TOP ACTIVATIONS
MAX = 15.407

49 ERA in 54 1 / 3 IP in 2014
shorter period of 16 1 / 2 months since the start
get at least 8 1 / 2 hours of sleep a
BB ratio in 37 1 / 3 innings . I projected
As soon as we have reached a boil , the Red
at 6 - 11 1 / 2 this week .
kowski during 7 - on - 7 drills and then intercept
l inson , John O ' K ane , J ovan
Sheen 2008 Alec Baldwin 2008 Steve Care ll
of the match have morphed into nerves , dread and bewild
ap uni o N ā n ā k uli . E
than the recommended 8 1 / 2 to 9 1 /
see .[ 117 ] A br asions around the eyes ,
United States often carry My c ob acter ium le p
un cus , and My c opl asma hom inis which
s )} 5 . O - O { ( 0 s
list . From Edward Has b rou ck 's transcript of
Money Morning . 16 W . Madison St . Baltimore ,
contract , A du says . Ben
uch , what loss ," he exclaim s . There are

MIN ACTIVATIONS
MIN = -14.857

save , your character now receives secret voices in his or
to condo developments are knee - j erk . They 're
only to stand up ankle - deep in water .
paper from publication in J AMA showing that its drug ,
condo developments are knee - j erk . They 're often
as Visa , Pro ctor & Gamble , Coca - Cola
people , this j à v u isn
08 Rating : 5 Crit ique : Three of
R eed argues , persu as ively , that a vibrant
heat to low and cook f rit ters on each side
b iz arro j à v u that rare
short limit : 7 R TS thr : off Frag ment
ALL PERSON EL UPDATE : 05 45 z K USH AM
young voters , says D ella Vol pe . At worse
for public monitoring and accountability ; and iv ) mandate that
for a heavy , knee - high , tackle on Vladimir
angle F ( 0 , ($ i * $ FontSize *
public monitoring and accountability ; and iv ) mandate that pictures
7 R TS thr : off Frag ment thr : off
the input image paths for image Path in paths . list

INTERVAL 7.841 - 15.407
CONTAINS 0.112%

s past the edge of the Universe ? Y
о е в ы е
and the Cuban flag was flying over the radio shack and
S . A . I . R . Des ren se
down clues 8 d 8 . Euro list

INTERVAL 0.275 - 7.841
CONTAINS 44.822%

a 405 1 against shot . To put
, keeps honey bees , cultiv ates mushrooms , b akes
The one time that O ma eda
out . I mean , I guess we re
and England on October 29 . Republic Of Ireland

INTERVAL -7.291 - 0.275
CONTAINS 54.894%

future tra itors and supported locking them up in intern ment
uably , were 10 years , loaded up with many expectations
ito . For photographic evidence of Manson 's chi
. Jim Do oley , director of
always had it . In this moment and in

INTERVAL -14.857 - -7.291
CONTAINS 0.172%

December 2009 10 : 31 , e u inside , Sof
looks like immediately after read () returns to a pop /
so sad to watch . James Comey s leadership
, IT GO ES ST RA IGHT TO THE GEAR S
z 1 . Height ), $ SR . Width , $
Token49
Token ID2920
Feature activation+2.12e+00

Pos logit contributions
race+1.251
Redd+1.247
Wiki+1.155
ERA+1.123
Stack+1.099
Neg logit contributions
 Samar-0.959
 amy-0.861
olicy-0.817
mble-0.796
format-0.793
Token ERA
Token ID18802
Feature activation+4.80e-01

Pos logit contributions
race+1.372
Redd+1.344
Wiki+1.217
ERA+1.208
Stack+1.148
Neg logit contributions
 Samar-1.716
 amy-1.555
olicy-1.507
format-1.475
oker-1.464
Token in
Token ID287
Feature activation+3.45e+00

Pos logit contributions
race+0.353
Redd+0.349
Wiki+0.320
ERA+0.310
Stack+0.303
Neg logit contributions
 Samar-0.347
 amy-0.311
olicy-0.296
format-0.293
oker-0.290
Token 54
Token ID7175
Feature activation+4.32e+00

Pos logit contributions
race+2.396
Redd+2.372
Wiki+2.144
ERA+2.095
Stack+2.031
Neg logit contributions
 Samar-2.569
 amy-2.336
olicy-2.258
format-2.207
oker-2.203
Token 1
Token ID352
Feature activation+4.84e+00

Pos logit contributions
race+2.887
Redd+2.850
Wiki+2.578
ERA+2.544
Stack+2.437
Neg logit contributions
 Samar-3.375
 amy-3.080
olicy-2.928
oker-2.879
format-2.875
Token/
Token ID14
Feature activation+1.54e+01

Pos logit contributions
race+3.503
Redd+3.481
Wiki+3.162
ERA+3.073
Stack+3.033
Neg logit contributions
 Samar-3.508
 amy-3.185
olicy-3.025
format-2.975
oker-2.974
Token3
Token ID18
Feature activation+7.43e+00

Pos logit contributions
Redd+6.867
race+6.810
Stack+5.986
ERA+5.817
Wiki+5.697
Neg logit contributions
 Samar-14.381
 amy-13.897
olicy-13.328
mble-13.274
 rul-12.859
Token IP
Token ID6101
Feature activation+4.31e+00

Pos logit contributions
race+3.811
Redd+3.740
Wiki+3.238
ERA+3.208
Stack+3.086
Neg logit contributions
 Samar-6.852
 amy-6.375
olicy-6.131
oker-6.040
mble-6.012
Token in
Token ID287
Feature activation+5.55e-01

Pos logit contributions
race+3.112
Redd+3.095
Wiki+2.796
ERA+2.782
Stack+2.680
Neg logit contributions
 Samar-3.119
 amy-2.811
olicy-2.680
format-2.634
oker-2.620
Token 2014
Token ID1946
Feature activation-1.15e+00

Pos logit contributions
race+0.404
Redd+0.400
Wiki+0.367
ERA+0.353
Stack+0.346
Neg logit contributions
 Samar-0.406
 amy-0.364
olicy-0.346
format-0.344
oker-0.341
Token
Token ID198
Feature activation-7.45e-01

Pos logit contributions
 Samar+0.790
 amy+0.702
olicy+0.662
format+0.661
oker+0.656
Neg logit contributions
race-0.886
Redd-0.878
Wiki-0.811
ERA-0.777
Stack-0.768
Token shorter
Token ID12238
Feature activation+2.77e+00

Pos logit contributions
race+0.365
Redd+0.358
Wiki+0.329
ERA+0.319
Stack+0.313
Neg logit contributions
 Samar-0.336
 amy-0.300
olicy-0.286
format-0.282
oker-0.280
Token period
Token ID2278
Feature activation-2.51e-02

Pos logit contributions
race+1.897
Redd+1.845
Wiki+1.695
ERA+1.633
Stack+1.601
Neg logit contributions
 Samar-2.125
 amy-1.909
olicy-1.846
oker-1.819
format-1.806
Token of
Token ID286
Feature activation+4.06e-01

Pos logit contributions
 Samar+0.018
 amy+0.017
olicy+0.016
format+0.016
oker+0.016
Neg logit contributions
race-0.018
Redd-0.018
Wiki-0.016
ERA-0.016
Stack-0.015
Token 16
Token ID1467
Feature activation-5.96e-02

Pos logit contributions
race+0.294
Redd+0.290
Wiki+0.266
ERA+0.256
Stack+0.251
Neg logit contributions
 Samar-0.299
 amy-0.269
olicy-0.256
format-0.254
oker-0.252
Token 1
Token ID352
Feature activation+2.06e+00

Pos logit contributions
 Samar+0.042
 amy+0.038
olicy+0.036
format+0.035
oker+0.035
Neg logit contributions
race-0.045
Redd-0.045
Wiki-0.041
ERA-0.039
Stack-0.039
Token/
Token ID14
Feature activation+1.49e+01

Pos logit contributions
race+1.536
Redd+1.510
Wiki+1.389
ERA+1.339
Stack+1.320
Neg logit contributions
 Samar-1.465
 amy-1.312
olicy-1.246
format-1.233
oker-1.226
Token2
Token ID17
Feature activation+6.63e+00

Pos logit contributions
race+7.883
Redd+7.074
Wiki+6.622
ERA+6.479
Stack+6.401
Neg logit contributions
 Samar-12.285
olicy-11.488
mble-11.304
 amy-11.263
oker-10.697
Token months
Token ID1933
Feature activation+1.21e+00

Pos logit contributions
race+4.635
Redd+4.414
Wiki+4.140
ERA+4.020
Stack+3.907
Neg logit contributions
 Samar-4.942
 amy-4.367
olicy-4.207
mble-4.185
oker-4.156
Token since
Token ID1201
Feature activation+3.13e+00

Pos logit contributions
race+0.901
Redd+0.884
Wiki+0.813
ERA+0.786
Stack+0.773
Neg logit contributions
 Samar-0.861
 amy-0.769
olicy-0.733
format-0.723
oker-0.720
Token the
Token ID262
Feature activation+1.84e+00

