TOP ACTIVATIONS
MAX = 19.121

hold together . 4 . Make 6 p att ies .
c v 2 . morphology Ex ( gray , c v
2 . Ga ussian Bl ur ( gray , ( 3
s protests with relative len iency . Although tear
c v 2 . im read ( image Path ) image
Year for the second year in a row . Thursday night
( place versus direction ), ( H ) Type 4 probe
UM T ER TI P ART IS .
S EC UN D P ART IS .
ethics ( and campaign - f inance ) tra vest y
} 1 2 3 void vert ( in out app data
the curry mix to come to a boil , we chop
the money that both parties are pouring into this race ,
) ( Example : Your + 1 shield keeps
asked " to sign a nond is closure agreement before we
vulnerable position for Ferry to have left him .
BLACK FO OT T OC RE P ORTS 100 % EX
Duncan says . Pay your taxes . Pay your
LA X security line with Marilyn Manson ," the witness ,
its terminal maneuver and re orient itself . This maneuver would

MIN ACTIVATIONS
MIN = -19.377

AC LU _ OR ) May 29 , 2017
( IPS - type ) @ 144 Hz ( OD =
AC LU _ OR ) May 29 , 2017
( IPS - type ) @ 144 Hz ( Tr ace
c py In Memory 4 66 284 4 64 406 Mem
inches long and a cap 1 inch in diameter average .
( IPS - type ) @ 144 Hz ( Tr ace
AC LU _ OR ) May 29 , 2017
AC LU _ OR ) May 29 , 2017
And the Congress may by general Laws prescribe the Man ner
The Laz low Show 2008 01 12 O & A -
AC LU _ OR ) May 29 , 2017
. Number 1 I think for quite a while will always
Reading 55 80 953 16 27 145 Flat buff ers Reading
Naval Air Station in South We ym outh . This is
signature was not required at Cas ert a .[ 34 ]
Cycl iste FD J - Big Mat ) s . t
/ in coming / article 35 79 23 12 . e
[ return address ] | + -------------------- --+ + -------------------- --+
mobile devices . First published Dec . 1 ,

INTERVAL 9.497 - 19.121
CONTAINS 0.533%

years later , the relationship is still going strong at Aut
intersection of Bl oor St . W . and Mill Rd
in N . Eng l . J . Med ., Peter
states ". T rots ky ism isn
building in Liverpool , U . K ., to remove the

INTERVAL -0.128 - 9.497
CONTAINS 51.630%

to be a woman , and we re all
. The executions took place on Sunday November 3
then , to see the guy in our story make a
illegal settlements in Jerusalem , as if there are no consequences
failure . NASA Headquarters formed another board of inquiry to investigate

INTERVAL -9.753 - -0.128
CONTAINS 47.402%

which at 72 - stories is one of the largest office
found out about Josh s history , leading him
may also be in the pipeline as Raj oy
, pun ks were often objects of contempt . Due to
T ear V oid Ray J KS Le en ock L

INTERVAL -19.377 - -9.753
CONTAINS 0.435%

't have a place in our American story , because you
10 % of their worldwide annual turnover . The
h oub 2008 Charlie Sheen 2009 Alec Baldwin
based singer onstage at the First Avenue venue during her enc
[ Black E lo " 25 67 "] [ P ly
Token hold
Token ID1745
Feature activation-6.90e+00

Pos logit contributions
FU+2.982
iu+2.978
 reign+2.971
isphere+2.918
utic+2.893
Neg logit contributions
aturdays-2.142
irtual-1.963
onder-1.937
xxxx-1.909
lear-1.891
Token together
Token ID1978
Feature activation+4.96e+00

Pos logit contributions
onder+4.122
coat+3.985
xxxx+3.930
aturdays+3.911
lear+3.831
Neg logit contributions
isphere-5.255
FU-5.026
PN-5.007
iu-4.977
utic-4.972
Token.
Token ID13
Feature activation+4.90e+00

Pos logit contributions
iu+2.401
FU+2.370
PI+2.292
PN+2.292
isphere+2.261
Neg logit contributions
aturdays-4.559
irtual-4.347
 millenn-4.330
onder-4.190
lear-4.120
Token 4
Token ID604
Feature activation-1.40e+00

Pos logit contributions
isphere+3.049
FU+3.039
iu+3.021
PN+3.002
utic+2.940
Neg logit contributions
onder-3.521
aturdays-3.517
irtual-3.378
xxxx-3.363
ierra-3.332
Token.
Token ID13
Feature activation+9.27e+00

Pos logit contributions
onder+1.057
aturdays+1.053
xxxx+1.022
lear+1.019
irtual+1.017
Neg logit contributions
isphere-0.841
FU-0.819
iu-0.818
PN-0.809
utic-0.800
Token Make
Token ID6889
Feature activation+1.91e+01

Pos logit contributions
iu+5.357
FU+5.139
PI+5.138
lete+5.102
isphere+5.003
Neg logit contributions
aturdays-7.152
onder-6.968
irtual-6.805
ierra-6.797
xxxx-6.738
Token 6
Token ID718
Feature activation+4.98e+00

Pos logit contributions
iu+6.381
PI+6.076
 reign+5.959
 poaching+5.471
 KING+5.450
Neg logit contributions
aturdays-17.923
 millenn-17.392
irtual-17.240
retty-16.659
onder-16.628
Token p
Token ID279
Feature activation-5.42e+00

Pos logit contributions
iu+2.314
PN+2.298
PI+2.296
 reign+2.272
isphere+2.249
Neg logit contributions
aturdays-4.416
onder-4.352
irtual-4.338
lear-4.200
xxxx-4.191
Tokenatt
Token ID1078
Feature activation-1.51e+00

Pos logit contributions
onder+3.490
aturdays+3.335
lear+3.327
coat+3.277
xxxx+3.264
Neg logit contributions
isphere-3.883
FU-3.826
PN-3.732
iu-3.698
ILA-3.690
Tokenies
Token ID444
Feature activation+6.77e+00

Pos logit contributions
onder+1.267
aturdays+1.261
xxxx+1.229
lear+1.228
coat+1.222
Neg logit contributions
isphere-0.784
FU-0.768
iu-0.756
PN-0.754
utic-0.740
Token.
Token ID13
Feature activation+9.33e+00

Pos logit contributions
iu+3.102
FU+3.024
PI+2.973
PN+2.946
isphere+2.911
Neg logit contributions
aturdays-6.273
irtual-5.996
 millenn-5.898
onder-5.817
lear-5.744
Token c
Token ID269
Feature activation-1.44e+00

Pos logit contributions
iu+2.204
isphere+2.203
 reign+2.185
FU+2.107
PN+2.101
Neg logit contributions
aturdays-4.100
irtual-3.927
onder-3.860
lear-3.774
xxxx-3.728
Tokenv
Token ID85
Feature activation-1.18e+00

Pos logit contributions
aturdays+1.030
onder+1.027
irtual+0.991
xxxx+0.989
lear+0.988
Neg logit contributions
isphere-0.923
FU-0.905
iu-0.904
PN-0.894
utic-0.882
Token2
Token ID17
Feature activation+7.46e+00

Pos logit contributions
onder+1.051
aturdays+1.042
xxxx+1.023
lear+1.019
irtual+1.015
Neg logit contributions
isphere-0.545
FU-0.527
iu-0.525
PN-0.518
utic-0.510
Token.
Token ID764
Feature activation+4.31e+00

Pos logit contributions
iu+2.640
FU+2.502
PI+2.460
PN+2.420
 reign+2.345
Neg logit contributions
aturdays-7.956
 millenn-7.810
irtual-7.553
onder-7.211
retty-7.144
Token morphology
Token ID46320
Feature activation+5.84e+00

Pos logit contributions
isphere+2.150
FU+2.082
iu+2.080
PN+2.047
utic+2.040
Neg logit contributions
aturdays-3.700
onder-3.666
irtual-3.555
xxxx-3.543
coat-3.530
TokenEx
Token ID3109
Feature activation+1.87e+01

Pos logit contributions
FU+3.630
PN+3.481
PI+3.451
iu+3.407
isphere+3.355
Neg logit contributions
aturdays-4.567
irtual-4.334
onder-4.295
lear-4.256
uli-4.164
Token (
Token ID357
Feature activation+4.42e+00

Pos logit contributions
FU+3.412
PI+3.277
PN+3.212
iu+2.980
PH+2.718
Neg logit contributions
 millenn-23.105
aturdays-21.354
 challeng-21.159
irtual-20.018
retty-19.578
Token gray
Token ID12768
Feature activation+1.08e+01

Pos logit contributions
iu+3.449
isphere+3.438
FU+3.355
 reign+3.335
PN+3.310
Neg logit contributions
aturdays-2.636
irtual-2.485
onder-2.434
xxxx-2.315
lear-2.307
Token,
Token ID837
Feature activation+6.39e+00

Pos logit contributions
iu+4.102
FU+3.858
PI+3.842
PN+3.836
 reign+3.661
Neg logit contributions
 millenn-11.281
aturdays-11.099
irtual-10.413
retty-9.942
 challeng-9.931
Token c
Token ID269
Feature activation-1.97e+00

Pos logit contributions
 reign+2.935
isphere+2.924
iu+2.912
PN+2.814
FU+2.745
Neg logit contributions
aturdays-5.852
irtual-5.608
onder-5.476
lear-5.373
xxxx-5.280
Tokenv
Token ID85
Feature activation-1.02e+00

Pos logit contributions
onder+1.392
aturdays+1.385
xxxx+1.340
lear+1.339
irtual+1.336
Neg logit contributions
isphere-1.276
FU-1.250
iu-1.247
PN-1.236
utic-1.218
Token2
Token ID17
Feature activation+9.63e+00

Pos logit contributions
onder+0.411
aturdays+0.411
xxxx+0.399
irtual+0.399
lear+0.399
Neg logit contributions
isphere-0.207
FU-0.200
iu-0.200
PN-0.197
utic-0.194
Token.
Token ID764
Feature activation+6.90e+00

Pos logit contributions
iu+3.029
PI+2.833
FU+2.829
PN+2.734
 reign+2.625
Neg logit contributions
aturdays-10.664
 millenn-10.610
irtual-10.068
retty-9.581
onder-9.550
Token Ga
Token ID12822
Feature activation-4.18e+00

Pos logit contributions
isphere+4.059
iu+4.002
FU+3.959
utic+3.874
PN+3.831
Neg logit contributions
aturdays-5.283
onder-5.118
irtual-4.999
xxxx-4.927
lear-4.902
Tokenussian
Token ID31562
Feature activation+5.09e+00

Pos logit contributions
onder+0.847
aturdays+0.775
irtual+0.708
coat+0.702
xxxx+0.689
Neg logit contributions
isphere-4.819
FU-4.761
iu-4.744
PN-4.734
PI-4.688
TokenBl
Token ID3629
Feature activation+1.27e+00

Pos logit contributions
FU+2.663
PN+2.651
iu+2.619
PI+2.610
isphere+2.486
Neg logit contributions
aturdays-4.329
onder-4.179
irtual-4.105
lear-4.015
ierra-4.003
Tokenur
Token ID333
Feature activation+1.85e+01

Pos logit contributions
iu+0.687
isphere+0.686
FU+0.678
utic+0.665
PN+0.659
Neg logit contributions
aturdays-1.051
onder-1.015
irtual-1.003
xxxx-0.996
lear-0.991
Token (
Token ID357
Feature activation+3.88e+00

Pos logit contributions
FU+3.550
PN+3.413
PI+3.358
iu+3.092
PH+2.733
Neg logit contributions
 millenn-22.102
aturdays-20.866
 challeng-20.393
irtual-19.782
retty-19.277
Token gray
Token ID12768
Feature activation+8.25e+00

Pos logit contributions
isphere+3.065
iu+3.049
FU+2.999
PN+2.951
 reign+2.949
Neg logit contributions
aturdays-2.255
irtual-2.125
onder-2.108
xxxx-2.016
coat-1.999
Token,
Token ID837
Feature activation+7.72e+00

Pos logit contributions
iu+3.470
FU+3.335
PI+3.299
PN+3.244
isphere+3.153
Neg logit contributions
aturdays-8.037
 millenn-7.909
irtual-7.554
onder-7.255
retty-7.194
Token (
Token ID357
Feature activation-4.69e+00

Pos logit contributions
iu+2.689
 reign+2.679
isphere+2.632
PN+2.582
PI+2.563
Neg logit contributions
aturdays-7.850
irtual-7.556
onder-7.331
lear-7.259
retty-7.193
Token 3
Token ID513
Feature activation+3.76e+00

Pos logit contributions
onder+2.568
aturdays+2.462
xxxx+2.407
lear+2.407
coat+2.388
Neg logit contributions
isphere-3.793
iu-3.706
FU-3.705
PN-3.646
utic-3.639
Token
Token ID447
Feature activation+8.39e-01

Pos logit contributions
isphere+0.006
FU+0.006
iu+0.006
PN+0.005
utic+0.005
Neg logit contributions
aturdays-0.007
onder-0.007
irtual-0.007
lear-0.007
xxxx-0.007
Token
Token ID247
Feature activation-3.92e+00

Pos logit contributions
isphere+0.210
FU+0.199
iu+0.199
PN+0.193
utic+0.186
Neg logit contributions
aturdays-0.928
onder-0.927
irtual-0.906
xxxx-0.905
lear-0.905
Tokens
Token ID82
Feature activation-4.28e-01

Pos logit contributions
onder+2.682
aturdays+2.670
xxxx+2.641
lear+2.591
coat+2.591
Neg logit contributions
isphere-2.575
FU-2.526
PN-2.514
iu-2.485
utic-2.442
Token protests
Token ID8536
Feature activation-2.13e+00

Pos logit contributions
aturdays+0.314
onder+0.313
xxxx+0.302
irtual+0.302
lear+0.302
Neg logit contributions
isphere-0.266
FU-0.261
iu-0.260
PN-0.258
utic-0.254
Token with
Token ID351
Feature activation+6.31e+00

Pos logit contributions
onder+1.466
aturdays+1.442
lear+1.395
xxxx+1.394
coat+1.390
Neg logit contributions
isphere-1.432
FU-1.410
PN-1.394
iu-1.382
utic-1.368
Token relative
Token ID3585
Feature activation+1.82e+01

Pos logit contributions
isphere+3.737
iu+3.701
 reign+3.671
FU+3.663
utic+3.647
Neg logit contributions
aturdays-4.698
onder-4.565
irtual-4.541
xxxx-4.479
lear-4.439
Token len
Token ID18896
Feature activation+4.18e+00

Pos logit contributions
 reign+8.872
 cal+8.241
iu+8.082
utic+7.898
FU+7.830
Neg logit contributions
aturdays-13.670
irtual-13.594
覚醒-13.239
ortium-13.206
xxxx-13.089
Tokeniency
Token ID6160
Feature activation+4.10e+00

Pos logit contributions
iu+1.963
isphere+1.958
utic+1.851
FU+1.828
PN+1.815
Neg logit contributions
aturdays-3.759
onder-3.645
irtual-3.594
xxxx-3.553
lear-3.549
Token.
Token ID13
Feature activation-2.85e+00

Pos logit contributions
isphere+2.300
iu+2.287
FU+2.255
PN+2.219
utic+2.204
Neg logit contributions
aturdays-3.233
onder-3.162
irtual-3.110
lear-3.093
xxxx-3.092
Token Although
Token ID4900
Feature activation-1.90e+00

Pos logit contributions
onder+1.817
aturdays+1.789
xxxx+1.767
coat+1.753
lear+1.725
Neg logit contributions
isphere-2.056
FU-1.971
iu-1.961
PN-1.947
utic-1.942
Token tear
Token ID11626
Feature activation-8.90e+00

Pos logit contributions
aturdays+1.273
onder+1.266
xxxx+1.220
coat+1.218
lear+1.214
Neg logit contributions
isphere-1.295
FU-1.270
iu-1.258
PN-1.254
utic-1.247
Token c
Token ID269
Feature activation+1.39e+00

Pos logit contributions
isphere+1.070
iu+1.053
FU+1.031
PN+1.026
utic+1.017
Neg logit contributions
aturdays-1.604
onder-1.563
irtual-1.538
lear-1.516
xxxx-1.511
Tokenv
Token ID85
Feature activation-1.58e+00

Pos logit contributions
isphere+0.831
iu+0.828
FU+0.812
utic+0.802
PN+0.798
Neg logit contributions
aturdays-1.085
onder-1.038
irtual-1.030
xxxx-1.008
lear-1.008
Token2
Token ID17
Feature activation+7.46e+00

Pos logit contributions
onder+1.385
aturdays+1.358
xxxx+1.354
lear+1.344
coat+1.338
Neg logit contributions
isphere-0.761
FU-0.731
iu-0.725
PN-0.718
utic-0.713
Token.
Token ID764
Feature activation+6.27e+00

Pos logit contributions
iu+2.656
PI+2.503
FU+2.500
PN+2.451
 reign+2.363
Neg logit contributions
aturdays-7.844
 millenn-7.573
irtual-7.415
onder-7.223
retty-7.121
Token im
Token ID545
Feature activation+9.40e-01

Pos logit contributions
isphere+3.346
iu+3.282
FU+3.124
 reign+3.084
utic+3.064
Neg logit contributions
aturdays-5.240
onder-5.107
irtual-5.004
coat-4.974
xxxx-4.969
Tokenread
Token ID961
Feature activation+1.78e+01

Pos logit contributions
isphere+0.382
iu+0.372
FU+0.369
utic+0.354
PN+0.354
Neg logit contributions
aturdays-0.903
onder-0.887
irtual-0.870
xxxx-0.863
coat-0.861
Token (
Token ID357
Feature activation+8.39e+00

Pos logit contributions
PI+3.197
FU+3.162
iu+2.984
PN+2.969
 reign+2.756
Neg logit contributions
 millenn-20.892
aturdays-19.784
 challeng-18.781
irtual-18.626
retty-18.481
Token image
Token ID2939
Feature activation+2.98e-01

Pos logit contributions
iu+4.297
isphere+4.172
 reign+4.076
PI+4.029
utic+3.967
Neg logit contributions
aturdays-7.296
irtual-6.856
onder-6.735
retty-6.611
coat-6.600
TokenPath
Token ID15235
Feature activation+6.88e+00

Pos logit contributions
isphere+0.179
FU+0.175
iu+0.175
PN+0.173
utic+0.171
Neg logit contributions
aturdays-0.227
onder-0.225
irtual-0.218
lear-0.217
xxxx-0.217
Token )
Token ID1267
Feature activation+7.37e+00

Pos logit contributions
iu+3.164
FU+3.081
PI+3.064
PN+3.024
 reign+2.896
Neg logit contributions
aturdays-6.403
 millenn-6.129
irtual-6.120
onder-5.950
lear-5.796
Token image
Token ID2939
Feature activation+3.30e+00

Pos logit contributions
iu+3.948
isphere+3.784
 reign+3.745
PI+3.682
PN+3.632
Neg logit contributions
aturdays-6.236
irtual-5.905
onder-5.821
lear-5.695
xxxx-5.627
Token Year
Token ID6280
Feature activation-2.15e+00

Pos logit contributions
isphere+1.975
iu+1.964
FU+1.941
PN+1.924
utic+1.886
Neg logit contributions
aturdays-3.932
onder-3.860
irtual-3.816
lear-3.757
xxxx-3.737
Token for
Token ID329
Feature activation-4.66e+00

Pos logit contributions
aturdays+1.502
onder+1.497
irtual+1.445
coat+1.443
lear+1.440
Neg logit contributions
isphere-1.406
FU-1.382
iu-1.379
utic-1.351
PN-1.351
Token the
Token ID262
Feature activation-2.40e+00

Pos logit contributions
onder+2.954
aturdays+2.914
coat+2.864
xxxx+2.844
lear+2.830
Neg logit contributions
isphere-3.356
FU-3.217
PN-3.167
iu-3.158
utic-3.138
Token second
Token ID1218
Feature activation+4.23e+00

Pos logit contributions
aturdays+1.650
onder+1.648
xxxx+1.591
irtual+1.586
coat+1.585
Neg logit contributions
isphere-1.608
FU-1.552
iu-1.544
PN-1.537
utic-1.515
Token year
Token ID614
Feature activation+7.18e+00

Pos logit contributions
isphere+2.419
iu+2.412
FU+2.395
PN+2.363
PI+2.314
Neg logit contributions
aturdays-3.272
onder-3.264
lear-3.156
irtual-3.155
xxxx-3.143
Token in
Token ID287
Feature activation+1.77e+01

Pos logit contributions
iu+4.348
isphere+4.336
 reign+4.237
PN+4.216
FU+4.206
Neg logit contributions
aturdays-5.233
onder-5.146
irtual-4.961
lear-4.958
xxxx-4.903
Token a
Token ID257
Feature activation+9.43e+00

Pos logit contributions
 reign+7.964
iu+7.620
lete+7.555
FU+7.302
 KING+7.285
Neg logit contributions
aturdays-14.089
onder-13.585
irtual-13.213
coat-13.179
xxxx-13.178
Token row
Token ID5752
Feature activation+5.06e+00

Pos logit contributions
iu+4.827
FU+4.696
PN+4.687
 reign+4.650
PI+4.573
Neg logit contributions
aturdays-7.816
onder-7.656
irtual-7.477
coat-7.424
lear-7.383
Token.
Token ID13
Feature activation+3.18e+00

Pos logit contributions
isphere+2.877
iu+2.826
FU+2.805
PN+2.768
PI+2.728
Neg logit contributions
aturdays-3.931
onder-3.900
irtual-3.794
xxxx-3.786
lear-3.783
Token Thursday
Token ID3635
Feature activation+8.23e-01

Pos logit contributions
FU+2.068
isphere+2.068
iu+2.061
PN+2.048
PI+2.007
Neg logit contributions
aturdays-2.236
onder-2.197
irtual-2.159
lear-2.132
xxxx-2.108
Token night
Token ID1755
Feature activation+3.47e+00

Pos logit contributions
isphere+0.500
FU+0.489
iu+0.488
PN+0.482
utic+0.476
Neg logit contributions
aturdays-0.617
onder-0.616
irtual-0.595
xxxx-0.594
lear-0.594
Token (
Token ID357
Feature activation-6.95e-01

Pos logit contributions
isphere+2.685
iu+2.595
FU+2.590
PN+2.567
utic+2.554
Neg logit contributions
aturdays-5.368
onder-5.293
irtual-5.198
xxxx-5.159
lear-5.144
Tokenplace
Token ID5372
Feature activation+4.20e+00

Pos logit contributions
onder+0.512
aturdays+0.508
lear+0.498
coat+0.496
xxxx+0.493
Neg logit contributions
isphere-0.429
iu-0.418
FU-0.418
utic-0.411
PN-0.411
Token versus
Token ID9051
Feature activation+1.67e+00

Pos logit contributions
isphere+2.123
iu+2.062
FU+2.052
PN+2.033
utic+1.997
Neg logit contributions
aturdays-3.567
onder-3.536
xxxx-3.460
irtual-3.457
lear-3.438
Token direction
Token ID4571
Feature activation+2.00e+00

Pos logit contributions
isphere+0.920
FU+0.899
iu+0.898
PN+0.887
utic+0.873
Neg logit contributions
aturdays-1.343
onder-1.340
irtual-1.298
xxxx-1.297
lear-1.296
Token),
Token ID828
Feature activation+9.01e+00

Pos logit contributions
isphere+1.288
FU+1.259
iu+1.259
PN+1.245
utic+1.229
Neg logit contributions
aturdays-1.435
onder-1.428
irtual-1.381
xxxx-1.379
lear-1.377
Token (
Token ID357
Feature activation+1.75e+01

Pos logit contributions
isphere+4.308
PN+4.290
iu+4.272
FU+4.188
utic+4.155
Neg logit contributions
aturdays-7.481
onder-7.437
irtual-7.306
lear-7.242
xxxx-7.224
TokenH
Token ID39
Feature activation+4.95e+00

Pos logit contributions
FU+6.898
PN+6.579
iu+6.241
PI+6.084
GP+5.854
Neg logit contributions
aturdays-16.054
irtual-15.888
onder-15.408
ierra-15.136
ortium-14.865
Token)
Token ID8
Feature activation+5.23e+00

