.935
earance+0.913
 chimpanzees+0.867
eman+0.863
Neg logit contributions
lake-1.186
ール-1.163
dit-1.157
roller-1.094
storms-1.067
Token pensions
Token ID27581
Feature activation+5.55e+00

Pos logit contributions
istered+1.011
herty+0.960
earance+0.932
 chimpanzees+0.880
eman+0.875
Neg logit contributions
lake-1.512
ール-1.486
dit-1.479
roller-1.406
storms-1.374
Token.
Token ID13
Feature activation+1.19e+00

Pos logit contributions
istered+3.940
herty+3.803
earance+3.695
eman+3.556
 chimpanzees+3.549
Neg logit contributions
lake-4.416
ール-4.336
dit-4.292
roller-4.020
storms-3.904
Token It
Token ID632
Feature activation+1.18e+00

Pos logit contributions
istered+0.818
herty+0.782
earance+0.762
 chimpanzees+0.725
eman+0.721
Neg logit contributions
lake-0.992
ール-0.973
dit-0.968
roller-0.915
storms-0.892
Token appears
Token ID3568
Feature activation+1.16e+01

Pos logit contributions
istered+0.832
herty+0.798
earance+0.776
 chimpanzees+0.742
eman+0.738
Neg logit contributions
lake-0.961
ール-0.942
dit-0.938
roller-0.886
storms-0.860
Token that
Token ID326
Feature activation+2.02e+00

Pos logit contributions
istered+6.245
herty+6.102
earance+5.890
 comparative+5.814
 presumption+5.765
Neg logit contributions
ール-10.379
lake-10.375
dit-10.203
roller-9.648
storms-9.270
Token their
Token ID511
Feature activation+5.00e-01

Pos logit contributions
istered+1.370
herty+1.311
earance+1.274
 chimpanzees+1.219
 presumption+1.215
Neg logit contributions
lake-1.702
ール-1.676
dit-1.663
roller-1.573
storms-1.533
Token main
Token ID1388
Feature activation+4.85e-01

Pos logit contributions
istered+0.322
herty+0.308
earance+0.300
 chimpanzees+0.282
eman+0.281
Neg logit contributions
lake-0.438
ール-0.430
dit-0.428
roller-0.406
storms-0.395
Token concern
Token ID2328
Feature activation+8.53e-01

Pos logit contributions
istered+0.343
herty+0.328
earance+0.320
 chimpanzees+0.303
eman+0.302
Neg logit contributions
lake-0.396
ール-0.388
dit-0.386
roller-0.364
storms-0.355
Token is
Token ID318
Feature activation+3.00e+00

Pos logit contributions
istered+0.602
herty+0.576
earance+0.562
 chimpanzees+0.536
 presumption+0.532
Neg logit contributions
lake-0.697
ール-0.684
dit-0.680
roller-0.642
storms-0.625
Token on
Token ID319
Feature activation+2.41e-01

Pos logit contributions
istered+0.191
herty+0.183
earance+0.179
 chimpanzees+0.171
 presumption+0.171
Neg logit contributions
lake-0.190
ール-0.186
dit-0.185
roller-0.174
storms-0.169
Token unexpected
Token ID10059
Feature activation+3.36e+00

Pos logit contributions
istered+0.167
herty+0.160
earance+0.156
 chimpanzees+0.148
eman+0.147
Neg logit contributions
lake-0.199
ール-0.195
dit-0.194
roller-0.184
storms-0.180
Token market
Token ID1910
Feature activation+1.36e+00

Pos logit contributions
istered+2.286
herty+2.200
earance+2.138
 chimpanzees+2.051
 presumption+2.039
Neg logit contributions
lake-2.810
ール-2.762
dit-2.735
roller-2.597
storms-2.509
Token shifts
Token ID15381
Feature activation+5.01e-01

Pos logit contributions
istered+0.889
herty+0.843
earance+0.820
 chimpanzees+0.776
eman+0.771
Neg logit contributions
lake-1.195
ール-1.170
dit-1.168
roller-1.109
storms-1.086
Token never
Token ID1239
Feature activation+5.43e+00

Pos logit contributions
istered+0.368
herty+0.352
earance+0.344
 chimpanzees+0.329
 presumption+0.327
Neg logit contributions
lake-0.395
ール-0.387
dit-0.385
roller-0.363
storms-0.354
Token seems
Token ID2331
Feature activation+1.15e+01

Pos logit contributions
istered+3.765
herty+3.614
earance+3.542
 chimpanzees+3.386
 presumption+3.385
Neg logit contributions
lake-4.474
ール-4.354
dit-4.258
roller-4.118
storms-3.960
Token to
Token ID284
Feature activation+4.71e+00

Pos logit contributions
istered+6.541
earance+6.276
herty+6.223
 comparative+6.112
eman+6.110
Neg logit contributions
lake-10.109
ール-9.912
dit-9.812
roller-9.377
storms-9.073
Token damp
Token ID21151
Feature activation-9.01e-01

Pos logit contributions
istered+3.452
herty+3.321
earance+3.234
 presumption+3.119
 chimpanzees+3.116
Neg logit contributions
lake-3.680
ール-3.605
dit-3.530
roller-3.354
storms-3.274
Tokenen
Token ID268
Feature activation-6.17e-01

Pos logit contributions
lake+0.598
ール+0.584
dit+0.580
roller+0.541
storms+0.523
Neg logit contributions
istered-0.773
herty-0.746
earance-0.731
 chimpanzees-0.704
 presumption-0.698
Token their
Token ID511
Feature activation-4.38e-01

Pos logit contributions
lake+0.505
ール+0.493
dit+0.492
roller+0.466
storms+0.455
Neg logit contributions
istered-0.434
herty-0.416
earance-0.405
 chimpanzees-0.383
eman-0.382
Token determination
Token ID12123
Feature activation-5.53e-01

Pos logit contributions
lake+0.361
ール+0.354
dit+0.353
roller+0.334
storms+0.327
Neg logit contributions
istered-0.303
herty-0.291
earance-0.283
eman-0.267
 chimpanzees-0.267
Tokenacts
Token ID8656
Feature activation+1.46e-01

Pos logit contributions
istered+0.317
herty+0.304
earance+0.297
 chimpanzees+0.283
eman+0.282
Neg logit contributions
lake-0.338
ール-0.332
dit-0.329
roller-0.310
storms-0.302
Token could
Token ID714
Feature activation-5.87e-01

Pos logit contributions
istered+0.111
herty+0.106
earance+0.104
 chimpanzees+0.099
 presumption+0.099
Neg logit contributions
lake-0.112
ール-0.110
dit-0.109
roller-0.102
storms-0.100
Token not
Token ID407
Feature activation-1.98e+00

Pos logit contributions
lake+0.436
dit+0.425
ール+0.423
roller+0.399
storms+0.389
Neg logit contributions
istered-0.455
herty-0.438
earance-0.431
 chimpanzees-0.410
eman-0.408
Token change
Token ID1487
Feature activation+2.52e+00

Pos logit contributions
lake+1.415
dit+1.386
ール+1.368
roller+1.297
storms+1.258
Neg logit contributions
istered-1.576
herty-1.527
earance-1.489
 chimpanzees-1.417
eman-1.415
Token the
Token ID262
Feature activation-1.52e+00

Pos logit contributions
istered+1.736
herty+1.663
earance+1.619
 chimpanzees+1.548
 presumption+1.540
Neg logit contributions
lake-2.097
ール-2.062
dit-2.045
roller-1.934
storms-1.882
Token minds
Token ID9017
Feature activation-1.36e+01

Pos logit contributions
lake+1.246
dit+1.215
ール+1.208
roller+1.153
storms+1.120
Neg logit contributions
istered-1.066
herty-1.016
earance-0.991
eman-0.931
 chimpanzees-0.929
Token of
Token ID286
Feature activation-4.51e+00

Pos logit contributions
lake+8.041
dit+7.775
ール+7.749
roller+7.611
storms+7.603
Neg logit contributions
istered-10.860
herty-10.454
earance-10.002
 presumption-9.770
phan-9.741
Token Trump
Token ID1301
Feature activation+8.71e-01

Pos logit contributions
lake+3.416
dit+3.363
ール+3.296
roller+3.145
storms+3.068
Neg logit contributions
istered-3.389
herty-3.227
earance-3.193
eman-3.005
 presumption-2.940
Token supporters
Token ID5941
Feature activation-9.66e-01

Pos logit contributions
istered+0.700
herty+0.673
earance+0.659
 chimpanzees+0.632
eman+0.629
Neg logit contributions
lake-0.627
ール-0.613
dit-0.609
roller-0.571
storms-0.554
Token.
Token ID13
Feature activation+1.45e+00

Pos logit contributions
lake+0.728
ール+0.711
dit+0.709
roller+0.668
storms+0.650
Neg logit contributions
istered-0.742
herty-0.713
earance-0.698
 chimpanzees-0.666
 presumption-0.662
Token The
Token ID383
Feature activation+7.11e-01

Pos logit contributions
istered+1.014
herty+0.971
earance+0.946
 chimpanzees+0.901
eman+0.898
Neg logit contributions
lake-1.193
ール-1.170
dit-1.164
roller-1.100
storms-1.071
Token with
Token ID351
Feature activation-1.21e+00

Pos logit contributions
lake+1.414
ール+1.375
dit+1.371
roller+1.297
storms+1.265
Neg logit contributions
istered-1.359
herty-1.294
earance-1.261
 chimpanzees-1.193
eman-1.193
Token traces
Token ID20675
Feature activation+1.04e+00

Pos logit contributions
lake+0.986
ール+0.965
dit+0.962
roller+0.908
storms+0.886
Neg logit contributions
istered-0.850
herty-0.812
earance-0.793
 chimpanzees-0.751
eman-0.750
Token of
Token ID286
Feature activation-6.27e-01

Pos logit contributions
istered+0.737
herty+0.702
earance+0.688
 chimpanzees+0.660
eman+0.655
Neg logit contributions
lake-0.841
ール-0.826
dit-0.821
roller-0.776
storms-0.754
Token the
Token ID262
Feature activation-1.63e+00

Pos logit contributions
lake+0.526
ール+0.516
dit+0.514
roller+0.486
storms+0.474
Neg logit contributions
istered-0.428
herty-0.409
earance-0.399
 chimpanzees-0.379
eman-0.377
Token a
Token ID257
Feature activation-2.59e+00

Pos logit contributions
lake+1.292
ール+1.265
dit+1.262
roller+1.186
storms+1.154
Neg logit contributions
istered-1.186
herty-1.136
earance-1.110
eman-1.050
 chimpanzees-1.049
Token Cyr
Token ID40399
Feature activation-1.25e+01

Pos logit contributions
lake+2.072
ール+2.038
dit+2.030
roller+1.920
storms+1.836
Neg logit contributions
istered-1.857
herty-1.767
earance-1.740
 chimpanzees-1.657
eman-1.630
Tokenill
Token ID359
Feature activation+1.22e+00

Pos logit contributions
lake+9.475
dit+9.287
ール+9.183
roller+8.921
starter+8.816
Neg logit contributions
istered-8.535
earance-8.167
herty-7.796
 chimpanzees-7.424
 presumption-7.285
Tokenic
Token ID291
Feature activation-3.80e+00

Pos logit contributions
istered+0.734
herty+0.699
earance+0.679
 chimpanzees+0.641
 presumption+0.637
Neg logit contributions
lake-1.123
ール-1.109
dit-1.102
roller-1.049
storms-1.021
Token found
Token ID1043
Feature activation+8.04e-01

Pos logit contributions
lake+3.046
dit+2.974
ール+2.971
roller+2.820
storms+2.696
Neg logit contributions
istered-2.692
herty-2.587
earance-2.527
 chimpanzees-2.359
eman-2.357
Token in
Token ID287
Feature activation+5.99e-01

Pos logit contributions
istered+0.551
herty+0.527
earance+0.513
 chimpanzees+0.490
eman+0.488
Neg logit contributions
lake-0.671
ール-0.659
dit-0.656
roller-0.620
storms-0.603
Token their
Token ID511
Feature activation+4.62e-01

Pos logit contributions
istered+0.412
herty+0.394
earance+0.384
 chimpanzees+0.369
 presumption+0.365
Neg logit contributions
lake-0.499
ール-0.490
dit-0.485
roller-0.459
storms-0.447
Token.
Token ID13
Feature activation-3.27e-01

Pos logit contributions
lake+1.379
dit+1.350
ール+1.342
roller+1.275
storms+1.244
Neg logit contributions
istered-1.357
herty-1.303
earance-1.265
 chimpanzees-1.208
 presumption-1.191
Token It
Token ID632
Feature activation-9.74e-02

Pos logit contributions
lake+0.259
ール+0.254
dit+0.252
roller+0.237
storms+0.231
Neg logit contributions
istered-0.241
herty-0.229
earance-0.226
 chimpanzees-0.215
 presumption-0.213
Token could
Token ID714
Feature activation-2.77e+00

Pos logit contributions
lake+0.068
ール+0.066
dit+0.066
roller+0.061
storms+0.060
Neg logit contributions
istered-0.081
herty-0.078
earance-0.076
 chimpanzees-0.073
 presumption-0.073
Token be
Token ID307
Feature activation-3.70e+00

Pos logit contributions
lake+1.861
ール+1.803
dit+1.797
roller+1.694
storms+1.639
Neg logit contributions
istered-2.326
herty-2.238
earance-2.208
 chimpanzees-2.112
eman-2.106
Token a
Token ID257
Feature activation-3.66e+00

Pos logit contributions
lake+2.795
dit+2.726
ール+2.691
roller+2.568
storms+2.528
Neg logit contributions
istered-2.768
herty-2.659
earance-2.585
eman-2.479
ocyte-2.414
Token tweet
Token ID6126
Feature activation-1.22e+01

Pos logit contributions
lake+3.000
dit+2.906
ール+2.899
roller+2.785
storms+2.672
Neg logit contributions
istered-2.505
herty-2.398
earance-2.339
eman-2.234
 chimpanzees-2.200
Token you
Token ID345
Feature activation-1.93e-01

Pos logit contributions
lake+8.097
dit+8.063
storms+7.820
ール+7.677
roller+7.615
Neg logit contributions
istered-9.223
herty-8.931
earance-8.635
 chimpanzees-8.140
ieties-8.049
Token sent
Token ID1908
Feature activation-3.88e+00

Pos logit contributions
lake+0.148
ール+0.144
dit+0.144
roller+0.135
storms+0.131
Neg logit contributions
istered-0.147
herty-0.141
earance-0.138
 chimpanzees-0.132
eman-0.131
Token that
Token ID326
Feature activation-2.24e+00

Pos logit contributions
lake+2.970
dit+2.896
ール+2.878
roller+2.721
storms+2.689
Neg logit contributions
istered-2.917
herty-2.803
earance-2.736
eman-2.566
 chimpanzees-2.553
Token insulted
Token ID40102
Feature activation-5.00e+00

Pos logit contributions
lake+1.766
dit+1.719
ール+1.712
roller+1.615
storms+1.600
Neg logit contributions
istered-1.638
herty-1.560
earance-1.542
eman-1.454
 chimpanzees-1.441
Token a
Token ID257
Feature activation-1.32e+00

Pos logit contributions
lake+3.796
dit+3.664
ール+3.577
roller+3.467
storms+3.378
Neg logit contributions
istered-3.691
herty-3.561
earance-3.535
eman-3.301
 presumption-3.217
TokenOV
Token ID8874
Feature activation+3.10e+00

Pos logit contributions
lake+1.668
ール+1.612
dit+1.609
roller+1.514
storms+1.460
Neg logit contributions
istered-1.879
herty-1.808
earance-1.769
 chimpanzees-1.702
 presumption-1.691
Token and
Token ID290
Feature activation-6.30e-01

Pos logit contributions
istered+2.268
herty+2.178
earance+2.128
 chimpanzees+2.036
 presumption+2.034
Neg logit contributions
lake-2.409
ール-2.390
dit-2.355
roller-2.225
storms-2.162
Token the
Token ID262
Feature activation-8.60e-01

Pos logit contributions
lake+0.506
ール+0.495
dit+0.493
roller+0.465
storms+0.453
Neg logit contributions
istered-0.454
herty-0.434
earance-0.425
 chimpanzees-0.403
eman-0.402
Token n
Token ID299
Feature activation-1.15e+00

Pos logit contributions
lake+0.716
ール+0.699
dit+0.697
roller+0.659
storms+0.642
Neg logit contributions
istered-0.595
herty-0.569
earance-0.555
 chimpanzees-0.525
eman-0.525
Tokenv
Token ID85
Feature activation-5.34e-01