Pos logit contributions
race+2.230
Redd+2.164
Wiki+2.015
ERA+1.918
Stack+1.882
Neg logit contributions
 Samar-2.310
 amy-2.080
olicy-2.016
format-1.982
oker-1.969
Token start
Token ID923
Feature activation-3.46e-01

Pos logit contributions
race+1.291
Redd+1.253
Wiki+1.153
ERA+1.106
Stack+1.081
Neg logit contributions
 Samar-1.401
 amy-1.266
olicy-1.222
format-1.201
oker-1.195
Token get
Token ID651
Feature activation+2.21e+00

Pos logit contributions
race+0.035
Redd+0.034
Wiki+0.031
ERA+0.030
Stack+0.029
Neg logit contributions
 Samar-0.038
 amy-0.034
olicy-0.033
format-0.032
oker-0.032
Token at
Token ID379
Feature activation+3.50e+00

Pos logit contributions
race+1.607
Redd+1.570
Wiki+1.446
ERA+1.384
Stack+1.374
Neg logit contributions
 Samar-1.596
 amy-1.433
olicy-1.381
format-1.372
oker-1.365
Token least
Token ID1551
Feature activation+2.15e+00

Pos logit contributions
race+2.304
Redd+2.232
Wiki+2.026
ERA+1.959
Stack+1.908
Neg logit contributions
 Samar-2.784
 amy-2.535
format-2.440
olicy-2.414
mble-2.397
Token 8
Token ID807
Feature activation+3.10e+00

Pos logit contributions
race+1.584
Redd+1.554
Wiki+1.427
ERA+1.373
Stack+1.355
Neg logit contributions
 Samar-1.536
 amy-1.386
olicy-1.329
format-1.324
oker-1.305
Token 1
Token ID352
Feature activation+2.93e+00

Pos logit contributions
race+2.172
Redd+2.127
Wiki+1.951
ERA+1.871
Stack+1.847
Neg logit contributions
 Samar-2.342
 amy-2.106
olicy-2.025
format-2.001
oker-1.985
Token/
Token ID14
Feature activation+1.44e+01

Pos logit contributions
race+2.166
Redd+2.135
Wiki+1.959
ERA+1.884
Stack+1.863
Neg logit contributions
 Samar-2.099
 amy-1.888
olicy-1.790
format-1.778
oker-1.760
Token2
Token ID17
Feature activation+7.29e+00

Pos logit contributions
race+7.154
Redd+6.436
ERA+6.041
Wiki+5.878
Stack+5.689
Neg logit contributions
 Samar-12.534
mble-11.873
 amy-11.659
olicy-11.619
 rul-11.498
Token hours
Token ID2250
Feature activation+6.23e-01

Pos logit contributions
race+4.559
Redd+4.411
Wiki+3.997
ERA+3.824
Stack+3.816
Neg logit contributions
 Samar-5.830
 amy-5.308
olicy-5.129
mble-5.124
format-5.060
Token of
Token ID286
Feature activation+3.18e+00

Pos logit contributions
race+0.444
Redd+0.437
Wiki+0.399
ERA+0.383
Stack+0.378
Neg logit contributions
 Samar-0.464
 amy-0.418
olicy-0.400
format-0.397
oker-0.393
Token sleep
Token ID3993
Feature activation+1.96e+00

Pos logit contributions
race+2.104
Redd+2.056
Wiki+1.855
ERA+1.781
Stack+1.766
Neg logit contributions
 Samar-2.508
 amy-2.270
olicy-2.195
format-2.172
oker-2.148
Token a
Token ID257
Feature activation+1.93e+00

Pos logit contributions
race+1.428
Redd+1.397
Wiki+1.277
ERA+1.233
Stack+1.216
Neg logit contributions
 Samar-1.426
 amy-1.286
olicy-1.233
format-1.217
oker-1.204
TokenBB
Token ID15199
Feature activation+5.32e+00

Pos logit contributions
Redd+2.748
race+2.726
ERA+2.506
Wiki+2.461
Stack+2.343
Neg logit contributions
 Samar-3.512
 amy-3.258
olicy-3.051
mble-3.018
 Volvo-2.977
Token ratio
Token ID8064
Feature activation+4.81e+00

Pos logit contributions
race+2.703
Redd+2.623
ERA+2.370
Wiki+2.304
Stack+2.155
Neg logit contributions
 Samar-4.992
 amy-4.586
olicy-4.438
oker-4.381
mble-4.375
Token in
Token ID287
Feature activation+3.37e+00

Pos logit contributions
race+3.456
Redd+3.340
Wiki+3.057
ERA+3.050
Stack+2.916
Neg logit contributions
 Samar-3.458
 amy-3.140
olicy-3.054
format-2.952
oker-2.938
Token 37
Token ID5214
Feature activation+4.76e+00

Pos logit contributions
race+2.309
Redd+2.290
Wiki+2.065
ERA+2.027
Stack+1.957
Neg logit contributions
 Samar-2.552
 amy-2.318
olicy-2.239
format-2.196
oker-2.195
Token 1
Token ID352
Feature activation+5.92e+00

Pos logit contributions
race+3.293
Redd+3.254
Wiki+2.945
ERA+2.933
Stack+2.810
Neg logit contributions
 Samar-3.597
 amy-3.282
olicy-3.090
format-3.055
oker-3.047
Token/
Token ID14
Feature activation+1.41e+01

Pos logit contributions
race+3.866
Redd+3.783
Wiki+3.451
ERA+3.425
Stack+3.322
Neg logit contributions
 Samar-4.637
 amy-4.360
olicy-4.158
mble-4.124
 rul-4.017
Token3
Token ID18
Feature activation+9.71e+00

Pos logit contributions
race+6.592
Redd+6.299
ERA+5.820
Stack+5.560
Wiki+5.470
Neg logit contributions
 Samar-12.947
 amy-12.349
olicy-11.723
mble-11.505
oker-11.106
Token innings
Token ID16267
Feature activation+5.32e+00

Pos logit contributions
race+6.382
Redd+6.306
ERA+5.888
Wiki+5.587
Stack+5.537
Neg logit contributions
 Samar-7.244
 amy-6.689
olicy-6.285
oker-6.179
mble-6.149
Token.
Token ID13
Feature activation+2.16e-01

Pos logit contributions
race+3.832
Redd+3.748
ERA+3.408
Wiki+3.377
Stack+3.262
Neg logit contributions
 Samar-3.805
 amy-3.433
olicy-3.337
mble-3.221
oker-3.207
Token I
Token ID314
Feature activation+2.87e+00

Pos logit contributions
race+0.165
Redd+0.164
Wiki+0.151
ERA+0.145
Stack+0.143
Neg logit contributions
 Samar-0.149
 amy-0.133
olicy-0.126
format-0.125
oker-0.124
Token projected
Token ID13301
Feature activation-7.23e-01

Pos logit contributions
race+2.042
Redd+1.982
ERA+1.820
Wiki+1.801
Stack+1.713
Neg logit contributions
 Samar-2.134
 amy-1.909
olicy-1.834
format-1.826
oker-1.778
Token As
Token ID1081
Feature activation-4.63e-01

Pos logit contributions
race+3.516
Redd+3.483
Wiki+3.162
ERA+3.065
Stack+3.041
Neg logit contributions
 Samar-3.929
 amy-3.611
olicy-3.501
oker-3.434
mble-3.415
Token soon
Token ID2582
Feature activation+2.65e+00

Pos logit contributions
 Samar+0.317
 amy+0.282
olicy+0.268
format+0.265
oker+0.263
Neg logit contributions
race-0.359
Redd-0.354
Wiki-0.327
ERA-0.315
Stack-0.310
Token as
Token ID355
Feature activation+1.10e+00

Pos logit contributions
race+2.035
Redd+2.015
Wiki+1.858
ERA+1.787
Stack+1.758
Neg logit contributions
 Samar-1.830
 amy-1.626
olicy-1.544
format-1.532
oker-1.522
Token we
Token ID356
Feature activation+1.39e+00

Pos logit contributions
race+0.822
Redd+0.812
Wiki+0.746
ERA+0.718
Stack+0.705
Neg logit contributions
 Samar-0.788
 amy-0.705
olicy-0.671
format-0.666
oker-0.660
Token have
Token ID423
Feature activation+4.69e+00

Pos logit contributions
race+0.922
Redd+0.899
Wiki+0.818
ERA+0.786
Stack+0.775
Neg logit contributions
 Samar-1.105
 amy-0.997
olicy-0.964
format-0.949
oker-0.946
Token reached
Token ID4251
Feature activation+1.39e+01

Pos logit contributions
race+3.309
Redd+3.268
Wiki+2.968
ERA+2.868
Stack+2.849
Neg logit contributions
 Samar-3.411
 amy-3.034
olicy-3.025
oker-2.947
format-2.943
Token a
Token ID257
Feature activation+5.74e+00