Pos logit contributions
iu+3.094
PN+3.058
FU+3.044
isphere+3.034
PI+2.989
Neg logit contributions
aturdays-3.698
irtual-3.554
onder-3.523
lear-3.430
xxxx-3.368
Token Type
Token ID5994
Feature activation-4.01e+00

Pos logit contributions
isphere+3.273
iu+3.230
PN+3.216
FU+3.205
PI+3.152
Neg logit contributions
aturdays-3.788
onder-3.724
irtual-3.641
xxxx-3.605
lear-3.588
Token 4
Token ID604
Feature activation-1.90e+00

Pos logit contributions
onder+2.410
aturdays+2.394
coat+2.356
lear+2.354
xxxx+2.321
Neg logit contributions
isphere-2.959
FU-2.879
iu-2.873
PN-2.813
utic-2.811
Token probe
Token ID12774
Feature activation-1.27e+00

Pos logit contributions
onder+1.243
aturdays+1.210
lear+1.182
xxxx+1.179
coat+1.174
Neg logit contributions
isphere-1.345
FU-1.314
iu-1.313
utic-1.285
PN-1.283
TokenUM
Token ID5883
Feature activation+4.57e+00

Pos logit contributions
FU+3.174
iu+3.135
PN+3.116
PI+3.113
isphere+3.084
Neg logit contributions
aturdays-5.033
onder-4.994
irtual-4.914
lear-4.803
coat-4.794
Token T
Token ID309
Feature activation+1.05e+01

Pos logit contributions
FU+2.395
isphere+2.367
PN+2.355
iu+2.350
PI+2.338
Neg logit contributions
aturdays-3.810
onder-3.762
irtual-3.678
lear-3.625
coat-3.613
Token ER
Token ID13793
Feature activation-1.25e-01

Pos logit contributions
FU+4.927
PN+4.908
PI+4.863
iu+4.862
 KING+4.779
Neg logit contributions
aturdays-8.893
onder-8.608
lear-8.466
irtual-8.455
coat-8.427
TokenTI
Token ID25621
Feature activation+9.14e+00

Pos logit contributions
onder+0.092
aturdays+0.092
xxxx+0.089
irtual+0.089
lear+0.089
Neg logit contributions
isphere-0.077
iu-0.075
FU-0.075
PN-0.074
utic-0.073
Token
Token ID127
Feature activation+8.86e+00

Pos logit contributions
FU+4.762
PI+4.702
PN+4.686
iu+4.586
 KING+4.408
Neg logit contributions
aturdays-7.598
onder-7.378
irtual-7.234
lear-7.173
coat-7.106
Token
Token ID228
Feature activation+1.68e+01

Pos logit contributions
PN+3.943
FU+3.929
iu+3.871
ILA+3.860
PI+3.835
Neg logit contributions
aturdays-7.949
onder-7.897
irtual-7.624
lear-7.456
coat-7.433
Token P
Token ID350
Feature activation+4.00e+00

Pos logit contributions
PI+7.922
PN+7.685
FU+7.609
 KING+7.256
iu+7.016
Neg logit contributions
aturdays-14.012
irtual-13.450
onder-13.212
ierra-13.088
lear-12.851
Token ART
Token ID24278
Feature activation+1.15e+00

Pos logit contributions
isphere+1.915
FU+1.906
iu+1.884
PN+1.873
PI+1.844
Neg logit contributions
aturdays-3.494
onder-3.449
irtual-3.373
lear-3.352
coat-3.348
TokenIS
Token ID1797
Feature activation+3.51e+00

Pos logit contributions
isphere+0.479
FU+0.462
iu+0.462
PN+0.454
utic+0.446
Neg logit contributions
aturdays-1.080
onder-1.080
xxxx-1.051
irtual-1.050
lear-1.049
Token.
Token ID764
Feature activation+1.12e-01

Pos logit contributions
FU+1.661
isphere+1.656
iu+1.649
PN+1.635
PI+1.603
Neg logit contributions
aturdays-3.085
onder-3.059
irtual-2.980
lear-2.967
xxxx-2.953
Token
Token ID198
Feature activation+3.52e+00

Pos logit contributions
isphere+0.083
FU+0.081
iu+0.081
PN+0.080
utic+0.079
Neg logit contributions
onder-0.069
aturdays-0.069
xxxx-0.067
lear-0.066
irtual-0.066
Token S
Token ID311
Feature activation+4.00e+00

Pos logit contributions
FU+4.293
PN+4.182
iu+4.179
PI+4.128
utic+4.083
Neg logit contributions
aturdays-6.210
onder-6.084
irtual-5.927
lear-5.927
coat-5.871
Token EC
Token ID13182
Feature activation-8.70e-01

Pos logit contributions
isphere+2.040
FU+2.033
iu+2.019
PN+2.000
PI+1.965
Neg logit contributions
aturdays-3.372
onder-3.330
irtual-3.263
lear-3.243
coat-3.220
TokenUN
Token ID4944
Feature activation+7.02e+00

Pos logit contributions
onder+0.686
aturdays+0.678
xxxx+0.667
lear+0.661
irtual+0.659
Neg logit contributions
isphere-0.501
iu-0.476
FU-0.470
utic-0.469
PN-0.464
TokenD
Token ID35
Feature activation+3.97e+00

Pos logit contributions
FU+3.214
PN+3.154
PI+3.085
iu+3.050
isphere+3.018
Neg logit contributions
aturdays-6.360
onder-6.227
irtual-6.137
lear-6.013
coat-5.995
Token
Token ID127
Feature activation+8.14e+00

Pos logit contributions
FU+1.515
iu+1.508
isphere+1.502
PN+1.483
PI+1.445
Neg logit contributions
aturdays-3.846
onder-3.816
irtual-3.741
lear-3.717
coat-3.706
Token
Token ID228
Feature activation+1.67e+01

Pos logit contributions
FU+3.681
PN+3.651
iu+3.630
ILA+3.563
PI+3.539
Neg logit contributions
aturdays-7.224
onder-7.170
irtual-6.937
lear-6.816
coat-6.798
Token P
Token ID350
Feature activation+6.77e+00

Pos logit contributions
PI+8.260
FU+8.081
PN+8.043
 KING+7.767
iu+7.431
Neg logit contributions
aturdays-13.437
irtual-12.869
onder-12.692
ierra-12.503
lear-12.315
Token ART
Token ID24278
Feature activation-1.48e+00

Pos logit contributions
FU+3.350
PN+3.280
PI+3.272
iu+3.272
isphere+3.268
Neg logit contributions
aturdays-5.804
onder-5.661
irtual-5.572
coat-5.510
lear-5.505
TokenIS
Token ID1797
Feature activation+3.69e+00

Pos logit contributions
onder+1.333
aturdays+1.322
xxxx+1.306
lear+1.294
irtual+1.291
Neg logit contributions
isphere-0.662
FU-0.629
iu-0.628
utic-0.623
PN-0.614
Token.
Token ID764
Feature activation+8.78e-01

Pos logit contributions
FU+1.808
isphere+1.794
iu+1.790
PN+1.783
PI+1.749
Neg logit contributions
aturdays-3.190
onder-3.159
irtual-3.080
lear-3.062
coat-3.041
Token
Token ID198
Feature activation+3.24e+00

Pos logit contributions
isphere+0.637
FU+0.624
iu+0.624
PN+0.618
utic+0.610
Neg logit contributions
aturdays-0.555
onder-0.554
xxxx-0.532
irtual-0.531
lear-0.531
Token ethics
Token ID14458
Feature activation+3.17e+00

Pos logit contributions
onder+0.839
aturdays+0.834
lear+0.805
coat+0.804
xxxx+0.803
Neg logit contributions
isphere-0.900
FU-0.886
iu-0.876
PN-0.874
utic-0.869
Token (
Token ID357
Feature activation+4.10e-01

Pos logit contributions
isphere+2.262
iu+2.235
FU+2.212
PN+2.198
utic+2.163
Neg logit contributions
aturdays-2.048
onder-2.012
irtual-1.969
xxxx-1.955
lear-1.944
Tokenand
Token ID392
Feature activation+2.06e+00

Pos logit contributions
isphere+0.263
FU+0.257
iu+0.256
PN+0.253
utic+0.252
Neg logit contributions
onder-0.293
aturdays-0.292
lear-0.283
xxxx-0.282
irtual-0.282
Token campaign
Token ID1923
Feature activation+2.47e+00

Pos logit contributions
isphere+1.364
iu+1.333
FU+1.329
PN+1.316
utic+1.300
Neg logit contributions
aturdays-1.439
onder-1.427
irtual-1.381
xxxx-1.381
lear-1.378
Token-
Token ID12
Feature activation+3.75e+00

Pos logit contributions
isphere+1.364
FU+1.334
iu+1.332
PN+1.313
utic+1.297
Neg logit contributions
aturdays-1.997
onder-1.976
irtual-1.925
xxxx-1.922
lear-1.919
Tokenf
Token ID69
Feature activation+1.67e+01

Pos logit contributions
isphere+1.897
FU+1.885
iu+1.873
PN+1.842
PI+1.815
Neg logit contributions
aturdays-3.188
onder-3.134
irtual-3.059
xxxx-3.050
lear-3.027
Tokeninance
Token ID14149
Feature activation+7.04e+00

Pos logit contributions
iu+3.696
lete+3.580
isphere+3.355
angle+3.269
resp+3.219
Neg logit contributions
aturdays-17.084
 millenn-17.007
irtual-16.865
覚醒-16.718
xxxx-16.107
Token)
Token ID8
Feature activation+1.12e+00

Pos logit contributions
isphere+4.435
iu+4.382
FU+4.338
 reign+4.312
utic+4.256
Neg logit contributions
aturdays-5.006
onder-4.873
lear-4.783
irtual-4.776
xxxx-4.771
Token tra
Token ID1291
Feature activation+1.57e+00

Pos logit contributions
isphere+0.843
FU+0.828
iu+0.828
PN+0.820
utic+0.811
Neg logit contributions
aturdays-0.672
onder-0.670
irtual-0.642
xxxx-0.641
lear-0.641
Tokenvest
Token ID4223
Feature activation+7.74e+00

Pos logit contributions
isphere+1.035
iu+1.015
FU+1.004
PN+0.995
utic+0.988
Neg logit contributions
aturdays-1.106
onder-1.094
irtual-1.061
xxxx-1.057
lear-1.053
Tokeny
Token ID88
Feature activation-5.62e-01

Pos logit contributions
iu+4.147
utic+3.902
isphere+3.815
lete+3.672
FU+3.656
Neg logit contributions
aturdays-6.517
onder-6.281
irtual-6.191
 millenn-6.071
coat-6.012
Token }
Token ID1782
Feature activation+1.42e+00

Pos logit contributions
onder+3.377
aturdays+3.359
xxxx+3.302
irtual+3.288
lear+3.239
Neg logit contributions
isphere-3.601
FU-3.528
PN-3.497
iu-3.472
utic-3.458
Token 1
Token ID352
Feature activation+6.88e-01

Pos logit contributions
isphere+1.020
FU+1.001
iu+1.001
PN+0.991
utic+0.979
Neg logit contributions
aturdays-0.908
onder-0.906
irtual-0.870
xxxx-0.869
lear-0.868
Token 2
Token ID362
Feature activation-1.22e+00

Pos logit contributions
isphere+0.480
FU+0.468
iu+0.467
PN+0.462
utic+0.460
Neg logit contributions
onder-0.457
aturdays-0.453
xxxx-0.438
lear-0.437
irtual-0.437
Token 3
Token ID513
Feature activation+2.23e+00

Pos logit contributions
aturdays+0.717
onder+0.713
xxxx+0.684
irtual+0.683
lear+0.677
Neg logit contributions
isphere-0.942
FU-0.927
iu-0.925
PN-0.915
utic-0.910
Token void
Token ID7951
Feature activation+1.91e-01

Pos logit contributions
isphere+1.558
FU+1.529
iu+1.527
PN+1.512
utic+1.494
Neg logit contributions
aturdays-1.468
onder-1.463
irtual-1.408
xxxx-1.406
lear-1.405
Token vert
Token ID9421
Feature activation+1.67e+01

Pos logit contributions
isphere+0.112
FU+0.110
iu+0.110
PN+0.108
utic+0.107
Neg logit contributions
aturdays-0.147
onder-0.147
irtual-0.142
xxxx-0.142
lear-0.142
Token (
Token ID357
Feature activation+8.78e-01

Pos logit contributions
iu+3.942
PN+3.683
FU+3.668
PI+3.625
 reign+3.594
Neg logit contributions
aturdays-16.894
 millenn-16.710
onder-16.013
irtual-15.896
retty-15.843
Token in
Token ID287
Feature activation-2.06e+00

Pos logit contributions
isphere+0.568
iu+0.556
FU+0.556
PN+0.549
utic+0.542
Neg logit contributions
aturdays-0.625
onder-0.623
irtual-0.601
lear-0.600
xxxx-0.600
Tokenout
Token ID448
Feature activation+5.35e+00

Pos logit contributions
onder+0.818
aturdays+0.785
xxxx+0.759
irtual+0.750
lear+0.749
Neg logit contributions
isphere-1.980
FU-1.967
PN-1.951
iu-1.947
utic-1.922
Token app
Token ID598
Feature activation-8.46e+00

Pos logit contributions
isphere+2.731
iu+2.729
 reign+2.674
PN+2.636
FU+2.618
Neg logit contributions
aturdays-4.565
irtual-4.364
onder-4.308
uli-4.215
ierra-4.211
Tokendata
Token ID7890
Feature activation+7.64e-01

Pos logit contributions
onder+3.900
xxxx+3.887
lear+3.779
coat+3.504
uli+3.478
Neg logit contributions
FU-7.319
PN-7.253
ILA-7.179
 KING-7.149
isphere-7.135
Token the
Token ID262
Feature activation+7.28e+00

Pos logit contributions
isphere+1.075
FU+1.055
iu+1.054
PN+1.044
utic+1.032
Neg logit contributions
aturdays-0.979
onder-0.977
irtual-0.939
xxxx-0.937
lear-0.936
Token curry
Token ID34611
Feature activation+8.88e+00

Pos logit contributions
iu+4.918
 reign+4.841
isphere+4.832
FU+4.815
PN+4.794
Neg logit contributions
aturdays-4.685
onder-4.632
irtual-4.562
lear-4.502
ierra-4.455
Token mix
Token ID5022
Feature activation+4.16e+00

Pos logit contributions
isphere+4.697
iu+4.683
PN+4.640
FU+4.614
PI+4.605
Neg logit contributions
aturdays-7.113
irtual-6.878
onder-6.864
lear-6.786
ierra-6.692
Token to
Token ID284
Feature activation+4.89e+00

Pos logit contributions
isphere+2.514
iu+2.482
FU+2.461
PN+2.427
PI+2.390
Neg logit contributions
aturdays-3.121
onder-3.075
irtual-2.999
lear-2.990
xxxx-2.982
Token come
Token ID1282
Feature activation+1.25e+01

Pos logit contributions
FU+3.100
isphere+3.085
iu+3.081
 reign+3.013
PI+2.991
Neg logit contributions
aturdays-3.511
onder-3.386
lear-3.321
irtual-3.303
xxxx-3.295
Token to
Token ID284
Feature activation+1.66e+01

Pos logit contributions
iu+7.024
isphere+6.921
lete+6.854
 reign+6.831
FU+6.691
Neg logit contributions
aturdays-9.140
onder-8.722
ierra-8.721
lear-8.695
irtual-8.687
Token a
Token ID257
Feature activation+1.30e+01

Pos logit contributions
iu+8.247
lete+8.139
PN+8.120
FU+8.101
 reign+8.012
Neg logit contributions
aturdays-12.649
lear-11.680
xxxx-11.589
ierra-11.551
onder-11.487
Token boil
Token ID20667
Feature activation-2.43e+00

Pos logit contributions
iu+6.089
PI+6.012
PN+5.986
 reign+5.862
lete+5.806
Neg logit contributions
aturdays-10.912
onder-9.965
ierra-9.892
lear-9.879
irtual-9.822
Token,
Token ID11
Feature activation-2.94e+00

Pos logit contributions
onder+1.618
aturdays+1.578
coat+1.571
irtual+1.541
xxxx+1.528
Neg logit contributions
isphere-1.693
PN-1.643
utic-1.636
iu-1.628
FU-1.627
Token we
Token ID356
Feature activation-3.74e+00

Pos logit contributions
onder+1.941
aturdays+1.912
coat+1.891
irtual+1.861
xxxx+1.857
Neg logit contributions
isphere-2.046
PN-1.986
iu-1.971
utic-1.970
FU-1.966
Token chop
Token ID30506
Feature activation+2.28e+00

Pos logit contributions
onder+2.498
coat+2.395
aturdays+2.389
uli+2.345
irtual+2.342
Neg logit contributions
isphere-2.606
PN-2.538
utic-2.514
FU-2.505
iu-2.482
Token the
Token ID262
Feature activation-5.23e+00

Pos logit contributions
onder+1.613
aturdays+1.596
coat+1.553
irtual+1.545
xxxx+1.532
Neg logit contributions
isphere-1.640
FU-1.615
iu-1.598
utic-1.584
PN-1.583
Token money
Token ID1637
Feature activation+6.70e+00

Pos logit contributions
onder+3.462
aturdays+3.377
coat+3.329
lear+3.264
xxxx+3.259
Neg logit contributions
FU-3.524
isphere-3.505
iu-3.477
utic-3.411
PN-3.402
Token that
Token ID326
Feature activation+4.90e+00

Pos logit contributions
isphere+4.144
iu+4.076
FU+4.054
PN+4.030
PI+3.952
Neg logit contributions
aturdays-4.910
irtual-4.706
onder-4.686
xxxx-4.616
lear-4.580
Token both
Token ID1111
Feature activation+7.84e+00

Pos logit contributions
isphere+3.000
iu+2.944
FU+2.906
PN+2.886
 reign+2.847
Neg logit contributions
aturdays-3.655
onder-3.571
irtual-3.509
xxxx-3.491
lear-3.467
Token parties
Token ID4671
Feature activation+8.32e+00

Pos logit contributions
isphere+4.619
iu+4.548
PN+4.498
FU+4.444
 reign+4.364
Neg logit contributions
aturdays-5.881
onder-5.714
irtual-5.691
xxxx-5.673
lear-5.624
Token are
Token ID389
Feature activation+1.65e+01

Pos logit contributions
isphere+4.752
 reign+4.709
iu+4.637
FU+4.615
PN+4.544
Neg logit contributions
aturdays-6.434
irtual-6.211
xxxx-6.121
onder-6.061
lear-6.021
Token pouring
Token ID23147
Feature activation+3.99e+00

Pos logit contributions
 reign+8.796
 poaching+8.460
lete+8.111
iu+8.099
PN+7.932
Neg logit contributions
aturdays-12.578
irtual-12.209
xxxx-11.782
onder-11.687
lear-11.640
Token into
Token ID656
Feature activation+6.14e-01

Pos logit contributions
isphere+2.332
iu+2.298
FU+2.274
PN+2.250
utic+2.214
Neg logit contributions
aturdays-3.075
onder-3.048
irtual-2.973
lear-2.973
xxxx-2.948
Token this
Token ID428
Feature activation-3.52e+00

Pos logit contributions
isphere+0.417
FU+0.409
iu+0.408
PN+0.404
utic+0.399
Neg logit contributions
aturdays-0.417
onder-0.416
irtual-0.400
xxxx-0.400
lear-0.400
Token race
Token ID3234
Feature activation+4.29e-01

Pos logit contributions
onder+2.260
aturdays+2.217
coat+2.165
lear+2.150
xxxx+2.136
Neg logit contributions
isphere-2.429
FU-2.406
iu-2.392
utic-2.387
PN-2.386
Token,
Token ID11
Feature activation+3.74e+00

Pos logit contributions
isphere+0.264
FU+0.258
iu+0.258
PN+0.255
utic+0.252
Neg logit contributions
onder-0.318
aturdays-0.317
xxxx-0.306
irtual-0.306
lear-0.306
Token )
Token ID1267
Feature activation+4.48e+00

Pos logit contributions
isphere+3.024
iu+2.984
FU+2.966
PN+2.965
PI+2.911
Neg logit contributions
aturdays-3.230
onder-3.165
irtual-3.058
lear-3.056
xxxx-3.048
Token
Token ID198
Feature activation+2.35e+00

Pos logit contributions
isphere+2.890
FU+2.856
iu+2.853
PN+2.832
PI+2.783
Neg logit contributions
aturdays-3.150
onder-3.122
irtual-3.004
lear-2.989
xxxx-2.976
Token
Token ID198
Feature activation+5.98e+00

Pos logit contributions
iu+1.517
FU+1.516
PN+1.510
PI+1.490
isphere+1.474
Neg logit contributions
aturdays-1.756
irtual-1.669
onder-1.640
lear-1.592
 millenn-1.572
Token(
Token ID7
Feature activation+1.63e+00

Pos logit contributions
FU+3.497
PN+3.476
isphere+3.475
iu+3.475
PI+3.399
Neg logit contributions
aturdays-4.532
onder-4.472
irtual-4.360
xxxx-4.276
lear-4.260
TokenExample
Token ID16281
Feature activation+1.79e+00

Pos logit contributions
isphere+1.106
FU+1.085
iu+1.084
PN+1.073
utic+1.060
Neg logit contributions
aturdays-1.109
onder-1.107
irtual-1.066
xxxx-1.064
lear-1.063
Token:
Token ID25
Feature activation+1.64e+01

Pos logit contributions
iu+0.919
FU+0.915
isphere+0.913
PN+0.907
PI+0.884
Neg logit contributions
aturdays-1.539
onder-1.487
irtual-1.482
lear-1.446
xxxx-1.420
Token Your
Token ID3406
Feature activation+9.71e+00

Pos logit contributions
utic+7.294
PN+7.110
iu+7.032
PI+6.892
 KING+6.880
Neg logit contributions
aturdays-13.324
onder-13.229
ierra-12.390
irtual-12.360
coat-12.338
Token +
Token ID1343
Feature activation+2.98e+00

Pos logit contributions
iu+4.536
PI+4.389
 reign+4.378
PN+4.309
utic+4.308
Neg logit contributions
aturdays-8.286
onder-8.106
irtual-7.907
lear-7.752
ierra-7.711
Token1
Token ID16
Feature activation+6.24e+00

Pos logit contributions
iu+1.423
FU+1.406
PN+1.381
isphere+1.377
PI+1.374
Neg logit contributions
aturdays-2.699
onder-2.589
irtual-2.586
lear-2.522
ierra-2.489
Token shield
Token ID7614
Feature activation+8.16e+00

Pos logit contributions
iu+3.795
isphere+3.679
 reign+3.660
FU+3.654
PN+3.616
Neg logit contributions
aturdays-4.852
irtual-4.572
onder-4.567
lear-4.307
xxxx-4.270
Token keeps
Token ID7622
Feature activation+6.70e-01

Pos logit contributions
 reign+3.035
FU+2.785
iu+2.754
isphere+2.702
 KING+2.689
Neg logit contributions
aturdays-8.015
onder-7.868
irtual-7.696
xxxx-7.606
lear-7.557
Token asked
Token ID1965
Feature activation-4.87e+00

Pos logit contributions
isphere+0.336
iu+0.330
FU+0.330
PN+0.327
utic+0.324
Neg logit contributions
aturdays-0.247
onder-0.246
irtual-0.235
xxxx-0.235
lear-0.234
Token "
Token ID366
Feature activation-3.08e+00

Pos logit contributions
onder+2.887
aturdays+2.795
coat+2.732
xxxx+2.729
lear+2.720
Neg logit contributions
FU-3.566
isphere-3.556
PN-3.529
iu-3.490
utic-3.477
Tokento
Token ID1462
Feature activation-3.36e+00

Pos logit contributions
onder+2.127
aturdays+2.095
lear+2.057
xxxx+2.055
coat+2.047
Neg logit contributions
isphere-2.021
FU-1.963
iu-1.959
utic-1.959
PN-1.944
Token sign
Token ID1051
Feature activation-6.36e-02