Pos logit contributions
lake+0.861
dit+0.837
ール+0.835
roller+0.785
storms+0.762
Neg logit contributions
istered-0.901
herty-0.868
earance-0.846
 chimpanzees-0.814
 presumption-0.810
Tokenme
Token ID1326
Feature activation-1.20e+01

Pos logit contributions
lake+0.391
ール+0.382
dit+0.380
roller+0.357
storms+0.346
Neg logit contributions
istered-0.422
herty-0.406
earance-0.397
 chimpanzees-0.380
 presumption-0.378
Token storage
Token ID6143
Feature activation+2.56e+00

Pos logit contributions
lake+9.128
dit+9.010
ール+8.532
roller+8.271
GO+7.863
Neg logit contributions
istered-7.961
herty-7.863
earance-7.424
 chimpanzees-7.400
 presumption-7.251
Token driver
Token ID4639
Feature activation-8.80e-01

Pos logit contributions
istered+1.790
herty+1.705
earance+1.668
 chimpanzees+1.598
 presumption+1.591
Neg logit contributions
lake-2.079
ール-2.064
dit-2.036
roller-1.918
storms-1.880
Token.
Token ID13
Feature activation+1.63e+00

Pos logit contributions
lake+0.664
ール+0.646
dit+0.644
roller+0.608
storms+0.590
Neg logit contributions
istered-0.678
herty-0.651
earance-0.636
 chimpanzees-0.607
eman-0.604
Token Amer
Token ID33391
Feature activation-3.37e-01

Pos logit contributions
istered+1.092
herty+1.045
earance+1.013
 chimpanzees+0.966
eman+0.963
Neg logit contributions
lake-1.384
ール-1.363
dit-1.355
roller-1.282
storms-1.251
Token has
Token ID468
Feature activation-3.54e+00

Pos logit contributions
lake+0.265
ール+0.259
dit+0.258
roller+0.243
storms+0.237
Neg logit contributions
istered-0.248
herty-0.238
earance-0.232
 chimpanzees-0.222
eman-0.221
Token come
Token ID1282
Feature activation+8.91e-01

Pos logit contributions
lake+1.097
ール+1.074
dit+1.068
roller+1.010
storms+0.985
Neg logit contributions
istered-1.101
herty-1.056
earance-1.038
 chimpanzees-0.989
 presumption-0.986
Token and
Token ID290
Feature activation+2.20e+00

Pos logit contributions
istered+0.654
herty+0.626
earance+0.612
 chimpanzees+0.585
eman+0.582
Neg logit contributions
lake-0.703
ール-0.689
dit-0.686
roller-0.646
storms-0.627
Token go
Token ID467
Feature activation-1.28e+00

Pos logit contributions
istered+1.749
herty+1.682
earance+1.644
 chimpanzees+1.580
 presumption+1.573
Neg logit contributions
lake-1.603
ール-1.565
dit-1.557
roller-1.456
storms-1.412
Token on
Token ID319
Feature activation+1.50e+00

Pos logit contributions
lake+0.923
ール+0.908
dit+0.897
roller+0.842
storms+0.830
Neg logit contributions
istered-1.015
herty-0.970
earance-0.955
 chimpanzees-0.911
 presumption-0.906
Token their
Token ID511
Feature activation+2.53e-01

Pos logit contributions
istered+1.077
herty+1.032
earance+1.008
 chimpanzees+0.962
 presumption+0.957
Neg logit contributions
lake-1.203
ール-1.180
dit-1.173
roller-1.106
storms-1.077
Token minds
Token ID9017
Feature activation-1.18e+01

Pos logit contributions
istered+0.155
herty+0.148
earance+0.143
 chimpanzees+0.135
eman+0.134
Neg logit contributions
lake-0.230
ール-0.227
dit-0.225
roller-0.215
storms-0.210
Token all
Token ID477
Feature activation+2.33e+00

Pos logit contributions
lake+7.219
ール+7.086
dit+6.879
storms+6.830
roller+6.677
Neg logit contributions
istered-9.264
earance-8.800
herty-8.776
ideon-8.503
 chimpanzees-8.448
Token the
Token ID262
Feature activation-1.67e-01

Pos logit contributions
istered+1.468
herty+1.398
earance+1.360
 chimpanzees+1.285
eman+1.279
Neg logit contributions
lake-2.078
ール-2.042
dit-2.031
roller-1.929
storms-1.885
Token time
Token ID640
Feature activation+1.08e+00

Pos logit contributions
lake+0.134
ール+0.131
dit+0.130
roller+0.123
storms+0.121
Neg logit contributions
istered-0.121
herty-0.116
earance-0.113
eman-0.107
 chimpanzees-0.107
Token:
Token ID25
Feature activation-6.34e-01

Pos logit contributions
istered+0.831
herty+0.798
earance+0.780
 chimpanzees+0.746
eman+0.742
Neg logit contributions
lake-0.820
ール-0.803
dit-0.798
roller-0.750
storms-0.729
Token
Token ID564
Feature activation-9.16e-01

Pos logit contributions
lake+0.510
ール+0.499
dit+0.496
roller+0.472
storms+0.460
Neg logit contributions
istered-0.456
herty-0.433
earance-0.426
eman-0.401
 chimpanzees-0.400
Token tested
Token ID6789
Feature activation+4.46e+00

Pos logit contributions
lake+2.604
dit+2.528
ール+2.521
roller+2.348
storms+2.294
Neg logit contributions
istered-2.753
herty-2.634
earance-2.601
eman-2.463
 chimpanzees-2.459
Token and
Token ID290
Feature activation+8.01e-01

Pos logit contributions
istered+2.974
herty+2.835
earance+2.738
 chimpanzees+2.668
 presumption+2.651
Neg logit contributions
ール-3.760
lake-3.723
dit-3.678
roller-3.488
storms-3.378
Token deployed
Token ID12380
Feature activation-5.59e-01

Pos logit contributions
istered+0.553
herty+0.530
earance+0.515
 chimpanzees+0.493
eman+0.490
Neg logit contributions
lake-0.666
ール-0.655
dit-0.649
roller-0.615
storms-0.599
Token this
Token ID428
Feature activation-4.97e-02

Pos logit contributions
lake+0.455
ール+0.441
dit+0.441
roller+0.417
storms+0.406
Neg logit contributions
istered-0.397
herty-0.381
earance-0.372
 chimpanzees-0.352
eman-0.352
Token as
Token ID355
Feature activation-3.58e+00

Pos logit contributions
lake+0.041
ール+0.040
dit+0.040
roller+0.037
storms+0.036
Neg logit contributions
istered-0.035
herty-0.034
earance-0.033
 chimpanzees-0.031
eman-0.031
Token well
Token ID880
Feature activation-1.15e+01

Pos logit contributions
lake+2.832
dit+2.715
ール+2.707
roller+2.578
storms+2.499
Neg logit contributions
istered-2.583
herty-2.504
earance-2.458
 chimpanzees-2.313
 presumption-2.300
Token,
Token ID11
Feature activation-1.91e+00

Pos logit contributions
lake+7.003
dit+6.641
ール+6.551
roller+6.247
storms+6.190
Neg logit contributions
istered-9.235
earance-8.959
herty-8.844
 chimpanzees-8.449
 presumption-8.403
Token and
Token ID290
Feature activation-1.52e+00

Pos logit contributions
lake+1.457
ール+1.411
dit+1.411
roller+1.329
storms+1.297
Neg logit contributions
istered-1.451
herty-1.389
earance-1.367
 chimpanzees-1.293
eman-1.288
Token shared
Token ID4888
Feature activation-3.78e+00

Pos logit contributions
lake+1.206
ール+1.175
dit+1.171
roller+1.104
storms+1.076
Neg logit contributions
istered-1.116
herty-1.066
earance-1.046
 chimpanzees-0.992
eman-0.989
Token some
Token ID617
Feature activation-1.92e+00

Pos logit contributions
lake+2.781
ール+2.661
dit+2.661
roller+2.515
storms+2.457
Neg logit contributions
istered-2.936
herty-2.809
earance-2.753
eman-2.596
 chimpanzees-2.595
Token results
Token ID2482
Feature activation+1.71e+00

Pos logit contributions
lake+1.559
dit+1.507
ール+1.506
roller+1.433
storms+1.396
Neg logit contributions
istered-1.362
herty-1.301
earance-1.280
eman-1.201
 chimpanzees-1.198
Token deliver
Token ID5203
Feature activation-4.97e+00

Pos logit contributions
lake+2.388
ール+2.322
dit+2.299
roller+2.207
storms+2.116
Neg logit contributions
istered-2.082
herty-2.001
earance-1.958
eman-1.843
 chimpanzees-1.842
Token on
Token ID319
Feature activation+6.12e-01

Pos logit contributions
lake+3.693
ール+3.578
dit+3.553
roller+3.375
storms+3.258
Neg logit contributions
istered-3.804
herty-3.672
earance-3.564
 presumption-3.371
eman-3.354
Token other
Token ID584
Feature activation-4.40e-01

Pos logit contributions
istered+0.427
herty+0.408
earance+0.399
 chimpanzees+0.380
eman+0.378
Neg logit contributions
lake-0.504
ール-0.495
dit-0.492
roller-0.465
storms-0.453
Token maps
Token ID8739
Feature activation-5.03e+00

Pos logit contributions
lake+0.355
ール+0.347
dit+0.345
roller+0.327
storms+0.318
Neg logit contributions
istered-0.315
herty-0.301
earance-0.295
 chimpanzees-0.280
eman-0.279
Token as
Token ID355
Feature activation-3.72e+00

Pos logit contributions
lake+3.586
ール+3.493
dit+3.436
roller+3.292
storms+3.194
Neg logit contributions
istered-3.992
herty-3.855
earance-3.712
 presumption-3.590
 chimpanzees-3.588
Token well
Token ID880
Feature activation-1.14e+01

Pos logit contributions
lake+3.024
ール+2.954
dit+2.910
roller+2.780
storms+2.695
Neg logit contributions
istered-2.604
herty-2.525
earance-2.446
eman-2.306
 presumption-2.304
Token.
Token ID13
Feature activation-1.75e+00

Pos logit contributions
lake+6.711
ール+6.672
dit+6.358
roller+6.138
storms+5.964
Neg logit contributions
istered-9.508
herty-9.032
earance-8.925
 chimpanzees-8.643
 presumption-8.598
Token
Token ID198
Feature activation-4.91e-01

Pos logit contributions
lake+1.448
ール+1.420
dit+1.408
roller+1.334
storms+1.291
Neg logit contributions
istered-1.223
herty-1.162
earance-1.146
 chimpanzees-1.084
 presumption-1.074
Token
Token ID198
Feature activation-7.27e-01

Pos logit contributions
lake+0.432
ール+0.424
dit+0.422
roller+0.401
storms+0.391
Neg logit contributions
istered-0.315
herty-0.300
earance-0.293
 chimpanzees-0.277
 presumption-0.275
TokenKey
Token ID9218
Feature activation-1.60e+00

Pos logit contributions
lake+0.591
ール+0.577
dit+0.574
roller+0.546
storms+0.527
Neg logit contributions
istered-0.518
herty-0.498
earance-0.487
 chimpanzees-0.466
 presumption-0.463
Tokend
Token ID67
Feature activation+1.13e+00

Pos logit contributions
lake+1.208
ール+1.177
dit+1.177
roller+1.102
storms+1.071
Neg logit contributions
istered-1.234
herty-1.190
earance-1.161
 chimpanzees-1.112
 presumption-1.105
Token people
Token ID661
Feature activation-3.79e+00

Pos logit contributions
istered+1.518
herty+1.454
earance+1.416
 chimpanzees+1.356
 presumption+1.350
Neg logit contributions
lake-1.667
ール-1.637
dit-1.626
roller-1.532
storms-1.491
Token make
Token ID787
Feature activation-5.26e+00

Pos logit contributions
lake+2.903
dit+2.817
ール+2.802
roller+2.663
storms+2.592
Neg logit contributions
istered-2.842
herty-2.727
earance-2.678
eman-2.530
 chimpanzees-2.524
Token up
Token ID510
Feature activation-2.67e+00

Pos logit contributions
lake+3.864
dit+3.806
ール+3.726
roller+3.538
storms+3.499
Neg logit contributions
istered-4.018
herty-3.843
earance-3.739
eman-3.563
ocyte-3.555
Token their
Token ID511
Feature activation-1.26e+00

Pos logit contributions
lake+2.045
dit+1.990
ール+1.990
roller+1.866
storms+1.834
Neg logit contributions
istered-2.023
herty-1.928
earance-1.880
 chimpanzees-1.792
eman-1.786
Token own
Token ID898
Feature activation-4.64e+00

Pos logit contributions
lake+1.049
ール+1.025
dit+1.022
roller+0.968
storms+0.948
Neg logit contributions
istered-0.869
herty-0.832
earance-0.808
 chimpanzees-0.767
eman-0.761
Token minds
Token ID9017
Feature activation-1.13e+01

Pos logit contributions
lake+2.943
dit+2.817
ール+2.803
roller+2.602
storms+2.570
Neg logit contributions
istered-4.053
herty-3.880
earance-3.818
eman-3.626
ocyte-3.614
Token.
Token ID13
Feature activation+1.41e-02

Pos logit contributions
lake+6.718
dit+6.632
ール+6.591
storms+6.309
roller+6.032
Neg logit contributions
istered-9.184
earance-8.695
herty-8.695
ocyte-8.305
 cumbers-8.215
Token
Token ID198
Feature activation+8.24e-01

Pos logit contributions
istered+0.010
herty+0.009
earance+0.009
 chimpanzees+0.009
 presumption+0.009
Neg logit contributions
lake-0.012
ール-0.011
dit-0.011
roller-0.011
storms-0.010
Token
Token ID198
Feature activation+4.76e-01

Pos logit contributions
istered+0.505
herty+0.482
earance+0.465
eman+0.442
 chimpanzees+0.440
Neg logit contributions
lake-0.745
ール-0.735
dit-0.730
roller-0.693
storms-0.678
Token5
Token ID20
Feature activation+7.06e-01

Pos logit contributions
istered+0.340
herty+0.325
earance+0.318
 chimpanzees+0.303
 presumption+0.301
Neg logit contributions
lake-0.385
ール-0.377
dit-0.375
roller-0.354
storms-0.345
Token.
Token ID13
Feature activation+7.40e-01

Pos logit contributions
istered+0.532
herty+0.514
earance+0.497
eman+0.478
 chimpanzees+0.477
Neg logit contributions
lake-0.539
ール-0.529
dit-0.527
roller-0.495
storms-0.481
Tokenworked
Token ID32931
Feature activation+1.82e+00

Pos logit contributions
lake+0.331
dit+0.320
ール+0.320
roller+0.300
storms+0.289
Neg logit contributions
istered-0.390
herty-0.376
earance-0.369
 chimpanzees-0.356
 presumption-0.353
Token the
Token ID262
Feature activation-3.47e+00

Pos logit contributions
istered+1.263
herty+1.213
earance+1.181
 chimpanzees+1.126
eman+1.122
Neg logit contributions
lake-1.497
ール-1.469
dit-1.460
roller-1.380
storms-1.346
Token film
Token ID2646
Feature activation+4.89e-01

Pos logit contributions
lake+2.914
ール+2.846
dit+2.839
roller+2.694
storms+2.602
Neg logit contributions
istered-2.362
herty-2.226
earance-2.169
eman-2.019
 chimpanzees-2.015
Token into
Token ID656
Feature activation-1.24e+00

Pos logit contributions
istered+0.363
herty+0.349
earance+0.340
 chimpanzees+0.325
eman+0.324
Neg logit contributions
lake-0.381
ール-0.374
dit-0.372
roller-0.350
storms-0.340
Token the
Token ID262
Feature activation-3.07e+00

Pos logit contributions
lake+0.951
ール+0.927
dit+0.923
roller+0.870
storms+0.844
Neg logit contributions
istered-0.939
herty-0.896
earance-0.878
 chimpanzees-0.837
 presumption-0.833
Token meditation
Token ID16901
Feature activation-1.13e+01

Pos logit contributions
lake+2.614
ール+2.543
dit+2.528
roller+2.413
storms+2.323
Neg logit contributions
istered-2.062
herty-1.949
earance-1.904
eman-1.789
 chimpanzees-1.785
Token on
Token ID319
Feature activation+1.85e-03

Pos logit contributions
lake+8.218
dit+7.781
ール+7.570
roller+7.540
storms+7.089
Neg logit contributions
herty-7.897
istered-7.864
earance-7.724
 presumption-7.239
ideon-7.198
Token relationships
Token ID6958
Feature activation+3.20e+00