Pos logit contributions
race+8.174
Redd+8.104
ERA+6.938
Wiki+6.876
Stack+6.775
Neg logit contributions
 Samar-10.417
oker-9.309
format-9.191
olicy-9.161
 amy-9.080
Token boil
Token ID20667
Feature activation+1.61e+00

Pos logit contributions
race+4.014
Redd+3.929
Wiki+3.522
ERA+3.435
Stack+3.369
Neg logit contributions
 Samar-4.292
 amy-3.810
olicy-3.705
oker-3.699
format-3.633
Token,
Token ID11
Feature activation+9.43e-01

Pos logit contributions
race+1.218
Redd+1.203
Wiki+1.106
ERA+1.067
Stack+1.048
Neg logit contributions
 Samar-1.131
 amy-1.009
olicy-0.957
format-0.951
oker-0.941
Token the
Token ID262
Feature activation+1.16e+00

Pos logit contributions
race+0.664
Redd+0.655
Wiki+0.598
ERA+0.575
Stack+0.567
Neg logit contributions
 Samar-0.710
 amy-0.638
olicy-0.612
format-0.605
oker-0.602
Token Red
Token ID2297
Feature activation-2.06e+00

Pos logit contributions
race+0.987
Redd+0.975
Wiki+0.904
ERA+0.874
Stack+0.864
Neg logit contributions
 Samar-0.704
 amy-0.612
olicy-0.592
format-0.581
oker-0.573
Token at
Token ID379
Feature activation-1.37e+00

Pos logit contributions
race+0.664
Redd+0.656
Wiki+0.586
ERA+0.559
Stack+0.543
Neg logit contributions
 Samar-1.032
 amy-0.945
olicy-0.909
format-0.902
oker-0.896
Token 6
Token ID718
Feature activation-2.95e+00

Pos logit contributions
 Samar+0.995
 amy+0.893
olicy+0.846
format+0.841
oker+0.835
Neg logit contributions
race-1.006
Redd-0.996
Wiki-0.914
ERA-0.877
Stack-0.862
Token-
Token ID12
Feature activation+1.60e+00

Pos logit contributions
 Samar+1.817
 amy+1.607
format+1.516
oker+1.510
olicy+1.490
Neg logit contributions
Redd-2.457
race-2.452
Wiki-2.255
ERA-2.180
Stack-2.143
Token11
Token ID1157
Feature activation+5.62e+00

Pos logit contributions
race+1.234
Redd+1.212
Wiki+1.122
ERA+1.080
Stack+1.064
Neg logit contributions
 Samar-1.113
 amy-0.994
olicy-0.943
mble-0.914
format-0.912
Token 1
Token ID352
Feature activation+4.92e+00

Pos logit contributions
race+3.890
Redd+3.774
Wiki+3.451
ERA+3.389
Stack+3.273
Neg logit contributions
 Samar-4.240
 amy-3.750
olicy-3.675
format-3.570
mble-3.540
Token/
Token ID14
Feature activation+1.35e+01

Pos logit contributions
race+3.430
Redd+3.388
Wiki+3.076
ERA+3.018
Stack+2.961
Neg logit contributions
 Samar-3.705
 amy-3.318
olicy-3.197
format-3.114
mble-3.104
Token2
Token ID17
Feature activation+8.24e+00

Pos logit contributions
race+7.746
Redd+7.281
ERA+6.669
Wiki+6.467
Stack+6.254
Neg logit contributions
 Samar-11.107
 amy-10.022
olicy-10.015
mble-9.867
 rul-9.544
Token this
Token ID428
Feature activation+1.36e+00

Pos logit contributions
race+5.404
Redd+5.297
Wiki+4.849
ERA+4.753
 waivers+4.605
Neg logit contributions
 Samar-6.236
 amy-5.584
olicy-5.540
mble-5.470
format-5.279
Token week
Token ID1285
Feature activation+1.72e-01

Pos logit contributions
race+0.973
Redd+0.961
Wiki+0.879
ERA+0.845
Stack+0.828
Neg logit contributions
 Samar-1.007
 amy-0.907
olicy-0.869
format-0.855
oker-0.850
Token.
Token ID13
Feature activation-8.48e-01

Pos logit contributions
race+0.132
Redd+0.131
Wiki+0.121
ERA+0.116
Stack+0.114
Neg logit contributions
 Samar-0.119
 amy-0.106
olicy-0.100
format-0.100
oker-0.099
Token
Token ID198
Feature activation+3.10e-01

Pos logit contributions
 Samar+0.598
 amy+0.532
olicy+0.504
format+0.502
oker+0.498
Neg logit contributions
race-0.641
Redd-0.633
Wiki-0.582
ERA-0.560
Stack-0.550
Tokenkowski
Token ID26216
Feature activation+1.32e+00

Pos logit contributions
race+0.031
Redd+0.030
Wiki+0.027
ERA+0.027
Stack+0.026
Neg logit contributions
 Samar-0.039
 amy-0.035
olicy-0.033
format-0.033
 Volvo-0.032
Token during
Token ID1141
Feature activation+1.11e+00

Pos logit contributions
race+0.980
Redd+0.963
Wiki+0.882
ERA+0.852
Stack+0.838
Neg logit contributions
 Samar-0.943
 amy-0.854
olicy-0.814
format-0.804
oker-0.796
Token 7
Token ID767
Feature activation+2.73e+00

Pos logit contributions
race+0.834
Redd+0.827
Wiki+0.757
ERA+0.729
Stack+0.716
Neg logit contributions
 Samar-0.783
 amy-0.705
olicy-0.670
format-0.664
oker-0.659
Token-
Token ID12
Feature activation+3.34e+00

Pos logit contributions
race+2.019
Redd+1.981
Wiki+1.830
ERA+1.753
Stack+1.739
Neg logit contributions
 Samar-1.940
 amy-1.755
olicy-1.672
format-1.649
oker-1.630
Tokenon
Token ID261
Feature activation+5.12e+00

Pos logit contributions
race+2.736
Redd+2.629
Wiki+2.451
ERA+2.364
Stack+2.355
Neg logit contributions
 Samar-2.181
 amy-1.974
mble-1.816
olicy-1.806
format-1.761
Token-
Token ID12
Feature activation+1.34e+01

Pos logit contributions
race+3.466
Redd+3.367
Wiki+3.094
ERA+2.994
Stack+2.963
Neg logit contributions
 Samar-3.891
 amy-3.662
olicy-3.521
 rul-3.480
mble-3.480
Token7
Token ID22
Feature activation+5.28e+00

Pos logit contributions
race+6.419
Redd+5.966
Wiki+5.459
Stack+5.299
ERA+5.184
Neg logit contributions
 Samar-12.440
 amy-11.513
 rul-11.342
mble-11.021
olicy-10.842
Token drills
Token ID26721
Feature activation+3.02e+00

Pos logit contributions
Redd+3.556
race+3.543
Wiki+3.167
ERA+3.060
 waivers+3.048
Neg logit contributions
 Samar-3.941
 amy-3.615
olicy-3.472
oker-3.412
format-3.404
Token and
Token ID290
Feature activation-1.07e+00

Pos logit contributions
race+2.220
Redd+2.187
Wiki+1.989
ERA+1.933
Stack+1.892
Neg logit contributions
 Samar-2.140
 amy-1.946
olicy-1.856
format-1.830
oker-1.818
Token then
Token ID788
Feature activation-3.15e+00

Pos logit contributions
 Samar+0.763
 amy+0.684
olicy+0.650
format+0.645
oker+0.639
Neg logit contributions
race-0.792
Redd-0.784
Wiki-0.719
ERA-0.692
Stack-0.680
Token intercept
Token ID15788
Feature activation-1.65e+00

Pos logit contributions
 Samar+2.101
 amy+1.854
olicy+1.725
format+1.722
 Hug+1.708
Neg logit contributions
race-2.515
Redd-2.481
Wiki-2.303
ERA-2.217
Stack-2.174
Tokenl
Token ID75
Feature activation+7.05e+00

Pos logit contributions
 Samar+3.475
 amy+3.165
oker+3.021
format+3.008
olicy+2.952
Neg logit contributions
Redd-3.080
race-3.052
Wiki-2.794
ERA-2.714
Stack-2.639
Tokeninson
Token ID7899
Feature activation+2.60e-01

Pos logit contributions
race+3.351
Redd+3.178
Wiki+2.806
Stack+2.541
idon+2.532
Neg logit contributions
 Samar-6.801
olicy-6.381
 amy-6.328
format-5.967
artney-5.943
Token,
Token ID11
Feature activation-3.79e-01

Pos logit contributions
race+0.199
Redd+0.198
Wiki+0.182
ERA+0.175
Stack+0.172
Neg logit contributions
 Samar-0.181
 amy-0.162
olicy-0.153
format-0.152
oker-0.150
Token John
Token ID1757
Feature activation-2.75e+00