Pos logit contributions
onder+2.158
aturdays+2.096
xxxx+2.076
coat+2.074
lear+2.056
Neg logit contributions
isphere-2.363
iu-2.318
PN-2.312
FU-2.300
utic-2.275
Token a
Token ID257
Feature activation+4.80e+00

Pos logit contributions
aturdays+0.043
onder+0.043
xxxx+0.042
irtual+0.041
lear+0.041
Neg logit contributions
isphere-0.043
iu-0.042
FU-0.042
PN-0.042
utic-0.041
Token nond
Token ID30745
Feature activation+1.62e+01

Pos logit contributions
isphere+2.931
iu+2.910
FU+2.895
PN+2.854
utic+2.809
Neg logit contributions
aturdays-3.615
onder-3.511
irtual-3.409
lear-3.387
xxxx-3.362
Tokenis
Token ID271
Feature activation+1.53e+00

Pos logit contributions
iu+5.458
lete+4.872
isphere+4.870
FU+4.637
resp+4.502
Neg logit contributions
aturdays-15.765
覚醒-14.711
 millenn-14.607
xxxx-14.557
coat-14.557
Tokenclosure
Token ID17966
Feature activation+3.36e+00

Pos logit contributions
isphere+1.139
FU+1.112
PN+1.109
iu+1.107
utic+1.094
Neg logit contributions
onder-0.947
aturdays-0.933
xxxx-0.907
coat-0.906
irtual-0.903
Token agreement
Token ID4381
Feature activation+1.53e+00

Pos logit contributions
isphere+2.533
FU+2.507
iu+2.500
PN+2.477
utic+2.451
Neg logit contributions
aturdays-2.049
onder-2.009
irtual-1.929
xxxx-1.920
lear-1.912
Token before
Token ID878
Feature activation-4.15e+00

Pos logit contributions
isphere+1.030
FU+1.010
iu+1.009
PN+0.999
utic+0.986
Neg logit contributions
aturdays-1.044
onder-1.042
irtual-1.004
xxxx-1.002
lear-1.002
Token we
Token ID356
Feature activation-2.56e+00

Pos logit contributions
onder+2.667
aturdays+2.632
lear+2.581
xxxx+2.580
coat+2.545
Neg logit contributions
isphere-2.871
FU-2.828
PN-2.797
iu-2.784
utic-2.781
Token vulnerable
Token ID8826
Feature activation+4.32e+00

Pos logit contributions
onder+0.408
aturdays+0.403
xxxx+0.389
lear+0.388
coat+0.387
Neg logit contributions
isphere-0.512
FU-0.507
iu-0.498
PN-0.496
utic-0.494
Token position
Token ID2292
Feature activation+3.01e+00

Pos logit contributions
isphere+2.663
iu+2.635
PN+2.599
FU+2.597
PI+2.550
Neg logit contributions
aturdays-3.171
onder-3.135
irtual-3.076
lear-3.036
xxxx-3.026
Token for
Token ID329
Feature activation+7.42e-01

Pos logit contributions
isphere+1.872
iu+1.836
FU+1.827
PN+1.804
utic+1.774
Neg logit contributions
aturdays-2.232
onder-2.207
irtual-2.144
lear-2.133
xxxx-2.132
Token Ferry
Token ID42609
Feature activation+1.15e+01

Pos logit contributions
isphere+0.474
FU+0.464
iu+0.463
PN+0.459
utic+0.454
Neg logit contributions
onder-0.532
aturdays-0.532
irtual-0.513
xxxx-0.513
lear-0.512
Token to
Token ID284
Feature activation+1.29e+01

Pos logit contributions
isphere+5.638
iu+5.543
 reign+5.429
PN+5.332
FU+5.314
Neg logit contributions
aturdays-9.495
irtual-9.060
onder-9.031
lear-8.842
xxxx-8.808
Token have
Token ID423
Feature activation+1.60e+01

Pos logit contributions
 reign+7.912
FU+7.463
iu+7.454
isphere+7.317
 KING+6.931
Neg logit contributions
aturdays-9.648
irtual-9.313
xxxx-8.839
retty-8.823
uli-8.795
Token left
Token ID1364
Feature activation+1.24e+01

Pos logit contributions
 reign+8.029
isphere+7.664
iu+7.584
FU+7.298
 KING+7.137
Neg logit contributions
aturdays-12.586
irtual-12.237
onder-11.909
xxxx-11.713
retty-11.706
Token him
Token ID683
Feature activation+5.09e+00

Pos logit contributions
iu+6.586
FU+6.474
 reign+6.467
isphere+6.402
 KING+6.280
Neg logit contributions
aturdays-9.314
irtual-9.157
onder-9.134
lear-8.837
xxxx-8.805
Token.
Token ID13
Feature activation+3.64e+00

Pos logit contributions
isphere+2.962
iu+2.917
FU+2.861
 reign+2.815
PN+2.805
Neg logit contributions
aturdays-3.917
onder-3.848
irtual-3.813
xxxx-3.732
lear-3.713
Token
Token ID198
Feature activation-9.71e-01

Pos logit contributions
iu+2.423
FU+2.421
isphere+2.421
PN+2.389
PI+2.352
Neg logit contributions
aturdays-2.496
onder-2.453
irtual-2.409
lear-2.369
xxxx-2.343
Token
Token ID198
Feature activation+1.54e+00

Pos logit contributions
aturdays+0.635
onder+0.626
irtual+0.609
lear+0.601
xxxx+0.598
Neg logit contributions
isphere-0.687
iu-0.680
FU-0.679
PN-0.672
utic-0.661
Token BLACK
Token ID31963
Feature activation+2.79e+00

Pos logit contributions
isphere+1.702
FU+1.701
iu+1.691
PN+1.672
PI+1.641
Neg logit contributions
aturdays-2.562
onder-2.540
irtual-2.472
lear-2.460
xxxx-2.443
TokenFO
Token ID6080
Feature activation+1.91e+00

Pos logit contributions
isphere+0.986
FU+0.976
iu+0.953
PN+0.947
PI+0.916
Neg logit contributions
aturdays-2.795
onder-2.783
irtual-2.722
lear-2.710
xxxx-2.706
TokenOT
Token ID2394
Feature activation+2.27e+00

Pos logit contributions
FU+0.852
PN+0.835
isphere+0.830
iu+0.817
PI+0.809
Neg logit contributions
aturdays-1.762
onder-1.712
irtual-1.711
lear-1.684
xxxx-1.663
Token T
Token ID309
Feature activation+9.81e+00

Pos logit contributions
isphere+1.451
FU+1.436
iu+1.426
PN+1.419
utic+1.395
Neg logit contributions
aturdays-1.620
onder-1.609
irtual-1.561
lear-1.551
xxxx-1.548
TokenOC
Token ID4503
Feature activation+6.15e+00

Pos logit contributions
PN+2.312
PI+2.187
FU+2.179
iu+1.951
ILA+1.867
Neg logit contributions
aturdays-11.322
 millenn-11.081
irtual-11.050
lear-10.660
onder-10.573
Token RE
Token ID4526
Feature activation+1.59e+01

Pos logit contributions
FU+3.096
PN+3.048
iu+3.006
 KING+3.002
PI+2.985
Neg logit contributions
aturdays-5.206
onder-5.104
irtual-5.050
lear-4.926
coat-4.924
TokenP
Token ID47
Feature activation-4.13e-01

Pos logit contributions
PN+5.851
PI+5.774
FU+5.612
PA+4.817
PH+4.655
Neg logit contributions
 millenn-17.494
aturdays-16.662
irtual-16.552
ortium-15.874
 challeng-15.692
TokenORTS
Token ID33002
Feature activation+6.98e+00

Pos logit contributions
onder+0.257
aturdays+0.257
xxxx+0.247
lear+0.246
irtual+0.245
Neg logit contributions
isphere-0.304
iu-0.297
FU-0.297
PN-0.293
utic-0.292
Token 100
Token ID1802
Feature activation+1.70e+00

Pos logit contributions
FU+4.238
iu+4.170
PN+4.161
 KING+4.144
PI+4.112
Neg logit contributions
aturdays-5.163
onder-5.081
irtual-5.026
lear-4.888
coat-4.781
Token%
Token ID4
Feature activation+4.73e+00

Pos logit contributions
FU+1.242
PN+1.229
iu+1.228
isphere+1.218
PI+1.209
Neg logit contributions
aturdays-1.097
onder-1.055
irtual-1.048
lear-1.015
ierra-0.996
Token EX
Token ID7788
Feature activation+5.59e+00

Pos logit contributions
FU+2.407
PN+2.377
isphere+2.360
iu+2.336
PI+2.334
Neg logit contributions
aturdays-3.977
onder-3.936
irtual-3.871
lear-3.800
xxxx-3.791
Token
Token ID447
Feature activation+2.37e+00

Pos logit contributions
isphere+2.124
FU+2.100
iu+2.094
PN+2.082
utic+2.048
Neg logit contributions
aturdays-2.346
onder-2.336
irtual-2.263
lear-2.251
xxxx-2.248
Token
Token ID251
Feature activation+2.70e+00

Pos logit contributions
isphere+0.752
FU+0.725
iu+0.724
PN+0.705
utic+0.684
Neg logit contributions
aturdays-2.465
onder-2.454
irtual-2.407
lear-2.391
xxxx-2.389
Token Duncan
Token ID18625
Feature activation+2.31e+00

Pos logit contributions
isphere+1.645
iu+1.618
FU+1.612
PN+1.590
utic+1.563
Neg logit contributions
aturdays-2.003
onder-1.990
irtual-1.940
xxxx-1.924
lear-1.919
Token says
Token ID1139
Feature activation+5.46e-01

Pos logit contributions
isphere+1.404
iu+1.383
FU+1.373
PN+1.353
utic+1.332
Neg logit contributions
aturdays-1.728
onder-1.716
irtual-1.665
xxxx-1.657
lear-1.650
Token.
Token ID13
Feature activation+7.54e+00

Pos logit contributions
isphere+0.336
FU+0.328
iu+0.327
PN+0.325
utic+0.320
Neg logit contributions
onder-0.405
aturdays-0.405
lear-0.391
xxxx-0.390
irtual-0.390
Token Pay
Token ID7119
Feature activation+1.59e+01

Pos logit contributions
FU+4.507
iu+4.475
PN+4.456
PI+4.374
utic+4.364
Neg logit contributions
aturdays-5.522
onder-5.412
irtual-5.404
lear-5.257
coat-5.146
Token your
Token ID534
Feature activation+3.62e+00

Pos logit contributions
iu+8.960
PI+8.719
utic+8.609
ing+8.355
PN+8.335
Neg logit contributions
aturdays-10.790
onder-10.354
irtual-10.308
uli-10.120
lear-10.096
Token taxes
Token ID5704
Feature activation-2.64e-01

Pos logit contributions
isphere+2.252
iu+2.241
FU+2.210
PN+2.189
utic+2.170
Neg logit contributions
aturdays-2.612
onder-2.592
irtual-2.519
xxxx-2.497
lear-2.493
Token.
Token ID13
Feature activation+6.14e+00

Pos logit contributions
aturdays+0.189
onder+0.189
xxxx+0.182
irtual+0.181
lear+0.181
Neg logit contributions
isphere-0.169
FU-0.166
iu-0.165
PN-0.164
utic-0.162
Token Pay
Token ID7119
Feature activation+1.21e+01

Pos logit contributions
FU+3.875
iu+3.837
PN+3.798
utic+3.744
isphere+3.743
Neg logit contributions
aturdays-4.370
onder-4.283
irtual-4.203
lear-4.134
ierra-4.050
Token your
Token ID534
Feature activation+4.79e-01

Pos logit contributions
iu+6.630
PI+6.507
utic+6.406
isphere+6.365
PN+6.308
Neg logit contributions
aturdays-8.939
onder-8.829
irtual-8.591
uli-8.534
lear-8.497
Token LA
Token ID9131
Feature activation+1.15e+00

Pos logit contributions
isphere+1.072
FU+1.051
iu+1.050
PN+1.039
utic+1.025
Neg logit contributions
aturdays-1.155
onder-1.153
irtual-1.111
xxxx-1.110
lear-1.109
TokenX
Token ID55
Feature activation+2.32e+00

Pos logit contributions
isphere+0.788
FU+0.773
iu+0.772
PN+0.765
utic+0.755
Neg logit contributions
aturdays-0.770
onder-0.769
irtual-0.740
xxxx-0.739
lear-0.738
Token security
Token ID2324
Feature activation+1.96e+00

Pos logit contributions
isphere+1.523
iu+1.493
FU+1.492
PN+1.476
utic+1.454
Neg logit contributions
aturdays-1.629
onder-1.619
lear-1.563
irtual-1.562
xxxx-1.557
Token line
Token ID1627
Feature activation+1.72e+00

Pos logit contributions
isphere+1.244
FU+1.218
iu+1.218
PN+1.204
utic+1.188
Neg logit contributions
aturdays-1.412
onder-1.407
irtual-1.359
xxxx-1.356
lear-1.356
Token with
Token ID351
Feature activation+4.99e+00

Pos logit contributions
isphere+1.092
FU+1.070
iu+1.069
PN+1.056
utic+1.043
Neg logit contributions
aturdays-1.237
onder-1.233
irtual-1.191
lear-1.188
xxxx-1.188
Token Marilyn
Token ID40769
Feature activation+1.58e+01

Pos logit contributions
isphere+3.218
iu+3.163
FU+3.158
PN+3.113
utic+3.070
Neg logit contributions
aturdays-3.526
onder-3.472
irtual-3.373
lear-3.350
xxxx-3.331
Token Manson
Token ID41645
Feature activation+3.42e+00

Pos logit contributions
isphere+7.867
iu+7.747
FU+7.527
 KING+7.509
PI+7.472
Neg logit contributions
aturdays-11.693
irtual-11.429
onder-11.407
lear-11.305
xxxx-10.951
Token,"
Token ID553
Feature activation+1.37e+00

Pos logit contributions
isphere+2.090
iu+2.061
FU+2.045
PN+2.015
utic+1.992
Neg logit contributions
aturdays-2.532
onder-2.522
irtual-2.441
lear-2.433
xxxx-2.418
Token the
Token ID262
Feature activation-1.50e+00

Pos logit contributions
isphere+0.883
FU+0.866
iu+0.866
PN+0.856
utic+0.843
Neg logit contributions
aturdays-0.976
onder-0.972
irtual-0.938
xxxx-0.937
lear-0.935
Token witness
Token ID4973
Feature activation-3.70e-01

Pos logit contributions
onder+1.075
aturdays+1.060
xxxx+1.037
lear+1.029
coat+1.027
Neg logit contributions
isphere-0.956
FU-0.952
iu-0.937
PN-0.928
utic-0.926
Token,
Token ID11
Feature activation-7.38e+00

Pos logit contributions
onder+0.248
aturdays+0.246
lear+0.238
xxxx+0.238
irtual+0.237
Neg logit contributions
isphere-0.254
FU-0.250
iu-0.248
PN-0.247
utic-0.245
Token its
Token ID663
Feature activation+1.47e+00

Pos logit contributions
isphere+1.774
FU+1.743
iu+1.735
PN+1.718
utic+1.695
Neg logit contributions
aturdays-2.023
onder-2.005
irtual-1.948
lear-1.944
xxxx-1.942
Token terminal
Token ID12094
Feature activation-7.76e-01

Pos logit contributions
isphere+0.976
FU+0.957
iu+0.956
PN+0.946
utic+0.934
Neg logit contributions
aturdays-1.023
onder-1.021
irtual-0.984
xxxx-0.982
lear-0.982
Token maneuver
Token ID20186
Feature activation+8.98e+00

Pos logit contributions
onder+0.539
aturdays+0.537
xxxx+0.517
irtual+0.517
lear+0.515
Neg logit contributions
isphere-0.512
iu-0.501
PN-0.500
FU-0.499
utic-0.493
Token and
Token ID290
Feature activation+1.48e+00

Pos logit contributions
isphere+4.930
FU+4.884
iu+4.800
utic+4.793
 reign+4.725
Neg logit contributions
aturdays-6.882
onder-6.769
lear-6.706
xxxx-6.645
irtual-6.603
Token re
Token ID302
Feature activation+3.60e+00

Pos logit contributions
isphere+1.008
FU+0.989
iu+0.989
PN+0.979
utic+0.967
Neg logit contributions
onder-1.002
aturdays-1.001
irtual-0.963
xxxx-0.961
lear-0.960
Tokenorient
Token ID13989
Feature activation+1.58e+01

Pos logit contributions
isphere+2.269
iu+2.237
FU+2.231
PN+2.177
utic+2.176
Neg logit contributions
aturdays-2.620
onder-2.575
irtual-2.495
xxxx-2.493
lear-2.486
Token itself
Token ID2346
Feature activation+5.65e+00

Pos logit contributions
isphere+8.304
iu+7.867
FU+7.730
 reign+7.646
PI+7.637
Neg logit contributions
aturdays-11.584
lear-11.331
irtual-11.254
xxxx-11.191
onder-10.951
Token.
Token ID13
Feature activation-8.53e-01

Pos logit contributions
isphere+3.420
iu+3.333
FU+3.291
PN+3.248
PI+3.209
Neg logit contributions
aturdays-4.240
onder-4.160
irtual-4.120
lear-4.064
xxxx-4.044
Token This
Token ID770
Feature activation+6.10e-01

Pos logit contributions
onder+0.561
aturdays+0.556
xxxx+0.542
coat+0.534
lear+0.533
Neg logit contributions
isphere-0.600
iu-0.583
FU-0.579
PN-0.574
utic-0.570
Token maneuver
Token ID20186
Feature activation+6.90e+00

Pos logit contributions
isphere+0.371
iu+0.363
FU+0.363
PN+0.359
utic+0.354
Neg logit contributions
aturdays-0.456
onder-0.456
xxxx-0.440
irtual-0.439
lear-0.439
Token would
Token ID561
Feature activation+2.39e+00

Pos logit contributions
isphere+4.048
iu+3.886
utic+3.850
FU+3.834
 reign+3.800
Neg logit contributions
aturdays-5.244
onder-5.138
lear-5.062
irtual-5.047
xxxx-5.007
TokenAC
Token ID2246
Feature activation+1.40e+00

Pos logit contributions
xxxx+4.540
onder+4.469
lear+4.435
coat+4.364
aturdays+4.286
Neg logit contributions
isphere-3.039
utic-2.844
iu-2.799
FU-2.768
lete-2.746
TokenLU
Token ID41596
Feature activation-6.46e-01

Pos logit contributions
isphere+0.522
FU+0.521
iu+0.516
PN+0.509
PI+0.492
Neg logit contributions
aturdays-1.391
onder-1.367
irtual-1.346
coat-1.332
lear-1.328
Token_
Token ID62
Feature activation+1.75e+00

Pos logit contributions
aturdays+0.398
onder+0.397
irtual+0.381
xxxx+0.380
lear+0.380
Neg logit contributions
isphere-0.478
FU-0.469
iu-0.469
PN-0.465
utic-0.459
TokenOR
Token ID1581
Feature activation-5.44e-01

Pos logit contributions
FU+0.671
PN+0.669
iu+0.658
isphere+0.658
PI+0.648
Neg logit contributions
aturdays-1.741
irtual-1.689
onder-1.687
lear-1.651
coat-1.640
Token)
Token ID8
Feature activation-1.99e-01

Pos logit contributions
aturdays+0.363
onder+0.360
irtual+0.348
lear+0.346
xxxx+0.345
Neg logit contributions
isphere-0.377
FU-0.372
iu-0.372
PN-0.368
utic-0.362
Token May
Token ID1737
Feature activation-1.94e+01

Pos logit contributions
aturdays+0.190
onder+0.190
irtual+0.185
xxxx+0.185
lear+0.184
Neg logit contributions
isphere-0.080
FU-0.078
iu-0.078
PN-0.076
utic-0.074
Token 29
Token ID2808
Feature activation-2.74e+00

Pos logit contributions
lear+3.401
xxxx+3.132
uli+3.127
onder+3.083
coat+2.917
Neg logit contributions
isphere-19.213
FU-18.454
ILA-18.297
utic-18.071
PN-18.029
Token,
Token ID11
Feature activation+2.63e+00

Pos logit contributions
onder+1.866
xxxx+1.814
aturdays+1.812
coat+1.790
lear+1.789
Neg logit contributions
isphere-1.869
FU-1.799
iu-1.785
PN-1.776
utic-1.773
Token 2017
Token ID2177
Feature activation-2.26e+00

Pos logit contributions
iu+1.545
FU+1.519
PN+1.513
isphere+1.492
PI+1.483
Neg logit contributions
aturdays-2.098
onder-2.008
irtual-2.004
lear-1.959
coat-1.925
Token
Token ID198
Feature activation+3.74e+00

Pos logit contributions
onder+1.340
aturdays+1.332
xxxx+1.279
lear+1.279
irtual+1.270
Neg logit contributions
isphere-1.720
FU-1.679
iu-1.672
PN-1.658
utic-1.649
Token
Token ID198
Feature activation+2.64e+00

Pos logit contributions
iu+2.307
FU+2.275
PN+2.239
PI+2.238
isphere+2.188
Neg logit contributions
aturdays-2.965
irtual-2.833
 millenn-2.785
onder-2.703
lear-2.623
Token (
Token ID357
Feature activation-6.47e+00

Pos logit contributions
isphere+1.454
iu+1.439
FU+1.435
PN+1.434
PI+1.405
Neg logit contributions
aturdays-3.089
onder-3.018
irtual-2.972
lear-2.955
xxxx-2.921
TokenIPS
Token ID47643
Feature activation-6.76e+00

Pos logit contributions
onder+3.533
xxxx+3.491
coat+3.380
lear+3.329
aturdays+3.317
Neg logit contributions
isphere-5.090
utic-5.011
iu-4.914
 reign-4.843
lete-4.834
Token-
Token ID12
Feature activation-6.47e+00

Pos logit contributions
onder+4.065
xxxx+4.005
coat+3.952
lear+3.830
ierra+3.733
Neg logit contributions
isphere-5.027
utic-4.824
iu-4.786
FU-4.723
lete-4.675
Tokentype
Token ID4906
Feature activation-2.38e+00

Pos logit contributions
onder+4.510
coat+4.412
xxxx+4.380
lear+4.322
uli+4.147
Neg logit contributions
isphere-4.216
ITNESS-4.023
FU-4.017
iu-4.017
utic-3.992
Token)
Token ID8
Feature activation+1.10e+00

Pos logit contributions
onder+1.504
aturdays+1.465
xxxx+1.450
coat+1.434
lear+1.430
Neg logit contributions
isphere-1.738
FU-1.690
iu-1.688
PN-1.674
utic-1.665
Token @
Token ID2488
Feature activation-1.92e+01

Pos logit contributions
isphere+0.704
FU+0.690
iu+0.690
PN+0.682
utic+0.672
Neg logit contributions
aturdays-0.789
onder-0.787
irtual-0.760
xxxx-0.758
lear-0.758
Token 144
Token ID20224
Feature activation-9.41e+00

Pos logit contributions
xxxx+6.565
coat+6.560
uli+6.226
aturdays+6.208
onder+6.192
Neg logit contributions
isphere-16.134
utic-15.174
FU-15.048
lete-14.699
PN-14.603
TokenHz
Token ID7399
Feature activation+7.14e+00

Pos logit contributions
xxxx+5.902
onder+5.763
lear+5.431
coat+5.366
aturdays+5.294
Neg logit contributions
isphere-6.694
utic-6.456
iu-6.375
lete-6.283
 poaching-6.162
Token (
Token ID357
Feature activation-6.31e+00

Pos logit contributions
isphere+2.869
FU+2.824
PN+2.811
iu+2.804
PI+2.749
Neg logit contributions
aturdays-6.606
onder-6.544
lear-6.379
irtual-6.367
xxxx-6.364
TokenOD
Token ID3727
Feature activation+8.60e+00