Pos logit contributions
istered+0.001
herty+0.001
earance+0.001
eman+0.001
 chimpanzees+0.001
Neg logit contributions
lake-0.002
ール-0.002
dit-0.002
roller-0.002
storms-0.001
Token and
Token ID290
Feature activation-8.55e-02

Pos logit contributions
istered+2.298
herty+2.202
earance+2.159
 chimpanzees+2.061
eman+2.048
Neg logit contributions
lake-2.557
ール-2.511
dit-2.491
roller-2.355
storms-2.280
Token life
Token ID1204
Feature activation-1.51e+00

Pos logit contributions
lake+0.076
dit+0.074
ール+0.074
roller+0.070
storms+0.069
Neg logit contributions
istered-0.054
herty-0.052
earance-0.050
eman-0.047
 chimpanzees-0.047
Token that
Token ID326
Feature activation+1.57e-01

Pos logit contributions
lake+1.162
dit+1.138
ール+1.136
roller+1.067
storms+1.056
Neg logit contributions
istered-1.131
herty-1.094
earance-1.054
eman-1.007
 chimpanzees-1.005
Token will
Token ID481
Feature activation-5.07e+00

Pos logit contributions
lake+0.290
ール+0.283
dit+0.282
roller+0.265
storms+0.259
Neg logit contributions
istered-0.294
herty-0.282
earance-0.276
 chimpanzees-0.263
 presumption-0.262
Token drop
Token ID4268
Feature activation-1.63e+00

Pos logit contributions
lake+3.699
dit+3.530
ール+3.518
roller+3.397
storms+3.235
Neg logit contributions
istered-3.909
herty-3.733
earance-3.620
eman-3.473
ilial-3.406
Token AMC
Token ID36239
Feature activation+1.06e-01

Pos logit contributions
lake+1.288
ール+1.265
dit+1.256
roller+1.185
storms+1.161
Neg logit contributions
istered-1.188
herty-1.134
earance-1.099
eman-1.055
 chimpanzees-1.046
Token,
Token ID11
Feature activation-3.68e+00

Pos logit contributions
istered+0.082
herty+0.078
earance+0.077
 chimpanzees+0.073
eman+0.073
Neg logit contributions
lake-0.080
ール-0.078
dit-0.078
roller-0.073
storms-0.072
Token as
Token ID355
Feature activation-4.93e+00

Pos logit contributions
lake+2.782
dit+2.738
ール+2.712
roller+2.592
storms+2.509
Neg logit contributions
istered-2.766
herty-2.635
earance-2.577
eman-2.450
 chimpanzees-2.417
Token well
Token ID880
Feature activation-1.13e+01

Pos logit contributions
lake+3.802
dit+3.720
ール+3.715
roller+3.500
storms+3.419
Neg logit contributions
istered-3.598
herty-3.440
earance-3.352
eman-3.207
 chimpanzees-3.187
Token as
Token ID355
Feature activation-6.37e+00

Pos logit contributions
lake+6.843
ール+6.562
dit+6.538
roller+6.305
storms+6.005
Neg logit contributions
istered-9.253
herty-8.773
earance-8.716
eman-8.642
 chimpanzees-8.396
Token the
Token ID262
Feature activation-4.33e+00

Pos logit contributions
lake+4.671
dit+4.608
ール+4.568
roller+4.365
storms+4.259
Neg logit contributions
istered-4.701
herty-4.500
earance-4.409
eman-4.226
 presumption-4.113
Token AMC
Token ID36239
Feature activation+7.65e-01

Pos logit contributions
lake+3.476
dit+3.460
ール+3.411
roller+3.259
storms+3.169
Neg logit contributions
istered-2.952
herty-2.849
earance-2.788
eman-2.653
 chimpanzees-2.568
Token-
Token ID12
Feature activation-5.42e+00

Pos logit contributions
istered+0.539
herty+0.515
earance+0.504
eman+0.477
 chimpanzees+0.477
Neg logit contributions
lake-0.627
dit-0.614
ール-0.613
roller-0.578
storms-0.564
Tokenowned
Token ID11990
Feature activation-3.10e+00

Pos logit contributions
lake+3.757
dit+3.688
ール+3.602
roller+3.459
storms+3.349
Neg logit contributions
istered-4.353
herty-4.247
earance-4.131
 chimpanzees-4.025
 presumption-4.007
Token.
Token ID13
Feature activation+1.12e+00

Pos logit contributions
lake+4.660
ール+4.604
dit+4.526
roller+4.273
storms+4.268
Neg logit contributions
istered-5.340
earance-5.165
herty-5.108
 presumption-4.899
 chimpanzees-4.872
Token
Token ID198
Feature activation-4.00e-01

Pos logit contributions
istered+0.722
herty+0.687
earance+0.669
 chimpanzees+0.634
eman+0.630
Neg logit contributions
lake-0.985
ール-0.967
dit-0.962
roller-0.912
storms-0.891
Token
Token ID198
Feature activation-8.58e-01

Pos logit contributions
lake+0.355
ール+0.349
dit+0.347
roller+0.329
storms+0.322
Neg logit contributions
istered-0.253
herty-0.241
earance-0.234
 chimpanzees-0.222
eman-0.221
TokenIn
Token ID818
Feature activation-1.63e+00

Pos logit contributions
lake+0.710
ール+0.695
dit+0.692
roller+0.657
storms+0.637
Neg logit contributions
istered-0.596
herty-0.570
earance-0.562
 chimpanzees-0.539
 presumption-0.533
Token a
Token ID257
Feature activation+9.12e-02

Pos logit contributions
lake+1.307
ール+1.286
dit+1.274
roller+1.203
storms+1.175
Neg logit contributions
istered-1.175
herty-1.120
earance-1.101
 chimpanzees-1.047
 presumption-1.038
Token tweet
Token ID6126
Feature activation-1.13e+01

Pos logit contributions
istered+0.063
herty+0.060
earance+0.059
 chimpanzees+0.056
eman+0.056
Neg logit contributions
lake-0.076
ール-0.074
dit-0.073
roller-0.070
storms-0.068
Token to
Token ID284
Feature activation-3.27e+00

Pos logit contributions
lake+7.531
dit+7.231
ール+7.191
storms+7.057
roller+6.899
Neg logit contributions
istered-8.682
herty-8.307
earance-8.188
 chimpanzees-7.912
phan-7.608
Token his
Token ID465
Feature activation-2.50e+00

Pos logit contributions
lake+2.601
dit+2.543
ール+2.540
roller+2.401
storms+2.333
Neg logit contributions
istered-2.363
herty-2.246
earance-2.219
 chimpanzees-2.112
eman-2.096
Token 1
Token ID352
Feature activation+1.70e+00

Pos logit contributions
lake+1.869
dit+1.831
ール+1.824
roller+1.709
storms+1.663
Neg logit contributions
istered-1.923
herty-1.843
earance-1.814
 chimpanzees-1.725
eman-1.720
Token.
Token ID13
Feature activation+2.48e+00

Pos logit contributions
istered+1.288
herty+1.238
earance+1.207
 chimpanzees+1.156
eman+1.152
Neg logit contributions
lake-1.298
ール-1.273
dit-1.265
roller-1.191
storms-1.159
Token6
Token ID21
Feature activation+4.56e+00

Pos logit contributions
istered+1.716
herty+1.648
earance+1.596
eman+1.529
 chimpanzees+1.513
Neg logit contributions
lake-2.037
ール-1.999
dit-1.983
roller-1.883
storms-1.838
Token ren
Token ID8851
Feature activation-2.85e+00

Pos logit contributions
lake+2.421
dit+2.360
ール+2.335
roller+2.220
storms+2.143
Neg logit contributions
istered-2.310
herty-2.199
earance-2.150
eman-2.050
 chimpanzees-2.027
Tokenounce
Token ID8652
Feature activation-3.31e+00

Pos logit contributions
lake+1.076
dit+1.026
ール+1.004
roller+0.886
storms+0.820
Neg logit contributions
istered-3.266
herty-3.184
earance-3.137
 chimpanzees-3.096
 presumption-3.065
Token them
Token ID606
Feature activation-4.42e+00

Pos logit contributions
lake+2.553
ール+2.486
dit+2.465
roller+2.327
storms+2.272
Neg logit contributions
istered-2.478
herty-2.373
earance-2.310
eman-2.195
 presumption-2.178
Token immediately
Token ID3393
Feature activation-3.57e+00

Pos logit contributions
lake+3.318
ール+3.257
dit+3.231
roller+3.030
storms+2.985
Neg logit contributions
istered-3.373
herty-3.215
earance-3.136
eman-2.972
 chimpanzees-2.972
Token as
Token ID355
Feature activation-3.16e+00

Pos logit contributions
lake+2.565
ール+2.518
dit+2.503
roller+2.335
storms+2.304
Neg logit contributions
istered-2.845
herty-2.722
earance-2.663
 chimpanzees-2.531
eman-2.528
Token well
Token ID880
Feature activation-1.13e+01

Pos logit contributions
lake+2.528
ール+2.444
dit+2.424
roller+2.303
storms+2.262
Neg logit contributions
istered-2.286
herty-2.188
earance-2.109
eman-2.019
 chimpanzees-1.992
Token,
Token ID11
Feature activation-1.52e+00

Pos logit contributions
lake+6.526
ール+6.420
dit+6.386
storms+5.944
roller+5.861
Neg logit contributions
istered-9.551
earance-8.951
herty-8.941
 chimpanzees-8.575
ocyte-8.448
Token given
Token ID1813
Feature activation-3.76e+00

Pos logit contributions
lake+1.151
ール+1.125
dit+1.121
roller+1.054
storms+1.027
Neg logit contributions
istered-1.167
herty-1.114
earance-1.089
 chimpanzees-1.036
eman-1.036
Token that
Token ID326
Feature activation+1.14e+00

Pos logit contributions
lake+3.086
ール+2.965
dit+2.939
roller+2.803
storms+2.748
Neg logit contributions
istered-2.618
herty-2.500
earance-2.424
eman-2.294
 chimpanzees-2.273
Token even
Token ID772
Feature activation-1.53e+00

Pos logit contributions
istered+0.821
herty+0.786
earance+0.768
 chimpanzees+0.738
 presumption+0.734
Neg logit contributions
lake-0.913
ール-0.901
dit-0.896
roller-0.843
storms-0.820
Token if
Token ID611
Feature activation-2.92e+00

Pos logit contributions
lake+1.136
ール+1.108
dit+1.103
roller+1.037
storms+1.008
Neg logit contributions
istered-1.196
herty-1.151
earance-1.123
eman-1.071
 chimpanzees-1.068
Token including
Token ID1390
Feature activation-1.85e+00

Pos logit contributions
lake+0.732
ール+0.716
dit+0.712
roller+0.670
storms+0.654
Neg logit contributions
istered-0.762
herty-0.731
earance-0.714
 chimpanzees-0.682
eman-0.680
Token an
Token ID281
Feature activation-3.33e+00

Pos logit contributions
lake+1.428
ール+1.394
dit+1.388
roller+1.313
storms+1.283
Neg logit contributions
istered-1.387
herty-1.329
earance-1.297
 chimpanzees-1.231
eman-1.227
Token image
Token ID2939
Feature activation+1.32e+00

Pos logit contributions
lake+2.485
ール+2.423
dit+2.409
roller+2.275
storms+2.203
Neg logit contributions
istered-2.585
herty-2.494
earance-2.406
 chimpanzees-2.315
 presumption-2.283
Token falsely
Token ID24566
Feature activation-4.10e+00

Pos logit contributions
istered+0.951
herty+0.910
earance+0.891
 chimpanzees+0.850
 presumption+0.846
Neg logit contributions
lake-1.056
ール-1.040
dit-1.029
roller-0.970
storms-0.945
Token suggesting
Token ID9524
Feature activation+1.88e+00

Pos logit contributions
lake+3.293
dit+3.193
ール+3.185
roller+2.989
storms+2.931
Neg logit contributions
istered-2.938
herty-2.812
earance-2.735
 chimpanzees-2.607
eman-2.563
Token Kurt
Token ID20642
Feature activation-1.11e+01

Pos logit contributions
istered+1.267
herty+1.211
earance+1.178
 chimpanzees+1.127
 presumption+1.117
Neg logit contributions
lake-1.596
ール-1.566
dit-1.558
roller-1.471
storms-1.434
Token Cob
Token ID14828
Feature activation-1.04e+01

Pos logit contributions
lake+6.923
ール+6.917
dit+6.441
roller+6.126
storms+6.106
Neg logit contributions
istered-9.391
earance-9.194
herty-9.020
 chimpanzees-8.692
 presumption-8.598
Tokenain
Token ID391
Feature activation-6.21e+00

Pos logit contributions
lake+7.800
dit+7.200
ール+6.835
roller+6.416
starter+6.269
Neg logit contributions
istered-8.276
herty-7.881
earance-7.848
 chimpanzees-7.605
 presumption-7.506
Token had
Token ID550
Feature activation-3.95e+00

Pos logit contributions
lake+4.534
ール+4.378
dit+4.352
roller+4.061
storms+3.974
Neg logit contributions
istered-4.809
earance-4.588
herty-4.561
 presumption-4.306
 chimpanzees-4.296
Token predicted
Token ID11001
Feature activation-1.17e+00

Pos logit contributions
lake+2.864
dit+2.810
ール+2.779
roller+2.588
storms+2.519
Neg logit contributions
istered-3.100
herty-2.974
earance-2.927
eman-2.771
 presumption-2.759
Token Donald
Token ID3759
Feature activation+2.50e-01

Pos logit contributions
lake+0.943
ール+0.919
dit+0.915
roller+0.865
storms+0.849
Neg logit contributions
istered-0.847
herty-0.807
earance-0.795
 presumption-0.745
 chimpanzees-0.743
Token have
Token ID423
Feature activation-3.61e+00

Pos logit contributions
lake+0.967
ール+0.941
dit+0.940
roller+0.890
storms+0.855
Neg logit contributions
istered-0.988
herty-0.944
earance-0.928
 chimpanzees-0.885
 presumption-0.879
Token to
Token ID284
Feature activation+1.02e-01

Pos logit contributions
lake+2.803
ール+2.742
dit+2.739
roller+2.570
storms+2.522
Neg logit contributions
istered-2.651
herty-2.532
earance-2.496
 chimpanzees-2.341
eman-2.320
Token target
Token ID2496
Feature activation+4.08e-01

Pos logit contributions
istered+0.074
herty+0.071
earance+0.069
 chimpanzees+0.066
eman+0.066
Neg logit contributions
lake-0.082
ール-0.080
dit-0.080
roller-0.075
storms-0.073
Token him
Token ID683
Feature activation-3.78e+00

Pos logit contributions
istered+0.292
herty+0.279
earance+0.273
 chimpanzees+0.260
eman+0.258
Neg logit contributions
lake-0.330
ール-0.323
dit-0.322
roller-0.304
storms-0.296
Token as
Token ID355
Feature activation-2.45e+00

Pos logit contributions
lake+2.805
ール+2.735
dit+2.718
roller+2.570
storms+2.506
Neg logit contributions
istered-2.914
herty-2.789
earance-2.732
 chimpanzees-2.611
 presumption-2.593
Token well
Token ID880
Feature activation-1.11e+01

Pos logit contributions
lake+1.810
ール+1.771
dit+1.760
roller+1.658
storms+1.622
Neg logit contributions
istered-1.888
herty-1.807
earance-1.773
 chimpanzees-1.684
 presumption-1.673
Token and
Token ID290
Feature activation-8.14e-01

Pos logit contributions
lake+6.897
ール+6.742
dit+6.735
roller+6.343
storms+6.154
Neg logit contributions
istered-8.968
herty-8.432
earance-8.403
 chimpanzees-8.143
 presumption-7.931
Token make
Token ID787
Feature activation-2.73e+00

Pos logit contributions
lake+0.644
ール+0.629
dit+0.628
roller+0.593
storms+0.575
Neg logit contributions
istered-0.595
herty-0.570
earance-0.557
 chimpanzees-0.530
eman-0.528
Token the
Token ID262
Feature activation-1.45e+00

Pos logit contributions
lake+2.069
dit+2.025
ール+2.008
roller+1.898
storms+1.849
Neg logit contributions
istered-2.083
herty-1.995
earance-1.937
 chimpanzees-1.850
eman-1.848
Token damage
Token ID2465
Feature activation-7.94e-02