Pos logit contributions
 Samar+0.273
 amy+0.244
olicy+0.231
format+0.230
oker+0.228
Neg logit contributions
race-0.281
Redd-0.278
Wiki-0.256
ERA-0.246
Stack-0.242
Token O
Token ID440
Feature activation-3.91e-01

Pos logit contributions
 Samar+2.025
 amy+1.776
 Hug+1.696
format+1.695
olicy+1.690
Neg logit contributions
race-1.995
Redd-1.977
Wiki-1.816
ERA-1.761
Stack-1.703
Token'
Token ID6
Feature activation+1.28e+01

Pos logit contributions
 Samar+0.230
 amy+0.201
olicy+0.188
format+0.186
oker+0.184
Neg logit contributions
race-0.341
Redd-0.338
Wiki-0.314
ERA-0.304
Stack-0.299
TokenK
Token ID42
Feature activation+4.41e+00

Pos logit contributions
Redd+7.105
race+6.443
ERA+5.950
Wiki+5.902
Stack+5.815
Neg logit contributions
 Samar-10.261
 amy-9.940
olicy-9.811
mble-9.790
 rul-9.710
Tokenane
Token ID1531
Feature activation+2.75e-01

Pos logit contributions
race+3.905
Redd+3.776
ERA+3.515
Wiki+3.501
idon+3.386
Neg logit contributions
 Samar-2.519
 amy-2.164
olicy-2.029
format-1.953
 Hug-1.950
Token,
Token ID11
Feature activation+1.73e-01

Pos logit contributions
race+0.210
Redd+0.208
Wiki+0.192
ERA+0.184
Stack+0.181
Neg logit contributions
 Samar-0.191
 amy-0.171
olicy-0.161
format-0.160
oker-0.159
Token J
Token ID449
Feature activation-4.61e+00

Pos logit contributions
race+0.128
Redd+0.127
Wiki+0.116
ERA+0.112
Stack+0.110
Neg logit contributions
 Samar-0.124
 amy-0.112
olicy-0.106
format-0.105
oker-0.104
Tokenovan
Token ID22590
Feature activation-3.92e+00

Pos logit contributions
 Samar+3.310
 amy+2.973
oker+2.886
olicy+2.834
format+2.830
Neg logit contributions
Redd-3.312
race-3.298
Wiki-3.025
ERA-2.895
Stack-2.862
Token Sheen
Token ID50189
Feature activation+3.98e+00

Pos logit contributions
 Samar+1.820
 amy+1.466
format+1.316
 Hug+1.295
oker+1.289
Neg logit contributions
race-4.206
Redd-4.178
Wiki-3.928
ERA-3.827
Stack-3.768
Token 2008
Token ID3648
Feature activation-1.56e-01

Pos logit contributions
race+2.940
Redd+2.884
Wiki+2.672
ERA+2.555
Stack+2.516
Neg logit contributions
 Samar-2.819
 amy-2.542
olicy-2.418
format-2.405
oker-2.380
Token Alec
Token ID38285
Feature activation-2.44e+00

Pos logit contributions
 Samar+0.112
 amy+0.100
olicy+0.095
format+0.094
oker+0.093
Neg logit contributions
race-0.115
Redd-0.114
Wiki-0.105
ERA-0.101
Stack-0.099
Token Baldwin
Token ID26402
Feature activation-1.33e+00

Pos logit contributions
 Samar+1.935
 amy+1.745
format+1.658
olicy+1.658
oker+1.646
Neg logit contributions
race-1.629
Redd-1.611
Wiki-1.462
ERA-1.400
Stack-1.369
Token
Token ID198
Feature activation+1.28e+00

Pos logit contributions
 Samar+0.912
 amy+0.816
olicy+0.773
format+0.763
oker+0.757
Neg logit contributions
race-1.033
Redd-1.022
Wiki-0.943
ERA-0.908
Stack-0.892
Token
Token ID198
Feature activation+1.28e+01

Pos logit contributions
race+0.944
Redd+0.929
Wiki+0.859
ERA+0.818
Stack+0.811
Neg logit contributions
 Samar-0.929
 amy-0.850
olicy-0.818
mble-0.804
 rul-0.795
Token2008
Token ID11528
Feature activation-1.40e+00

Pos logit contributions
race+9.239
Redd+9.200
Wiki+8.494
ERA+8.170
Stack+8.106
Neg logit contributions
 eleph-9.403
 rul-9.321
 Samar-9.180
 amy-8.420
-8.359
Token Steve
Token ID6542
Feature activation-1.13e+00

Pos logit contributions
 Samar+0.988
 amy+0.879
format+0.821
oker+0.814
olicy+0.813
Neg logit contributions
race-1.058
Redd-1.053
Wiki-0.957
ERA-0.933
Stack-0.909
Token Care
Token ID7276
Feature activation-7.13e-01

Pos logit contributions
 Samar+0.421
 amy+0.342
olicy+0.307
format+0.300
oker+0.293
Neg logit contributions
race-1.230
Redd-1.219
Wiki-1.152
ERA-1.123
Stack-1.109
Tokenll
Token ID297
Feature activation+6.50e+00

Pos logit contributions
 Samar+0.579
 amy+0.528
olicy+0.505
format+0.497
oker+0.493
Neg logit contributions
race-0.466
Redd-0.458
Wiki-0.414
ERA-0.395
Stack-0.389
Token
Token ID198
Feature activation+3.23e+00

Pos logit contributions
race+4.186
Redd+4.047
Wiki+3.840
ERA+3.581
Stack+3.566
Neg logit contributions
 Samar-4.954
 amy-4.696
olicy-4.634
mble-4.603
 rul-4.530
Token of
Token ID286
Feature activation+6.99e-02

Pos logit contributions
 Samar+0.149
 amy+0.134
olicy+0.128
format+0.127
oker+0.125
Neg logit contributions
race-0.147
Redd-0.146
Wiki-0.133
ERA-0.128
Stack-0.126
Token the
Token ID262
Feature activation+4.12e-01

Pos logit contributions
race+0.053
Redd+0.053
Wiki+0.048
ERA+0.047
Stack+0.046
Neg logit contributions
 Samar-0.049
 amy-0.044
olicy-0.041
format-0.041
oker-0.041
Token match
Token ID2872
Feature activation+2.52e+00

Pos logit contributions
race+0.308
Redd+0.304
Wiki+0.279
ERA+0.269
Stack+0.263
Neg logit contributions
 Samar-0.292
 amy-0.262
olicy-0.251
format-0.247
oker-0.246
Token have
Token ID423
Feature activation+4.86e-01

Pos logit contributions
race+1.820
Redd+1.775
Wiki+1.625
ERA+1.565
Stack+1.544
Neg logit contributions
 Samar-1.838
 amy-1.653
olicy-1.602
format-1.564
oker-1.548
Token morphed
Token ID49976
Feature activation+3.43e+00

Pos logit contributions
race+0.362
Redd+0.358
Wiki+0.329
ERA+0.316
Stack+0.311
Neg logit contributions
 Samar-0.346
 amy-0.309
olicy-0.295
format-0.292
oker-0.290
Token into
Token ID656
Feature activation+1.28e+01

Pos logit contributions
race+2.225
Redd+2.188
Wiki+1.975
ERA+1.890
Stack+1.849
Neg logit contributions
 Samar-2.730
 amy-2.475
olicy-2.430
oker-2.382
format-2.372
Token nerves
Token ID25377
Feature activation+1.88e+00

Pos logit contributions
race+8.651
Redd+8.546
Wiki+7.724
 waivers+7.547
ERA+7.457
Neg logit contributions
 Samar-8.251
olicy-7.684
format-7.351
oker-7.341
mble-7.288
Token,
Token ID11
Feature activation+3.23e-01

Pos logit contributions
race+1.366
Redd+1.347
Wiki+1.233
ERA+1.186
Stack+1.165
Neg logit contributions
 Samar-1.380
 amy-1.240
olicy-1.190
format-1.171
oker-1.160
Token dread
Token ID15157
Feature activation+9.02e-01

Pos logit contributions
race+0.245
Redd+0.243
Wiki+0.224
ERA+0.215
Stack+0.211
Neg logit contributions
 Samar-0.226
 amy-0.202
olicy-0.192
format-0.190
oker-0.189
Token and
Token ID290
Feature activation+4.50e+00

Pos logit contributions
race+0.658
Redd+0.652
Wiki+0.598
ERA+0.574
Stack+0.564
Neg logit contributions
 Samar-0.657
 amy-0.590
olicy-0.560
format-0.557
oker-0.552
Token bewild
Token ID34672
Feature activation+2.72e+00

Pos logit contributions
race+3.384
Redd+3.325
Wiki+3.059
ERA+2.932
Stack+2.894
Neg logit contributions
 Samar-3.106
 amy-2.760
olicy-2.721
format-2.662
oker-2.636
Tokenap
Token ID499
Feature activation+2.61e+00

Pos logit contributions
race+3.422
Redd+3.268
Wiki+3.014
ERA+2.830
Stack+2.740
Neg logit contributions
 Samar-5.147
 amy-4.694
olicy-4.501
format-4.479
mble-4.433
Tokenuni
Token ID35657
Feature activation+2.78e+00