Pos logit contributions
onder+4.213
xxxx+4.186
coat+4.054
lear+4.048
aturdays+3.913
Neg logit contributions
isphere-4.326
utic-4.168
iu-4.059
lete-3.991
 KING-3.967
Token =
Token ID796
Feature activation-5.08e+00

Pos logit contributions
iu+4.568
isphere+4.518
PI+4.504
PN+4.470
FU+4.444
Neg logit contributions
aturdays-7.002
onder-6.815
xxxx-6.589
irtual-6.569
coat-6.554
TokenAC
Token ID2246
Feature activation-7.06e-02

Pos logit contributions
xxxx+5.632
lear+5.495
onder+5.485
coat+5.352
aturdays+5.234
Neg logit contributions
isphere-4.072
utic-3.841
iu-3.716
FU-3.711
 reign-3.710
TokenLU
Token ID41596
Feature activation-1.92e+00

Pos logit contributions
aturdays+0.068
onder+0.067
irtual+0.066
xxxx+0.065
lear+0.065
Neg logit contributions
isphere-0.028
FU-0.028
iu-0.027
PN-0.027
utic-0.026
Token_
Token ID62
Feature activation+9.06e-01

Pos logit contributions
onder+1.144
aturdays+1.125
xxxx+1.103
lear+1.091
coat+1.086
Neg logit contributions
isphere-1.461
FU-1.426
iu-1.425
PN-1.407
utic-1.406
TokenOR
Token ID1581
Feature activation-5.49e-01

Pos logit contributions
isphere+0.358
FU+0.357
PN+0.355
iu+0.353
PI+0.344
Neg logit contributions
aturdays-0.877
onder-0.860
irtual-0.851
lear-0.840
coat-0.835
Token)
Token ID8
Feature activation-7.19e-01

Pos logit contributions
aturdays+0.367
onder+0.363
irtual+0.352
lear+0.349
xxxx+0.348
Neg logit contributions
isphere-0.379
FU-0.374
iu-0.374
PN-0.370
utic-0.364
Token May
Token ID1737
Feature activation-1.90e+01

Pos logit contributions
onder+0.662
aturdays+0.662
lear+0.645
xxxx+0.642
irtual+0.642
Neg logit contributions
isphere-0.315
FU-0.302
iu-0.301
PN-0.297
utic-0.291
Token 29
Token ID2808
Feature activation-2.36e+00

Pos logit contributions
lear+3.211
xxxx+3.124
onder+3.020
coat+2.998
uli+2.993
Neg logit contributions
isphere-18.995
FU-18.135
ILA-17.990
utic-17.856
PN-17.638
Token,
Token ID11
Feature activation+3.18e+00

Pos logit contributions
onder+1.625
aturdays+1.591
xxxx+1.575
lear+1.559
coat+1.558
Neg logit contributions
isphere-1.584
FU-1.532
iu-1.522
PN-1.512
utic-1.505
Token 2017
Token ID2177
Feature activation-7.91e-01

Pos logit contributions
iu+1.841
PN+1.797
FU+1.795
PI+1.764
isphere+1.752
Neg logit contributions
aturdays-2.588
irtual-2.467
onder-2.459
lear-2.408
coat-2.357
Token
Token ID198
Feature activation+3.62e+00

Pos logit contributions
onder+0.482
aturdays+0.480
lear+0.460
xxxx+0.460
irtual+0.458
Neg logit contributions
isphere-0.592
FU-0.580
iu-0.578
PN-0.573
utic-0.568
Token
Token ID198
Feature activation-6.69e+00

Pos logit contributions
iu+2.239
FU+2.203
PN+2.173
PI+2.167
isphere+2.131
Neg logit contributions
aturdays-2.856
irtual-2.729
 millenn-2.671
onder-2.601
lear-2.529
Token (
Token ID357
Feature activation-6.19e+00

Pos logit contributions
isphere+1.434
iu+1.400
FU+1.392
PN+1.385
PI+1.352
Neg logit contributions
aturdays-2.553
onder-2.535
irtual-2.468
lear-2.465
xxxx-2.463
TokenIPS
Token ID47643
Feature activation-5.12e+00

Pos logit contributions
onder+3.615
aturdays+3.531
xxxx+3.492
lear+3.453
coat+3.435
Neg logit contributions
isphere-4.627
utic-4.497
iu-4.459
FU-4.407
lete-4.391
Token-
Token ID12
Feature activation-7.16e+00

Pos logit contributions
onder+3.260
xxxx+3.167
coat+3.137
lear+3.075
aturdays+3.058
Neg logit contributions
isphere-3.652
iu-3.532
utic-3.530
FU-3.494
lete-3.433
Tokentype
Token ID4906
Feature activation-4.30e+00

Pos logit contributions
onder+4.884
coat+4.776
xxxx+4.743
lear+4.665
uli+4.478
Neg logit contributions
isphere-4.713
ITNESS-4.512
FU-4.493
iu-4.493
utic-4.488
Token)
Token ID8
Feature activation-1.70e+00

Pos logit contributions
onder+2.556
xxxx+2.466
coat+2.423
aturdays+2.395
lear+2.379
Neg logit contributions
isphere-3.289
FU-3.177
iu-3.173
utic-3.167
PN-3.147
Token @
Token ID2488
Feature activation-1.89e+01

Pos logit contributions
onder+1.145
aturdays+1.143
xxxx+1.099
lear+1.093
irtual+1.092
Neg logit contributions
isphere-1.168
FU-1.140
iu-1.130
utic-1.119
PN-1.117
Token 144
Token ID20224
Feature activation-9.50e+00

Pos logit contributions
xxxx+7.653
coat+7.510
onder+7.308
uli+7.111
aturdays+7.054
Neg logit contributions
isphere-14.864
utic-13.913
FU-13.594
lete-13.523
iu-13.239
TokenHz
Token ID7399
Feature activation+4.38e+00

Pos logit contributions
xxxx+5.936
onder+5.861
lear+5.514
aturdays+5.433
coat+5.408
Neg logit contributions
isphere-6.689
utic-6.493
iu-6.419
lete-6.285
 poaching-6.160
Token (
Token ID357
Feature activation-7.54e+00

Pos logit contributions
isphere+1.945
iu+1.903
FU+1.902
PN+1.890
PI+1.844
Neg logit contributions
aturdays-3.946
onder-3.918
lear-3.818
irtual-3.814
xxxx-3.808
TokenTr
Token ID2898
Feature activation-6.56e+00

Pos logit contributions
onder+5.100
aturdays+4.900
lear+4.886
xxxx+4.870
coat+4.823
Neg logit contributions
isphere-4.991
utic-4.760
iu-4.674
FU-4.622
lete-4.616
Tokenace
Token ID558
Feature activation-1.15e-01

Pos logit contributions
onder+4.637
xxxx+4.428
lear+4.415
coat+4.352
ierra+4.292
Neg logit contributions
FU-4.269
isphere-4.188
PN-4.154
ILA-4.112
MENTS-4.042
Tokenc
Token ID66
Feature activation-4.79e+00

Pos logit contributions
onder+2.021
aturdays+1.991
xxxx+1.948
coat+1.943
lear+1.942
Neg logit contributions
isphere-2.041
FU-2.014
iu-1.992
PN-1.984
utic-1.951
Tokenpy
Token ID9078
Feature activation-1.15e+00

Pos logit contributions
onder+3.449
xxxx+3.375
aturdays+3.354
lear+3.349
coat+3.337
Neg logit contributions
isphere-3.007
FU-2.932
iu-2.884
PN-2.845
ILA-2.821
TokenIn
Token ID818
Feature activation+3.95e-01

Pos logit contributions
onder+0.766
aturdays+0.759
xxxx+0.748
lear+0.738
irtual+0.733
Neg logit contributions
isphere-0.796
FU-0.769
iu-0.767
utic-0.764
PN-0.754
TokenMemory
Token ID30871
Feature activation-2.06e+00

Pos logit contributions
isphere+0.235
FU+0.234
iu+0.232
PN+0.231
PI+0.227
Neg logit contributions
aturdays-0.304
onder-0.299
irtual-0.291
lear-0.288
coat-0.286
Token 4
Token ID604
Feature activation-5.72e+00

Pos logit contributions
aturdays+1.315
onder+1.312
xxxx+1.260
irtual+1.248
lear+1.246
Neg logit contributions
isphere-1.499
FU-1.452
iu-1.442
PN-1.420
utic-1.417
Token66
Token ID2791
Feature activation-1.83e+01

Pos logit contributions
onder+2.849
xxxx+2.784
aturdays+2.621
coat+2.605
lear+2.565
Neg logit contributions
isphere-5.011
FU-4.721
utic-4.719
PN-4.661
iu-4.653
Token284
Token ID30336
Feature activation-8.14e-01

Pos logit contributions
xxxx+3.773
uli+2.588
onder+2.407
ierra+2.349
xxxxxxxx+2.193
Neg logit contributions
isphere-19.725
utic-18.786
 KING-18.597
ITNESS-18.521
FU-18.496
Token 4
Token ID604
Feature activation-1.48e+01

Pos logit contributions
onder+0.545
aturdays+0.544
xxxx+0.524
lear+0.522
irtual+0.522
Neg logit contributions
isphere-0.561
FU-0.547
iu-0.547
PN-0.540
utic-0.535
Token64
Token ID2414
Feature activation-1.42e+01

Pos logit contributions
onder+3.197
xxxx+3.138
coat+2.622
uli+2.432
xxxxxxxx+2.345
Neg logit contributions
isphere-15.982
utic-15.578
 poaching-15.348
rency-15.018
ITNESS-14.880
Token406
Token ID29703
Feature activation-4.04e+00

Pos logit contributions
xxxx+5.337
onder+5.303
xxxxxxxx+4.735
lear+4.699
coat+4.499
Neg logit contributions
 reign-12.839
 KING-12.704
iu-12.649
isphere-12.631
ILA-12.449
Token Mem
Token ID4942
Feature activation-1.59e+00

Pos logit contributions
onder+2.015
xxxx+1.971
aturdays+1.908
coat+1.901
lear+1.886
Neg logit contributions
isphere-3.493
FU-3.359
iu-3.340
utic-3.315
PN-3.314
Token inches
Token ID8331
Feature activation-8.74e+00

Pos logit contributions
onder+8.672
xxxx+8.557
aturdays+8.156
uli+7.834
hell+7.807
Neg logit contributions
isphere-10.269
ITNESS-10.081
utic-10.062
FU-10.014
lete-9.821
Token long
Token ID890
Feature activation-9.35e+00

Pos logit contributions
onder+5.188
xxxx+5.080
aturdays+5.005
coat+4.868
ierra+4.815
Neg logit contributions
FU-6.270
iu-6.127
ITNESS-6.097
PN-6.001
rency-5.992
Token and
Token ID290
Feature activation-6.00e+00

Pos logit contributions
onder+5.721
xxxx+5.642
aturdays+5.535
coat+5.436
ierra+5.346
Neg logit contributions
FU-6.463
isphere-6.315
ITNESS-6.275
PN-6.223
iu-6.192
Token a
Token ID257
Feature activation-7.93e+00

Pos logit contributions
onder+3.686
aturdays+3.596
xxxx+3.525
coat+3.515
lear+3.422
Neg logit contributions
FU-4.323
isphere-4.296
iu-4.187
PN-4.181
utic-4.169
Token cap
Token ID1451
Feature activation-1.11e+01

Pos logit contributions
onder+5.059
xxxx+4.837
coat+4.788
aturdays+4.783
lear+4.716
Neg logit contributions
FU-5.452
isphere-5.426
utic-5.187
PN-5.161
iu-5.159
Token 1
Token ID352
Feature activation-1.81e+01

Pos logit contributions
onder+6.401
xxxx+6.104
aturdays+6.079
coat+6.073
lear+6.064
Neg logit contributions
FU-7.865
ITNESS-7.707
PN-7.459
isphere-7.436
ILA-7.356
Token inch
Token ID11111
Feature activation-1.11e+01

Pos logit contributions
onder+9.140
xxxx+8.733
coat+8.542
lear+7.942
uli+7.896
Neg logit contributions
ITNESS-12.645
utic-12.370
isphere-12.362
FU-12.045
rency-11.767
Token in
Token ID287
Feature activation-3.48e+00

Pos logit contributions
onder+5.897
xxxx+5.663
coat+5.540
aturdays+5.522
lear+5.380
Neg logit contributions
FU-8.501
ITNESS-8.376
utic-8.208
iu-8.159
PN-8.112
Token diameter
Token ID14753
Feature activation-7.81e+00

Pos logit contributions
onder+1.317
aturdays+1.297
xxxx+1.237
coat+1.224
lear+1.208
Neg logit contributions
isphere-3.374
FU-3.354
iu-3.306
PN-3.291
utic-3.280
Token average
Token ID2811
Feature activation-5.70e+00

Pos logit contributions
onder+4.878
aturdays+4.792
xxxx+4.772
coat+4.670
ierra+4.566
Neg logit contributions
FU-5.332
isphere-5.311
PN-5.143
iu-5.127
ITNESS-5.114
Token.
Token ID13
Feature activation-4.61e+00

Pos logit contributions
onder+3.348
aturdays+3.295
xxxx+3.268
coat+3.242
lear+3.173
Neg logit contributions
FU-4.195
isphere-4.177
PN-4.071
iu-4.040
utic-4.029
Token (
Token ID357
Feature activation-7.33e+00

Pos logit contributions
iu+1.980
PN+1.972
FU+1.949
PI+1.943
isphere+1.899
Neg logit contributions
aturdays-5.194
irtual-4.953
onder-4.897
lear-4.857
 millenn-4.759
TokenIPS
Token ID47643
Feature activation-4.01e+00

Pos logit contributions
onder+3.958
xxxx+3.883
coat+3.730
aturdays+3.691
lear+3.675
Neg logit contributions
isphere-5.795
utic-5.687
iu-5.530
lete-5.528
 KING-5.495
Token-
Token ID12
Feature activation-6.32e+00

Pos logit contributions
onder+2.628
xxxx+2.550
coat+2.527
aturdays+2.499
lear+2.496
Neg logit contributions
isphere-2.806
iu-2.708
FU-2.692
utic-2.690
PN-2.646
Tokentype
Token ID4906
Feature activation-2.93e+00

Pos logit contributions
onder+4.416
coat+4.309
xxxx+4.293
lear+4.229
uli+4.082
Neg logit contributions
isphere-4.091
FU-3.934
iu-3.917
ILA-3.891
ITNESS-3.887
Token)
Token ID8
Feature activation-7.20e-01

Pos logit contributions
onder+1.822
xxxx+1.761
aturdays+1.760
coat+1.740
lear+1.725
Neg logit contributions
isphere-2.164
FU-2.096
iu-2.093
PN-2.076
utic-2.071
Token @
Token ID2488
Feature activation-1.79e+01

Pos logit contributions
onder+0.506
aturdays+0.505
xxxx+0.488
lear+0.486
irtual+0.485
Neg logit contributions
isphere-0.471
FU-0.460
iu-0.459
PN-0.454
utic-0.450
Token 144
Token ID20224
Feature activation-9.26e+00

Pos logit contributions
coat+5.810
onder+5.788
xxxx+5.764
aturdays+5.466
uli+5.464
Neg logit contributions
isphere-15.745
utic-14.759
FU-14.692
lete-14.474
iu-14.164
TokenHz
Token ID7399
Feature activation+4.81e+00

Pos logit contributions
xxxx+5.847
onder+5.721
lear+5.373
coat+5.308
aturdays+5.251
Neg logit contributions
isphere-6.556
utic-6.348
iu-6.221
lete-6.160
 poaching-6.038
Token (
Token ID357
Feature activation-8.84e+00

Pos logit contributions
isphere+2.021
iu+2.005
FU+1.990
PN+1.978
PI+1.928
Neg logit contributions
aturdays-4.449
onder-4.400
lear-4.288
xxxx-4.284
irtual-4.280
TokenTr
Token ID2898
Feature activation-6.83e+00

Pos logit contributions
onder+5.820
lear+5.563
aturdays+5.530
xxxx+5.481
coat+5.445
Neg logit contributions
isphere-5.950
utic-5.627
iu-5.527
lete-5.513
FU-5.482
Tokenace
Token ID558
Feature activation+1.62e+00

Pos logit contributions
onder+4.809
xxxx+4.597
lear+4.570
coat+4.523
ierra+4.445
Neg logit contributions
FU-4.480
isphere-4.368
PN-4.352
ILA-4.305
MENTS-4.230
TokenAC
Token ID2246
Feature activation+1.44e+00

Pos logit contributions
xxxx+3.835
onder+3.805
lear+3.751
coat+3.715
aturdays+3.668
Neg logit contributions
isphere-2.436
utic-2.276
iu-2.260
FU-2.222
lete-2.204
TokenLU
Token ID41596
Feature activation+1.21e-01

Pos logit contributions
FU+0.536
isphere+0.533
iu+0.529
PN+0.521
PI+0.504
Neg logit contributions
aturdays-1.436
onder-1.409
irtual-1.389
coat-1.373
lear-1.369
Token_
Token ID62
Feature activation+2.71e+00

Pos logit contributions
isphere+0.087
FU+0.087
iu+0.086
PN+0.086
PI+0.084
Neg logit contributions
aturdays-0.077
onder-0.076
irtual-0.074
lear-0.073
xxxx-0.072
TokenOR
Token ID1581
Feature activation+8.64e-01

Pos logit contributions
PN+1.002
FU+1.000
iu+0.972
PI+0.968
isphere+0.951
Neg logit contributions
aturdays-2.764
irtual-2.680
onder-2.644
lear-2.594
coat-2.575
Token)
Token ID8
Feature activation+6.68e-01

Pos logit contributions
FU+0.573
iu+0.572
isphere+0.571
PN+0.566
PI+0.557
Neg logit contributions
aturdays-0.612
onder-0.590
irtual-0.584
lear-0.571
xxxx-0.562
Token May
Token ID1737
Feature activation-1.76e+01

Pos logit contributions
isphere+0.254
iu+0.250
FU+0.250
PN+0.245
PI+0.238
Neg logit contributions
aturdays-0.655
onder-0.648
irtual-0.636
lear-0.630
xxxx-0.629
Token 29
Token ID2808
Feature activation-1.96e+00

Pos logit contributions
lear+3.086
uli+2.947
onder+2.934
xxxx+2.794
coat+2.596
Neg logit contributions
isphere-17.908
FU-17.227
ILA-17.093
utic-16.839
PN-16.825
Token,
Token ID11
Feature activation+3.02e+00

Pos logit contributions
onder+1.361
aturdays+1.341
xxxx+1.317
lear+1.307
coat+1.304
Neg logit contributions
isphere-1.298
FU-1.259
iu-1.253
PN-1.244
utic-1.235
Token 2017
Token ID2177
Feature activation-1.40e+00

Pos logit contributions
iu+1.756
FU+1.725
PN+1.719
isphere+1.686
PI+1.685
Neg logit contributions
aturdays-2.435
irtual-2.325
onder-2.320
lear-2.270
coat-2.227
Token
Token ID198
Feature activation+2.92e+00

Pos logit contributions
onder+0.832
aturdays+0.813
xxxx+0.800
coat+0.789
lear+0.789
Neg logit contributions
isphere-1.074
FU-1.036
iu-1.035
utic-1.026
PN-1.025
Token
Token ID198
Feature activation+4.92e+00

Pos logit contributions
iu+1.839
FU+1.819
PN+1.791
PI+1.787
isphere+1.761
Neg logit contributions
aturdays-2.257
irtual-2.157
 millenn-2.087
onder-2.077
lear-2.015
TokenAC
Token ID2246
Feature activation+1.60e+00

Pos logit contributions
xxxx+3.687
onder+3.664
lear+3.607
coat+3.581
aturdays+3.540
Neg logit contributions
isphere-2.311
utic-2.160
iu-2.149
FU-2.111
lete-2.092
TokenLU
Token ID41596
Feature activation+3.44e-01

Pos logit contributions
FU+0.592
isphere+0.587
iu+0.584
PN+0.575
PI+0.557
Neg logit contributions
aturdays-1.608
onder-1.573
irtual-1.554
coat-1.535
lear-1.529
Token_
Token ID62
Feature activation+2.74e+00

Pos logit contributions
isphere+0.247
FU+0.245
iu+0.245
PN+0.243
PI+0.239
Neg logit contributions
aturdays-0.223
onder-0.218
irtual-0.212
lear-0.209
xxxx-0.207
TokenOR
Token ID1581
Feature activation+1.94e-01

Pos logit contributions
PN+1.013
FU+1.012
iu+0.983
PI+0.979
isphere+0.960
Neg logit contributions
aturdays-2.792
irtual-2.707
onder-2.669
lear-2.618
coat-2.599
Token)
Token ID8
Feature activation+3.27e-01

Pos logit contributions
isphere+0.131
FU+0.130
iu+0.130
PN+0.129
PI+0.127
Neg logit contributions
aturdays-0.134
onder-0.130
irtual-0.128
lear-0.126
xxxx-0.125
Token May
Token ID1737
Feature activation-1.72e+01

Pos logit contributions
isphere+0.127
FU+0.124
iu+0.124
PN+0.122
utic+0.119
Neg logit contributions
aturdays-0.318
onder-0.315
irtual-0.309
lear-0.307
xxxx-0.307
Token 29
Token ID2808
Feature activation-2.03e+00

Pos logit contributions
xxxx+2.681
onder+2.399
coat+2.372
lear+2.342
uli+2.279
Neg logit contributions
isphere-18.485
utic-17.399
FU-17.193
rency-17.190
-17.063
Token,
Token ID11
Feature activation+2.32e+00

Pos logit contributions
onder+1.412
aturdays+1.390
xxxx+1.368
lear+1.356
coat+1.353
Neg logit contributions
isphere-1.352
FU-1.311
iu-1.305
PN-1.295
utic-1.287
Token 2017
Token ID2177
Feature activation-1.99e+00

Pos logit contributions
iu+1.372
FU+1.354
PN+1.347
isphere+1.334
PI+1.320
Neg logit contributions
aturdays-1.834
onder-1.760
irtual-1.754
lear-1.716
coat-1.688
Token
Token ID198
Feature activation+2.23e+00

Pos logit contributions
onder+1.180
aturdays+1.145
xxxx+1.140
coat+1.120
lear+1.117
Neg logit contributions
isphere-1.536
FU-1.479
iu-1.477
utic-1.468
PN-1.464
Token
Token ID198
Feature activation+4.39e+00

Pos logit contributions
iu+1.431
FU+1.419
PN+1.397
PI+1.390
isphere+1.386
Neg logit contributions
aturdays-1.679
irtual-1.604
onder-1.560
 millenn-1.525
lear-1.511
Token And
Token ID843
Feature activation+3.44e+00

Pos logit contributions
isphere+1.114
FU+1.089
iu+1.088
PN+1.075
utic+1.064
Neg logit contributions
onder-1.022
aturdays-1.020
xxxx-0.979
irtual-0.979
lear-0.976
Token the
Token ID262
Feature activation-2.53e+00

Pos logit contributions
isphere+2.212
iu+2.193
FU+2.186
PN+2.162
utic+2.129
Neg logit contributions
aturdays-2.447
onder-2.413
irtual-2.338
xxxx-2.337
lear-2.331
Token Congress
Token ID3162
Feature activation+6.42e-01

Pos logit contributions
onder+1.793
irtual+1.688
lear+1.687
aturdays+1.687
coat+1.686
Neg logit contributions
isphere-1.667
FU-1.617
utic-1.600
iu-1.595
PN-1.584
Token may
Token ID743
Feature activation+2.92e+00

Pos logit contributions
isphere+0.491
FU+0.483
iu+0.482
PN+0.478
utic+0.473
Neg logit contributions
aturdays-0.381
onder-0.379
irtual-0.362
xxxx-0.361
lear-0.361
Token by
Token ID416
Feature activation-7.49e+00

Pos logit contributions
isphere+1.787
FU+1.783
iu+1.770
PN+1.740
PI+1.731
Neg logit contributions
aturdays-2.163
onder-2.131
irtual-2.088
lear-2.066
xxxx-2.065
Token general
Token ID2276
Feature activation-1.69e+01