Pos logit contributions
lake+1.110
dit+1.080
ール+1.080
roller+1.020
storms+0.993
Neg logit contributions
istered-1.092
herty-1.048
earance-1.019
 chimpanzees-0.968
eman-0.964
Token drop
Token ID4268
Feature activation+2.11e+00

Pos logit contributions
lake+0.063
ール+0.062
dit+0.061
roller+0.058
storms+0.056
Neg logit contributions
istered-0.058
herty-0.056
earance-0.054
 chimpanzees-0.052
eman-0.052
Token,
Token ID11
Feature activation-2.18e+00

Pos logit contributions
lake+0.984
dit+0.961
ール+0.958
roller+0.899
storms+0.874
Neg logit contributions
istered-1.072
herty-1.025
earance-1.005
 chimpanzees-0.964
 presumption-0.957
Token or
Token ID393
Feature activation-2.94e+00

Pos logit contributions
lake+1.564
dit+1.531
ール+1.522
roller+1.437
storms+1.392
Neg logit contributions
istered-1.744
herty-1.668
earance-1.647
 chimpanzees-1.566
 presumption-1.558
Token join
Token ID4654
Feature activation-2.13e+00

Pos logit contributions
lake+2.223
dit+2.157
ール+2.151
roller+2.041
storms+1.987
Neg logit contributions
istered-2.239
herty-2.136
earance-2.120
 chimpanzees-1.997
eman-1.991
Token in
Token ID287
Feature activation-1.02e+00

Pos logit contributions
lake+1.869
dit+1.824
ール+1.822
roller+1.729
storms+1.697
Neg logit contributions
istered-1.373
herty-1.308
earance-1.286
 chimpanzees-1.210
 presumption-1.203
Token the
Token ID262
Feature activation-2.62e+00

Pos logit contributions
lake+0.839
ール+0.822
dit+0.818
roller+0.774
storms+0.754
Neg logit contributions
istered-0.718
herty-0.686
earance-0.670
 chimpanzees-0.637
eman-0.634
Token conversation
Token ID5273
Feature activation-1.11e+01

Pos logit contributions
lake+1.545
dit+1.494
ール+1.486
roller+1.396
storms+1.341
Neg logit contributions
istered-2.432
herty-2.343
earance-2.322
 chimpanzees-2.218
eman-2.214
Token on
Token ID319
Feature activation-9.52e-01

Pos logit contributions
lake+6.933
dit+6.751
ール+6.706
roller+6.455
storms+6.406
Neg logit contributions
istered-8.894
herty-8.542
earance-8.465
 chimpanzees-7.944
 presumption-7.942
Token our
Token ID674
Feature activation+8.10e-01

Pos logit contributions
lake+0.756
ール+0.738
dit+0.737
roller+0.697
storms+0.682
Neg logit contributions
istered-0.691
herty-0.660
earance-0.652
 chimpanzees-0.614
 presumption-0.611
Token Forum
Token ID14867
Feature activation-4.69e+00

Pos logit contributions
istered+0.623
herty+0.598
earance+0.584
 chimpanzees+0.560
eman+0.557
Neg logit contributions
lake-0.611
ール-0.599
dit-0.594
roller-0.558
storms-0.542
Token.
Token ID13
Feature activation-1.71e+00

Pos logit contributions
lake+3.347
dit+3.278
ール+3.241
roller+3.077
storms+2.987
Neg logit contributions
istered-3.754
herty-3.594
earance-3.529
 chimpanzees-3.357
 presumption-3.342
Token<|endoftext|>
Token ID50256
Feature activation-7.23e-01

Pos logit contributions
lake+1.324
dit+1.296
ール+1.293
roller+1.216
storms+1.179
Neg logit contributions
istered-1.276
herty-1.213
earance-1.200
 chimpanzees-1.149
 presumption-1.140
Token guy
Token ID3516
Feature activation-2.47e+00

Pos logit contributions
istered+0.853
herty+0.813
earance+0.798
 chimpanzees+0.760
eman+0.754
Neg logit contributions
lake-0.946
ール-0.924
dit-0.919
roller-0.873
storms-0.844
Token.
Token ID13
Feature activation+9.39e-02

Pos logit contributions
lake+1.802
ール+1.757
dit+1.746
roller+1.653
storms+1.603
Neg logit contributions
istered-1.955
herty-1.856
earance-1.840
 chimpanzees-1.745
 presumption-1.739
Token Patrick
Token ID9925
Feature activation-3.17e+00

Pos logit contributions
istered+0.066
herty+0.063
earance+0.062
 chimpanzees+0.059
 presumption+0.058
Neg logit contributions
lake-0.077
ール-0.076
dit-0.075
roller-0.071
storms-0.069
Token sings
Token ID33041
Feature activation-2.10e+00

Pos logit contributions
lake+2.470
ール+2.404
dit+2.370
roller+2.257
storms+2.207
Neg logit contributions
istered-2.349
earance-2.246
herty-2.224
 presumption-2.110
 chimpanzees-2.088
Token as
Token ID355
Feature activation-6.40e-05

Pos logit contributions
lake+1.676
dit+1.627
ール+1.626
roller+1.542
storms+1.505
Neg logit contributions
istered-1.520
herty-1.458
earance-1.429
 presumption-1.337
 chimpanzees-1.333
Token well
Token ID880
Feature activation-1.10e+01

Pos logit contributions
lake+0.000
ール+0.000
dit+0.000
roller+0.000
storms+0.000
Neg logit contributions
istered-0.000
herty-0.000
earance-0.000
 chimpanzees-0.000
 presumption-0.000
Token.
Token ID13
Feature activation-7.41e-01

Pos logit contributions
lake+6.431
dit+6.290
ール+6.270
roller+5.876
storms+5.731
Neg logit contributions
istered-9.241
earance-8.864
herty-8.770
 presumption-8.345
ocyte-8.292
Token Not
Token ID1892
Feature activation-3.66e+00

Pos logit contributions
lake+0.590
ール+0.580
dit+0.574
roller+0.543
storms+0.527
Neg logit contributions
istered-0.542
herty-0.512
earance-0.507
 chimpanzees-0.480
 presumption-0.478
Token to
Token ID284
Feature activation-8.69e-01

Pos logit contributions
lake+2.832
ール+2.782
dit+2.756
roller+2.620
storms+2.531
Neg logit contributions
istered-2.698
herty-2.586
earance-2.530
 presumption-2.402
 chimpanzees-2.379
Token put
Token ID1234
Feature activation-2.19e+00

Pos logit contributions
lake+0.700
ール+0.688
dit+0.682
roller+0.639
storms+0.624
Neg logit contributions
istered-0.623
herty-0.597
earance-0.582
eman-0.550
 chimpanzees-0.546
Token words
Token ID2456
Feature activation-5.39e+00

Pos logit contributions
lake+1.563
ール+1.537
dit+1.523
roller+1.415
storms+1.383
Neg logit contributions
istered-1.758
herty-1.697
earance-1.653
eman-1.571
 presumption-1.554
Token will
Token ID481
Feature activation-2.69e+00

Pos logit contributions
istered+2.339
herty+2.251
earance+2.185
 chimpanzees+2.094
eman+2.092
Neg logit contributions
lake-2.559
ール-2.524
dit-2.502
roller-2.336
storms-2.298
Token have
Token ID423
Feature activation-3.59e+00

Pos logit contributions
lake+1.838
dit+1.785
ール+1.777
roller+1.696
storms+1.607
Neg logit contributions
istered-2.205
herty-2.122
earance-2.112
eman-1.994
 chimpanzees-1.990
Token a
Token ID257
Feature activation-5.15e-01

Pos logit contributions
lake+2.772
dit+2.717
ール+2.690
roller+2.572
storms+2.482
Neg logit contributions
istered-2.631
herty-2.491
earance-2.478
eman-2.339
 chimpanzees-2.332
Token stall
Token ID22549
Feature activation-8.62e-01

Pos logit contributions
lake+0.433
ール+0.422
dit+0.419
roller+0.402
storms+0.386
Neg logit contributions
istered-0.350
herty-0.333
earance-0.327
 chimpanzees-0.309
eman-0.309
Token as
Token ID355
Feature activation-2.15e+00

Pos logit contributions
lake+0.690
ール+0.678
dit+0.674
roller+0.643
storms+0.622
Neg logit contributions
istered-0.620
herty-0.595
earance-0.576
 chimpanzees-0.550
eman-0.546
Token well
Token ID880
Feature activation-1.10e+01

Pos logit contributions
lake+1.759
ール+1.729
dit+1.711
roller+1.636
storms+1.574
Neg logit contributions
istered-1.491
herty-1.424
earance-1.405
 chimpanzees-1.323
eman-1.317
Token,
Token ID11
Feature activation-2.16e+00

Pos logit contributions
lake+6.821
ール+6.724
dit+6.636
roller+6.495
storms+6.140
Neg logit contributions
istered-8.804
earance-8.333
herty-8.301
 chimpanzees-7.976
ideon-7.831
Token so
Token ID523
Feature activation-1.37e+00

Pos logit contributions
lake+1.639
ール+1.598
dit+1.598
roller+1.518
storms+1.463
Neg logit contributions
istered-1.637
herty-1.565
earance-1.537
 chimpanzees-1.453
eman-1.450
Token pop
Token ID1461
Feature activation+1.29e+00

Pos logit contributions
lake+1.053
ール+1.024
dit+1.021
roller+0.970
storms+0.936
Neg logit contributions
istered-1.030
herty-0.983
earance-0.968
 chimpanzees-0.920
eman-0.915
Token by
Token ID416
Feature activation-1.17e+00

Pos logit contributions
istered+0.944
herty+0.905
earance+0.883
 chimpanzees+0.843
 presumption+0.838
Neg logit contributions
lake-1.027
ール-1.006
dit-1.001
roller-0.944
storms-0.919
Token and
Token ID290
Feature activation-4.51e-01

Pos logit contributions
lake+0.897
ール+0.875
dit+0.872
roller+0.827
storms+0.805
Neg logit contributions
istered-0.877
herty-0.841
earance-0.824
 chimpanzees-0.787
 presumption-0.779
Token team
Token ID1074
Feature activation+1.59e+00

Pos logit contributions
istered+1.254
herty+1.195
earance+1.158
 chimpanzees+1.094
eman+1.093
Neg logit contributions
lake-1.919
ール-1.891
dit-1.881
roller-1.784
storms-1.745
Token that
Token ID326
Feature activation-4.13e-01

Pos logit contributions
istered+1.062
herty+1.019
earance+0.989
 chimpanzees+0.943
eman+0.942
Neg logit contributions
lake-1.351
ール-1.328
dit-1.325
roller-1.244
storms-1.218
Token was
Token ID373
Feature activation-7.66e-01

Pos logit contributions
lake+0.315
ール+0.308
dit+0.307
roller+0.288
storms+0.280
Neg logit contributions
istered-0.314
herty-0.302
earance-0.295
 chimpanzees-0.282
eman-0.280
Token playing
Token ID2712
Feature activation+7.35e-01

Pos logit contributions
lake+0.628
ール+0.614
dit+0.611
roller+0.580
storms+0.564
Neg logit contributions
istered-0.537
herty-0.516
earance-0.504
 chimpanzees-0.476
eman-0.473
Token as
Token ID355
Feature activation-4.82e-01

Pos logit contributions
istered+0.497
herty+0.473
earance+0.462
 chimpanzees+0.441
 presumption+0.439
Neg logit contributions
lake-0.622
ール-0.611
dit-0.608
roller-0.574
storms-0.560
Token well
Token ID880
Feature activation-1.10e+01

Pos logit contributions
lake+0.414
ール+0.406
dit+0.404
roller+0.383
storms+0.373
Neg logit contributions
istered-0.320
herty-0.306
earance-0.298
 chimpanzees-0.282
eman-0.281
Token as
Token ID355
Feature activation-3.08e+00

Pos logit contributions
lake+6.572
ール+6.550
dit+6.258
roller+6.107
storms+5.782
Neg logit contributions
istered-8.951
earance-8.760
herty-8.720
ocyte-8.403
eman-8.293
Token anyone
Token ID2687
Feature activation-5.59e+00

Pos logit contributions
lake+2.230
ール+2.172
dit+2.141
roller+2.027
storms+1.965
Neg logit contributions
istered-2.437
herty-2.356
earance-2.301
 chimpanzees-2.182
eman-2.180
Token in
Token ID287
Feature activation-1.86e+00

Pos logit contributions
lake+4.112
ール+4.048
dit+3.911
roller+3.772
storms+3.663
Neg logit contributions
istered-4.288
herty-4.084
earance-4.061
eman-3.795
 chimpanzees-3.780
Token football
Token ID4346
Feature activation+3.81e+00

Pos logit contributions
lake+1.571
ール+1.532
dit+1.505
roller+1.445
storms+1.415
Neg logit contributions
istered-1.272
herty-1.212
earance-1.171
 chimpanzees-1.118
 presumption-1.104
Token and
Token ID290
Feature activation+4.88e-02

Pos logit contributions
istered+2.666
herty+2.566
earance+2.495
 presumption+2.388
 chimpanzees+2.378
Neg logit contributions
lake-3.068
ール-3.016
dit-3.009
roller-2.837
storms-2.745
Token
Token ID251
Feature activation+4.81e-01

Pos logit contributions
istered+0.522
herty+0.502
earance+0.489
 chimpanzees+0.467
eman+0.465
Neg logit contributions
lake-0.572
ール-0.560
dit-0.558
roller-0.526
storms-0.512
Token the
Token ID262
Feature activation+4.06e-02

Pos logit contributions
istered+0.346
herty+0.331
earance+0.323
 chimpanzees+0.307
eman+0.306
Neg logit contributions
lake-0.388
ール-0.379
dit-0.379
roller-0.356
storms-0.348
Token demands
Token ID8665
Feature activation-4.37e+00

Pos logit contributions
istered+0.028
herty+0.027
earance+0.026
 chimpanzees+0.025
eman+0.025
Neg logit contributions
lake-0.034
dit-0.033
ール-0.033
roller-0.031
storms-0.030
Token by
Token ID416
Feature activation+2.69e+00

Pos logit contributions
lake+3.160
dit+3.113
ール+3.103
roller+2.900
storms+2.829
Neg logit contributions
istered-3.399
herty-3.202
earance-3.147
 chimpanzees-3.033
 presumption-3.014
Token Kentucky
Token ID11867
Feature activation-1.40e-01

Pos logit contributions
istered+1.806
herty+1.733
earance+1.683
 chimpanzees+1.609
 presumption+1.594
Neg logit contributions
lake-2.281
ール-2.242
dit-2.220
roller-2.107
storms-2.058
Token Fried
Token ID15442
Feature activation-1.09e+01

Pos logit contributions
lake+0.116
dit+0.113
ール+0.112
roller+0.106
storms+0.103
Neg logit contributions
istered-0.098
herty-0.093
earance-0.092
 presumption-0.086
 chimpanzees-0.086
Token Chicken
Token ID16405
Feature activation+3.21e+00

Pos logit contributions
lake+6.071
dit+5.672
roller+5.323
ール+5.125
starter+4.979
Neg logit contributions
istered-10.109
herty-9.689
earance-9.386
 presumption-9.112
ideon-8.997
Token that
Token ID326
Feature activation+8.26e-01

Pos logit contributions
istered+2.239
herty+2.149
earance+2.092
 chimpanzees+2.011
eman+2.005
Neg logit contributions
lake-2.608
ール-2.585
dit-2.552
roller-2.407
storms-2.351
Token the
Token ID262
Feature activation-7.83e-02

Pos logit contributions
istered+0.615
herty+0.590
earance+0.576
 chimpanzees+0.551
eman+0.548
Neg logit contributions
lake-0.643
ール-0.630
dit-0.626
roller-0.590
storms-0.574
Token EU
Token ID4576
Feature activation+3.02e+00

Pos logit contributions
lake+0.068
dit+0.066
ール+0.066
roller+0.062
storms+0.060
Neg logit contributions
istered-0.052
herty-0.050
earance-0.048
eman-0.045
 chimpanzees-0.045
Token lift
Token ID10303
Feature activation+1.90e+00

Pos logit contributions
istered+2.049
herty+1.964
earance+1.909
 chimpanzees+1.827
 presumption+1.822
Neg logit contributions
lake-2.528
ール-2.499
dit-2.473
roller-2.343
storms-2.286
Token the
Token ID262
Feature activation-1.09e+00

Pos logit contributions
lake+0.120
ール+0.117
dit+0.117
roller+0.111
storms+0.108
Neg logit contributions
istered-0.092
herty-0.088
earance-0.086
 chimpanzees-0.081
 presumption-0.081
Token film
Token ID2646
Feature activation-1.49e+00