Pos logit contributions
race+1.728
Redd+1.700
Wiki+1.561
ERA+1.480
Stack+1.447
Neg logit contributions
 Samar-2.085
 amy-1.900
olicy-1.799
format-1.786
oker-1.771
Token o
Token ID267
Feature activation+1.93e+00

Pos logit contributions
race+2.081
Redd+2.050
Wiki+1.898
ERA+1.826
Stack+1.793
Neg logit contributions
 Samar-1.939
 amy-1.742
olicy-1.672
format-1.652
oker-1.637
Token N
Token ID399
Feature activation+6.48e+00

Pos logit contributions
race+1.463
Redd+1.444
Wiki+1.332
ERA+1.279
Stack+1.256
Neg logit contributions
 Samar-1.338
 amy-1.201
olicy-1.143
format-1.136
oker-1.121
Tokenā
Token ID10235
Feature activation+4.63e+00

Pos logit contributions
race+4.218
Redd+3.998
Wiki+3.738
ERA+3.635
idon+3.517
Neg logit contributions
 Samar-5.095
 amy-4.588
olicy-4.446
format-4.373
 Volvo-4.326
Tokenn
Token ID77
Feature activation+1.27e+01

Pos logit contributions
race+3.397
Redd+3.283
Wiki+3.053
ERA+2.899
idon+2.859
Neg logit contributions
 Samar-3.296
 amy-2.957
olicy-2.839
format-2.786
oker-2.767
Tokenā
Token ID10235
Feature activation+3.71e+00

Pos logit contributions
race+7.480
Redd+6.704
Wiki+6.485
idon+6.259
ERA+6.159
Neg logit contributions
 Samar-9.772
 amy-8.771
olicy-8.758
 Volvo-8.562
format-8.482
Tokenk
Token ID74
Feature activation+1.04e+01

Pos logit contributions
race+2.554
Redd+2.491
Wiki+2.296
ERA+2.180
Stack+2.149
Neg logit contributions
 Samar-2.833
 amy-2.563
olicy-2.457
format-2.423
oker-2.405
Tokenuli
Token ID32176
Feature activation+3.90e+00

Pos logit contributions
race+6.475
Redd+6.043
Wiki+5.778
ERA+5.348
idon+5.326
Neg logit contributions
 Samar-8.123
 amy-7.512
olicy-6.934
 Hug-6.923
format-6.910
Token.
Token ID13
Feature activation+2.76e+00

Pos logit contributions
race+2.894
Redd+2.842
Wiki+2.645
ERA+2.532
Stack+2.490
Neg logit contributions
 Samar-2.693
 amy-2.421
olicy-2.347
format-2.311
oker-2.291
Token E
Token ID412
Feature activation+2.33e-01

Pos logit contributions
race+2.084
Redd+2.055
Wiki+1.896
ERA+1.826
Stack+1.792
Neg logit contributions
 Samar-1.913
 amy-1.718
olicy-1.647
format-1.620
oker-1.613
Token than
Token ID621
Feature activation+4.65e+00

Pos logit contributions
 Samar+1.190
 amy+1.082
format+1.010
 Hug+0.999
bm+0.997
Neg logit contributions
Redd-1.038
race-1.034
Wiki-0.947
ERA-0.906
Stack-0.882
Token the
Token ID262
Feature activation+1.02e+00

Pos logit contributions
race+3.181
Redd+3.103
Wiki+2.778
ERA+2.705
Stack+2.650
Neg logit contributions
 Samar-3.456
 amy-3.153
olicy-3.088
format-3.059
oker-3.040
Token recommended
Token ID7151
Feature activation+3.31e+00

Pos logit contributions
race+0.834
Redd+0.827
Wiki+0.764
ERA+0.739
Stack+0.726
Neg logit contributions
 Samar-0.646
 amy-0.572
olicy-0.541
format-0.536
oker-0.531
Token 8
Token ID807
Feature activation+2.10e+00

Pos logit contributions
race+2.300
Redd+2.259
Wiki+2.045
ERA+1.975
Stack+1.935
Neg logit contributions
 Samar-2.480
 amy-2.241
olicy-2.173
format-2.143
oker-2.134
Token 1
Token ID352
Feature activation+1.81e+00

Pos logit contributions
race+1.559
Redd+1.540
Wiki+1.414
ERA+1.360
Stack+1.337
Neg logit contributions
 Samar-1.510
 amy-1.352
olicy-1.286
format-1.275
oker-1.265
Token/
Token ID14
Feature activation+1.26e+01

Pos logit contributions
race+1.276
Redd+1.253
Wiki+1.152
ERA+1.106
Stack+1.092
Neg logit contributions
 Samar-1.353
 amy-1.232
olicy-1.198
mble-1.173
oker-1.151
Token2
Token ID17
Feature activation+8.21e+00

Pos logit contributions
race+6.265
Redd+5.889
ERA+5.366
Wiki+5.158
Stack+5.101
Neg logit contributions
 eleph-11.289
 Samar-11.026
mble-10.937
 rul-10.879
-10.853
Token to
Token ID284
Feature activation+3.37e+00

Pos logit contributions
race+5.183
Redd+5.060
Wiki+4.570
ERA+4.422
Stack+4.356
Neg logit contributions
 Samar-6.498
 amy-5.842
olicy-5.655
mble-5.566
oker-5.561
Token 9
Token ID860
Feature activation+8.58e+00

Pos logit contributions
race+2.352
Redd+2.299
Wiki+2.091
ERA+2.018
Stack+1.980
Neg logit contributions
 Samar-2.546
 amy-2.300
olicy-2.199
format-2.175
oker-2.161
Token 1
Token ID352
Feature activation+2.57e+00

Pos logit contributions
race+5.564
Redd+5.397
Wiki+4.896
ERA+4.676
Stack+4.643
Neg logit contributions
 Samar-6.629
 amy-5.958
olicy-5.762
mble-5.677
oker-5.667
Token/
Token ID14
Feature activation+1.06e+01

Pos logit contributions
race+1.792
Redd+1.754
Wiki+1.604
ERA+1.534
Stack+1.521
Neg logit contributions
 Samar-1.930
 amy-1.756
olicy-1.703
mble-1.668
format-1.654
Token see
Token ID766
Feature activation+1.26e+00

Pos logit contributions
 Samar+2.594
 amy+2.321
format+2.167
oker+2.130
 Hug+2.126
Neg logit contributions
Redd-3.137
race-3.104
Wiki-2.867
ERA-2.776
Stack-2.709
Token.[
Token ID3693
Feature activation+7.36e+00

Pos logit contributions
race+0.928
Redd+0.913
Wiki+0.837
ERA+0.803
Stack+0.791
Neg logit contributions
 Samar-0.909
 amy-0.815
olicy-0.783
format-0.768
oker-0.762
Token117
Token ID17657
Feature activation-4.11e+00

Pos logit contributions
race+6.510
Redd+6.386
Wiki+5.976
ERA+5.767
Stack+5.743
Neg logit contributions
 Samar-4.199
 amy-3.612
olicy-3.521
mble-3.338
oker-3.255
Token]
Token ID60
Feature activation+3.00e-01

Pos logit contributions
 Samar+2.735
 amy+2.499
olicy+2.325
format+2.316
bm+2.280
Neg logit contributions
Redd-3.151
race-3.133
Wiki-2.862
ERA-2.829
Stack-2.727
Token A
Token ID317
Feature activation-1.36e+00

Pos logit contributions
race+0.229
Redd+0.226
Wiki+0.209
ERA+0.200
Stack+0.197
Neg logit contributions
 Samar-0.208
 amy-0.187
olicy-0.178
format-0.176
oker-0.174
Tokenbr
Token ID1671
Feature activation+1.23e+01

Pos logit contributions
 Samar+0.900
 amy+0.799
olicy+0.749
format+0.746
oker+0.740
Neg logit contributions
race-1.077
Redd-1.071
Wiki-0.987
ERA-0.952
Stack-0.937
Tokenasions
Token ID39327
Feature activation+5.22e+00

Pos logit contributions
race+8.617
Redd+7.872
Wiki+7.731
idon+7.467
ERA+7.315
Neg logit contributions
 Samar-8.355
mble-7.423
 amy-7.336
olicy-7.183
 Volvo-7.108
Token around
Token ID1088
Feature activation+4.73e-01

Pos logit contributions
race+3.663
Redd+3.513
Wiki+3.263
Stack+3.053
ERA+3.045
Neg logit contributions
 Samar-3.888
 amy-3.453
olicy-3.439
format-3.350
mble-3.287
Token the
Token ID262
Feature activation+8.16e-01

Pos logit contributions
race+0.366
Redd+0.362
Wiki+0.333
ERA+0.321
Stack+0.315
Neg logit contributions
 Samar-0.324
 amy-0.288
olicy-0.275
format-0.273
oker-0.269
Token eyes
Token ID2951
Feature activation-1.31e+00