Pos logit contributions
onder+4.731
coat+4.684
lear+4.547
uli+4.468
aturdays+4.434
Neg logit contributions
isphere-5.284
FU-4.976
iu-4.934
utic-4.884
PN-4.866
Token Laws
Token ID21153
Feature activation-2.29e+00

Pos logit contributions
lear+8.439
 Sent+8.367
coat+8.321
 Stories+8.065
irtual+7.978
Neg logit contributions
isphere-12.871
FU-12.044
-11.532
utic-11.512
PN-11.420
Token prescribe
Token ID32651
Feature activation+4.49e+00

Pos logit contributions
onder+1.590
aturdays+1.560
lear+1.519
xxxx+1.516
coat+1.507
Neg logit contributions
isphere-1.528
iu-1.490
PN-1.488
FU-1.484
utic-1.464
Token the
Token ID262
Feature activation-5.02e+00

Pos logit contributions
isphere+2.837
iu+2.828
PN+2.811
FU+2.803
utic+2.770
Neg logit contributions
aturdays-3.204
onder-3.116
irtual-3.062
xxxx-3.033
ierra-3.004
Token Man
Token ID1869
Feature activation-1.94e+00

Pos logit contributions
onder+3.322
aturdays+3.189
lear+3.186
xxxx+3.137
coat+3.132
Neg logit contributions
isphere-3.492
FU-3.436
iu-3.327
PI-3.240
utic-3.235
Tokenner
Token ID1008
Feature activation+2.69e+00

Pos logit contributions
onder+0.865
aturdays+0.851
lear+0.799
xxxx+0.796
irtual+0.795
Neg logit contributions
isphere-1.768
FU-1.753
PN-1.744
iu-1.735
utic-1.715
TokenThe
Token ID464
Feature activation-3.10e+00

Pos logit contributions
onder+2.257
xxxx+2.237
aturdays+2.236
coat+2.197
lear+2.189
Neg logit contributions
isphere-2.155
utic-2.066
iu-2.062
FU-2.022
lete-2.000
Token Laz
Token ID22807
Feature activation-8.04e-01

Pos logit contributions
onder+2.171
aturdays+2.164
xxxx+2.101
coat+2.088
lear+2.087
Neg logit contributions
isphere-2.018
FU-1.971
iu-1.955
PN-1.939
utic-1.915
Tokenlow
Token ID9319
Feature activation+9.81e-01

Pos logit contributions
aturdays+0.554
onder+0.553
lear+0.530
irtual+0.530
xxxx+0.527
Neg logit contributions
isphere-0.538
FU-0.531
iu-0.526
PN-0.523
utic-0.517
Token Show
Token ID5438
Feature activation-4.48e+00

Pos logit contributions
isphere+0.635
FU+0.623
iu+0.622
PN+0.615
utic+0.607
Neg logit contributions
aturdays-0.696
onder-0.694
irtual-0.670
xxxx-0.668
lear-0.668
Token 2008
Token ID3648
Feature activation-7.87e+00

Pos logit contributions
aturdays+3.060
onder+3.031
xxxx+3.009
lear+2.983
coat+2.961
Neg logit contributions
isphere-2.938
FU-2.896
iu-2.822
PN-2.817
utic-2.806
Token01
Token ID486
Feature activation-1.69e+01

Pos logit contributions
xxxx+3.836
onder+3.801
coat+3.633
lear+3.478
aturdays+3.360
Neg logit contributions
isphere-6.835
utic-6.582
lete-6.443
iu-6.442
FU-6.408
Token12
Token ID1065
Feature activation-1.84e+00

Pos logit contributions
xxxx+4.427
onder+3.918
ierra+3.528
aturdays+3.446
coat+3.420
Neg logit contributions
isphere-16.507
utic-16.429
PN-16.042
iu-15.994
rency-15.960
Token O
Token ID440
Feature activation+4.87e+00

Pos logit contributions
onder+1.449
aturdays+1.427
xxxx+1.405
coat+1.401
lear+1.397
Neg logit contributions
isphere-1.049
FU-1.004
iu-1.004
utic-0.991
PN-0.990
Token&
Token ID5
Feature activation+3.20e+00

Pos logit contributions
PN+2.085
FU+2.076
iu+2.067
PI+2.031
isphere+1.893
Neg logit contributions
aturdays-4.741
irtual-4.620
 millenn-4.476
onder-4.455
ortium-4.312
TokenA
Token ID32
Feature activation-3.44e+00

Pos logit contributions
FU+1.692
PN+1.665
PI+1.634
iu+1.625
ILA+1.562
Neg logit contributions
aturdays-2.837
irtual-2.733
onder-2.694
 millenn-2.603
lear-2.586
Token-
Token ID12
Feature activation+1.17e+00

Pos logit contributions
onder+2.306
xxxx+2.244
coat+2.229
aturdays+2.228
lear+2.207
Neg logit contributions
isphere-2.367
iu-2.274
FU-2.273
utic-2.256
PN-2.244
TokenAC
Token ID2246
Feature activation+1.96e+00

Pos logit contributions
onder+3.094
xxxx+3.092
lear+3.037
coat+3.019
aturdays+3.012
Neg logit contributions
isphere-1.847
iu-1.730
utic-1.727
FU-1.704
lete-1.672
TokenLU
Token ID41596
Feature activation+4.48e-01

Pos logit contributions
FU+0.717
isphere+0.706
iu+0.706
PN+0.695
PI+0.674
Neg logit contributions
aturdays-1.986
onder-1.937
irtual-1.918
coat-1.892
lear-1.882
Token_
Token ID62
Feature activation+2.90e+00

Pos logit contributions
isphere+0.321
FU+0.319
iu+0.318
PN+0.316
PI+0.310
Neg logit contributions
aturdays-0.290
onder-0.285
irtual-0.276
lear-0.273
xxxx-0.270
TokenOR
Token ID1581
Feature activation+1.10e+00

Pos logit contributions
FU+1.070
PN+1.067
iu+1.035
PI+1.033
isphere+1.006
Neg logit contributions
aturdays-2.973
irtual-2.883
onder-2.840
lear-2.781
ierra-2.760
Token)
Token ID8
Feature activation+8.17e-01

Pos logit contributions
FU+0.725
iu+0.724
isphere+0.721
PN+0.715
PI+0.704
Neg logit contributions
aturdays-0.786
onder-0.755
irtual-0.749
lear-0.730
xxxx-0.718
Token May
Token ID1737
Feature activation-1.69e+01

Pos logit contributions
isphere+0.308
iu+0.304
FU+0.304
PN+0.297
PI+0.289
Neg logit contributions
aturdays-0.805
onder-0.794
irtual-0.782
lear-0.772
xxxx-0.771
Token 29
Token ID2808
Feature activation-1.76e+00

Pos logit contributions
xxxx+3.000
onder+2.689
coat+2.537
uli+2.415
lear+2.343
Neg logit contributions
isphere-18.199
utic-17.253
rency-17.081
-16.870
FU-16.827
Token,
Token ID11
Feature activation+1.89e+00

Pos logit contributions
onder+1.232
aturdays+1.219
xxxx+1.192
lear+1.184
coat+1.180
Neg logit contributions
isphere-1.161
FU-1.128
iu-1.124
PN-1.115
utic-1.106
Token 2017
Token ID2177
Feature activation-1.48e+00

Pos logit contributions
iu+1.129
FU+1.117
PN+1.111
isphere+1.107
PI+1.088
Neg logit contributions
aturdays-1.467
onder-1.416
irtual-1.404
lear-1.378
coat-1.357
Token
Token ID198
Feature activation+1.82e+00

Pos logit contributions
onder+0.897
aturdays+0.878
xxxx+0.866
coat+0.853
lear+0.853
Neg logit contributions
isphere-1.123
FU-1.088
iu-1.086
PN-1.077
utic-1.075
Token
Token ID198
Feature activation+3.87e-01

Pos logit contributions
iu+1.188
FU+1.179
PN+1.162
isphere+1.158
PI+1.154
Neg logit contributions
aturdays-1.350
irtual-1.291
onder-1.266
lear-1.223
 millenn-1.213
Token.
Token ID13
Feature activation-5.00e+00

Pos logit contributions
onder+3.401
xxxx+3.370
aturdays+3.367
coat+3.276
irtual+3.274
Neg logit contributions
isphere-3.768
FU-3.684
iu-3.653
PN-3.638
utic-3.630
TokenNumber
Token ID15057
Feature activation-4.33e+00

Pos logit contributions
onder+3.330
aturdays+3.327
xxxx+3.273
coat+3.203
irtual+3.166
Neg logit contributions
isphere-3.377
iu-3.224
utic-3.206
FU-3.198
lete-3.158
Token 1
Token ID352
Feature activation-3.70e+00

Pos logit contributions
onder+2.721
aturdays+2.713
xxxx+2.612
coat+2.600
lear+2.568
Neg logit contributions
isphere-3.140
FU-3.028
PN-2.985
iu-2.980
utic-2.974
Token I
Token ID314
Feature activation-5.03e+00

Pos logit contributions
onder+2.513
aturdays+2.490
xxxx+2.433
lear+2.404
irtual+2.400
Neg logit contributions
isphere-2.474
FU-2.398
iu-2.391
utic-2.384
PN-2.381
Token think
Token ID892
Feature activation-4.42e+00

Pos logit contributions
onder+3.130
lear+2.934
aturdays+2.929
coat+2.917
xxxx+2.896
Neg logit contributions
isphere-3.689
utic-3.559
PN-3.536
FU-3.522
iu-3.513
Token for
Token ID329
Feature activation-1.68e+01

Pos logit contributions
aturdays+2.727
onder+2.727
lear+2.636
xxxx+2.633
coat+2.623
Neg logit contributions
isphere-3.184
iu-3.084
FU-3.078
PN-3.061
utic-3.045
Token quite
Token ID2407
Feature activation-1.98e+00

Pos logit contributions
onder+5.609
aturdays+5.179
lear+4.997
coat+4.888
retty+4.821
Neg logit contributions
isphere-14.904
PN-14.780
ILA-14.699
iu-14.363
FU-14.238
Token a
Token ID257
Feature activation-7.79e+00

Pos logit contributions
onder+1.275
aturdays+1.265
xxxx+1.224
coat+1.219
lear+1.218
Neg logit contributions
isphere-1.415
FU-1.378
iu-1.373
PN-1.366
utic-1.354
Token while
Token ID981
Feature activation-5.19e+00

Pos logit contributions
onder+4.184
coat+4.091
xxxx+3.993
aturdays+3.973
lear+3.965
Neg logit contributions
isphere-6.175
utic-6.057
PN-6.029
FU-5.938
iu-5.890
Token will
Token ID481
Feature activation-6.86e+00

Pos logit contributions
onder+3.070
xxxx+2.972
coat+2.919
lear+2.883
aturdays+2.878
Neg logit contributions
isphere-3.923
FU-3.825
PN-3.799
utic-3.778
iu-3.772
Token always
Token ID1464
Feature activation-6.64e+00

Pos logit contributions
onder+3.562
xxxx+3.341
coat+3.300
lear+3.252
aturdays+3.205
Neg logit contributions
PN-5.675
isphere-5.665
FU-5.551
utic-5.539
PI-5.443
TokenReading
Token ID36120
Feature activation-9.38e-01

Pos logit contributions
onder+1.194
aturdays+1.175
xxxx+1.172
lear+1.155
coat+1.141
Neg logit contributions
isphere-1.123
iu-1.080
FU-1.073
utic-1.070
PN-1.057
Token 55
Token ID5996
Feature activation-1.59e+01

Pos logit contributions
onder+0.600
aturdays+0.600
lear+0.575
xxxx+0.571
coat+0.570
Neg logit contributions
isphere-0.675
FU-0.660
iu-0.659
PN-0.649
utic-0.643
Token80
Token ID1795
Feature activation-1.55e+01

Pos logit contributions
xxxx+6.761
onder+5.962
coat+5.449
xxxxxxxx+5.365
ona+5.131
Neg logit contributions
isphere-14.274
 poaching-13.751
utic-13.747
-13.398
rency-13.395
Token953
Token ID49649
Feature activation-8.16e+00

Pos logit contributions
xxxx+5.112
onder+5.060
coat+5.046
ierra+4.942
uli+4.806
Neg logit contributions
-13.876
ILA-13.759
isphere-13.731
FU-13.708
 OW-13.552
Token 16
Token ID1467
Feature activation-1.18e+01

Pos logit contributions
xxxx+2.985
onder+2.961
lear+2.806
aturdays+2.722
coat+2.615
Neg logit contributions
isphere-8.029
PN-7.632
FU-7.567
utic-7.564
iu-7.502
Token27
Token ID1983
Feature activation-1.68e+01

Pos logit contributions
xxxx+3.668
onder+3.596
coat+2.885
lear+2.822
xxxxxxxx+2.812
Neg logit contributions
isphere-12.228
utic-11.690
-11.465
ILA-11.425
rency-11.414
Token145
Token ID18781
Feature activation-7.33e+00

Pos logit contributions
onder+4.822
coat+4.657
xxxx+4.509
lear+4.006
asta+3.935
Neg logit contributions
isphere-16.548
utic-15.761
 reign-15.696
PN-15.644
iu-15.641
Token Flat
Token ID21939
Feature activation-1.05e+01

Pos logit contributions
onder+2.884
aturdays+2.861
xxxx+2.829
coat+2.802
irtual+2.796
Neg logit contributions
isphere-6.940
FU-6.670
iu-6.653
PN-6.591
utic-6.502
Tokenbuff
Token ID36873
Feature activation-6.02e+00

Pos logit contributions
coat+3.491
onder+3.419
xxxx+3.406
lear+3.389
uli+3.129
Neg logit contributions
isphere-10.239
PN-10.099
FU-10.096
 KING-9.993
ILA-9.987
Tokeners
Token ID364
Feature activation-6.66e+00

Pos logit contributions
onder+4.065
xxxx+3.944
lear+3.886
coat+3.878
aturdays+3.834
Neg logit contributions
isphere-4.128
FU-4.004
PN-3.943
iu-3.888
utic-3.875
TokenReading
Token ID36120
Feature activation-2.97e+00

Pos logit contributions
onder+4.072
xxxx+4.069
lear+3.918
aturdays+3.879
coat+3.808
Neg logit contributions
isphere-4.939
utic-4.702
iu-4.667
FU-4.539
 reign-4.524
Token Naval
Token ID20818
Feature activation-4.98e+00

Pos logit contributions
isphere+0.291
FU+0.286
iu+0.286
PN+0.283
utic+0.280
Neg logit contributions
aturdays-0.228
onder-0.228
irtual-0.218
xxxx-0.218
lear-0.218
Token Air
Token ID3701
Feature activation-7.01e+00

Pos logit contributions
onder+2.317
coat+2.225
xxxx+2.212
lear+2.162
aturdays+2.154
Neg logit contributions
isphere-4.400
utic-4.302
FU-4.260
iu-4.249
PN-4.217
Token Station
Token ID9327
Feature activation-1.01e+00

Pos logit contributions
onder+3.126
coat+2.997
xxxx+2.980
lear+2.849
aturdays+2.817
Neg logit contributions
isphere-6.357
FU-6.199
utic-6.142
PN-6.098
iu-6.083
Token in
Token ID287
Feature activation-2.65e+00

Pos logit contributions
onder+0.701
aturdays+0.697
xxxx+0.675
lear+0.673
irtual+0.672
Neg logit contributions
isphere-0.665
FU-0.653
iu-0.649
PN-0.644
utic-0.637
Token South
Token ID2520
Feature activation-1.40e+00

Pos logit contributions
onder+2.315
aturdays+2.297
lear+2.268
xxxx+2.251
coat+2.243
Neg logit contributions
isphere-1.257
FU-1.233
iu-1.212
PN-1.196
utic-1.192
Token We
Token ID775
Feature activation-1.66e+01

Pos logit contributions
aturdays+0.872
onder+0.868
lear+0.834
xxxx+0.833
coat+0.828
Neg logit contributions
isphere-1.020
FU-1.011
iu-1.007
PN-1.002
utic-0.992
Tokenym
Token ID4948
Feature activation-7.31e+00

Pos logit contributions
onder+6.691
xxxx+6.592
lear+6.529
ierra+6.132
uli+6.004
Neg logit contributions
FU-14.284
 KING-13.881
MENTS-13.860
ILA-13.815
isphere-13.753
Tokenouth
Token ID1536
Feature activation+2.34e-01

Pos logit contributions
onder+1.434
lear+1.219
xxxx+1.189
aturdays+1.088
uli+1.064
Neg logit contributions
FU-8.348
ILA-8.338
PN-8.323
isphere-8.299
PI-8.216
Token.
Token ID13
Feature activation+2.58e+00

Pos logit contributions
isphere+0.133
iu+0.132
FU+0.132
PN+0.130
PI+0.127
Neg logit contributions
aturdays-0.186
onder-0.183
irtual-0.179
lear-0.177
xxxx-0.176
Token This
Token ID770
Feature activation+9.03e-02

Pos logit contributions
isphere+1.789
FU+1.752
iu+1.751
PN+1.737
utic+1.716
Neg logit contributions
aturdays-1.711
onder-1.698
irtual-1.636
lear-1.631
xxxx-1.629
Token is
Token ID318
Feature activation-1.84e+00

Pos logit contributions
isphere+0.053
iu+0.052
FU+0.052
PN+0.052
utic+0.051
Neg logit contributions
aturdays-0.070
onder-0.069
irtual-0.067
lear-0.067
xxxx-0.066
Token signature
Token ID9877
Feature activation-4.23e+00

Pos logit contributions
isphere+1.140
FU+1.120
iu+1.119
PN+1.106
utic+1.092
Neg logit contributions
aturdays-1.133
onder-1.129
irtual-1.088
xxxx-1.085
lear-1.084
Token was
Token ID373
Feature activation-2.95e-01

Pos logit contributions
onder+2.775
coat+2.716
lear+2.702
aturdays+2.695
xxxx+2.687
Neg logit contributions
isphere-2.867
PN-2.787
FU-2.786
utic-2.785
iu-2.779
Token not
Token ID407
Feature activation+1.67e+00

Pos logit contributions
onder+0.199
aturdays+0.197
lear+0.192
xxxx+0.191
coat+0.191
Neg logit contributions
isphere-0.200
FU-0.197
iu-0.196
PN-0.195
utic-0.193
Token required
Token ID2672
Feature activation+6.79e-01

Pos logit contributions
isphere+1.116
FU+1.095
iu+1.093
PN+1.083
utic+1.070
Neg logit contributions
aturdays-1.149
onder-1.148
irtual-1.105
xxxx-1.104
lear-1.103
Token at
Token ID379
Feature activation+2.83e+00

Pos logit contributions
isphere+0.414
FU+0.405
iu+0.404
PN+0.400
utic+0.395
Neg logit contributions
onder-0.507
aturdays-0.506
xxxx-0.489
lear-0.488
irtual-0.488
Token Cas
Token ID11294
Feature activation-1.66e+01

Pos logit contributions
isphere+1.857
iu+1.847
FU+1.831
PN+1.818
utic+1.789
Neg logit contributions
aturdays-1.977
onder-1.957
irtual-1.889
lear-1.882
xxxx-1.871
Tokenert
Token ID861
Feature activation+1.86e-01

Pos logit contributions
onder+8.869
ierra+7.883
uli+7.812
xxxx+7.765
coat+7.763
Neg logit contributions
FU-12.153
isphere-11.980
ITNESS-11.913
PN-11.901
 KING-11.854
Tokena
Token ID64
Feature activation+2.63e+00

Pos logit contributions
isphere+0.115
iu+0.115
FU+0.113
PN+0.111
utic+0.110
Neg logit contributions
aturdays-0.139
onder-0.136
irtual-0.133
lear-0.132
xxxx-0.131
Token.[
Token ID3693
Feature activation-4.65e+00

Pos logit contributions
isphere+1.524
iu+1.493
FU+1.491
PN+1.470
utic+1.448
Neg logit contributions
aturdays-2.052
onder-2.034
irtual-1.975
lear-1.971
xxxx-1.966
Token34
Token ID2682
Feature activation-1.39e+00

Pos logit contributions
onder+1.851
coat+1.774
lear+1.773
xxxx+1.763
aturdays+1.742
Neg logit contributions
isphere-4.400
FU-4.329
utic-4.258
iu-4.251
PN-4.234
Token]
Token ID60
Feature activation-1.09e+00

Pos logit contributions
onder+1.059
aturdays+1.054
xxxx+1.025
coat+1.021
irtual+1.020
Neg logit contributions
isphere-0.822
FU-0.803
iu-0.799
PN-0.790
utic-0.781
Token Cycl
Token ID28007
Feature activation-1.25e+00

Pos logit contributions
iu+2.554
FU+2.532
PN+2.479
isphere+2.472
utic+2.461
Neg logit contributions
aturdays-4.580
onder-4.380
irtual-4.366
lear-4.232
ierra-4.163
Tokeniste
Token ID40833
Feature activation+2.52e+00

Pos logit contributions
onder+0.666
aturdays+0.665
xxxx+0.634
lear+0.632
irtual+0.632
Neg logit contributions
isphere-1.025
FU-1.009
iu-1.007
PN-1.001
utic-0.990
Token FD
Token ID30002
Feature activation+7.96e+00

Pos logit contributions
isphere+1.251
FU+1.244
iu+1.238
PN+1.222
utic+1.196
Neg logit contributions
aturdays-2.164
onder-2.143
irtual-2.091
lear-2.087
xxxx-2.077
TokenJ
Token ID41
Feature activation+3.78e+00

Pos logit contributions
FU+3.762
PN+3.691
iu+3.657
PI+3.643
IFF+3.263
Neg logit contributions
aturdays-7.427
irtual-7.311
 millenn-7.180
onder-6.863
lear-6.825
Token -
Token ID532
Feature activation-2.61e+00

Pos logit contributions
iu+1.774
FU+1.771
PN+1.744
PI+1.705
isphere+1.691
Neg logit contributions
aturdays-3.485
irtual-3.327
onder-3.256
lear-3.203
ierra-3.156
Token Big
Token ID4403
Feature activation-1.65e+01

Pos logit contributions
onder+1.291
aturdays+1.275
lear+1.226
xxxx+1.223
irtual+1.219
Neg logit contributions
isphere-2.261
FU-2.206
iu-2.192
PN-2.165
utic-2.148
TokenMat
Token ID19044
Feature activation-3.68e+00

Pos logit contributions
xxxx+5.700
coat+5.519
onder+5.445
lear+4.996
xxxxxxxx+4.806
Neg logit contributions
isphere-15.038
rency-14.437
utic-14.430
 poaching-14.360
iu-14.164
Token)
Token ID8
Feature activation-5.30e+00

Pos logit contributions
onder+2.269
xxxx+2.184
aturdays+2.164
coat+2.162
lear+2.144
Neg logit contributions
isphere-2.761
FU-2.653
iu-2.630
PN-2.623
utic-2.614
Token s
Token ID264
Feature activation+1.20e+00

Pos logit contributions
onder+3.831
aturdays+3.804
xxxx+3.713
irtual+3.647
lear+3.636
Neg logit contributions
isphere-3.361
FU-3.167
iu-3.122
utic-3.106
PN-3.100
Token.
Token ID13
Feature activation-2.40e+00

Pos logit contributions
iu+0.655
FU+0.652
isphere+0.647
PN+0.640
PI+0.627
Neg logit contributions
aturdays-0.995
irtual-0.961
onder-0.956
lear-0.930
xxxx-0.918
Tokent
Token ID83
Feature activation+2.79e+00

Pos logit contributions
onder+1.564
aturdays+1.545
xxxx+1.503
lear+1.500
coat+1.492
Neg logit contributions
isphere-1.700
FU-1.660
iu-1.655
PN-1.643
utic-1.625
Token/
Token ID14
Feature activation+3.95e+00

Pos logit contributions
iu+1.889
FU+1.863
PN+1.845
PI+1.826
isphere+1.768
Neg logit contributions
aturdays-3.555
irtual-3.413
onder-3.351
 millenn-3.321
lear-3.277
Tokenin
Token ID259
Feature activation-2.18e+00