Pos logit contributions
lake+0.895
ール+0.877
dit+0.872
roller+0.826
storms+0.803
Neg logit contributions
istered-0.764
herty-0.726
earance-0.709
 chimpanzees-0.672
eman-0.668
Token are
Token ID389
Feature activation-1.08e+00

Pos logit contributions
lake+1.127
ール+1.098
dit+1.094
roller+1.031
storms+1.003
Neg logit contributions
istered-1.140
herty-1.090
earance-1.064
 chimpanzees-1.021
 presumption-1.014
Token true
Token ID2081
Feature activation-2.30e+00

Pos logit contributions
lake+0.888
ール+0.871
dit+0.866
roller+0.819
storms+0.798
Neg logit contributions
istered-0.763
herty-0.723
earance-0.705
 chimpanzees-0.672
 presumption-0.665
Token as
Token ID355
Feature activation-3.25e+00

Pos logit contributions
lake+1.693
ール+1.658
dit+1.646
roller+1.544
storms+1.511
Neg logit contributions
istered-1.816
herty-1.731
earance-1.692
 chimpanzees-1.621
 presumption-1.612
Token well
Token ID880
Feature activation-1.08e+01

Pos logit contributions
lake+2.656
ール+2.603
dit+2.564
roller+2.446
storms+2.386
Neg logit contributions
istered-2.275
herty-2.163
earance-2.110
 chimpanzees-2.002
eman-1.994
Token,
Token ID11
Feature activation-3.00e+00

Pos logit contributions
lake+6.534
ール+6.440
dit+6.343
roller+5.986
storms+5.839
Neg logit contributions
istered-9.067
earance-8.415
herty-8.304
 chimpanzees-8.171
 presumption-8.044
Token and
Token ID290
Feature activation-2.45e+00

Pos logit contributions
lake+2.193
ール+2.142
dit+2.140
roller+2.011
storms+1.952
Neg logit contributions
istered-2.366
herty-2.231
earance-2.196
 chimpanzees-2.096
eman-2.087
Token a
Token ID257
Feature activation-1.48e+00

Pos logit contributions
lake+1.952
ール+1.899
dit+1.893
roller+1.791
storms+1.744
Neg logit contributions
istered-1.785
herty-1.694
earance-1.664
 chimpanzees-1.577
eman-1.573
Token potential
Token ID2785
Feature activation+3.14e-01

Pos logit contributions
lake+1.226
ール+1.203
dit+1.192
roller+1.137
storms+1.094
Neg logit contributions
istered-1.020
herty-0.964
earance-0.940
 chimpanzees-0.900
eman-0.894
Token battle
Token ID3344
Feature activation-4.32e+00

Pos logit contributions
istered+0.220
herty+0.211
earance+0.205
 chimpanzees+0.196
eman+0.195
Neg logit contributions
lake-0.257
ール-0.252
dit-0.251
roller-0.237
storms-0.231
Token nation
Token ID3277
Feature activation-8.36e-01

Pos logit contributions
istered+0.383
herty+0.367
earance+0.359
 chimpanzees+0.339
eman+0.338
Neg logit contributions
lake-0.451
dit-0.441
ール-0.441
roller-0.416
storms-0.406
Token favors
Token ID23866
Feature activation+3.33e+00

Pos logit contributions
lake+0.663
ール+0.647
dit+0.645
roller+0.608
storms+0.595
Neg logit contributions
istered-0.610
herty-0.586
earance-0.572
 chimpanzees-0.543
eman-0.543
Token,
Token ID11
Feature activation+1.36e+00

Pos logit contributions
istered+2.367
herty+2.268
earance+2.206
 chimpanzees+2.123
 presumption+2.115
Neg logit contributions
lake-2.688
ール-2.640
dit-2.616
roller-2.479
storms-2.400
Token as
Token ID355
Feature activation-7.00e-02

Pos logit contributions
istered+0.990
herty+0.949
earance+0.926
 chimpanzees+0.884
eman+0.879
Neg logit contributions
lake-1.080
ール-1.059
dit-1.053
roller-0.993
storms-0.966
Token we
Token ID356
Feature activation+2.44e+00

Pos logit contributions
lake+0.056
ール+0.055
dit+0.055
roller+0.051
storms+0.050
Neg logit contributions
istered-0.051
herty-0.049
earance-0.047
 chimpanzees-0.045
eman-0.045
Token see
Token ID766
Feature activation+7.40e+00

Pos logit contributions
istered+1.738
herty+1.665
earance+1.622
 chimpanzees+1.552
 presumption+1.543
Neg logit contributions
lake-1.971
ール-1.937
dit-1.920
roller-1.814
storms-1.767
Token far
Token ID1290
Feature activation+1.46e+00

Pos logit contributions
istered+4.911
herty+4.640
 chimpanzees+4.503
earance+4.476
 presumption+4.423
Neg logit contributions
lake-6.195
ール-6.154
dit-6.012
roller-5.786
storms-5.436
Token too
Token ID1165
Feature activation-1.05e+00

Pos logit contributions
istered+1.084
herty+1.039
earance+1.015
 chimpanzees+0.969
eman+0.964
Neg logit contributions
lake-1.146
ール-1.123
dit-1.117
roller-1.052
storms-1.024
Token many
Token ID867
Feature activation-1.11e+00

Pos logit contributions
lake+0.830
ール+0.810
dit+0.801
roller+0.756
storms+0.745
Neg logit contributions
istered-0.764
herty-0.731
earance-0.719
eman-0.681
 presumption-0.673
Token people
Token ID661
Feature activation-2.05e+00

Pos logit contributions
lake+0.894
dit+0.870
ール+0.869
roller+0.818
storms+0.802
Neg logit contributions
istered-0.789
herty-0.758
earance-0.743
eman-0.700
 chimpanzees-0.692
Token lie
Token ID6486
Feature activation-2.01e+00

Pos logit contributions
lake+1.633
dit+1.589
ール+1.588
roller+1.500
storms+1.468
Neg logit contributions
istered-1.472
herty-1.418
earance-1.379
eman-1.305
 chimpanzees-1.291
Token that
Token ID326
Feature activation+3.09e-01

Pos logit contributions
lake+1.247
ール+1.232
dit+1.218
roller+1.156
storms+1.124
Neg logit contributions
istered-1.139
herty-1.086
earance-1.067
eman-1.011
 chimpanzees-1.006
Token doesn
Token ID1595
Feature activation+8.82e-02

Pos logit contributions
istered+0.233
herty+0.224
earance+0.219
 chimpanzees+0.209
eman+0.208
Neg logit contributions
lake-0.237
ール-0.232
dit-0.230
roller-0.217
storms-0.211
Token
Token ID447
Feature activation-4.37e-01

Pos logit contributions
istered+0.068
herty+0.065
earance+0.064
 chimpanzees+0.061
eman+0.061
Neg logit contributions
lake-0.066
ール-0.065
dit-0.065
roller-0.061
storms-0.059
Token
Token ID247
Feature activation-9.83e-01

Pos logit contributions
lake+0.331
ール+0.326
dit+0.323
roller+0.304
storms+0.294
Neg logit contributions
istered-0.335
herty-0.320
earance-0.315
 chimpanzees-0.302
eman-0.299
Tokent
Token ID83
Feature activation-5.94e-01

Pos logit contributions
lake+0.687
ール+0.668
dit+0.668
roller+0.622
storms+0.603
Neg logit contributions
istered-0.813
herty-0.779
earance-0.767
 chimpanzees-0.738
 presumption-0.732
Token show
Token ID905
Feature activation+7.30e+00

Pos logit contributions
lake+0.463
dit+0.452
ール+0.451
roller+0.425
storms+0.411
Neg logit contributions
istered-0.443
herty-0.423
earance-0.415
 chimpanzees-0.392
eman-0.390
Token female
Token ID4048
Feature activation+1.62e+00

Pos logit contributions
istered+5.373
herty+5.229
earance+5.119
 chimpanzees+4.963
eman+4.868
Neg logit contributions
lake-5.455
ール-5.343
dit-5.246
roller-4.895
storms-4.810
Token comic
Token ID9048
Feature activation+7.26e-01

Pos logit contributions
istered+1.021
herty+0.972
earance+0.945
eman+0.891
 chimpanzees+0.890
Neg logit contributions
lake-1.440
ール-1.415
dit-1.409
roller-1.337
storms-1.306
Token book
Token ID1492
Feature activation+3.85e+00

Pos logit contributions
istered+0.504
herty+0.483
earance+0.470
 chimpanzees+0.447
eman+0.444
Neg logit contributions
lake-0.601
ール-0.590
dit-0.587
roller-0.555
storms-0.541
Token characters
Token ID3435
Feature activation+1.70e+00

Pos logit contributions
istered+2.672
herty+2.555
earance+2.495
 chimpanzees+2.385
 presumption+2.377
Neg logit contributions
lake-3.183
ール-3.123
dit-3.097
roller-2.928
storms-2.851
Token do
Token ID466
Feature activation+2.57e+00

Pos logit contributions
istered+1.222
herty+1.170
earance+1.142
 chimpanzees+1.089
eman+1.083
Neg logit contributions
lake-1.367
ール-1.340
dit-1.333
roller-1.258
storms-1.225
Token And
Token ID843
Feature activation+6.64e-01

Pos logit contributions
istered+0.989
herty+0.946
earance+0.921
 chimpanzees+0.873
eman+0.865
Neg logit contributions
lake-1.250
ール-1.223
dit-1.219
roller-1.148
storms-1.124
Token the
Token ID262
Feature activation+1.84e+00

Pos logit contributions
istered+0.466
herty+0.447
earance+0.436
 chimpanzees+0.413
eman+0.410
Neg logit contributions
lake-0.546
ール-0.533
dit-0.531
roller-0.500
storms-0.490
Token Congress
Token ID3162
Feature activation+2.60e+00

Pos logit contributions
istered+1.159
herty+1.096
earance+1.065
 chimpanzees+1.003
eman+0.994
Neg logit contributions
lake-1.657
dit-1.621
ール-1.614
roller-1.534
storms-1.500
Token may
Token ID743
Feature activation+2.12e+00

Pos logit contributions
istered+1.426
herty+1.348
earance+1.306
 chimpanzees+1.225
eman+1.211
Neg logit contributions
lake-2.539
ール-2.496
dit-2.487
roller-2.374
storms-2.321
Token by
Token ID416
Feature activation+2.98e+00

Pos logit contributions
istered+1.696
herty+1.632
earance+1.596
 chimpanzees+1.530
eman+1.523
Neg logit contributions
lake-1.536
ール-1.502
dit-1.493
roller-1.399
storms-1.358
Token general
Token ID2276
Feature activation+6.58e+00

Pos logit contributions
istered+1.688
herty+1.611
earance+1.549
 presumption+1.490
eman+1.480
Neg logit contributions
lake-2.827
ール-2.790
dit-2.777
roller-2.652
storms-2.578
Token Laws
Token ID21153
Feature activation-7.98e-01

Pos logit contributions
istered+3.737
herty+3.575
earance+3.445
 presumption+3.405
eman+3.361
Neg logit contributions
lake-6.059
ール-6.040
dit-5.963
roller-5.774
storms-5.545
Token prescribe
Token ID32651
Feature activation-7.58e-01

Pos logit contributions
lake+0.608
dit+0.590
ール+0.588
roller+0.554
storms+0.536
Neg logit contributions
istered-0.607
herty-0.584
earance-0.577
 chimpanzees-0.545
eman-0.536
Token the
Token ID262
Feature activation+4.95e-01

Pos logit contributions
lake+0.576
ール+0.563
dit+0.561
roller+0.521
storms+0.512
Neg logit contributions
istered-0.583
herty-0.553
earance-0.541
 chimpanzees-0.514
eman-0.508
Token Man
Token ID1869
Feature activation-3.03e+00

Pos logit contributions
istered+0.329
herty+0.311
earance+0.301
 chimpanzees+0.284
eman+0.284
Neg logit contributions
lake-0.429
dit-0.421
ール-0.419
roller-0.394
storms-0.387
Tokenner
Token ID1008
Feature activation-1.65e+00

Pos logit contributions
lake+1.855
dit+1.823
ール+1.792
roller+1.637
storms+1.626
Neg logit contributions
istered-2.686
herty-2.645
earance-2.590
 chimpanzees-2.487
 presumption-2.474
Token Raw
Token ID16089
Feature activation-3.39e-01

Pos logit contributions
lake+0.661
dit+0.635
ール+0.632
roller+0.594
storms+0.571
Neg logit contributions
istered-0.769
herty-0.744
earance-0.734
 presumption-0.700
 chimpanzees-0.699
Tokenl
Token ID75
Feature activation+5.97e+00

Pos logit contributions
lake+0.196
dit+0.189
ール+0.181
roller+0.172
storms+0.163
Neg logit contributions
istered-0.327
herty-0.311
earance-0.310
 presumption-0.301
 chimpanzees-0.298
Tokeninson
Token ID7899
Feature activation+3.42e+00

Pos logit contributions
istered+1.991
herty+1.841
earance+1.691
eman+1.576
 chimpanzees+1.515
Neg logit contributions
ール-6.931
lake-6.929
dit-6.838
roller-6.566
storms-6.521
Token,
Token ID11
Feature activation+7.21e-01

Pos logit contributions
istered+2.473
herty+2.381
earance+2.304
 chimpanzees+2.212
eman+2.210
Neg logit contributions
lake-2.712
ール-2.674
dit-2.660
roller-2.501
storms-2.434
Token John
Token ID1757
Feature activation+2.94e-01

Pos logit contributions
istered+0.577
herty+0.554
earance+0.545
 chimpanzees+0.519
 presumption+0.517
Neg logit contributions
lake-0.521
ール-0.509
dit-0.507
roller-0.473
storms-0.460
Token O
Token ID440
Feature activation+6.70e+00

Pos logit contributions
istered+0.223
herty+0.213
earance+0.211
 chimpanzees+0.201
 presumption+0.200
Neg logit contributions
lake-0.225
ール-0.218
dit-0.217
roller-0.207
storms-0.199
Token'
Token ID6
Feature activation+6.60e+00

Pos logit contributions
istered+3.951
herty+3.719
earance+3.556
eman+3.516
 presumption+3.313
Neg logit contributions
ール-6.147
lake-6.077
dit-5.932
storms-5.648
roller-5.607
TokenK
Token ID42
Feature activation+9.58e-01

Pos logit contributions
istered+3.938
herty+3.754
earance+3.582
eman+3.519
 presumption+3.392
Neg logit contributions
lake-5.954
ール-5.902
dit-5.834
roller-5.509
storms-5.500
Tokenane
Token ID1531
Feature activation-7.19e-01

Pos logit contributions
istered+0.599
herty+0.562
earance+0.551
 chimpanzees+0.525
 presumption+0.520
Neg logit contributions
lake-0.864
dit-0.844
ール-0.842
roller-0.805
storms-0.781
Token,
Token ID11
Feature activation+2.44e-02

Pos logit contributions
lake+0.545
ール+0.530
dit+0.528
roller+0.497
storms+0.484
Neg logit contributions
istered-0.551
herty-0.526
earance-0.519
 chimpanzees-0.493
 presumption-0.492
Token J
Token ID449
Feature activation-3.11e+00

Pos logit contributions
istered+0.020
herty+0.019
earance+0.018
 chimpanzees+0.018
 presumption+0.017
Neg logit contributions
lake-0.018
ール-0.017
dit-0.017
roller-0.016
storms-0.015
Token woman
Token ID2415
Feature activation+3.05e+00

Pos logit contributions
istered+0.413
herty+0.393
earance+0.382
 chimpanzees+0.362
eman+0.360
Neg logit contributions
lake-0.578
ール-0.567
dit-0.564
roller-0.536
storms-0.523
Token,
Token ID11
Feature activation+9.22e-01

Pos logit contributions
istered+2.219
herty+2.134
earance+2.077
 chimpanzees+1.995
eman+1.983
Neg logit contributions
lake-2.411
ール-2.364
dit-2.355
roller-2.208
storms-2.148
Token their
Token ID511
Feature activation+3.86e+00

Pos logit contributions
istered+0.665
herty+0.636
earance+0.621
 chimpanzees+0.590
eman+0.588
Neg logit contributions
lake-0.739
ール-0.724
dit-0.720
roller-0.680
storms-0.663
Token love
Token ID1842
Feature activation+3.87e+00