Pos logit contributions
race+0.665
Redd+0.658
Wiki+0.608
ERA+0.588
Stack+0.577
Neg logit contributions
 Samar-0.526
 amy-0.464
olicy-0.441
format-0.437
oker-0.431
Token,
Token ID11
Feature activation-2.00e+00

Pos logit contributions
 Samar+0.930
 amy+0.837
format+0.784
oker+0.780
olicy+0.779
Neg logit contributions
Redd-0.975
race-0.970
Wiki-0.891
ERA-0.863
Stack-0.841
Token United
Token ID1578
Feature activation-2.24e+00

Pos logit contributions
 Samar+5.048
 amy+4.526
format+4.122
 Volvo+4.115
oker+4.073
Neg logit contributions
race-4.917
Redd-4.870
Wiki-4.458
ERA-4.373
Stack-4.217
Token States
Token ID1829
Feature activation-4.78e-01

Pos logit contributions
 Samar+1.784
 amy+1.588
format+1.514
olicy+1.499
 Hug+1.489
Neg logit contributions
Redd-1.481
race-1.479
Wiki-1.340
ERA-1.309
Stack-1.273
Token often
Token ID1690
Feature activation+3.62e-01

Pos logit contributions
 Samar+0.338
 amy+0.303
olicy+0.285
format+0.284
oker+0.281
Neg logit contributions
race-0.360
Redd-0.357
Wiki-0.328
ERA-0.316
Stack-0.310
Token carry
Token ID3283
Feature activation+4.87e-02

Pos logit contributions
race+0.260
Redd+0.257
Wiki+0.235
ERA+0.226
Stack+0.222
Neg logit contributions
 Samar-0.269
 amy-0.242
olicy-0.229
format-0.228
oker-0.226
Token My
Token ID2011
Feature activation+3.51e+00

Pos logit contributions
race+0.037
Redd+0.037
Wiki+0.034
ERA+0.033
Stack+0.032
Neg logit contributions
 Samar-0.034
 amy-0.030
olicy-0.029
format-0.029
oker-0.028
Tokenc
Token ID66
Feature activation+1.22e+01

Pos logit contributions
race+3.110
Redd+3.029
Wiki+2.842
ERA+2.768
Stack+2.706
Neg logit contributions
 Samar-2.039
 amy-1.752
olicy-1.674
format-1.612
oker-1.594
Tokenob
Token ID672
Feature activation+2.61e+00

Pos logit contributions
race+6.818
Redd+6.214
Wiki+6.081
ERA+5.974
idon+5.624
Neg logit contributions
 Samar-9.697
olicy-8.815
mble-8.704
 amy-8.413
 Volvo-8.344
Tokenacter
Token ID7321
Feature activation+4.70e+00

Pos logit contributions
race+1.718
Redd+1.660
Wiki+1.523
ERA+1.457
Stack+1.420
Neg logit contributions
 Samar-2.102
 amy-1.903
olicy-1.826
format-1.795
 Hug-1.773
Tokenium
Token ID1505
Feature activation+3.86e+00

Pos logit contributions
race+1.931
Redd+1.817
Wiki+1.645
ERA+1.515
Stack+1.458
Neg logit contributions
 Samar-4.787
 amy-4.429
olicy-4.426
format-4.334
oker-4.314
Token le
Token ID443
Feature activation+4.91e+00

Pos logit contributions
race+3.490
Redd+3.431
Wiki+3.246
ERA+3.134
Stack+3.086
Neg logit contributions
 Samar-2.045
 amy-1.737
olicy-1.735
oker-1.691
format-1.669
Tokenp
Token ID79
Feature activation+5.73e+00

Pos logit contributions
race+3.691
Redd+3.580
Wiki+3.351
ERA+3.219
idon+3.167
Neg logit contributions
 Samar-3.395
 amy-3.068
olicy-2.871
format-2.815
 Hug-2.803
Tokenun
Token ID403
Feature activation-1.57e+00

Pos logit contributions
race+2.167
Redd+2.114
Wiki+1.959
ERA+1.880
Stack+1.839
Neg logit contributions
 Samar-2.209
 amy-1.975
olicy-1.903
format-1.864
oker-1.844
Tokencus
Token ID9042
Feature activation+2.26e+00

Pos logit contributions
 Samar+0.891
 amy+0.773
format+0.722
olicy+0.717
oker+0.710
Neg logit contributions
Redd-1.388
race-1.388
Wiki-1.284
ERA-1.248
Stack-1.229
Token,
Token ID11
Feature activation+2.40e+00

Pos logit contributions
race+1.798
Redd+1.769
Wiki+1.644
ERA+1.580
Stack+1.556
Neg logit contributions
 Samar-1.495
 amy-1.312
olicy-1.274
format-1.248
oker-1.243
Token and
Token ID290
Feature activation+4.36e+00

Pos logit contributions
race+1.825
Redd+1.800
Wiki+1.664
ERA+1.596
Stack+1.568
Neg logit contributions
 Samar-1.649
 amy-1.479
olicy-1.428
format-1.408
oker-1.400
Token My
Token ID2011
Feature activation+3.53e+00

Pos logit contributions
race+3.369
Redd+3.321
Wiki+3.081
ERA+2.950
Stack+2.895
Neg logit contributions
 Samar-2.852
 amy-2.558
olicy-2.509
format-2.475
oker-2.457
Tokenc
Token ID66
Feature activation+1.22e+01

Pos logit contributions
race+3.291
Redd+3.185
Wiki+3.013
ERA+2.928
Stack+2.866
Neg logit contributions
 Samar-1.905
 amy-1.643
olicy-1.524
 Volvo-1.452
oker-1.446
Tokenopl
Token ID20106
Feature activation+3.03e+00

Pos logit contributions
race+6.146
Redd+5.303
Wiki+5.001
idon+4.968
ERA+4.931
Neg logit contributions
 Samar-10.604
 amy-9.646
olicy-9.473
mble-9.400
staking-9.360
Tokenasma
Token ID11797
Feature activation+4.37e+00

Pos logit contributions
race+2.809
Redd+2.705
Wiki+2.568
ERA+2.484
idon+2.453
Neg logit contributions
 Samar-1.655
 amy-1.419
olicy-1.321
format-1.275
 Hug-1.268
Token hom
Token ID3488
Feature activation+1.70e+00

Pos logit contributions
race+3.314
Redd+3.243
Wiki+3.042
ERA+2.902
Stack+2.843
Neg logit contributions
 Samar-3.002
 amy-2.625
olicy-2.611
oker-2.544
format-2.512
Tokeninis
Token ID16661
Feature activation+1.97e+00

Pos logit contributions
race+1.240
Redd+1.220
Wiki+1.119
ERA+1.077
Stack+1.053
Neg logit contributions
 Samar-1.251
 amy-1.126
olicy-1.066
format-1.061
oker-1.045
Token which
Token ID543
Feature activation+4.71e+00

Pos logit contributions
race+1.422
Redd+1.396
Wiki+1.286
ERA+1.230
Stack+1.212
Neg logit contributions
 Samar-1.444
 amy-1.291
olicy-1.242
format-1.224
oker-1.219
Tokens
Token ID82
Feature activation-5.25e+00

Pos logit contributions
 Samar+3.359
 amy+2.929
format+2.874
cs+2.836
bm+2.831
Neg logit contributions
Redd-4.257
race-4.165
Wiki-3.890
ERA-3.771
idon-3.678
Token)}
Token ID38165
Feature activation-4.24e+00

Pos logit contributions
 Samar+3.974
 amy+3.553
format+3.479
oker+3.434
bm+3.427
Neg logit contributions
race-3.556
Redd-3.548
Wiki-3.159
ERA-3.040
Stack-2.984
Token 5
Token ID642
Feature activation+1.27e+00

Pos logit contributions
 Samar+2.841
 amy+2.508
olicy+2.412
oker+2.402
format+2.379
Neg logit contributions
race-3.313
Redd-3.301
Wiki-3.008
ERA-2.931
idon-2.794
Token.
Token ID13
Feature activation+2.82e+00

Pos logit contributions
race+0.968
Redd+0.946
Wiki+0.880
ERA+0.843
Stack+0.834
Neg logit contributions
 Samar-0.889
 amy-0.808
olicy-0.770
mble-0.755
 rul-0.741
Token O
Token ID440
Feature activation-1.82e+00

Pos logit contributions
race+2.084
Redd+2.064
Wiki+1.884
ERA+1.817
Stack+1.798
Neg logit contributions
 Samar-1.993
 amy-1.784
olicy-1.711
mble-1.689
format-1.686
Token-
Token ID12
Feature activation+1.20e+01

Pos logit contributions
 Samar+1.191
 amy+1.058
olicy+1.001
format+1.001
oker+0.990
Neg logit contributions
race-1.452
Redd-1.444
Wiki-1.335
ERA-1.287
Stack-1.262
TokenO
Token ID46
Feature activation+2.24e+00