Pos logit contributions
isphere+2.816
iu+2.802
FU+2.759
PN+2.740
PI+2.716
Neg logit contributions
aturdays-2.540
onder-2.486
xxxx-2.404
irtual-2.401
lear-2.364
Tokencoming
Token ID4976
Feature activation-4.30e+00

Pos logit contributions
onder+1.480
aturdays+1.474
lear+1.420
xxxx+1.420
coat+1.419
Neg logit contributions
isphere-1.468
iu-1.438
FU-1.437
PN-1.428
utic-1.406
Token/
Token ID14
Feature activation+7.04e-01

Pos logit contributions
onder+3.160
aturdays+3.116
xxxx+3.019
lear+3.018
coat+3.015
Neg logit contributions
isphere-2.671
FU-2.580
utic-2.576
iu-2.573
PN-2.540
Tokenarticle
Token ID20205
Feature activation-4.61e+00

Pos logit contributions
isphere+0.601
FU+0.592
iu+0.591
PN+0.586
utic+0.581
Neg logit contributions
aturdays-0.354
onder-0.353
irtual-0.335
xxxx-0.335
lear-0.334
Token35
Token ID2327
Feature activation-1.64e+01

Pos logit contributions
onder+2.265
aturdays+2.227
lear+2.214
xxxx+2.212
coat+2.140
Neg logit contributions
isphere-3.930
iu-3.844
FU-3.838
utic-3.796
PN-3.771
Token79
Token ID3720
Feature activation-7.90e+00

Pos logit contributions
xxxx+6.692
onder+5.781
xxxxxxxx+5.763
lear+5.553
coat+5.472
Neg logit contributions
isphere-14.065
iu-13.881
ILA-13.616
rency-13.501
 poaching-13.476
Token23
Token ID1954
Feature activation-5.95e+00

Pos logit contributions
xxxx+4.346
onder+4.206
coat+4.040
lear+4.013
aturdays+4.004
Neg logit contributions
isphere-6.276
utic-5.883
FU-5.858
iu-5.843
 reign-5.812
Token12
Token ID1065
Feature activation-2.75e+00

Pos logit contributions
xxxx+2.763
onder+2.735
aturdays+2.603
coat+2.590
lear+2.556
Neg logit contributions
isphere-5.299
utic-5.025
FU-5.017
iu-4.997
PN-4.991
Token.
Token ID13
Feature activation-3.97e-01

Pos logit contributions
onder+1.935
xxxx+1.886
coat+1.870
lear+1.864
aturdays+1.849
Neg logit contributions
isphere-1.820
FU-1.725
utic-1.712
PN-1.711
iu-1.706
Tokene
Token ID68
Feature activation+5.17e+00

Pos logit contributions
aturdays+0.231
onder+0.228
irtual+0.221
xxxx+0.218
lear+0.216
Neg logit contributions
isphere-0.311
iu-0.306
FU-0.305
PN-0.301
utic-0.297
Token [
Token ID685
Feature activation-3.20e+00

Pos logit contributions
isphere+0.308
FU+0.300
iu+0.299
PN+0.295
utic+0.289
Neg logit contributions
aturdays-0.609
onder-0.608
irtual-0.591
xxxx-0.591
lear-0.590
Tokenreturn
Token ID7783
Feature activation+3.57e-01

Pos logit contributions
onder+1.424
xxxx+1.366
aturdays+1.338
coat+1.334
lear+1.332
Neg logit contributions
isphere-2.916
FU-2.856
utic-2.846
iu-2.826
PN-2.825
Token address
Token ID2209
Feature activation+9.76e-01

Pos logit contributions
isphere+0.298
FU+0.293
iu+0.292
PN+0.290
utic+0.288
Neg logit contributions
onder-0.186
aturdays-0.186
xxxx-0.178
lear-0.177
irtual-0.177
Token]
Token ID60
Feature activation-1.39e+00

Pos logit contributions
isphere+0.525
iu+0.519
FU+0.516
PN+0.511
PI+0.499
Neg logit contributions
aturdays-0.809
onder-0.791
irtual-0.779
lear-0.769
xxxx-0.763
Token |
Token ID930
Feature activation+3.61e+00

Pos logit contributions
onder+0.848
aturdays+0.838
xxxx+0.818
lear+0.811
coat+0.807
Neg logit contributions
isphere-1.039
FU-1.014
iu-1.012
PN-1.003
utic-0.997
Token +
Token ID1343
Feature activation-1.64e+01

Pos logit contributions
iu+1.886
FU+1.857
isphere+1.832
PN+1.818
PI+1.797
Neg logit contributions
aturdays-3.098
irtual-2.964
onder-2.963
lear-2.889
ierra-2.838
Token--------------------
Token ID19351
Feature activation-3.03e+00

Pos logit contributions
xxxx+3.075
onder+2.340
coat+2.285
uli+1.848
lear+1.841
Neg logit contributions
isphere-18.316
utic-17.398
lete-17.238
rency-17.183
 poaching-16.984
Token--+
Token ID44785
Feature activation+4.50e+00

Pos logit contributions
onder+1.794
aturdays+1.761
xxxx+1.752
coat+1.734
lear+1.721
Neg logit contributions
isphere-2.314
FU-2.248
iu-2.241
utic-2.225
PN-2.217
Token +
Token ID1343
Feature activation-1.47e+01

Pos logit contributions
iu+2.267
FU+2.201
PI+2.162
PN+2.148
isphere+2.137
Neg logit contributions
aturdays-4.014
irtual-3.836
onder-3.781
lear-3.685
 millenn-3.675
Token--------------------
Token ID19351
Feature activation-3.90e+00

Pos logit contributions
xxxx+3.166
onder+2.548
coat+2.453
lear+2.129
xxxxxxxx+2.077
Neg logit contributions
isphere-16.311
utic-15.456
lete-15.345
rency-15.258
 poaching-15.032
Token--+
Token ID44785
Feature activation-2.86e-01

Pos logit contributions
onder+2.237
xxxx+2.206
coat+2.182
aturdays+2.178
lear+2.150
Neg logit contributions
isphere-3.025
FU-2.926
utic-2.916
iu-2.912
PN-2.887
Token mobile
Token ID5175
Feature activation-2.88e+00

Pos logit contributions
onder+1.692
aturdays+1.685
irtual+1.627
coat+1.621
lear+1.617
Neg logit contributions
isphere-1.838
FU-1.819
PN-1.787
iu-1.784
utic-1.773
Token devices
Token ID4410
Feature activation-3.32e+00

Pos logit contributions
onder+1.788
aturdays+1.749
irtual+1.672
lear+1.670
xxxx+1.670
Neg logit contributions
isphere-2.114
FU-2.084
utic-2.071
iu-2.070
PN-2.052
Token.
Token ID13
Feature activation-1.05e-01

Pos logit contributions
onder+2.329
aturdays+2.296
lear+2.221
irtual+2.212
coat+2.208
Neg logit contributions
isphere-2.164
FU-2.116
PN-2.100
iu-2.096
utic-2.073
Token
Token ID198
Feature activation-4.40e+00

Pos logit contributions
onder+0.066
aturdays+0.066
xxxx+0.064
lear+0.063
irtual+0.063
Neg logit contributions
isphere-0.077
FU-0.075
iu-0.075
PN-0.074
utic-0.073
Token
Token ID198
Feature activation-2.61e+00

Pos logit contributions
onder+2.510
xxxx+2.449
coat+2.400
lear+2.378
aturdays+2.333
Neg logit contributions
isphere-3.488
FU-3.338
utic-3.316
PN-3.306
iu-3.306
TokenFirst
Token ID5962
Feature activation-1.64e+01

Pos logit contributions
onder+1.777
aturdays+1.741
xxxx+1.740
lear+1.729
coat+1.727
Neg logit contributions
isphere-1.746
utic-1.690
iu-1.663
FU-1.651
PN-1.630
Token published
Token ID3199
Feature activation-4.38e+00

Pos logit contributions
aturdays+9.544
irtual+9.354
coat+9.277
lear+9.249
onder+9.161
Neg logit contributions
utic-10.433
isphere-9.800
lete-9.707
iu-9.587
rency-9.546
Token Dec
Token ID4280
Feature activation-4.35e+00

Pos logit contributions
aturdays+3.004
onder+2.997
xxxx+2.893
irtual+2.881
lear+2.871
Neg logit contributions
isphere-2.873
FU-2.820
utic-2.818
PN-2.765
iu-2.756
Token.
Token ID13
Feature activation+3.72e-01

Pos logit contributions
onder+2.954
aturdays+2.863
xxxx+2.862
lear+2.831
coat+2.819
Neg logit contributions
isphere-2.966
FU-2.856
utic-2.805
PN-2.797
iu-2.776
Token 1
Token ID352
Feature activation+8.25e-01

Pos logit contributions
isphere+0.287
iu+0.285
FU+0.284
PN+0.282
utic+0.277
Neg logit contributions
aturdays-0.217
onder-0.215
irtual-0.208
lear-0.205
xxxx-0.204
Token,
Token ID11
Feature activation+1.03e+00

Pos logit contributions
isphere+0.523
FU+0.513
iu+0.513
PN+0.508
utic+0.499
Neg logit contributions
aturdays-0.597
onder-0.594
irtual-0.575
xxxx-0.573
lear-0.573
Token years
Token ID812
Feature activation+7.16e+00

Pos logit contributions
isphere+3.208
iu+3.103
FU+3.091
PN+3.062
PI+3.029
Neg logit contributions
aturdays-2.952
onder-2.920
irtual-2.852
lear-2.825
xxxx-2.820
Token later
Token ID1568
Feature activation+7.72e-01

Pos logit contributions
isphere+4.198
iu+4.053
 reign+4.007
FU+3.967
PN+3.953
Neg logit contributions
aturdays-5.404
irtual-5.283
onder-5.276
lear-5.174
xxxx-5.101
Token,
Token ID11
Feature activation-4.02e-02

Pos logit contributions
isphere+0.496
FU+0.486
iu+0.485
PN+0.480
utic+0.474
Neg logit contributions
aturdays-0.552
onder-0.551
irtual-0.531
xxxx-0.530
lear-0.530
Token the
Token ID262
Feature activation+1.97e+00

Pos logit contributions
aturdays+0.028
onder+0.028
irtual+0.026
xxxx+0.026
lear+0.026
Neg logit contributions
isphere-0.027
FU-0.027
iu-0.027
PN-0.026
utic-0.026
Token relationship
Token ID2776
Feature activation+6.44e+00

Pos logit contributions
isphere+1.385
iu+1.355
FU+1.354
PN+1.340
utic+1.325
Neg logit contributions
aturdays-1.289
onder-1.281
irtual-1.239
lear-1.237
xxxx-1.229
Token is
Token ID318
Feature activation+1.22e+01

Pos logit contributions
isphere+3.614
 reign+3.570
FU+3.535
iu+3.530
PN+3.498
Neg logit contributions
aturdays-5.044
onder-4.929
irtual-4.893
lear-4.825
xxxx-4.784
Token still
Token ID991
Feature activation+9.19e+00

Pos logit contributions
 reign+6.950
iu+6.585
isphere+6.548
 KING+6.390
PN+6.348
Neg logit contributions
aturdays-9.101
irtual-9.004
onder-8.800
ierra-8.617
xxxx-8.589
Token going
Token ID1016
Feature activation+7.07e+00

Pos logit contributions
 reign+5.704
iu+5.583
isphere+5.579
PN+5.515
FU+5.400
Neg logit contributions
aturdays-6.501
irtual-6.355
onder-6.263
ierra-6.170
coat-6.033
Token strong
Token ID1913
Feature activation-6.20e-01

Pos logit contributions
isphere+3.671
iu+3.616
PN+3.577
FU+3.559
 reign+3.541
Neg logit contributions
aturdays-5.711
irtual-5.656
lear-5.595
onder-5.562
ierra-5.521
Token at
Token ID379
Feature activation-4.32e+00

Pos logit contributions
onder+0.455
aturdays+0.454
xxxx+0.438
lear+0.436
irtual+0.436
Neg logit contributions
isphere-0.387
FU-0.379
iu-0.378
PN-0.373
utic-0.370
Token Aut
Token ID5231
Feature activation-3.63e+00

Pos logit contributions
onder+2.956
aturdays+2.905
xxxx+2.837
irtual+2.820
coat+2.819
Neg logit contributions
isphere-2.865
FU-2.815
PN-2.782
iu-2.781
utic-2.728
Token intersection
Token ID16246
Feature activation+1.14e+01

Pos logit contributions
isphere+1.195
iu+1.172
FU+1.169
PN+1.157
utic+1.142
Neg logit contributions
aturdays-1.349
onder-1.344
irtual-1.300
lear-1.297
xxxx-1.295
Token of
Token ID286
Feature activation+6.56e+00

Pos logit contributions
isphere+5.630
iu+5.520
 reign+5.497
FU+5.457
PN+5.445
Neg logit contributions
aturdays-8.989
onder-8.868
irtual-8.851
lear-8.656
ierra-8.614
Token Bl
Token ID1086
Feature activation-6.05e-01

Pos logit contributions
isphere+4.057
iu+4.045
PN+3.990
FU+3.945
 KING+3.930
Neg logit contributions
aturdays-4.700
onder-4.579
irtual-4.563
lear-4.451
xxxx-4.421
Tokenoor
Token ID2675
Feature activation+3.89e+00

Pos logit contributions
onder+0.421
aturdays+0.414
lear+0.400
irtual+0.399
xxxx+0.397
Neg logit contributions
isphere-0.406
FU-0.401
PN-0.395
iu-0.394
PI-0.387
Token St
Token ID520
Feature activation+5.92e+00

Pos logit contributions
isphere+2.430
iu+2.388
FU+2.363
PN+2.360
PI+2.310
Neg logit contributions
aturdays-2.837
onder-2.810
irtual-2.744
lear-2.714
xxxx-2.711
Token.
Token ID13
Feature activation+1.05e+01

Pos logit contributions
isphere+3.291
iu+3.251
PN+3.190
FU+3.178
utic+3.115
Neg logit contributions
aturdays-4.680
onder-4.607
irtual-4.532
lear-4.499
coat-4.483
Token W
Token ID370
Feature activation+8.83e+00

Pos logit contributions
iu+5.434
isphere+5.401
PN+5.389
FU+5.316
 KING+5.269
Neg logit contributions
aturdays-8.262
onder-8.170
irtual-8.107
lear-7.984
coat-7.924
Token.
Token ID13
Feature activation+9.59e+00

Pos logit contributions
isphere+4.774
iu+4.762
PN+4.704
FU+4.670
PI+4.604
Neg logit contributions
aturdays-6.867
onder-6.733
irtual-6.668
lear-6.640
coat-6.638
Token and
Token ID290
Feature activation+3.58e+00

Pos logit contributions
iu+5.050
isphere+5.041
PN+4.991
 reign+4.909
FU+4.902
Neg logit contributions
aturdays-7.500
irtual-7.436
onder-7.344
lear-7.189
coat-7.174
Token Mill
Token ID9212
Feature activation-5.59e+00

Pos logit contributions
isphere+2.190
iu+2.167
FU+2.141
PN+2.139
utic+2.095
Neg logit contributions
aturdays-2.658
onder-2.621
irtual-2.569
lear-2.533
xxxx-2.526
Token Rd
Token ID20769
Feature activation+5.89e+00

Pos logit contributions
onder+4.121
aturdays+3.975
coat+3.900
lear+3.881
uli+3.854
Neg logit contributions
FU-3.518
isphere-3.367
PN-3.364
PI-3.308
utic-3.286
Token in
Token ID287
Feature activation+3.49e+00

Pos logit contributions
isphere+2.283
iu+2.264
FU+2.231
PN+2.224
utic+2.172
Neg logit contributions
aturdays-2.660
onder-2.639
lear-2.563
xxxx-2.554
irtual-2.552
Token N
Token ID399
Feature activation+2.77e+00

Pos logit contributions
isphere+2.330
iu+2.319
PN+2.317
FU+2.299
PI+2.262
Neg logit contributions
aturdays-2.411
onder-2.355
irtual-2.280
lear-2.271
xxxx-2.266
Token.
Token ID13
Feature activation+7.91e+00

Pos logit contributions
isphere+1.593
iu+1.584
FU+1.584
PN+1.565
PI+1.533
Neg logit contributions
aturdays-2.149
onder-2.127
irtual-2.071
lear-2.067
xxxx-2.060
Token Eng
Token ID1985
Feature activation+2.94e+00

Pos logit contributions
PN+4.055
iu+4.039
FU+3.981
PI+3.961
isphere+3.955
Neg logit contributions
aturdays-6.563
irtual-6.367
onder-6.354
coat-6.227
xxxx-6.219
Tokenl
Token ID75
Feature activation+2.06e+00

Pos logit contributions
iu+1.441
PN+1.429
isphere+1.404
FU+1.396
utic+1.386
Neg logit contributions
aturdays-2.518
onder-2.481
irtual-2.457
xxxx-2.435
lear-2.403
Token.
Token ID13
Feature activation+1.11e+01

Pos logit contributions
isphere+1.186
iu+1.174
FU+1.163
PN+1.156
utic+1.134
Neg logit contributions
aturdays-1.612
onder-1.592
irtual-1.559
lear-1.541
xxxx-1.538
Token J
Token ID449
Feature activation+4.79e+00

Pos logit contributions
PN+5.417
iu+5.299
PI+5.115
utic+5.032
 KING+4.867
Neg logit contributions
aturdays-9.851
irtual-9.562
onder-9.336
lear-9.013
coat-9.005
Token.
Token ID13
Feature activation+9.78e+00

Pos logit contributions
iu+2.630
PN+2.610
utic+2.581
isphere+2.580
FU+2.565
Neg logit contributions
aturdays-3.894
onder-3.777
irtual-3.741
xxxx-3.665
lear-3.664
Token Med
Token ID2019
Feature activation+3.20e+00

Pos logit contributions
PN+5.185
iu+5.159
utic+5.091
PI+4.895
lete+4.876
Neg logit contributions
aturdays-8.172
irtual-7.840
onder-7.580
ierra-7.562
lear-7.414
Token.,
Token ID1539
Feature activation-3.48e-02

Pos logit contributions
isphere+1.821
iu+1.815
FU+1.781
PN+1.778
utic+1.769
Neg logit contributions
aturdays-2.500
onder-2.477
irtual-2.411
xxxx-2.401
lear-2.393
Token Peter
Token ID5613
Feature activation+1.98e+00

Pos logit contributions
onder+0.024
aturdays+0.024
irtual+0.023
lear+0.023
xxxx+0.023
Neg logit contributions
isphere-0.023
FU-0.023
iu-0.022
PN-0.022
utic-0.022
Token
Token ID247
Feature activation-2.59e+00

Pos logit contributions
aturdays+3.464
onder+3.458
xxxx+3.370
coat+3.353
lear+3.349
Neg logit contributions
isphere-2.937
FU-2.917
iu-2.885
PN-2.850
utic-2.809
Token states
Token ID2585
Feature activation-6.29e+00

Pos logit contributions
onder+1.860
aturdays+1.853
xxxx+1.800
lear+1.788
irtual+1.782
Neg logit contributions
isphere-1.639
FU-1.600
iu-1.588
PN-1.576
utic-1.553
Token".
Token ID1911
Feature activation-1.94e-01

Pos logit contributions
onder+4.177
aturdays+4.135
lear+4.061
xxxx+4.041
coat+4.032
Neg logit contributions
isphere-4.146
FU-4.070
iu-4.005
PN-3.990
utic-3.968
Token
Token ID198
Feature activation+1.84e+00

Pos logit contributions
onder+0.127
aturdays+0.127
xxxx+0.123
lear+0.122
coat+0.121
Neg logit contributions
isphere-0.137
iu-0.133
FU-0.133
PN-0.131
utic-0.131
Token
Token ID198
Feature activation+9.37e-01

Pos logit contributions
FU+1.221
iu+1.212
PN+1.210
PI+1.192
isphere+1.185
Neg logit contributions
aturdays-1.330
irtual-1.272
onder-1.259
lear-1.216
ierra-1.197
TokenT
Token ID51
Feature activation+9.94e+00

Pos logit contributions
isphere+0.629
iu+0.615
FU+0.615
PN+0.607
utic+0.603
Neg logit contributions
onder-0.642
aturdays-0.642
xxxx-0.619
lear-0.618
irtual-0.617
Tokenrots
Token ID24744
Feature activation-3.31e+00

Pos logit contributions
iu+6.600
FU+6.476
PN+6.445
PI+6.335
isphere+6.333
Neg logit contributions
aturdays-6.320
onder-6.275
xxxx-6.163
lear-6.160
coat-6.154
Tokenky
Token ID2584
Feature activation+9.62e-01

Pos logit contributions
onder+2.270
aturdays+2.269
irtual+2.192
xxxx+2.188
coat+2.171
Neg logit contributions
isphere-2.216
FU-2.172
PN-2.135
utic-2.109
iu-2.102
Tokenism
Token ID1042
Feature activation+1.08e+00

Pos logit contributions
isphere+0.598
FU+0.585
iu+0.585
PN+0.578
utic+0.570
Neg logit contributions
aturdays-0.708
onder-0.706
irtual-0.682
xxxx-0.681
lear-0.680
Token isn
Token ID2125
Feature activation-5.10e-02

Pos logit contributions
isphere+0.681
iu+0.668
FU+0.666
PN+0.658
utic+0.651
Neg logit contributions
aturdays-0.779
onder-0.776
irtual-0.749
lear-0.749
xxxx-0.748
Token
Token ID447
Feature activation-5.19e-01

Pos logit contributions
aturdays+0.037
onder+0.037
irtual+0.036
lear+0.035
xxxx+0.035
Neg logit contributions
isphere-0.032
iu-0.032
FU-0.032
PN-0.031
utic-0.031
Token building
Token ID2615
Feature activation+3.31e-01

Pos logit contributions
isphere+1.034
FU+1.011
iu+1.009
PN+0.997
utic+0.982
Neg logit contributions
aturdays-1.434
onder-1.432
irtual-1.385
xxxx-1.384
lear-1.383
Token in
Token ID287
Feature activation+2.85e+00

Pos logit contributions
isphere+0.220
FU+0.218
iu+0.216
PN+0.215
utic+0.214
Neg logit contributions
onder-0.228
aturdays-0.226
xxxx-0.218
coat-0.218
lear-0.217
Token Liverpool
Token ID11761
Feature activation+2.70e+00

Pos logit contributions
isphere+1.720
iu+1.693
FU+1.686
PN+1.660
utic+1.640
Neg logit contributions
aturdays-2.144
onder-2.137
irtual-2.062
lear-2.061
xxxx-2.050
Token,
Token ID11
Feature activation+3.89e+00

Pos logit contributions
isphere+1.724
iu+1.689
FU+1.687
PN+1.667
utic+1.644
Neg logit contributions
aturdays-1.936
onder-1.930
irtual-1.863
lear-1.862
xxxx-1.861
Token U
Token ID471
Feature activation+5.23e+00

Pos logit contributions
isphere+2.311
FU+2.255
iu+2.254
PN+2.233
PI+2.184
Neg logit contributions
aturdays-2.946
onder-2.943
irtual-2.859
xxxx-2.850
lear-2.842
Token.
Token ID13
Feature activation+1.09e+01

Pos logit contributions
isphere+2.913
FU+2.884
PN+2.866
iu+2.820
PI+2.814
Neg logit contributions
aturdays-4.164
onder-4.112
irtual-4.035
lear-4.005
coat-3.949
TokenK
Token ID42
Feature activation+1.30e+00

Pos logit contributions
FU+3.506
PN+3.488
PI+3.335
isphere+3.269
iu+3.210
Neg logit contributions
onder-10.711
aturdays-10.612
irtual-10.560
lear-10.445
xxxx-10.312
Token.,
Token ID1539
Feature activation+5.27e+00

Pos logit contributions
isphere+0.793
FU+0.775
iu+0.773
PN+0.765
utic+0.755
Neg logit contributions
aturdays-0.971
onder-0.971
irtual-0.937
xxxx-0.936
lear-0.936
Token to
Token ID284
Feature activation+5.36e+00