Pos logit contributions
istered+2.399
herty+2.277
earance+2.229
 presumption+2.121
 chimpanzees+2.116
Neg logit contributions
lake-3.471
ール-3.416
dit-3.394
roller-3.220
storms-3.146
Tokenmaking
Token ID8601
Feature activation-5.38e-02

Pos logit contributions
istered+2.616
herty+2.501
earance+2.486
 chimpanzees+2.355
 presumption+2.354
Neg logit contributions
lake-3.210
ール-3.171
dit-3.144
roller-2.961
storms-2.863
Token often
Token ID1690
Feature activation+7.12e+00

Pos logit contributions
lake+0.044
ール+0.043
dit+0.042
roller+0.040
storms+0.039
Neg logit contributions
istered-0.038
herty-0.037
earance-0.036
 chimpanzees-0.034
eman-0.034
Token ve
Token ID1569
Feature activation-4.10e+00

Pos logit contributions
istered+4.369
herty+4.221
earance+4.082
 chimpanzees+3.943
 presumption+3.922
Neg logit contributions
lake-6.281
ール-6.160
dit-6.129
roller-5.821
storms-5.538
Tokeners
Token ID364
Feature activation-3.97e+00

Pos logit contributions
lake+3.828
dit+3.804
ール+3.728
roller+3.622
storms+3.567
Neg logit contributions
istered-2.273
earance-2.170
herty-2.142
 presumption-2.069
 chimpanzees-2.009
Token into
Token ID656
Feature activation+1.09e+00

Pos logit contributions
lake+2.675
ール+2.598
dit+2.594
roller+2.389
storms+2.363
Neg logit contributions
istered-3.284
herty-3.206
earance-3.121
eman-2.941
 chimpanzees-2.936
Token far
Token ID1290
Feature activation+2.71e-01

Pos logit contributions
istered+0.720
herty+0.687
earance+0.667
 chimpanzees+0.631
eman+0.629
Neg logit contributions
lake-0.945
ール-0.927
dit-0.923
roller-0.875
storms-0.854
Tokence
Token ID344
Feature activation-1.05e+00

Pos logit contributions
istered+0.199
herty+0.191
earance+0.187
 chimpanzees+0.178
 presumption+0.176
Neg logit contributions
lake-0.215
ール-0.210
dit-0.209
roller-0.197
storms-0.192
Token Castro
Token ID21193
Feature activation+2.90e+00

Pos logit contributions
istered+0.605
herty+0.578
earance+0.570
 chimpanzees+0.543
 presumption+0.541
Neg logit contributions
lake-0.649
ール-0.632
dit-0.632
roller-0.595
storms-0.576
Token
Token ID198
Feature activation+8.84e-01

Pos logit contributions
istered+2.393
herty+2.330
earance+2.254
eman+2.173
 chimpanzees+2.171
Neg logit contributions
lake-2.001
ール-1.965
dit-1.950
roller-1.819
storms-1.772
Token
Token ID198
Feature activation+7.91e-01

Pos logit contributions
istered+0.549
herty+0.524
earance+0.506
 chimpanzees+0.479
eman+0.479
Neg logit contributions
lake-0.794
ール-0.783
dit-0.778
roller-0.739
storms-0.722
TokenThe
Token ID464
Feature activation+1.33e+00

Pos logit contributions
istered+0.536
herty+0.511
earance+0.500
 chimpanzees+0.476
 presumption+0.472
Neg logit contributions
lake-0.672
ール-0.658
dit-0.654
roller-0.621
storms-0.604
Token coaches
Token ID11070
Feature activation+3.49e-01

Pos logit contributions
istered+0.926
herty+0.886
earance+0.864
 chimpanzees+0.822
eman+0.818
Neg logit contributions
lake-1.100
ール-1.079
dit-1.073
roller-1.015
storms-0.989
Token stride
Token ID33769
Feature activation+9.24e-03

Pos logit contributions
istered+0.253
herty+0.242
earance+0.237
 chimpanzees+0.225
 presumption+0.224
Neg logit contributions
lake-0.278
ール-0.272
dit-0.271
roller-0.256
storms-0.249
Token off
Token ID572
Feature activation+3.61e+00

Pos logit contributions
istered+0.007
herty+0.007
earance+0.007
 chimpanzees+0.007
eman+0.007
Neg logit contributions
lake-0.007
ール-0.007
dit-0.007
roller-0.006
storms-0.006
Token,
Token ID11
Feature activation+2.40e+00

Pos logit contributions
istered+2.606
herty+2.489
earance+2.431
 chimpanzees+2.338
 presumption+2.324
Neg logit contributions
lake-2.863
ール-2.812
dit-2.786
roller-2.631
storms-2.558
Token important
Token ID1593
Feature activation+2.75e+00

Pos logit contributions
istered+1.676
herty+1.604
earance+1.563
 chimpanzees+1.495
 presumption+1.484
Neg logit contributions
lake-1.981
ール-1.944
dit-1.931
roller-1.825
storms-1.778
Token men
Token ID1450
Feature activation+9.85e-01

Pos logit contributions
istered+1.960
herty+1.885
earance+1.833
 chimpanzees+1.761
 presumption+1.748
Neg logit contributions
lake-2.219
ール-2.179
dit-2.160
roller-2.045
storms-1.987
Token on
Token ID319
Feature activation+2.77e+00

Pos logit contributions
istered+0.689
herty+0.659
earance+0.642
 chimpanzees+0.611
eman+0.608
Neg logit contributions
lake-0.812
ール-0.797
dit-0.792
roller-0.749
storms-0.730
Token,
Token ID11
Feature activation+1.60e+00

Pos logit contributions
lake+0.023
ール+0.023
dit+0.023
roller+0.022
storms+0.021
Neg logit contributions
istered-0.022
herty-0.021
earance-0.021
 chimpanzees-0.020
 presumption-0.020
Token some
Token ID617
Feature activation-7.14e-01

Pos logit contributions
istered+1.150
herty+1.100
earance+1.073
 chimpanzees+1.019
eman+1.017
Neg logit contributions
lake-1.293
ール-1.267
dit-1.263
roller-1.189
storms-1.161
Token quite
Token ID2407
Feature activation+2.83e-01

Pos logit contributions
lake+0.596
dit+0.584
ール+0.581
roller+0.549
storms+0.537
Neg logit contributions
istered-0.487
herty-0.469
earance-0.455
eman-0.429
 chimpanzees-0.427
Token disson
Token ID47080
Feature activation+2.01e+00

Pos logit contributions
istered+0.191
herty+0.183
earance+0.178
 chimpanzees+0.169
eman+0.168
Neg logit contributions
lake-0.240
ール-0.235
dit-0.234
roller-0.222
storms-0.216
Tokenant
Token ID415
Feature activation-9.92e-02

Pos logit contributions
istered+1.336
herty+1.271
earance+1.239
eman+1.173
 chimpanzees+1.168
Neg logit contributions
lake-1.723
ール-1.699
dit-1.683
roller-1.591
storms-1.560
Token
Token ID447
Feature activation+3.67e-01

Pos logit contributions
lake+0.077
ール+0.076
dit+0.076
roller+0.071
storms+0.070
Neg logit contributions
istered-0.073
herty-0.071
earance-0.069
 chimpanzees-0.065
eman-0.065
Token
Token ID251
Feature activation+1.74e+00

Pos logit contributions
istered+0.298
herty+0.286
earance+0.281
 chimpanzees+0.269
eman+0.268
Neg logit contributions
lake-0.262
ール-0.256
dit-0.254
roller-0.238
storms-0.231
Token seems
Token ID2331
Feature activation+8.98e+00

Pos logit contributions
istered+1.253
herty+1.200
earance+1.171
 chimpanzees+1.118
eman+1.112
Neg logit contributions
lake-1.403
ール-1.376
dit-1.366
roller-1.290
storms-1.255
Token to
Token ID284
Feature activation+3.44e+00

Pos logit contributions
istered+5.616
herty+5.369
earance+5.272
 chimpanzees+5.116
 presumption+5.089
Neg logit contributions
lake-7.622
ール-7.580
dit-7.355
roller-7.053
storms-6.823
Token stem
Token ID10717
Feature activation-9.64e-01

Pos logit contributions
istered+2.500
herty+2.403
earance+2.332
 chimpanzees+2.258
 presumption+2.242
Neg logit contributions
lake-2.715
ール-2.672
dit-2.633
roller-2.491
storms-2.423
Token from
Token ID422
Feature activation-4.07e-01

Pos logit contributions
lake+0.760
ール+0.746
dit+0.744
roller+0.702
storms+0.683
Neg logit contributions
istered-0.705
herty-0.676
earance-0.659
 chimpanzees-0.626
 presumption-0.624
Token-
Token ID12
Feature activation-1.50e+00

Pos logit contributions
istered+3.446
herty+3.324
earance+3.232
eman+3.104
 chimpanzees+3.085
Neg logit contributions
lake-3.224
ール-3.167
dit-3.142
roller-2.952
storms-2.863
Tokencapt
Token ID27144
Feature activation+9.55e-01

Pos logit contributions
lake+1.112
dit+1.074
ール+1.072
roller+1.014
storms+0.985
Neg logit contributions
istered-1.188
herty-1.137
earance-1.115
 chimpanzees-1.074
 presumption-1.061
Tokenain
Token ID391
Feature activation-1.46e+00

Pos logit contributions
istered+0.652
herty+0.621
earance+0.608
 chimpanzees+0.580
 presumption+0.579
Neg logit contributions
lake-0.803
ール-0.784
dit-0.779
roller-0.741
storms-0.721
Token Brian
Token ID8403
Feature activation+5.61e-01

Pos logit contributions
lake+1.068
ール+1.041
dit+1.038
roller+0.976
storms+0.946
Neg logit contributions
istered-1.149
herty-1.099
earance-1.080
 chimpanzees-1.037
 presumption-1.026
Token G
Token ID402
Feature activation+3.65e+00

Pos logit contributions
istered+0.435
herty+0.417
earance+0.408
 chimpanzees+0.392
 presumption+0.390
Neg logit contributions
lake-0.421
ール-0.410
dit-0.406
roller-0.383
storms-0.370
Tokenion
Token ID295
Feature activation+1.37e+00

Pos logit contributions
istered+1.876
herty+1.770
earance+1.716
eman+1.599
 chimpanzees+1.588
Neg logit contributions
lake-3.651
ール-3.629
dit-3.595
roller-3.415
storms-3.359
Tokenta
Token ID8326
Feature activation+3.82e+00

Pos logit contributions
istered+1.256
herty+1.211
earance+1.190
 chimpanzees+1.145
eman+1.145
Neg logit contributions
lake-0.825
ール-0.814
dit-0.794
roller-0.741
storms-0.714
Token,
Token ID11
Feature activation-6.74e-01

Pos logit contributions
istered+2.704
herty+2.630
earance+2.524
eman+2.439
 chimpanzees+2.401
Neg logit contributions
lake-3.075
ール-3.012
dit-3.011
roller-2.821
storms-2.753
Token heart
Token ID2612
Feature activation-1.06e+00

Pos logit contributions
lake+0.521
ール+0.509
dit+0.506
roller+0.478
storms+0.464
Neg logit contributions
istered-0.505
herty-0.480
earance-0.471
 chimpanzees-0.449
eman-0.445
Token-
Token ID12
Feature activation-3.89e-01

Pos logit contributions
lake+0.716
ール+0.698
dit+0.693
roller+0.649
storms+0.627
Neg logit contributions
istered-0.904
herty-0.873
earance-0.855
 chimpanzees-0.822
 presumption-0.817
Tokenand
Token ID392
Feature activation+3.20e+00

Pos logit contributions
lake+0.269
ール+0.263
dit+0.261
roller+0.244
storms+0.236
Neg logit contributions
istered-0.323
herty-0.311
earance-0.304
 chimpanzees-0.292
eman-0.291
Token custody
Token ID10804
Feature activation+7.43e-01

Pos logit contributions
lake+0.349
dit+0.340
ール+0.340
roller+0.323
storms+0.313
Neg logit contributions
istered-0.284
herty-0.272
earance-0.266
 chimpanzees-0.251
eman-0.250
Token of
Token ID286
Feature activation-3.59e-01

Pos logit contributions
istered+0.544
herty+0.520
earance+0.509
 chimpanzees+0.485
 presumption+0.483
Neg logit contributions
lake-0.588
ール-0.577
dit-0.573
roller-0.539
storms-0.525
Token ICE
Token ID23358
Feature activation-3.36e+00

Pos logit contributions
lake+0.298
dit+0.291
ール+0.291
roller+0.275
storms+0.268
Neg logit contributions
istered-0.248
herty-0.236
earance-0.231
eman-0.219
 chimpanzees-0.218
Token whilst
Token ID14590
Feature activation-1.64e+00

Pos logit contributions
lake+2.541
dit+2.480
ール+2.465
roller+2.311
storms+2.254
Neg logit contributions
istered-2.558
herty-2.440
earance-2.406
 chimpanzees-2.282
eman-2.272
Token she
Token ID673
Feature activation-2.16e+00

Pos logit contributions
lake+1.271
ール+1.245
dit+1.235
roller+1.167
storms+1.139
Neg logit contributions
istered-1.211
herty-1.164
earance-1.142
 chimpanzees-1.077
eman-1.076
Token waits
Token ID28364
Feature activation+2.20e+00

Pos logit contributions
lake+1.642
ール+1.601
dit+1.594
roller+1.500
storms+1.483
Neg logit contributions
istered-1.629
herty-1.556
earance-1.534
 chimpanzees-1.453
eman-1.444
Token for
Token ID329
Feature activation+4.20e+00

Pos logit contributions
istered+1.642
herty+1.574
earance+1.540
 chimpanzees+1.470
 presumption+1.463
Neg logit contributions
lake-1.712
ール-1.680
dit-1.668
roller-1.571
storms-1.526
Token her
Token ID607
Feature activation+3.71e+00

Pos logit contributions
istered+2.664
herty+2.528
earance+2.478
 chimpanzees+2.360
 presumption+2.357
Neg logit contributions
lake-3.693
ール-3.648
dit-3.599
roller-3.441
storms-3.333
Token trial
Token ID4473
Feature activation+5.49e+00

Pos logit contributions
istered+2.262
herty+2.145
earance+2.104
 presumption+2.013
 chimpanzees+2.001
Neg logit contributions
lake-3.353
ール-3.312
dit-3.284
roller-3.120
storms-3.061
Token.
Token ID13
Feature activation-2.84e-01

Pos logit contributions
istered+3.838
herty+3.662
earance+3.642
 presumption+3.474
 chimpanzees+3.454
Neg logit contributions
lake-4.416
ール-4.339
dit-4.320
roller-4.068
storms-3.962
Token Thompson
Token ID11654
Feature activation+3.88e+00

Pos logit contributions
lake+0.239
ール+0.235
dit+0.233
roller+0.220
storms+0.214
Neg logit contributions
istered-0.195
herty-0.183
earance-0.181
 chimpanzees-0.172
 presumption-0.170
Token to
Token ID284
Feature activation-1.22e+00

Pos logit contributions
lake+1.326
ール+1.297
dit+1.289
roller+1.217
storms+1.184
Neg logit contributions
istered-1.193
herty-1.144
earance-1.115
 chimpanzees-1.060
eman-1.058
Token fly
Token ID6129
Feature activation-3.63e-01

Pos logit contributions
lake+0.980
dit+0.958
ール+0.953
roller+0.905
storms+0.873
Neg logit contributions
istered-0.883
herty-0.842
earance-0.826
eman-0.780
 chimpanzees-0.778
Token yourself
Token ID3511
Feature activation-5.27e+00

Pos logit contributions
lake+0.280
ール+0.274
dit+0.273
roller+0.257
storms+0.250
Neg logit contributions
istered-0.273
herty-0.262
earance-0.256
 chimpanzees-0.244
eman-0.243
Token.
Token ID13
Feature activation-7.09e-01

Pos logit contributions
lake+3.780
dit+3.701
ール+3.671
roller+3.449
storms+3.392
Neg logit contributions
istered-4.132
herty-3.999
earance-3.951
 presumption-3.702
eman-3.698
Token You
Token ID921
Feature activation+7.05e-01

Pos logit contributions
lake+0.590
ール+0.577
dit+0.573
roller+0.542
storms+0.527
Neg logit contributions
istered-0.495
herty-0.468
earance-0.464
 chimpanzees-0.438
 presumption-0.435
Token really
Token ID1107
Feature activation+5.44e+00

Pos logit contributions
istered+0.538
herty+0.516
earance+0.505
 chimpanzees+0.482
eman+0.480
Neg logit contributions
lake-0.536
ール-0.525
dit-0.522
roller-0.491
storms-0.477
Token need
Token ID761
Feature activation+3.63e-01