Pos logit contributions
race+5.547
Redd+5.317
Stack+4.746
Wiki+4.677
ERA+4.260
Neg logit contributions
 Samar-11.803
 amy-10.652
mble-10.498
 eleph-10.199
 rul-10.156
Token {
Token ID1391
Feature activation+4.06e+00

Pos logit contributions
race+1.619
Redd+1.601
Wiki+1.465
ERA+1.415
Stack+1.392
Neg logit contributions
 Samar-1.631
 amy-1.472
olicy-1.391
format-1.380
mble-1.363
Token(
Token ID7
Feature activation+1.90e+00

Pos logit contributions
race+2.520
Redd+2.489
Wiki+2.275
ERA+2.150
Stack+2.138
Neg logit contributions
 Samar-3.447
 amy-3.228
olicy-3.098
mble-3.087
 rul-3.079
Token0
Token ID15
Feature activation-5.76e-01

Pos logit contributions
race+1.537
Redd+1.519
Wiki+1.404
ERA+1.360
Stack+1.341
Neg logit contributions
 Samar-1.232
 amy-1.097
olicy-1.032
format-1.006
oker-1.003
Tokens
Token ID82
Feature activation-4.51e+00

Pos logit contributions
 Samar+0.411
 amy+0.369
olicy+0.350
format+0.347
oker+0.344
Neg logit contributions
race-0.430
Redd-0.425
Wiki-0.391
ERA-0.376
Stack-0.369
Token list
Token ID1351
Feature activation+4.24e-01

Pos logit contributions
race+0.835
Redd+0.826
Wiki+0.765
ERA+0.740
Stack+0.728
Neg logit contributions
 Samar-0.643
 amy-0.569
olicy-0.537
format-0.533
oker-0.527
Token.
Token ID13
Feature activation-6.47e-01

Pos logit contributions
race+0.331
Redd+0.328
Wiki+0.302
ERA+0.291
Stack+0.286
Neg logit contributions
 Samar-0.287
 amy-0.256
olicy-0.242
format-0.240
oker-0.238
Token From
Token ID3574
Feature activation+2.52e-01

Pos logit contributions
 Samar+0.506
 amy+0.457
olicy+0.436
format+0.433
oker+0.430
Neg logit contributions
race-0.439
Redd-0.434
Wiki-0.394
ERA-0.378
Stack-0.370
Token Edward
Token ID10443
Feature activation-1.33e+00

Pos logit contributions
race+0.192
Redd+0.190
Wiki+0.174
ERA+0.168
Stack+0.165
Neg logit contributions
 Samar-0.177
 amy-0.158
olicy-0.149
format-0.148
oker-0.147
Token Has
Token ID7875
Feature activation-2.41e+00

Pos logit contributions
 Samar+0.915
 amy+0.804
olicy+0.763
format+0.756
 Hug+0.748
Neg logit contributions
race-1.035
Redd-1.022
Wiki-0.939
ERA-0.914
Stack-0.895
Tokenb
Token ID65
Feature activation+1.19e+01

Pos logit contributions
 Samar+1.387
 amy+1.204
format+1.127
olicy+1.120
oker+1.109
Neg logit contributions
race-2.112
Redd-2.102
Wiki-1.944
ERA-1.891
Stack-1.863
Tokenrou
Token ID472
Feature activation+4.34e-01

Pos logit contributions
race+7.809
Redd+7.262
Wiki+6.888
ERA+6.591
idon+6.358
Neg logit contributions
 Samar-8.298
 amy-7.707
olicy-7.540
 Volvo-7.420
format-7.395
Tokenck
Token ID694
Feature activation+1.49e+00

Pos logit contributions
race+0.340
Redd+0.337
Wiki+0.311
ERA+0.299
Stack+0.294
Neg logit contributions
 Samar-0.293
 amy-0.261
olicy-0.247
format-0.245
oker-0.243
Token's
Token ID338
Feature activation+6.19e-01

Pos logit contributions
race+1.071
Redd+1.060
Wiki+0.976
ERA+0.932
Stack+0.917
Neg logit contributions
 Samar-1.095
 amy-0.984
olicy-0.938
format-0.929
oker-0.920
Token transcript
Token ID14687
Feature activation+4.45e+00

Pos logit contributions
race+0.467
Redd+0.462
Wiki+0.424
ERA+0.409
Stack+0.401
Neg logit contributions
 Samar-0.437
 amy-0.391
olicy-0.371
format-0.368
oker-0.365
Token of
Token ID286
Feature activation+5.41e+00

Pos logit contributions
race+3.108
Redd+3.039
Wiki+2.828
ERA+2.663
Stack+2.649
Neg logit contributions
 Samar-3.307
 amy-2.996
olicy-2.894
format-2.839
oker-2.794
Token Money
Token ID12911
Feature activation+7.09e-01

Pos logit contributions
 Samar+0.411
 amy+0.366
olicy+0.345
format+0.343
oker+0.340
Neg logit contributions
race-0.453
Redd-0.449
Wiki-0.412
ERA-0.398
Stack-0.391
Token Morning
Token ID14410
Feature activation+2.72e+00

Pos logit contributions
race+0.467
Redd+0.462
Wiki+0.419
ERA+0.401
Stack+0.393
Neg logit contributions
 Samar-0.567
 amy-0.514
olicy-0.491
format-0.488
oker-0.484
Token.
Token ID13
Feature activation+3.28e+00

Pos logit contributions
race+2.034
Redd+2.005
Wiki+1.863
ERA+1.780
Stack+1.749
Neg logit contributions
 Samar-1.915
 amy-1.723
olicy-1.629
format-1.614
oker-1.604
Token 16
Token ID1467
Feature activation+9.33e-01

Pos logit contributions
race+2.237
Redd+2.199
Wiki+2.028
ERA+1.927
Stack+1.881
Neg logit contributions
 Samar-2.521
 amy-2.294
olicy-2.199
oker-2.151
format-2.145
Token W
Token ID370
Feature activation+3.05e+00

Pos logit contributions
race+0.706
Redd+0.697
Wiki+0.643
ERA+0.619
Stack+0.608
Neg logit contributions
 Samar-0.653
 amy-0.584
olicy-0.557
format-0.550
oker-0.547
Token.
Token ID13
Feature activation+1.19e+01

Pos logit contributions
race+2.266
Redd+2.244
Wiki+2.058
ERA+2.004
Stack+1.954
Neg logit contributions
 Samar-2.168
 amy-1.941
olicy-1.848
format-1.823
oker-1.806
Token Madison
Token ID14909
Feature activation+5.11e+00

Pos logit contributions
race+8.045
Redd+7.933
Wiki+7.383
ERA+7.295
Stack+7.095
Neg logit contributions
 Samar-7.992
olicy-7.533
 amy-7.516
mble-7.419
 rul-7.238
Token St
Token ID520
Feature activation+8.26e+00

Pos logit contributions
race+2.491
Redd+2.389
Wiki+2.149
ERA+2.052
Stack+1.987
Neg logit contributions
 Samar-4.827
 amy-4.488
olicy-4.419
format-4.344
mble-4.276
Token.
Token ID13
Feature activation+4.47e+00

Pos logit contributions
race+5.330
Redd+5.095
Wiki+4.681
ERA+4.490
Stack+4.384
Neg logit contributions
 Samar-6.566
 amy-5.968
olicy-5.739
format-5.554
 Volvo-5.536
Token Baltimore
Token ID10346
Feature activation-3.57e+00

Pos logit contributions
race+3.250
Redd+3.176
Wiki+2.937
ERA+2.808
Stack+2.755
Neg logit contributions
 Samar-3.239
 amy-2.927
olicy-2.815
format-2.734
mble-2.732
Token,
Token ID11
Feature activation-4.47e+00

Pos logit contributions
 Samar+2.179
 amy+1.937
format+1.773
oker+1.763
olicy+1.762
Neg logit contributions
Redd-2.987
race-2.986
Wiki-2.738
ERA-2.647
Stack-2.608
Token contract
Token ID2775
Feature activation+3.62e+00

Pos logit contributions
race+2.114
Redd+2.097
Wiki+1.939
ERA+1.868
Stack+1.817
Neg logit contributions
 Samar-1.965
 amy-1.744
olicy-1.698
format-1.672
oker-1.636
Token,
Token ID11
Feature activation+1.55e+00

Pos logit contributions
race+2.627
Redd+2.559
Wiki+2.347
ERA+2.306
Stack+2.260
Neg logit contributions
 Samar-2.643
 amy-2.325
olicy-2.236
format-2.200
oker-2.196
Token
Token ID447
Feature activation+1.05e+00

Pos logit contributions
race+1.143
Redd+1.131
Wiki+1.037
ERA+1.004
Stack+0.980
Neg logit contributions
 Samar-1.107
 amy-0.996
olicy-0.952
format-0.942
oker-0.933
Token
Token ID251
Feature activation-9.35e-01