Pos logit contributions
isphere+3.352
iu+3.291
FU+3.259
PN+3.234
PI+3.182
Neg logit contributions
aturdays-3.775
onder-3.756
xxxx-3.627
irtual-3.626
lear-3.603
Token remove
Token ID4781
Feature activation+6.86e+00

Pos logit contributions
isphere+3.166
FU+3.107
iu+3.105
PN+3.039
PI+3.001
Neg logit contributions
aturdays-4.108
onder-4.049
lear-3.925
xxxx-3.913
irtual-3.900
Token the
Token ID262
Feature activation+3.91e+00

Pos logit contributions
isphere+4.361
iu+4.339
FU+4.283
PN+4.206
PI+4.192
Neg logit contributions
onder-4.842
aturdays-4.772
xxxx-4.626
irtual-4.624
lear-4.607
Token to
Token ID284
Feature activation-5.47e+00

Pos logit contributions
onder+5.141
coat+4.972
xxxx+4.918
lear+4.834
aturdays+4.773
Neg logit contributions
isphere-6.205
FU-6.203
utic-6.137
PN-6.108
iu-5.910
Token be
Token ID307
Feature activation-6.87e+00

Pos logit contributions
onder+3.159
aturdays+3.002
coat+2.947
xxxx+2.917
lear+2.886
Neg logit contributions
isphere-4.305
PN-4.180
FU-4.153
iu-4.126
utic-4.089
Token a
Token ID257
Feature activation-4.60e+00

Pos logit contributions
onder+4.127
coat+3.991
xxxx+3.948
lear+3.896
aturdays+3.890
Neg logit contributions
isphere-5.061
FU-5.046
PN-4.958
utic-4.850
iu-4.850
Token woman
Token ID2415
Feature activation+7.96e-01

Pos logit contributions
onder+3.573
coat+3.491
xxxx+3.460
aturdays+3.439
lear+3.417
Neg logit contributions
isphere-2.653
FU-2.601
PN-2.553
iu-2.536
utic-2.532
Token,
Token ID11
Feature activation-1.66e+00

Pos logit contributions
isphere+0.512
FU+0.503
iu+0.501
PN+0.497
utic+0.490
Neg logit contributions
aturdays-0.568
onder-0.568
xxxx-0.547
irtual-0.546
lear-0.546
Token and
Token ID290
Feature activation+5.03e-01

Pos logit contributions
onder+1.098
aturdays+1.095
xxxx+1.063
lear+1.049
coat+1.047
Neg logit contributions
isphere-1.154
FU-1.128
iu-1.121
PN-1.116
utic-1.103
Token we
Token ID356
Feature activation-8.29e-01

Pos logit contributions
isphere+0.334
FU+0.327
iu+0.327
PN+0.324
utic+0.320
Neg logit contributions
aturdays-0.349
onder-0.349
xxxx-0.336
lear-0.335
irtual-0.335
Token
Token ID447
Feature activation+1.40e+00

Pos logit contributions
onder+0.591
aturdays+0.584
lear+0.569
xxxx+0.566
coat+0.565
Neg logit contributions
isphere-0.536
FU-0.525
iu-0.522
PN-0.521
utic-0.514
Token
Token ID247
Feature activation+6.29e-02

Pos logit contributions
isphere+0.432
FU+0.417
iu+0.417
PN+0.405
utic+0.392
Neg logit contributions
aturdays-1.469
onder-1.460
irtual-1.432
lear-1.423
xxxx-1.422
Tokenre
Token ID260
Feature activation-2.97e+00

Pos logit contributions
isphere+0.043
FU+0.043
iu+0.042
PN+0.042
utic+0.041
Neg logit contributions
onder-0.042
aturdays-0.042
lear-0.040
xxxx-0.040
coat-0.040
Token all
Token ID477
Feature activation-2.85e+00

Pos logit contributions
onder+1.907
aturdays+1.891
lear+1.834
xxxx+1.828
coat+1.820
Neg logit contributions
isphere-2.096
FU-2.088
PN-2.057
iu-2.048
utic-2.012
Token.
Token ID13
Feature activation-7.39e-01

Pos logit contributions
onder+2.280
aturdays+2.277
xxxx+2.176
irtual+2.175
lear+2.174
Neg logit contributions
isphere-2.152
FU-2.123
PN-2.089
iu-2.066
utic-2.057
Token
Token ID198
Feature activation+7.46e-01

Pos logit contributions
onder+0.455
aturdays+0.453
xxxx+0.436
irtual+0.434
lear+0.432
Neg logit contributions
isphere-0.552
FU-0.536
iu-0.532
PN-0.530
utic-0.524
Token
Token ID198
Feature activation-8.50e-01

Pos logit contributions
iu+0.501
FU+0.498
isphere+0.494
PN+0.493
PI+0.487
Neg logit contributions
aturdays-0.528
irtual-0.505
onder-0.503
lear-0.485
ierra-0.477
TokenThe
Token ID464
Feature activation+6.31e-01

Pos logit contributions
onder+0.568
aturdays+0.564
xxxx+0.555
lear+0.548
coat+0.545
Neg logit contributions
isphere-0.585
utic-0.563
iu-0.563
FU-0.560
PN-0.553
Token executions
Token ID30632
Feature activation+1.71e+00

Pos logit contributions
isphere+0.413
FU+0.405
iu+0.404
PN+0.400
utic+0.396
Neg logit contributions
aturdays-0.443
onder-0.442
irtual-0.426
xxxx-0.425
lear-0.425
Token took
Token ID1718
Feature activation+1.92e+00

Pos logit contributions
isphere+1.018
iu+0.996
FU+0.992
PN+0.982
utic+0.967
Neg logit contributions
aturdays-1.304
onder-1.295
xxxx-1.255
lear-1.253
irtual-1.253
Token place
Token ID1295
Feature activation+5.02e+00

Pos logit contributions
isphere+1.252
iu+1.227
FU+1.223
PN+1.212
utic+1.195
Neg logit contributions
aturdays-1.358
onder-1.352
irtual-1.307
xxxx-1.306
lear-1.304
Token on
Token ID319
Feature activation+9.13e-01

Pos logit contributions
isphere+3.007
iu+2.970
FU+2.889
PN+2.877
 reign+2.856
Neg logit contributions
aturdays-3.756
onder-3.740
lear-3.632
xxxx-3.631
irtual-3.630
Token Sunday
Token ID3502
Feature activation+6.13e+00

Pos logit contributions
isphere+0.580
FU+0.569
iu+0.568
PN+0.562
utic+0.554
Neg logit contributions
aturdays-0.658
onder-0.657
irtual-0.634
xxxx-0.633
lear-0.633
Token November
Token ID3389
Feature activation-2.55e-01

Pos logit contributions
iu+3.515
isphere+3.471
PN+3.408
 reign+3.360
FU+3.354
Neg logit contributions
aturdays-4.740
onder-4.630
lear-4.586
irtual-4.553
xxxx-4.550
Token 3
Token ID513
Feature activation-1.37e+00

Pos logit contributions
aturdays+0.146
onder+0.146
xxxx+0.140
irtual+0.139
lear+0.139
Neg logit contributions
isphere-0.199
FU-0.196
iu-0.195
PN-0.194
utic-0.192
Token then
Token ID788
Feature activation-3.00e-01

Pos logit contributions
isphere+0.223
FU+0.218
iu+0.217
PN+0.216
utic+0.213
Neg logit contributions
aturdays-0.227
onder-0.227
xxxx-0.218
irtual-0.218
lear-0.218
Token,
Token ID11
Feature activation+5.03e+00

Pos logit contributions
aturdays+0.211
onder+0.211
lear+0.203
irtual+0.202
xxxx+0.202
Neg logit contributions
isphere-0.196
FU-0.192
iu-0.191
PN-0.190
utic-0.188
Token to
Token ID284
Feature activation-4.37e-01

Pos logit contributions
isphere+3.141
iu+3.139
FU+3.083
PN+3.028
PI+3.023
Neg logit contributions
aturdays-3.587
onder-3.567
irtual-3.487
xxxx-3.451
lear-3.443
Token see
Token ID766
Feature activation-2.61e-01

Pos logit contributions
onder+0.284
aturdays+0.282
xxxx+0.271
irtual+0.270
lear+0.270
Neg logit contributions
isphere-0.311
FU-0.303
iu-0.303
PN-0.302
utic-0.298
Token the
Token ID262
Feature activation-3.35e+00

Pos logit contributions
onder+0.177
aturdays+0.177
irtual+0.171
xxxx+0.171
lear+0.170
Neg logit contributions
isphere-0.177
FU-0.173
iu-0.172
PN-0.171
utic-0.169
Token guy
Token ID3516
Feature activation+1.05e+00

Pos logit contributions
onder+2.305
aturdays+2.274
xxxx+2.211
coat+2.211
irtual+2.201
Neg logit contributions
isphere-2.237
FU-2.177
PN-2.161
iu-2.154
utic-2.124
Token in
Token ID287
Feature activation+1.18e+00

Pos logit contributions
isphere+0.680
FU+0.666
iu+0.663
PN+0.659
utic+0.650
Neg logit contributions
aturdays-0.745
onder-0.745
lear-0.718
irtual-0.718
xxxx-0.717
Token our
Token ID674
Feature activation-1.07e+01

Pos logit contributions
isphere+0.790
iu+0.777
FU+0.776
PN+0.768
utic+0.758
Neg logit contributions
aturdays-0.804
onder-0.800
irtual-0.771
xxxx-0.770
lear-0.770
Token story
Token ID1621
Feature activation-3.97e+00

Pos logit contributions
aturdays+6.804
onder+6.744
xxxx+6.698
coat+6.580
irtual+6.518
Neg logit contributions
isphere-7.040
PN-6.880
FU-6.872
lete-6.798
iu-6.792
Token make
Token ID787
Feature activation+9.10e+00

Pos logit contributions
onder+2.736
aturdays+2.718
lear+2.662
coat+2.648
xxxx+2.602
Neg logit contributions
isphere-2.593
PN-2.558
FU-2.540
utic-2.523
iu-2.511
Token a
Token ID257
Feature activation+5.13e+00

Pos logit contributions
iu+5.499
isphere+5.215
FU+5.206
 reign+5.183
PI+5.174
Neg logit contributions
aturdays-6.638
onder-6.446
irtual-6.347
xxxx-6.228
lear-6.206
Token illegal
Token ID5293
Feature activation-7.91e-01

Pos logit contributions
onder+4.535
aturdays+4.472
coat+4.396
irtual+4.348
xxxx+4.300
Neg logit contributions
isphere-5.819
FU-5.627
PN-5.503
utic-5.501
iu-5.476
Token settlements
Token ID18573
Feature activation-2.10e+00

Pos logit contributions
onder+0.352
aturdays+0.350
lear+0.332
xxxx+0.331
irtual+0.329
Neg logit contributions
isphere-0.720
FU-0.710
iu-0.707
PN-0.703
utic-0.699
Token in
Token ID287
Feature activation-5.24e+00

Pos logit contributions
onder+1.456
aturdays+1.450
xxxx+1.400
irtual+1.393
coat+1.392
Neg logit contributions
isphere-1.391
FU-1.361
iu-1.349
PN-1.338
utic-1.332
Token Jerusalem
Token ID10843
Feature activation-3.69e+00

Pos logit contributions
onder+3.061
aturdays+2.966
coat+2.892
xxxx+2.867
irtual+2.840
Neg logit contributions
isphere-3.998
FU-3.924
PN-3.880
iu-3.875
utic-3.857
Token,
Token ID11
Feature activation-2.19e+00

Pos logit contributions
onder+2.563
aturdays+2.533
xxxx+2.467
irtual+2.464
lear+2.421
Neg logit contributions
isphere-2.404
FU-2.362
iu-2.319
PN-2.305
utic-2.293
Token as
Token ID355
Feature activation+1.62e+00

Pos logit contributions
aturdays+1.457
onder+1.452
irtual+1.394
xxxx+1.384
coat+1.383
Neg logit contributions
isphere-1.517
FU-1.492
iu-1.476
PN-1.459
utic-1.453
Token if
Token ID611
Feature activation+3.31e+00

Pos logit contributions
isphere+1.010
FU+0.989
iu+0.988
PN+0.978
utic+0.963
Neg logit contributions
aturdays-1.182
onder-1.179
irtual-1.139
xxxx-1.138
lear-1.137
Token there
Token ID612
Feature activation-1.76e+00

Pos logit contributions
isphere+2.165
iu+2.131
FU+2.126
PN+2.108
PI+2.072
Neg logit contributions
aturdays-2.321
onder-2.308
irtual-2.246
lear-2.224
xxxx-2.222
Token are
Token ID389
Feature activation-3.29e-01

Pos logit contributions
onder+1.277
aturdays+1.253
lear+1.215
xxxx+1.214
coat+1.209
Neg logit contributions
isphere-1.118
FU-1.100
iu-1.089
PN-1.082
utic-1.070
Token no
Token ID645
Feature activation-5.81e+00

Pos logit contributions
onder+0.264
aturdays+0.263
xxxx+0.255
lear+0.254
coat+0.253
Neg logit contributions
isphere-0.182
FU-0.179
iu-0.177
PN-0.176
utic-0.173
Token consequences
Token ID6948
Feature activation-9.95e+00

Pos logit contributions
onder+3.652
aturdays+3.544
xxxx+3.433
lear+3.401
coat+3.394
Neg logit contributions
FU-4.133
isphere-4.106
iu-4.012
PN-4.008
utic-4.007
Token failure
Token ID5287
Feature activation-3.28e+00

Pos logit contributions
onder+1.225
aturdays+1.161
xxxx+1.140
lear+1.124
coat+1.120
Neg logit contributions
isphere-2.450
FU-2.396
iu-2.395
PN-2.380
utic-2.364
Token.
Token ID13
Feature activation+9.01e-01

Pos logit contributions
onder+2.332
aturdays+2.308
xxxx+2.242
lear+2.226
coat+2.222
Neg logit contributions
isphere-2.109
FU-2.055
iu-2.055
PN-2.006
utic-1.989
Token NASA
Token ID8884
Feature activation-2.14e+00

Pos logit contributions
isphere+0.625
iu+0.612
FU+0.611
PN+0.604
utic+0.599
Neg logit contributions
onder-0.598
aturdays-0.597
xxxx-0.575
lear-0.573
irtual-0.572
Token Headquarters
Token ID32193
Feature activation-7.38e+00

Pos logit contributions
onder+1.478
aturdays+1.475
xxxx+1.432
lear+1.424
irtual+1.412
Neg logit contributions
isphere-1.413
iu-1.396
FU-1.388
PN-1.364
utic-1.363
Token formed
Token ID7042
Feature activation+8.93e-01

Pos logit contributions
onder+4.810
aturdays+4.682
xxxx+4.580
ierra+4.517
lear+4.495
Neg logit contributions
utic-4.893
isphere-4.867
FU-4.832
iu-4.816
PN-4.747
Token another
Token ID1194
Feature activation+2.88e+00

Pos logit contributions
isphere+0.613
FU+0.601
iu+0.601
PN+0.595
utic+0.587
Neg logit contributions
aturdays-0.599
onder-0.598
irtual-0.575
xxxx-0.574
lear-0.574
Token board
Token ID3096
Feature activation+1.60e-02

Pos logit contributions
isphere+1.887
FU+1.845
iu+1.844
PN+1.830
utic+1.796
Neg logit contributions
aturdays-2.028
onder-2.003
irtual-1.941
xxxx-1.932
lear-1.931
Token of
Token ID286
Feature activation-1.74e+00

Pos logit contributions
isphere+0.011
FU+0.011
iu+0.011
PN+0.011
utic+0.011
Neg logit contributions
onder-0.011
aturdays-0.011
irtual-0.010
xxxx-0.010
lear-0.010
Token inquiry
Token ID12069
Feature activation+8.88e-01

Pos logit contributions
onder+1.161
aturdays+1.147
lear+1.119
irtual+1.112
xxxx+1.108
Neg logit contributions
isphere-1.203
FU-1.185
iu-1.182
PN-1.162
utic-1.151
Token to
Token ID284
Feature activation-5.24e-01

Pos logit contributions
isphere+0.586
FU+0.574
iu+0.574
PN+0.568
utic+0.561
Neg logit contributions
aturdays-0.618
onder-0.617
irtual-0.595
xxxx-0.594
lear-0.594
Token investigate
Token ID9161
Feature activation+1.71e+00

Pos logit contributions
onder+0.345
aturdays+0.340
lear+0.330
xxxx+0.330
irtual+0.329
Neg logit contributions
isphere-0.367
iu-0.359
FU-0.359
PN-0.355
utic-0.352
Token which
Token ID543
Feature activation-3.91e+00

Pos logit contributions
onder+1.682
aturdays+1.661
lear+1.602
coat+1.601
xxxx+1.594
Neg logit contributions
isphere-1.772
FU-1.739
iu-1.730
PN-1.707
utic-1.699
Token at
Token ID379
Feature activation-2.88e+00

Pos logit contributions
onder+2.819
aturdays+2.777
lear+2.696
coat+2.694
xxxx+2.686
Neg logit contributions
isphere-2.437
FU-2.404
iu-2.380
utic-2.366
PN-2.363
Token 72
Token ID7724
Feature activation+5.98e-01

Pos logit contributions
onder+2.011
aturdays+1.989
xxxx+1.932
lear+1.913
coat+1.910
Neg logit contributions
isphere-1.940
FU-1.843
PN-1.820
iu-1.816
utic-1.792
Token-
Token ID12
Feature activation-1.86e+00

Pos logit contributions
isphere+0.478
FU+0.470
iu+0.470
PN+0.465
utic+0.462
Neg logit contributions
aturdays-0.334
onder-0.334
xxxx-0.318
irtual-0.317
lear-0.316
Tokenstories
Token ID50164
Feature activation-5.66e+00

Pos logit contributions
onder+1.183
aturdays+1.172
xxxx+1.146
lear+1.129
coat+1.125
Neg logit contributions
isphere-1.340
iu-1.303
FU-1.299
PN-1.294
utic-1.289
Token is
Token ID318
Feature activation-1.89e+00

Pos logit contributions
onder+3.710
aturdays+3.623
xxxx+3.511
coat+3.465
lear+3.452
Neg logit contributions
isphere-3.848
PN-3.785
FU-3.778
ITNESS-3.770
iu-3.758
Token one
Token ID530
Feature activation-7.52e+00

Pos logit contributions
onder+1.266
aturdays+1.246
lear+1.207
xxxx+1.207
coat+1.205
Neg logit contributions
isphere-1.289
FU-1.272
iu-1.252
PN-1.250
utic-1.238
Token of
Token ID286
Feature activation-1.24e+00

Pos logit contributions
onder+4.488
coat+4.350
aturdays+4.344
lear+4.245
xxxx+4.228
Neg logit contributions
FU-5.382
isphere-5.369
PN-5.255
utic-5.208
iu-5.170
Token the
Token ID262
Feature activation-3.63e+00

Pos logit contributions
aturdays+0.819
onder+0.818
irtual+0.788
xxxx+0.787
lear+0.785
Neg logit contributions
isphere-0.866
FU-0.851
iu-0.838
PN-0.836
utic-0.825
Token largest
Token ID4387
Feature activation-8.02e+00

Pos logit contributions
onder+2.321
aturdays+2.284
xxxx+2.231
lear+2.213
coat+2.200
Neg logit contributions
isphere-2.558
FU-2.531
PN-2.490
iu-2.487
utic-2.454
Token office
Token ID2607
Feature activation-6.04e+00

Pos logit contributions
onder+4.802
aturdays+4.690
coat+4.667
lear+4.639
xxxx+4.573
Neg logit contributions
isphere-5.764
FU-5.752
PN-5.573
ITNESS-5.567
utic-5.547
Token found
Token ID1043
Feature activation+2.41e+00

Pos logit contributions
onder+2.797
xxxx+2.726
aturdays+2.721
lear+2.709
coat+2.679
Neg logit contributions
FU-2.938
isphere-2.923
iu-2.903
PN-2.871
utic-2.864
Token out
Token ID503
Feature activation-2.01e+00

Pos logit contributions
isphere+1.734
FU+1.716
iu+1.715
PN+1.700
utic+1.682
Neg logit contributions
aturdays-1.520
onder-1.509
lear-1.450
irtual-1.450
xxxx-1.443
Token about
Token ID546
Feature activation-1.56e+00

Pos logit contributions
onder+1.279
aturdays+1.272
xxxx+1.234
coat+1.226
lear+1.224
Neg logit contributions
isphere-1.436
FU-1.402
iu-1.396
PN-1.380
utic-1.372
Token Josh
Token ID8518
Feature activation+5.35e-01

Pos logit contributions
onder+0.975
aturdays+0.973
xxxx+0.939
irtual+0.937
coat+0.932
Neg logit contributions
isphere-1.145
FU-1.122
iu-1.112
PN-1.102
utic-1.089
Token
Token ID447
Feature activation-1.52e+00

Pos logit contributions
isphere+0.306
FU+0.299
iu+0.299
PN+0.295
utic+0.291
Neg logit contributions
aturdays-0.420
onder-0.419
irtual-0.406
xxxx-0.405
lear-0.405
Token
Token ID247
Feature activation-5.86e-01

Pos logit contributions
onder+1.609
aturdays+1.600
xxxx+1.578
lear+1.572
coat+1.567
Neg logit contributions
isphere-0.443
FU-0.421
iu-0.411
PN-0.408
utic-0.402
Tokens
Token ID82
Feature activation-3.91e+00

Pos logit contributions
aturdays+0.449
onder+0.447
irtual+0.433
lear+0.431
xxxx+0.430
Neg logit contributions
isphere-0.347
iu-0.340
FU-0.340
PN-0.336
utic-0.331
Token history
Token ID2106
Feature activation+5.90e-01

Pos logit contributions
onder+2.301
aturdays+2.285
xxxx+2.234
lear+2.225
coat+2.219
Neg logit contributions
isphere-2.961
FU-2.905
iu-2.882
PN-2.863
utic-2.831
Token,
Token ID11
Feature activation+1.24e+00

Pos logit contributions
isphere+0.362
FU+0.354
iu+0.354
PN+0.350
utic+0.345
Neg logit contributions
aturdays-0.438
onder-0.437
irtual-0.422
xxxx-0.422
lear-0.421
Token leading
Token ID3756
Feature activation-3.61e+00

Pos logit contributions
isphere+0.805
FU+0.789
iu+0.789
PN+0.782
utic+0.770
Neg logit contributions
aturdays-0.878
onder-0.876
irtual-0.844
lear-0.843
xxxx-0.842
Token him
Token ID683
Feature activation-5.98e+00

Pos logit contributions
onder+2.442
aturdays+2.410
xxxx+2.365
irtual+2.344
coat+2.330
Neg logit contributions
isphere-2.448
FU-2.372
iu-2.355
PN-2.322
utic-2.284
Token may
Token ID743
Feature activation+1.50e+00

Pos logit contributions
onder+1.865
aturdays+1.823
xxxx+1.780
coat+1.778
irtual+1.775
Neg logit contributions
isphere-1.815
FU-1.768
iu-1.766
PN-1.747
utic-1.727
Token also
Token ID635
Feature activation+2.80e+00

Pos logit contributions
isphere+1.032
FU+1.013
iu+1.012
PN+1.002
utic+0.989
Neg logit contributions
aturdays-1.010
onder-1.007
irtual-0.969
xxxx-0.968
lear-0.967
Token be
Token ID307
Feature activation+3.89e+00

Pos logit contributions
isphere+1.887
FU+1.864
iu+1.862
PN+1.831
utic+1.811
Neg logit contributions
aturdays-1.911
onder-1.880
irtual-1.826
lear-1.819
xxxx-1.815
Token in
Token ID287
Feature activation-3.66e+00

Pos logit contributions
isphere+2.461
iu+2.437
FU+2.407
PN+2.399
 reign+2.356
Neg logit contributions
aturdays-2.820
onder-2.775
irtual-2.706
xxxx-2.692
lear-2.658
Token the
Token ID262
Feature activation-4.24e+00