Pos logit contributions
istered+3.763
herty+3.598
earance+3.474
 chimpanzees+3.379
eman+3.363
Neg logit contributions
lake-4.413
ール-4.402
dit-4.218
roller-4.009
storms-3.943
Token your
Token ID534
Feature activation+2.70e+00

Pos logit contributions
istered+0.260
herty+0.249
earance+0.243
 chimpanzees+0.232
eman+0.230
Neg logit contributions
lake-0.293
ール-0.286
dit-0.284
roller-0.269
storms-0.262
Token engine
Token ID3113
Feature activation+1.83e+00

Pos logit contributions
istered+1.750
herty+1.667
earance+1.620
 chimpanzees+1.544
 presumption+1.541
Neg logit contributions
lake-2.356
ール-2.320
dit-2.305
roller-2.178
storms-2.133
Token to
Token ID284
Feature activation+2.73e-01

Pos logit contributions
istered+1.276
herty+1.220
earance+1.190
 chimpanzees+1.134
 presumption+1.128
Neg logit contributions
lake-1.515
ール-1.488
dit-1.478
roller-1.395
storms-1.360
Token
Token ID198
Feature activation+9.88e-01

Pos logit contributions
istered+0.199
herty+0.190
earance+0.186
 chimpanzees+0.177
eman+0.176
Neg logit contributions
lake-0.218
ール-0.213
dit-0.212
roller-0.200
storms-0.195
Token.
Token ID13
Feature activation-4.12e-01

Pos logit contributions
istered+0.507
herty+0.484
earance+0.471
 chimpanzees+0.448
 presumption+0.446
Neg logit contributions
lake-0.652
ール-0.641
dit-0.637
roller-0.604
storms-0.589
Token Moreno
Token ID43269
Feature activation-6.32e-01

Pos logit contributions
lake+0.340
ール+0.333
dit+0.331
roller+0.312
storms+0.304
Neg logit contributions
istered-0.289
herty-0.276
earance-0.270
 chimpanzees-0.257
 presumption-0.255
Token,
Token ID11
Feature activation-1.84e+00

Pos logit contributions
lake+0.482
ール+0.471
dit+0.469
roller+0.440
storms+0.429
Neg logit contributions
istered-0.480
herty-0.461
earance-0.451
 chimpanzees-0.430
eman-0.428
Token meanwhile
Token ID15066
Feature activation-3.15e+00

Pos logit contributions
lake+1.393
ール+1.364
dit+1.360
roller+1.275
storms+1.234
Neg logit contributions
istered-1.404
herty-1.352
earance-1.321
 chimpanzees-1.253
eman-1.244
Token,
Token ID11
Feature activation-2.10e+00

Pos logit contributions
lake+2.248
dit+2.185
ール+2.167
roller+2.046
storms+1.987
Neg logit contributions
istered-2.533
herty-2.430
earance-2.393
 chimpanzees-2.277
eman-2.260
Token served
Token ID4983
Feature activation-1.50e+00

Pos logit contributions
lake+1.648
dit+1.613
ール+1.611
roller+1.510
storms+1.478
Neg logit contributions
istered-1.537
herty-1.474
earance-1.438
 chimpanzees-1.364
eman-1.358
Token as
Token ID355
Feature activation+7.88e-02

Pos logit contributions
lake+1.102
dit+1.069
ール+1.064
roller+0.997
storms+0.972
Neg logit contributions
istered-1.165
herty-1.119
earance-1.097
eman-1.046
 chimpanzees-1.043
Token vice
Token ID7927
Feature activation+7.49e-01

Pos logit contributions
istered+0.056
herty+0.054
earance+0.053
 chimpanzees+0.050
eman+0.050
Neg logit contributions
lake-0.064
ール-0.062
dit-0.062
roller-0.059
storms-0.057
Token president
Token ID1893
Feature activation-8.24e-01

Pos logit contributions
istered+0.526
herty+0.503
earance+0.492
 chimpanzees+0.467
eman+0.464
Neg logit contributions
lake-0.616
ール-0.603
dit-0.600
roller-0.567
storms-0.553
Token under
Token ID739
Feature activation-1.43e+00

Pos logit contributions
lake+0.637
ール+0.622
dit+0.620
roller+0.584
storms+0.569
Neg logit contributions
istered-0.619
herty-0.593
earance-0.580
 chimpanzees-0.552
 presumption-0.548
Token Rafael
Token ID31918
Feature activation+2.50e+00

Pos logit contributions
lake+1.124
dit+1.103
ール+1.096
roller+1.035
storms+1.007
Neg logit contributions
istered-1.051
herty-1.006
earance-0.990
 chimpanzees-0.932
eman-0.930
Tokenka
Token ID4914
Feature activation+6.04e-01

Pos logit contributions
istered+0.712
herty+0.681
earance+0.657
eman+0.634
 chimpanzees+0.622
Neg logit contributions
lake-0.892
ール-0.885
dit-0.872
roller-0.829
storms-0.812
Tokenfor
Token ID1640
Feature activation-3.03e+00

Pos logit contributions
istered+0.423
herty+0.410
earance+0.397
eman+0.380
 chimpanzees+0.374
Neg logit contributions
lake-0.492
ール-0.486
dit-0.481
roller-0.452
storms-0.444
Token was
Token ID373
Feature activation-7.95e-02

Pos logit contributions
lake+2.437
ール+2.351
dit+2.346
roller+2.205
storms+2.175
Neg logit contributions
istered-2.157
herty-2.058
earance-2.037
 chimpanzees-1.930
 presumption-1.919
Token named
Token ID3706
Feature activation-1.43e+00

Pos logit contributions
lake+0.057
ール+0.056
dit+0.056
roller+0.052
storms+0.051
Neg logit contributions
istered-0.064
herty-0.061
earance-0.060
 chimpanzees-0.057
eman-0.057
Token Atlantic
Token ID10596
Feature activation+4.86e+00

Pos logit contributions
lake+1.086
ール+1.055
dit+1.052
roller+0.991
storms+0.958
Neg logit contributions
istered-1.092
herty-1.051
earance-1.034
 chimpanzees-0.986
eman-0.975
Token Coast
Token ID8545
Feature activation-4.35e+00

Pos logit contributions
istered+3.113
herty+2.995
earance+2.832
eman+2.746
 chimpanzees+2.719
Neg logit contributions
lake-4.197
dit-4.185
ール-4.176
roller-3.917
storms-3.823
Token Conference
Token ID8785
Feature activation-2.00e+00

Pos logit contributions
lake+3.854
dit+3.659
ール+3.653
roller+3.512
storms+3.403
Neg logit contributions
istered-2.738
herty-2.583
earance-2.567
 chimpanzees-2.422
phan-2.333
Token Men
Token ID6065
Feature activation-2.73e+00

Pos logit contributions
lake+1.623
ール+1.564
dit+1.557
roller+1.484
storms+1.431
Neg logit contributions
istered-1.430
herty-1.365
earance-1.353
 chimpanzees-1.273
eman-1.254
Token's
Token ID338
Feature activation-7.10e-01

Pos logit contributions
lake+1.936
dit+1.870
ール+1.865
roller+1.739
storms+1.683
Neg logit contributions
istered-2.221
herty-2.148
earance-2.119
 chimpanzees-2.028
 presumption-2.004
Token Basketball
Token ID25911
Feature activation+4.95e+00

Pos logit contributions
lake+0.510
ール+0.496
dit+0.494
roller+0.463
storms+0.448
Neg logit contributions
istered-0.570
herty-0.550
earance-0.542
 chimpanzees-0.517
eman-0.512
Token Player
Token ID7853
Feature activation-1.85e+00

Pos logit contributions
istered+3.184
herty+3.052
earance+2.899
 presumption+2.836
eman+2.821
Neg logit contributions
lake-4.249
ール-4.241
dit-4.194
roller-3.962
storms-3.896
Tokenuh
Token ID7456
Feature activation-2.69e-01

Pos logit contributions
lake+0.671
dit+0.651
ール+0.649
roller+0.606
storms+0.582
Neg logit contributions
istered-0.943
herty-0.906
earance-0.887
 chimpanzees-0.858
 presumption-0.856
Token"
Token ID1
Feature activation-3.85e-01

Pos logit contributions
lake+0.206
ール+0.201
dit+0.200
roller+0.188
storms+0.183
Neg logit contributions
istered-0.204
herty-0.196
earance-0.191
 chimpanzees-0.183
 presumption-0.182
Token on
Token ID319
Feature activation+1.68e+00

Pos logit contributions
lake+0.301
ール+0.294
dit+0.294
roller+0.277
storms+0.270
Neg logit contributions
istered-0.286
herty-0.272
earance-0.266
 chimpanzees-0.253
 presumption-0.252
Token the
Token ID262
Feature activation+8.31e-01

Pos logit contributions
istered+1.099
herty+1.048
earance+1.021
 chimpanzees+0.971
eman+0.965
Neg logit contributions
lake-1.457
ール-1.431
dit-1.421
roller-1.349
storms-1.315
Token other
Token ID584
Feature activation+1.02e+00

Pos logit contributions
istered+0.605
herty+0.579
earance+0.565
 chimpanzees+0.541
 presumption+0.538
Neg logit contributions
lake-0.661
ール-0.648
dit-0.644
roller-0.608
storms-0.592
Token end
Token ID886
Feature activation-1.81e-01

Pos logit contributions
istered+0.709
herty+0.678
earance+0.661
 chimpanzees+0.627
eman+0.624
Neg logit contributions
lake-0.848
ール-0.831
dit-0.828
roller-0.782
storms-0.762
Token of
Token ID286
Feature activation-3.60e-01

Pos logit contributions
lake+0.140
ール+0.137
dit+0.136
roller+0.128
storms+0.125
Neg logit contributions
istered-0.136
herty-0.130
earance-0.127
 chimpanzees-0.122
eman-0.121
Token the
Token ID262
Feature activation-5.55e-01

Pos logit contributions
lake+0.308
ール+0.302
dit+0.301
roller+0.285
storms+0.278
Neg logit contributions
istered-0.241
herty-0.230
earance-0.224
 chimpanzees-0.212
eman-0.211
Token phone
Token ID3072
Feature activation-1.07e+00

Pos logit contributions
lake+0.510
ール+0.499
dit+0.498
roller+0.473
storms+0.462
Neg logit contributions
istered-0.337
herty-0.320
earance-0.310
 chimpanzees-0.292
eman-0.290
Token.
Token ID13
Feature activation+1.73e+00

Pos logit contributions
lake+0.797
dit+0.777
ール+0.776
roller+0.728
storms+0.710
Neg logit contributions
istered-0.828
herty-0.793
earance-0.775
 chimpanzees-0.739
eman-0.735
Token This
Token ID770
Feature activation+2.34e+00

Pos logit contributions
istered+1.200
herty+1.153
earance+1.119
 chimpanzees+1.067
eman+1.064
Neg logit contributions
lake-1.429
ール-1.402
dit-1.394
roller-1.320
storms-1.285
Token
Token ID251
Feature activation-1.96e-01

Pos logit contributions
istered+0.414
herty+0.397
earance+0.390
 chimpanzees+0.373
eman+0.372
Neg logit contributions
lake-0.368
ール-0.362
dit-0.358
roller-0.335
storms-0.325
Token she
Token ID673
Feature activation+4.35e-01

Pos logit contributions
lake+0.153
dit+0.149
ール+0.149
roller+0.140
storms+0.136
Neg logit contributions
istered-0.146
herty-0.140
earance-0.137
 chimpanzees-0.131
 presumption-0.130
Token says
Token ID1139
Feature activation+3.89e-02

Pos logit contributions
istered+0.312
herty+0.297
earance+0.292
 chimpanzees+0.277
 presumption+0.276
Neg logit contributions
lake-0.353
ール-0.346
dit-0.344
roller-0.324
storms-0.316
Token,
Token ID11
Feature activation+9.22e-01

Pos logit contributions
istered+0.029
herty+0.028
earance+0.027
 chimpanzees+0.026
eman+0.026
Neg logit contributions
lake-0.030
ール-0.029
dit-0.029
roller-0.028
storms-0.027
Token
Token ID564
Feature activation+1.25e-01

Pos logit contributions
istered+0.637
herty+0.608
earance+0.593
 chimpanzees+0.564
eman+0.561
Neg logit contributions
lake-0.767
ール-0.753
dit-0.750
roller-0.708
storms-0.691
Token
Token ID250
Feature activation-8.57e-01

Pos logit contributions
istered+0.098
herty+0.094
earance+0.092
 chimpanzees+0.088
eman+0.087
Neg logit contributions
lake-0.093
ール-0.092
dit-0.090
roller-0.085
storms-0.083
Tokenthere
Token ID8117
Feature activation+1.29e+00

Pos logit contributions
lake+0.705
ール+0.688
dit+0.687
roller+0.651
storms+0.634
Neg logit contributions
istered-0.604
herty-0.577
earance-0.564
 chimpanzees-0.540
 presumption-0.533
Token were
Token ID547
Feature activation-2.95e+00

Pos logit contributions
istered+0.942
herty+0.903
earance+0.881
 chimpanzees+0.841
eman+0.837
Neg logit contributions
lake-1.017
ール-0.997
dit-0.991
roller-0.934
storms-0.909
Token very
Token ID845
Feature activation+1.70e+00

Pos logit contributions
lake+2.317
ール+2.265
dit+2.263
roller+2.133
storms+2.084
Neg logit contributions
istered-2.163
herty-2.057
earance-2.023
eman-1.905
 chimpanzees-1.898
Token few
Token ID1178
Feature activation+5.17e-01

Pos logit contributions
istered+1.121
herty+1.075
earance+1.043
 chimpanzees+0.999
 presumption+0.993
Neg logit contributions
lake-1.461
ール-1.438
dit-1.428
roller-1.348
storms-1.316
Token of
Token ID286
Feature activation-8.26e-01

Pos logit contributions
istered+0.290
herty+0.274
earance+0.266
 chimpanzees+0.248
eman+0.247
Neg logit contributions
lake-0.497
ール-0.489
dit-0.487
roller-0.464
storms-0.455
Token idea
Token ID2126
Feature activation+3.74e+00

Pos logit contributions
lake+0.747
ール+0.730
dit+0.729
roller+0.687
storms+0.674
Neg logit contributions
istered-0.575
herty-0.554
earance-0.539
eman-0.506
 chimpanzees-0.502
Token as
Token ID355
Feature activation+3.36e-01

Pos logit contributions
istered+2.499
herty+2.392
earance+2.324
 chimpanzees+2.222
eman+2.219
Neg logit contributions
lake-3.169
ール-3.122
dit-3.081
roller-2.934
storms-2.839
Token to
Token ID284
Feature activation-6.20e-01

Pos logit contributions
istered+0.238
herty+0.228
earance+0.223
 chimpanzees+0.212
 presumption+0.211
Neg logit contributions
lake-0.273
ール-0.268
dit-0.266
roller-0.251
storms-0.245
Token which
Token ID543
Feature activation-1.42e+00

Pos logit contributions
lake+0.531
ール+0.517
dit+0.517
roller+0.489
storms+0.480
Neg logit contributions
istered-0.415
herty-0.392
earance-0.383
 chimpanzees-0.361
eman-0.359
Token is
Token ID318
Feature activation-1.82e+00

Pos logit contributions
lake+1.173
dit+1.138
ール+1.134
roller+1.074
storms+1.053
Neg logit contributions
istered-0.991
herty-0.951
earance-0.928
eman-0.873
 chimpanzees-0.868
Token the
Token ID262
Feature activation-3.07e+00

Pos logit contributions
lake+1.472
ール+1.433
dit+1.427
roller+1.356
storms+1.335
Neg logit contributions
istered-1.291
herty-1.228
earance-1.211
 chimpanzees-1.132
 presumption-1.123
Token main
Token ID1388
Feature activation-1.92e+00

Pos logit contributions
lake+2.799
dit+2.718
ール+2.715
roller+2.617
storms+2.550
Neg logit contributions
istered-1.843
herty-1.729
earance-1.710
 chimpanzees-1.571
eman-1.557
Token contributor
Token ID18920
Feature activation-5.55e-01

Pos logit contributions
lake+1.483
dit+1.442
ール+1.439
roller+1.365
storms+1.320
Neg logit contributions
istered-1.447
herty-1.384
earance-1.359
 chimpanzees-1.286
eman-1.277
Token of
Token ID286
Feature activation+7.60e-01