Pos logit contributions
onder+2.256
aturdays+2.214
coat+2.148
lear+2.147
irtual+2.146
Neg logit contributions
isphere-2.686
FU-2.642
iu-2.605
PN-2.602
PI-2.573
Token pipeline
Token ID11523
Feature activation-9.81e-01

Pos logit contributions
onder+2.968
aturdays+2.907
coat+2.897
lear+2.855
xxxx+2.850
Neg logit contributions
isphere-2.730
iu-2.675
FU-2.664
PN-2.615
PI-2.604
Token as
Token ID355
Feature activation+6.46e+00

Pos logit contributions
onder+0.705
aturdays+0.698
xxxx+0.678
coat+0.674
irtual+0.674
Neg logit contributions
isphere-0.624
FU-0.612
iu-0.610
PN-0.605
utic-0.598
Token Raj
Token ID13308
Feature activation+1.01e-01

Pos logit contributions
iu+3.929
isphere+3.916
PN+3.908
FU+3.887
 reign+3.839
Neg logit contributions
aturdays-4.656
onder-4.641
xxxx-4.512
lear-4.502
irtual-4.499
Tokenoy
Token ID726
Feature activation+6.48e+00

Pos logit contributions
isphere+0.075
iu+0.074
FU+0.074
PN+0.073
utic+0.072
Neg logit contributions
aturdays-0.062
onder-0.062
irtual-0.060
lear-0.059
xxxx-0.059
Token
Token ID447
Feature activation+6.36e-01

Pos logit contributions
isphere+3.872
iu+3.871
FU+3.813
 reign+3.790
PN+3.760
Neg logit contributions
aturdays-4.798
onder-4.691
xxxx-4.550
irtual-4.548
lear-4.525
Token
Token ID247
Feature activation+7.89e-01

Pos logit contributions
isphere+0.182
FU+0.174
iu+0.174
PN+0.170
utic+0.164
Neg logit contributions
aturdays-0.680
onder-0.679
irtual-0.663
xxxx-0.663
lear-0.662
Token,
Token ID11
Feature activation-7.17e-01

Pos logit contributions
onder+0.949
aturdays+0.942
xxxx+0.911
coat+0.909
irtual+0.908
Neg logit contributions
isphere-0.968
FU-0.953
iu-0.942
PN-0.937
utic-0.929
Token pun
Token ID4000
Feature activation+2.20e+00

Pos logit contributions
onder+0.468
aturdays+0.465
xxxx+0.449
irtual+0.448
lear+0.447
Neg logit contributions
isphere-0.503
FU-0.495
iu-0.492
PN-0.487
utic-0.483
Tokenks
Token ID591
Feature activation+1.14e+00

Pos logit contributions
isphere+1.296
iu+1.270
FU+1.249
PN+1.239
PI+1.224
Neg logit contributions
aturdays-1.696
onder-1.683
irtual-1.627
xxxx-1.625
coat-1.616
Token were
Token ID547
Feature activation+4.77e-01

Pos logit contributions
isphere+0.732
FU+0.718
iu+0.717
PN+0.709
utic+0.700
Neg logit contributions
aturdays-0.808
onder-0.806
irtual-0.778
xxxx-0.776
lear-0.776
Token often
Token ID1690
Feature activation-2.97e+00

Pos logit contributions
isphere+0.326
FU+0.321
iu+0.319
PN+0.316
utic+0.313
Neg logit contributions
onder-0.320
aturdays-0.319
lear-0.308
xxxx-0.307
irtual-0.307
Token objects
Token ID5563
Feature activation-2.38e+00

Pos logit contributions
onder+1.934
aturdays+1.907
lear+1.865
coat+1.859
irtual+1.848
Neg logit contributions
isphere-2.047
FU-2.043
iu-2.011
PN-1.997
utic-1.980
Token of
Token ID286
Feature activation-2.57e+00

Pos logit contributions
onder+1.567
aturdays+1.526
lear+1.509
xxxx+1.507
coat+1.503
Neg logit contributions
isphere-1.622
FU-1.618
PN-1.592
iu-1.587
utic-1.563
Token contempt
Token ID18035
Feature activation-1.99e+00

Pos logit contributions
onder+1.467
aturdays+1.449
xxxx+1.412
coat+1.410
lear+1.409
Neg logit contributions
isphere-1.991
FU-1.962
iu-1.946
PN-1.934
PI-1.905
Token.
Token ID13
Feature activation-3.11e+00

Pos logit contributions
onder+1.377
aturdays+1.357
irtual+1.323
xxxx+1.321
coat+1.318
Neg logit contributions
isphere-1.321
FU-1.307
PN-1.286
iu-1.280
PI-1.262
Token Due
Token ID14444
Feature activation+2.43e+00

Pos logit contributions
onder+2.003
xxxx+1.955
aturdays+1.954
coat+1.916
lear+1.896
Neg logit contributions
isphere-2.227
FU-2.122
iu-2.112
utic-2.096
PN-2.082
Token to
Token ID284
Feature activation-3.45e+00

Pos logit contributions
isphere+1.492
iu+1.465
FU+1.460
PN+1.446
utic+1.425
Neg logit contributions
aturdays-1.802
onder-1.787
irtual-1.731
lear-1.729
xxxx-1.728
TokenT
Token ID51
Feature activation+2.75e+00

Pos logit contributions
isphere+0.944
FU+0.924
iu+0.923
PN+0.912
utic+0.899
Neg logit contributions
aturdays-1.206
onder-1.203
irtual-1.163
xxxx-1.162
lear-1.161
Tokenear
Token ID451
Feature activation+1.46e+00

Pos logit contributions
isphere+1.547
iu+1.533
FU+1.526
PN+1.511
utic+1.486
Neg logit contributions
aturdays-2.151
onder-2.139
irtual-2.093
xxxx-2.083
lear-2.080
TokenV
Token ID53
Feature activation-5.18e+00

Pos logit contributions
isphere+0.864
FU+0.845
iu+0.845
PN+0.834
utic+0.823
Neg logit contributions
aturdays-1.114
onder-1.112
irtual-1.075
xxxx-1.074
lear-1.073
Tokenoid
Token ID1868
Feature activation-6.92e+00

Pos logit contributions
onder+2.446
aturdays+2.317
xxxx+2.247
irtual+2.202
ierra+2.161
Neg logit contributions
isphere-4.575
FU-4.510
iu-4.446
utic-4.440
PN-4.423
TokenRay
Token ID19591
Feature activation+3.31e+00

Pos logit contributions
onder+2.693
xxxx+2.685
lear+2.598
coat+2.553
aturdays+2.523
Neg logit contributions
isphere-6.483
utic-6.367
iu-6.273
PN-6.231
FU-6.186
TokenJ
Token ID41
Feature activation-7.15e+00

Pos logit contributions
isphere+1.963
FU+1.930
iu+1.926
PN+1.913
PI+1.877
Neg logit contributions
aturdays-2.516
onder-2.507
irtual-2.450
lear-2.432
xxxx-2.421
TokenKS
Token ID27015
Feature activation-1.94e+00

Pos logit contributions
aturdays+5.583
onder+5.458
uli+5.281
xxxx+5.267
irtual+5.233
Neg logit contributions
isphere-4.004
FU-3.863
iu-3.818
utic-3.810
lete-3.726
TokenLe
Token ID3123
Feature activation-3.12e+00

Pos logit contributions
onder+1.555
aturdays+1.550
lear+1.510
xxxx+1.502
coat+1.490
Neg logit contributions
isphere-1.072
iu-1.049
FU-1.046
utic-1.033
PN-1.029
Tokenen
Token ID268
Feature activation-2.47e+00

Pos logit contributions
onder+2.162
aturdays+2.134
xxxx+2.068
lear+2.065
irtual+2.056
Neg logit contributions
isphere-2.080
FU-2.027
iu-2.008
PN-1.995
utic-1.978
Tokenock
Token ID735
Feature activation+3.53e+00

Pos logit contributions
onder+0.688
aturdays+0.663
xxxx+0.621
lear+0.621
coat+0.621
Neg logit contributions
isphere-2.668
FU-2.630
PN-2.614
iu-2.612
utic-2.592
TokenL
Token ID43
Feature activation+1.50e-01

Pos logit contributions
isphere+1.942
FU+1.902
iu+1.893
PN+1.888
PI+1.850
Neg logit contributions
aturdays-2.841
onder-2.822
irtual-2.761
lear-2.731
xxxx-2.731
Token't
Token ID470
Feature activation-4.65e+00

Pos logit contributions
aturdays+0.202
onder+0.200
irtual+0.195
lear+0.193
xxxx+0.192
Neg logit contributions
isphere-0.178
iu-0.176
FU-0.175
PN-0.173
utic-0.171
Token have
Token ID423
Feature activation-2.97e+00

Pos logit contributions
onder+2.459
coat+2.309
xxxx+2.270
lear+2.261
aturdays+2.260
Neg logit contributions
isphere-3.869
PN-3.821
FU-3.792
iu-3.749
utic-3.724
Token a
Token ID257
Feature activation-4.28e+00

Pos logit contributions
onder+1.944
aturdays+1.905
coat+1.863
lear+1.848
xxxx+1.837
Neg logit contributions
FU-2.071
isphere-2.063
iu-2.034
PN-2.032
utic-1.995
Token place
Token ID1295
Feature activation-1.81e+00

Pos logit contributions
onder+2.912
coat+2.806
lear+2.785
aturdays+2.773
xxxx+2.732
Neg logit contributions
FU-2.862
iu-2.814
isphere-2.812
PN-2.784
utic-2.780
Token in
Token ID287
Feature activation-7.90e+00

Pos logit contributions
onder+1.215
aturdays+1.194
coat+1.172
xxxx+1.165
irtual+1.159
Neg logit contributions
isphere-1.220
FU-1.218
PN-1.200
iu-1.200
utic-1.171
Token our
Token ID674
Feature activation-1.40e+01

Pos logit contributions
onder+4.313
aturdays+4.158
coat+4.153
xxxx+4.094
lear+4.042
Neg logit contributions
isphere-6.143
FU-6.090
iu-6.085
PN-6.023
utic-5.890
Token American
Token ID1605
Feature activation-6.33e+00

Pos logit contributions
onder+7.081
aturdays+6.783
coat+6.565
ierra+6.351
lear+6.315
Neg logit contributions
FU-10.544
PN-10.449
iu-10.297
ILA-10.197
PI-10.192
Token story
Token ID1621
Feature activation-5.62e+00

Pos logit contributions
onder+3.834
aturdays+3.696
ierra+3.584
xxxx+3.581
coat+3.564
Neg logit contributions
PN-4.563
FU-4.560
iu-4.560
isphere-4.553
lete-4.445
Token,
Token ID11
Feature activation+8.28e-01

Pos logit contributions
onder+3.575
aturdays+3.490
coat+3.406
lear+3.363
xxxx+3.352
Neg logit contributions
isphere-3.929
FU-3.921
PN-3.902
iu-3.884
utic-3.756
Token because
Token ID780
Feature activation+9.77e-01

Pos logit contributions
isphere+0.552
FU+0.542
iu+0.541
PN+0.536
utic+0.529
Neg logit contributions
aturdays-0.571
onder-0.568
irtual-0.549
lear-0.548
xxxx-0.547
Token you
Token ID345
Feature activation-1.72e+00

Pos logit contributions
isphere+0.651
FU+0.639
iu+0.638
PN+0.632
utic+0.624
Neg logit contributions
aturdays-0.674
onder-0.672
irtual-0.648
xxxx-0.647
lear-0.647
Token 10
Token ID838
Feature activation-5.94e+00

Pos logit contributions
onder+2.482
aturdays+2.479
coat+2.436
xxxx+2.401
lear+2.386
Neg logit contributions
isphere-2.801
FU-2.721
PN-2.693
iu-2.672
utic-2.654
Token%
Token ID4
Feature activation-2.27e+00

Pos logit contributions
aturdays+3.407
onder+3.397
xxxx+3.301
irtual+3.204
coat+3.186
Neg logit contributions
isphere-4.569
PN-4.398
FU-4.382
iu-4.340
lete-4.339
Token of
Token ID286
Feature activation-1.05e+00

Pos logit contributions
aturdays+1.555
onder+1.553
xxxx+1.491
lear+1.490
irtual+1.489
Neg logit contributions
isphere-1.521
iu-1.486
FU-1.486
PN-1.479
utic-1.448
Token their
Token ID511
Feature activation-4.84e+00

Pos logit contributions
onder+0.624
aturdays+0.623
xxxx+0.602
lear+0.602
coat+0.600
Neg logit contributions
isphere-0.798
FU-0.778
iu-0.777
PN-0.772
utic-0.764
Token worldwide
Token ID8688
Feature activation-4.67e+00

Pos logit contributions
onder+2.970
aturdays+2.921
xxxx+2.880
lear+2.880
coat+2.876
Neg logit contributions
isphere-3.472
FU-3.352
PN-3.350
iu-3.349
utic-3.341
Token annual
Token ID5079
Feature activation-1.00e+01

Pos logit contributions
onder+2.775
xxxx+2.727
aturdays+2.722
coat+2.706
lear+2.681
Neg logit contributions
isphere-3.394
FU-3.312
iu-3.301
utic-3.298
PN-3.295
Token turnover
Token ID25079
Feature activation-1.78e+00

Pos logit contributions
onder+5.441
coat+5.434
xxxx+5.328
aturdays+5.316
lear+5.295
Neg logit contributions
isphere-7.154
ITNESS-7.049
FU-7.005
lete-7.001
PN-6.971
Token.
Token ID13
Feature activation-3.32e+00

Pos logit contributions
onder+1.272
aturdays+1.265
xxxx+1.225
lear+1.221
irtual+1.219
Neg logit contributions
isphere-1.135
FU-1.108
iu-1.102
PN-1.099
utic-1.079
Token
Token ID198
Feature activation+3.23e-01

Pos logit contributions
onder+1.934
aturdays+1.889
xxxx+1.873
coat+1.857
lear+1.841
Neg logit contributions
isphere-2.581
FU-2.461
iu-2.455
PN-2.442
lete-2.426
Token
Token ID198
Feature activation-1.62e+00

Pos logit contributions
iu+0.220
isphere+0.219
FU+0.219
PN+0.217
PI+0.213
Neg logit contributions
aturdays-0.223
onder-0.215
irtual-0.213
lear-0.207
xxxx-0.204
TokenThe
Token ID464
Feature activation-2.43e-01

Pos logit contributions
onder+1.081
aturdays+1.068
xxxx+1.055
lear+1.047
coat+1.042
Neg logit contributions
isphere-1.114
iu-1.073
utic-1.072
FU-1.061
PN-1.049
Tokenh
Token ID71
Feature activation-2.51e+00

Pos logit contributions
onder+3.669
lear+3.557
xxxx+3.536
coat+3.523
aturdays+3.442
Neg logit contributions
isphere-3.676
PN-3.585
FU-3.584
PI-3.498
iu-3.494
Tokenoub
Token ID12944
Feature activation+1.75e-01

Pos logit contributions
onder+2.058
aturdays+2.033
xxxx+1.989
lear+1.978
irtual+1.972
Neg logit contributions
isphere-1.348
FU-1.309
iu-1.301
PN-1.294
utic-1.275
Token
Token ID198
Feature activation-1.47e+00

Pos logit contributions
isphere+0.123
FU+0.121
iu+0.121
PN+0.120
utic+0.118
Neg logit contributions
aturdays-0.114
onder-0.114
irtual-0.109
xxxx-0.109
lear-0.109
Token
Token ID198
Feature activation-3.68e+00

Pos logit contributions
aturdays+0.935
onder+0.931
irtual+0.896
lear+0.892
xxxx+0.892
Neg logit contributions
isphere-1.058
FU-1.040
iu-1.039
PN-1.029
utic-1.016
Token2008
Token ID11528
Feature activation-2.33e+00

Pos logit contributions
xxxx+2.390
onder+2.342
lear+2.320
coat+2.305
aturdays+2.290
Neg logit contributions
isphere-2.569
utic-2.493
FU-2.465
iu-2.452
 KING-2.434
Token Charlie
Token ID11526
Feature activation-1.00e+01

Pos logit contributions
onder+1.400
aturdays+1.370
xxxx+1.356
coat+1.345
lear+1.342
Neg logit contributions
isphere-1.767
FU-1.714
iu-1.706
PN-1.691
utic-1.685
Token Sheen
Token ID50189
Feature activation-6.62e+00

Pos logit contributions
xxxx+2.728
onder+2.614
coat+2.489
lear+2.302
ierra+2.253
Neg logit contributions
isphere-10.549
FU-10.308
utic-10.222
iu-10.158
PN-10.126
Token 2009
Token ID3717
Feature activation-5.53e+00

Pos logit contributions
onder+4.035
irtual+4.009
coat+3.991
xxxx+3.982
aturdays+3.932
Neg logit contributions
isphere-4.779
FU-4.627
PN-4.513
iu-4.446
PI-4.387
Token Alec
Token ID38285
Feature activation+2.27e+00

Pos logit contributions
onder+3.267
xxxx+3.180
coat+3.158
lear+3.117
aturdays+3.109
Neg logit contributions
isphere-4.192
FU-4.018
iu-3.969
utic-3.967
PN-3.950
Token Baldwin
Token ID26402
Feature activation-5.63e+00

Pos logit contributions
isphere+1.103
iu+1.093
FU+1.072
PN+1.059
PI+1.039
Neg logit contributions
aturdays-2.029
onder-1.954
irtual-1.942
lear-1.901
coat-1.878
Token
Token ID198
Feature activation-2.70e+00

Pos logit contributions
onder+3.133
xxxx+3.069
coat+2.989
lear+2.956
ierra+2.864
Neg logit contributions
isphere-4.504
FU-4.327
utic-4.297
PN-4.272
iu-4.266
Token based
Token ID1912
Feature activation-1.42e+00

Pos logit contributions
onder+0.873
aturdays+0.857
coat+0.838
xxxx+0.834
irtual+0.831
Neg logit contributions
isphere-0.882
FU-0.878
iu-0.871
utic-0.862
PN-0.862
Token singer
Token ID14015
Feature activation+1.61e+00

Pos logit contributions
onder+0.910
aturdays+0.894
coat+0.871
xxxx+0.870
irtual+0.867
Neg logit contributions
isphere-1.008
FU-0.998
iu-0.989
PN-0.984
utic-0.982
Token onstage
Token ID38500
Feature activation+7.75e+00

Pos logit contributions
isphere+1.030
iu+1.008
FU+1.006
PN+0.994
utic+0.979
Neg logit contributions
aturdays-1.159
onder-1.151
irtual-1.115
lear-1.112
xxxx-1.110
Token at
Token ID379
Feature activation-3.46e-01

Pos logit contributions
isphere+4.331
iu+4.242
FU+4.155
 reign+4.125
 KING+4.121
Neg logit contributions
aturdays-6.033
onder-5.872
irtual-5.833
lear-5.768
xxxx-5.723
Token the
Token ID262
Feature activation+1.43e+00

Pos logit contributions
onder+0.233
aturdays+0.232
irtual+0.224
lear+0.224
xxxx+0.223
Neg logit contributions
isphere-0.237
FU-0.233
iu-0.232
PN-0.229
utic-0.228
Token First
Token ID3274
Feature activation-1.12e+01

Pos logit contributions
isphere+0.904
iu+0.885
FU+0.883
PN+0.874
utic+0.862
Neg logit contributions
aturdays-1.037
onder-1.033
irtual-0.997
lear-0.996
xxxx-0.996
Token Avenue
Token ID8878
Feature activation+1.12e+00

Pos logit contributions
onder+7.108
aturdays+7.099
coat+6.968
irtual+6.780
xxxx+6.753
Neg logit contributions
utic-7.181
iu-6.860
FU-6.833
rency-6.788
ITNESS-6.736
Token venue
Token ID14359
Feature activation+3.96e+00

Pos logit contributions
isphere+0.759
FU+0.745
iu+0.744
PN+0.736
utic+0.727
Neg logit contributions
aturdays-0.765
onder-0.764
irtual-0.735
xxxx-0.734
lear-0.734
Token during
Token ID1141
Feature activation+2.03e+00

Pos logit contributions
isphere+2.453
iu+2.383
FU+2.381
PN+2.352
PI+2.301
Neg logit contributions
aturdays-2.941
onder-2.904
irtual-2.830
lear-2.815
xxxx-2.811
Token her
Token ID607
Feature activation+4.29e+00

Pos logit contributions
isphere+1.350
iu+1.322
FU+1.321
PN+1.308
utic+1.290
Neg logit contributions
aturdays-1.403
onder-1.398
irtual-1.348
xxxx-1.345
lear-1.345
Token enc
Token ID2207
Feature activation-2.78e+00

Pos logit contributions
isphere+2.718
iu+2.659
FU+2.628
PN+2.596
 reign+2.577
Neg logit contributions
aturdays-3.104
onder-3.062
irtual-2.988
lear-2.970
xxxx-2.957
Token [
Token ID685
Feature activation+1.22e+00

Pos logit contributions
FU+2.459
PN+2.426
iu+2.413
isphere+2.261
PI+2.247
Neg logit contributions
aturdays-6.836
irtual-6.597
onder-6.507
lear-6.447
 millenn-6.315
TokenBlack
Token ID9915
Feature activation+8.54e-01

Pos logit contributions
isphere+0.942
FU+0.925
iu+0.924
PN+0.915
utic+0.907
Neg logit contributions
aturdays-0.720
onder-0.719
irtual-0.687
xxxx-0.686
lear-0.686
TokenE
Token ID36
Feature activation+6.29e+00

Pos logit contributions
isphere+0.438
FU+0.431
iu+0.425
PN+0.423
PI+0.410
Neg logit contributions
aturdays-0.728
onder-0.718
irtual-0.701
lear-0.696
xxxx-0.695
Tokenlo
Token ID5439
Feature activation+7.08e+00

Pos logit contributions
iu+1.433
FU+1.356
isphere+1.344
PN+1.338
lete+1.338
Neg logit contributions
aturdays-7.065
irtual-6.921
onder-6.745
 millenn-6.727
xxxx-6.713
Token "
Token ID366
Feature activation-2.12e+00

Pos logit contributions
iu+3.885
PN+3.821
FU+3.812
PI+3.751
 reign+3.669
Neg logit contributions
aturdays-5.949
irtual-5.651
 millenn-5.616
lear-5.369
ierra-5.327
Token25
Token ID1495
Feature activation-1.02e+01

Pos logit contributions
onder+1.035
xxxx+1.024
aturdays+1.009
coat+0.987
lear+0.977
Neg logit contributions
isphere-1.851
utic-1.780
iu-1.777
FU-1.766
PN-1.756
Token67
Token ID3134
Feature activation-1.85e+00

Pos logit contributions
xxxx+4.216
onder+3.971
coat+3.915
xxxxxxxx+3.559
uli+3.430
Neg logit contributions
isphere-9.475
utic-9.056
rency-8.928
 poaching-8.892
-8.875
Token"]
Token ID8973
Feature activation+6.02e+00

Pos logit contributions
onder+1.102
aturdays+1.095
xxxx+1.057
lear+1.052
irtual+1.049
Neg logit contributions
isphere-1.400
FU-1.373
iu-1.371
PN-1.358
utic-1.347
Token [
Token ID685
Feature activation+1.46e+00

Pos logit contributions
PN+2.287
FU+2.282
iu+2.270
isphere+2.205
PI+2.146
Neg logit contributions
aturdays-5.982
irtual-5.797
onder-5.775
lear-5.710
ierra-5.586
TokenP
Token ID47
Feature activation+5.51e+00

Pos logit contributions
isphere+0.851
FU+0.830
iu+0.829
PN+0.817
utic+0.810
Neg logit contributions
onder-1.128
aturdays-1.128
irtual-1.091
xxxx-1.089
lear-1.087
Tokenly
Token ID306
Feature activation+4.09e+00

Pos logit contributions
isphere+2.126
FU+2.078
iu+2.017
PN+1.979
PI+1.925
Neg logit contributions
aturdays-5.411
irtual-5.264
lear-5.263
xxxx-5.236
onder-5.181