Pos logit contributions
lake+0.431
ール+0.422
dit+0.420
roller+0.396
storms+0.386
Neg logit contributions
istered-0.415
herty-0.397
earance-0.389
 chimpanzees-0.370
 presumption-0.368
Token R
Token ID371
Feature activation+1.31e-02

Pos logit contributions
istered+0.483
herty+0.460
earance+0.449
 chimpanzees+0.424
eman+0.421
Neg logit contributions
lake-0.672
ール-0.660
dit-0.657
roller-0.624
storms-0.610
TokenFI
Token ID11674
Feature activation-8.34e-01

Pos logit contributions
istered+0.015
herty+0.015
earance+0.015
 chimpanzees+0.014
eman+0.014
Neg logit contributions
lake-0.004
ール-0.004
dit-0.004
roller-0.004
storms-0.003
Tokenstruction
Token ID15019
Feature activation+2.90e-01

Pos logit contributions
lake+2.926
ール+2.872
dit+2.871
roller+2.703
storms+2.633
Neg logit contributions
istered-2.454
herty-2.355
earance-2.302
 chimpanzees-2.250
 presumption-2.209
Token in
Token ID287
Feature activation-4.84e-01

Pos logit contributions
istered+0.200
herty+0.191
earance+0.186
 chimpanzees+0.177
 presumption+0.175
Neg logit contributions
lake-0.243
ール-0.238
dit-0.236
roller-0.224
storms-0.219
Token Pre
Token ID3771
Feature activation-6.37e+00

Pos logit contributions
lake+0.394
ール+0.384
dit+0.382
roller+0.361
storms+0.352
Neg logit contributions
istered-0.345
herty-0.330
earance-0.323
 chimpanzees-0.307
 presumption-0.305
Tokeny
Token ID88
Feature activation+2.04e+00

Pos logit contributions
lake+2.968
dit+2.728
ール+2.562
roller+2.487
storms+2.316
Neg logit contributions
istered-6.740
herty-6.530
earance-6.483
 chimpanzees-6.380
 cumbers-6.352
Token as
Token ID355
Feature activation-1.45e+00

Pos logit contributions
istered+1.527
herty+1.467
earance+1.432
 chimpanzees+1.368
eman+1.366
Neg logit contributions
lake-1.576
ール-1.547
dit-1.536
roller-1.446
storms-1.405
Token well
Token ID880
Feature activation-1.00e+01

Pos logit contributions
lake+1.210
ール+1.178
dit+1.177
roller+1.113
storms+1.088
Neg logit contributions
istered-0.990
herty-0.945
earance-0.925
 chimpanzees-0.876
eman-0.875
Token.
Token ID13
Feature activation-8.72e-01

Pos logit contributions
lake+6.045
ール+5.860
dit+5.755
roller+5.437
storms+5.352
Neg logit contributions
istered-8.373
earance-8.017
herty-7.869
 chimpanzees-7.670
 presumption-7.651
Token But
Token ID887
Feature activation-1.28e+00

Pos logit contributions
lake+0.716
ール+0.698
dit+0.695
roller+0.656
storms+0.639
Neg logit contributions
istered-0.619
herty-0.586
earance-0.581
 chimpanzees-0.550
 presumption-0.546
Token where
Token ID810
Feature activation-6.56e-01

Pos logit contributions
lake+1.032
ール+1.004
dit+0.998
roller+0.945
storms+0.921
Neg logit contributions
istered-0.923
herty-0.879
earance-0.864
 chimpanzees-0.817
eman-0.815
Token Bio
Token ID16024
Feature activation-6.22e+00

Pos logit contributions
lake+0.508
ール+0.494
dit+0.492
roller+0.464
storms+0.451
Neg logit contributions
istered-0.495
herty-0.474
earance-0.465
 chimpanzees-0.442
eman-0.440
TokenShock
Token ID31646
Feature activation-6.67e-01

Pos logit contributions
lake+4.134
dit+3.930
ール+3.852
roller+3.651
storms+3.550
Neg logit contributions
istered-5.294
earance-5.062
herty-5.024
 presumption-4.837
 chimpanzees-4.831
Token it
Token ID340
Feature activation+5.08e-01

Pos logit contributions
istered+2.210
herty+2.117
earance+2.055
 chimpanzees+1.987
 presumption+1.980
Neg logit contributions
lake-2.642
ール-2.617
dit-2.600
roller-2.440
storms-2.372
Token
Token ID447
Feature activation-3.33e-01

Pos logit contributions
istered+0.364
herty+0.348
earance+0.340
 chimpanzees+0.324
 presumption+0.322
Neg logit contributions
lake-0.410
ール-0.402
dit-0.400
roller-0.377
storms-0.368
Token
Token ID247
Feature activation-3.68e-02

Pos logit contributions
lake+0.241
ール+0.236
dit+0.233
roller+0.219
storms+0.212
Neg logit contributions
istered-0.267
herty-0.256
earance-0.252
 chimpanzees-0.242
eman-0.240
Tokens
Token ID82
Feature activation-8.71e-01

Pos logit contributions
lake+0.027
ール+0.027
dit+0.026
roller+0.025
storms+0.024
Neg logit contributions
istered-0.029
herty-0.028
earance-0.027
 chimpanzees-0.026
 presumption-0.026
Token a
Token ID257
Feature activation-4.48e-01

Pos logit contributions
lake+0.695
ール+0.679
dit+0.675
roller+0.641
storms+0.623
Neg logit contributions
istered-0.630
herty-0.603
earance-0.590
 chimpanzees-0.559
 presumption-0.555
Token deliberate
Token ID18988
Feature activation-9.02e+00

Pos logit contributions
lake+0.381
ール+0.373
dit+0.370
roller+0.353
storms+0.342
Neg logit contributions
istered-0.301
herty-0.287
earance-0.280
 chimpanzees-0.266
eman-0.264
Token sense
Token ID2565
Feature activation+5.38e-01

Pos logit contributions
lake+6.642
ール+6.484
dit+6.346
roller+6.103
starter+5.879
Neg logit contributions
istered-6.653
herty-6.299
earance-6.170
 chimpanzees-5.936
ideon-5.812
Token of
Token ID286
Feature activation+1.53e+00

Pos logit contributions
istered+0.384
herty+0.367
earance+0.360
 chimpanzees+0.342
eman+0.342
Neg logit contributions
lake-0.434
ール-0.425
dit-0.423
roller-0.398
storms-0.388
Token al
Token ID435
Feature activation+9.55e-01

Pos logit contributions
istered+1.022
herty+0.976
earance+0.950
 chimpanzees+0.902
eman+0.897
Neg logit contributions
lake-1.315
ール-1.290
dit-1.283
roller-1.216
storms-1.186
Tokenoof
Token ID37711
Feature activation+2.03e+00

Pos logit contributions
istered+0.621
herty+0.587
earance+0.574
 chimpanzees+0.551
eman+0.544
Neg logit contributions
lake-0.829
dit-0.821
ール-0.817
roller-0.773
storms-0.753
Tokenness
Token ID1108
Feature activation+1.14e+00

Pos logit contributions
istered+1.638
herty+1.576
earance+1.538
 chimpanzees+1.477
eman+1.469
Neg logit contributions
lake-1.454
ール-1.423
dit-1.416
roller-1.324
storms-1.285
Tokeniness
Token ID1272
Feature activation+6.91e+00

Pos logit contributions
istered+2.181
herty+2.049
earance+1.984
 chimpanzees+1.854
eman+1.847
Neg logit contributions
lake-4.034
ール-3.971
dit-3.949
roller-3.775
storms-3.692
Token and
Token ID290
Feature activation+3.96e+00

Pos logit contributions
istered+4.754
herty+4.465
earance+4.408
 presumption+4.264
 chimpanzees+4.223
Neg logit contributions
lake-5.622
ール-5.485
dit-5.396
roller-5.226
storms-4.933
Token confusion
Token ID10802
Feature activation+6.64e-01

Pos logit contributions
istered+2.546
herty+2.421
earance+2.362
 presumption+2.244
 chimpanzees+2.242
Neg logit contributions
lake-3.487
ール-3.424
dit-3.393
roller-3.230
storms-3.141
Token to
Token ID284
Feature activation+2.19e+00

Pos logit contributions
istered+0.506
herty+0.486
earance+0.475
 chimpanzees+0.454
eman+0.452
Neg logit contributions
lake-0.505
ール-0.495
dit-0.492
roller-0.462
storms-0.451
Token the
Token ID262
Feature activation+3.10e+00

Pos logit contributions
istered+1.445
herty+1.375
earance+1.340
 chimpanzees+1.276
 presumption+1.271
Neg logit contributions
lake-1.884
ール-1.851
dit-1.837
roller-1.742
storms-1.699
Token minds
Token ID9017
Feature activation-7.61e+00

Pos logit contributions
istered+2.175
herty+2.076
earance+2.025
 chimpanzees+1.936
 presumption+1.936
Neg logit contributions
lake-2.544
ール-2.501
dit-2.473
roller-2.338
storms-2.286
Token of
Token ID286
Feature activation-1.17e-01

Pos logit contributions
lake+4.891
ール+4.791
dit+4.785
storms+4.487
roller+4.416
Neg logit contributions
istered-6.150
herty-6.043
earance-5.784
 chimpanzees-5.622
ideon-5.600
Token readers
Token ID7183
Feature activation+1.81e+00

Pos logit contributions
lake+0.098
dit+0.096
ール+0.096
roller+0.091
storms+0.088
Neg logit contributions
istered-0.079
herty-0.076
earance-0.074
eman-0.069
 chimpanzees-0.069
Token.
Token ID13
Feature activation+4.44e+00

Pos logit contributions
istered+1.360
herty+1.305
earance+1.274
 chimpanzees+1.219
eman+1.215
Neg logit contributions
lake-1.397
ール-1.369
dit-1.360
roller-1.280
storms-1.245
Token
Token ID198
Feature activation+5.29e+00

Pos logit contributions
istered+2.827
herty+2.720
earance+2.589
eman+2.499
 presumption+2.491
Neg logit contributions
lake-3.853
ール-3.793
dit-3.763
roller-3.605
storms-3.507
Token
Token ID198
Feature activation+4.67e+00

Pos logit contributions
istered+2.662
herty+2.590
earance+2.380
eman+2.362
 presumption+2.286
Neg logit contributions
ール-5.134
lake-5.132
dit-5.068
roller-4.851
storms-4.750
Token ren
Token ID8851
Feature activation-2.85e+00

Pos logit contributions
lake+2.421
dit+2.360
ール+2.335
roller+2.220
storms+2.143
Neg logit contributions
istered-2.310
herty-2.199
earance-2.150
eman-2.050
 chimpanzees-2.027
Tokenounce
Token ID8652
Feature activation-3.31e+00

Pos logit contributions
lake+1.076
dit+1.026
ール+1.004
roller+0.886
storms+0.820
Neg logit contributions
istered-3.266
herty-3.184
earance-3.137
 chimpanzees-3.096
 presumption-3.065
Token them
Token ID606
Feature activation-4.42e+00

Pos logit contributions
lake+2.553
ール+2.486
dit+2.465
roller+2.327
storms+2.272
Neg logit contributions
istered-2.478
herty-2.373
earance-2.310
eman-2.195
 presumption-2.178
Token immediately
Token ID3393
Feature activation-3.57e+00

Pos logit contributions
lake+3.318
ール+3.257
dit+3.231
roller+3.030
storms+2.985
Neg logit contributions
istered-3.373
herty-3.215
earance-3.136
eman-2.972
 chimpanzees-2.972
Token as
Token ID355
Feature activation-3.16e+00

Pos logit contributions
lake+2.565
ール+2.518
dit+2.503
roller+2.335
storms+2.304
Neg logit contributions
istered-2.845
herty-2.722
earance-2.663
 chimpanzees-2.531
eman-2.528
Token well
Token ID880
Feature activation-1.13e+01

Pos logit contributions
lake+2.528
ール+2.444
dit+2.424
roller+2.303
storms+2.262
Neg logit contributions
istered-2.286
herty-2.188
earance-2.109
eman-2.019
 chimpanzees-1.992
Token,
Token ID11
Feature activation-1.52e+00

Pos logit contributions
lake+6.526
ール+6.420
dit+6.386
storms+5.944
roller+5.861
Neg logit contributions
istered-9.551
earance-8.951
herty-8.941
 chimpanzees-8.575
ocyte-8.448
Token given
Token ID1813
Feature activation-3.76e+00

Pos logit contributions
lake+1.151
ール+1.125
dit+1.121
roller+1.054
storms+1.027
Neg logit contributions
istered-1.167
herty-1.114
earance-1.089
 chimpanzees-1.036
eman-1.036
Token that
Token ID326
Feature activation+1.14e+00

Pos logit contributions
lake+3.086
ール+2.965
dit+2.939
roller+2.803
storms+2.748
Neg logit contributions
istered-2.618
herty-2.500
earance-2.424
eman-2.294
 chimpanzees-2.273
Token even
Token ID772
Feature activation-1.53e+00

Pos logit contributions
istered+0.821
herty+0.786
earance+0.768
 chimpanzees+0.738
 presumption+0.734
Neg logit contributions
lake-0.913
ール-0.901
dit-0.896
roller-0.843
storms-0.820
Token if
Token ID611
Feature activation-2.92e+00

Pos logit contributions
lake+1.136
ール+1.108
dit+1.103
roller+1.037
storms+1.008
Neg logit contributions
istered-1.196
herty-1.151
earance-1.123
eman-1.071
 chimpanzees-1.068
Token Her
Token ID2332
Feature activation-2.07e+00

Pos logit contributions
lake+0.128
ール+0.125
dit+0.124
roller+0.118
storms+0.115
Neg logit contributions
istered-0.109
herty-0.104
earance-0.102
 chimpanzees-0.096
eman-0.096
Tokenok
Token ID482
Feature activation+4.34e+00

Pos logit contributions
lake+1.341
dit+1.304
ール+1.291
roller+1.199
storms+1.159
Neg logit contributions
istered-1.819
herty-1.754
earance-1.706
 chimpanzees-1.661
 presumption-1.646
Tokeniller
Token ID4665
Feature activation-1.93e+00

Pos logit contributions
istered+3.531
herty+3.408
earance+3.325
eman+3.242
 presumption+3.197
Neg logit contributions
lake-2.956
ール-2.941
dit-2.923
roller-2.726
storms-2.613
Token was
Token ID373
Feature activation-1.54e-01

Pos logit contributions
lake+1.482
ール+1.438
dit+1.437
roller+1.352
storms+1.324
Neg logit contributions
istered-1.461
herty-1.399
earance-1.369
 presumption-1.294
 chimpanzees-1.293
Token big
Token ID1263
Feature activation+3.53e+00

Pos logit contributions
lake+0.124
ール+0.121
dit+0.120
roller+0.114
storms+0.111
Neg logit contributions
istered-0.111
herty-0.106
earance-0.104
 chimpanzees-0.098
eman-0.098
Token enough
Token ID1576
Feature activation-7.03e+00

Pos logit contributions
istered+2.634
herty+2.529
earance+2.452
 chimpanzees+2.386
 presumption+2.372
Neg logit contributions
lake-2.701
ール-2.664
dit-2.634
roller-2.489
storms-2.394
Token that
Token ID326
Feature activation-2.25e+00

Pos logit contributions
lake+4.945
dit+4.821
ール+4.819
roller+4.499
storms+4.489
Neg logit contributions
istered-5.459
herty-5.234
earance-5.141
ocyte-4.790
 presumption-4.781
Token you
Token ID345
Feature activation-2.54e-01

Pos logit contributions
lake+1.722
ール+1.676
dit+1.672
roller+1.576
storms+1.542
Neg logit contributions
istered-1.704
herty-1.627
earance-1.601
 chimpanzees-1.507
eman-1.504
Token could
Token ID714
Feature activation-6.58e-01

Pos logit contributions
lake+0.172
dit+0.168
ール+0.167
roller+0.156
storms+0.151
Neg logit contributions
istered-0.215
herty-0.207
earance-0.204
 chimpanzees-0.194
eman-0.193
Token see
Token ID766
Feature activation+5.27e+00

Pos logit contributions
lake+0.528
dit+0.514
ール+0.509
roller+0.489
storms+0.471
Neg logit contributions
istered-0.473
herty-0.454
earance-0.446
 chimpanzees-0.416
eman-0.416
Token his
Token ID465
Feature activation-3.06e-01

Pos logit contributions
istered+3.447
herty+3.306
earance+3.216
 chimpanzees+3.182
 comparative+3.127
Neg logit contributions
lake-4.382
ール-4.373
dit-4.296
roller-4.098
storms-3.945