Pos logit contributions
race+0.839
Redd+0.832
Wiki+0.768
ERA+0.742
Stack+0.728
Neg logit contributions
 Samar-0.687
 amy-0.608
olicy-0.575
format-0.570
oker-0.564
Token A
Token ID317
Feature activation+1.01e+00

Pos logit contributions
 Samar+0.671
 amy+0.601
olicy+0.570
format+0.567
oker+0.562
Neg logit contributions
race-0.693
Redd-0.686
Wiki-0.630
ERA-0.605
Stack-0.595
Tokendu
Token ID646
Feature activation+1.18e+01

Pos logit contributions
race+0.768
Redd+0.761
Wiki+0.699
ERA+0.674
Stack+0.659
Neg logit contributions
 Samar-0.707
 amy-0.632
olicy-0.601
format-0.593
oker-0.588
Token says
Token ID1139
Feature activation+5.68e-01

Pos logit contributions
race+7.832
Redd+7.800
Wiki+7.265
ERA+7.043
Stack+6.983
Neg logit contributions
 Samar-7.858
 amy-7.183
olicy-7.041
format-6.916
mble-6.768
Token.
Token ID13
Feature activation+2.27e+00

Pos logit contributions
race+0.441
Redd+0.438
Wiki+0.403
ERA+0.390
Stack+0.382
Neg logit contributions
 Samar-0.385
 amy-0.344
olicy-0.327
format-0.323
oker-0.319
Token
Token ID564
Feature activation-1.25e+00

Pos logit contributions
Redd+1.650
race+1.644
Wiki+1.507
ERA+1.455
Stack+1.421
Neg logit contributions
 Samar-1.644
 amy-1.490
olicy-1.419
format-1.384
oker-1.383
Token
Token ID250
Feature activation+5.18e-01

Pos logit contributions
 Samar+1.118
 amy+1.034
olicy+0.994
format+0.988
oker+0.978
Neg logit contributions
race-0.694
Redd-0.686
Wiki-0.618
ERA-0.577
Stack-0.566
TokenBen
Token ID11696
Feature activation+3.44e+00

Pos logit contributions
race+0.338
Redd+0.334
Wiki+0.304
ERA+0.290
Stack+0.284
Neg logit contributions
 Samar-0.419
 amy-0.381
olicy-0.364
format-0.360
oker-0.357
Tokenuch
Token ID794
Feature activation-8.98e-01

Pos logit contributions
 Samar+2.525
 amy+2.277
olicy+2.151
format+2.138
oker+2.133
Neg logit contributions
Redd-2.784
race-2.780
Wiki-2.554
ERA-2.460
Stack-2.409
Token,
Token ID11
Feature activation+3.74e-01

Pos logit contributions
 Samar+0.598
 amy+0.532
olicy+0.501
format+0.497
oker+0.493
Neg logit contributions
race-0.712
Redd-0.707
Wiki-0.652
ERA-0.629
Stack-0.617
Token what
Token ID644
Feature activation+3.93e+00

Pos logit contributions
race+0.281
Redd+0.278
Wiki+0.256
ERA+0.246
Stack+0.242
Neg logit contributions
 Samar-0.264
 amy-0.235
olicy-0.225
format-0.223
oker-0.221
Token loss
Token ID2994
Feature activation+1.75e+00

Pos logit contributions
race+2.670
Redd+2.609
Wiki+2.375
ERA+2.286
Stack+2.280
Neg logit contributions
 Samar-2.968
 amy-2.676
olicy-2.639
oker-2.568
format-2.551
Token,"
Token ID553
Feature activation+6.31e+00

Pos logit contributions
race+1.223
Redd+1.192
Wiki+1.093
ERA+1.049
Stack+1.034
Neg logit contributions
 Samar-1.324
 amy-1.190
olicy-1.152
format-1.134
oker-1.131
Token he
Token ID339
Feature activation+1.17e+01

Pos logit contributions
race+4.571
Redd+4.484
Wiki+4.223
ERA+4.058
Stack+3.967
Neg logit contributions
 Samar-4.342
 amy-3.847
olicy-3.821
oker-3.683
format-3.665
Token exclaim
Token ID48775
Feature activation+5.39e-01

Pos logit contributions
race+7.124
Redd+6.864
Wiki+6.349
ERA+6.169
 waivers+6.045
Neg logit contributions
 Samar-8.797
olicy-8.214
mble-7.869
 amy-7.862
format-7.536
Tokens
Token ID82
Feature activation+4.34e+00

Pos logit contributions
race+0.382
Redd+0.375
Wiki+0.340
ERA+0.328
Stack+0.325
Neg logit contributions
 Samar-0.407
 amy-0.368
olicy-0.354
mble-0.343
format-0.342
Token.
Token ID13
Feature activation+1.87e+00

Pos logit contributions
race+3.198
Redd+3.145
Wiki+2.866
ERA+2.780
Stack+2.742
Neg logit contributions
 Samar-3.080
 amy-2.725
olicy-2.674
format-2.583
oker-2.580
Token There
Token ID1318
Feature activation+9.64e-02

Pos logit contributions
race+1.437
Redd+1.424
Wiki+1.318
ERA+1.267
Stack+1.249
Neg logit contributions
 Samar-1.278
 amy-1.153
olicy-1.098
format-1.073
oker-1.073
Token are
Token ID389
Feature activation+2.54e+00

Pos logit contributions
race+0.071
Redd+0.070
Wiki+0.064
ERA+0.062
Stack+0.060
Neg logit contributions
 Samar-0.070
 amy-0.063
olicy-0.060
format-0.059
oker-0.059
Token save
Token ID3613
Feature activation-4.67e-01

Pos logit contributions
race+1.401
Redd+1.331
Wiki+1.223
ERA+1.151
Stack+1.121
Neg logit contributions
 Samar-2.051
 amy-1.883
olicy-1.830
mble-1.791
format-1.783
Token,
Token ID11
Feature activation-1.38e+00

Pos logit contributions
 Samar+0.328
 amy+0.295
olicy+0.282
format+0.275
oker+0.274
Neg logit contributions
race-0.355
Redd-0.350
Wiki-0.324
ERA-0.311
Stack-0.306
Token your
Token ID534
Feature activation-2.83e+00

Pos logit contributions
 Samar+0.931
 amy+0.827
olicy+0.778
format+0.778
oker+0.769
Neg logit contributions
race-1.078
Redd-1.070
Wiki-0.985
ERA-0.951
Stack-0.934
Token character
Token ID2095
Feature activation+2.29e+00

Pos logit contributions
 Samar+1.997
 amy+1.784
format+1.682
oker+1.662
olicy+1.660
Neg logit contributions
race-2.129
Redd-2.126
Wiki-1.945
ERA-1.885
Stack-1.847
Token now
Token ID783
Feature activation-2.89e+00

Pos logit contributions
race+1.605
Redd+1.567
Wiki+1.462
Stack+1.375
ERA+1.375
Neg logit contributions
 Samar-1.722
 amy-1.560
olicy-1.518
mble-1.488
format-1.446
Token receives
Token ID11583
Feature activation-1.49e+01

Pos logit contributions
 Samar+1.832
 amy+1.620
format+1.507
olicy+1.506
oker+1.489
Neg logit contributions
race-2.383
Redd-2.368
Wiki-2.191
ERA-2.117
Stack-2.086
Token secret
Token ID3200
Feature activation-9.66e+00

Pos logit contributions
 Samar+4.846
 amy+3.677
 Hug+3.256
 nested+3.153
format+3.133
Neg logit contributions
Redd-15.720
race-14.692
Wiki-14.385
ERA-14.292
idon-14.034
Token voices
Token ID10839
Feature activation-4.62e+00

Pos logit contributions
 Samar+6.953
 amy+6.342
ults+5.849
 Volvo+5.701
 Hug+5.695
Neg logit contributions
Redd-6.762
race-6.738
Wiki-6.224
ERA-6.054
Stack-5.926
Token in
Token ID287
Feature activation-4.17e+00

Pos logit contributions
 Samar+2.902
 amy+2.543
format+2.438
oker+2.357
 Hug+2.354
Neg logit contributions
Redd-3.772
race-3.753
Wiki-3.471
ERA-3.398
idon-3.280
Token his
Token ID465
Feature activation-2.32e+00

Pos logit contributions
 Samar+2.898
 amy+2.578
format+2.471
oker+2.408
 Hug+2.398
Neg logit contributions
Redd-3.138
race-3.131
Wiki-2.899
ERA-2.813
Stack-2.711
Token or
Token ID393
Feature activation-2.81e-01

Pos logit contributions
 Samar+1.581
 amy+1.410
olicy+1.329
format+1.323
oker+1.313
Neg logit contributions
race-1.805
Redd-1.791
Wiki-1.651
ERA-1.591
Stack-1.561
Token to
Token ID284
Feature activation-2.05e-01

Pos logit contributions
race+2.418
Redd+2.323
Wiki+2.180
ERA+2.063
Stack+2.047
Neg logit contributions
 Samar-2.406
 amy-2.146
olicy-2.077
format-2.028
oker-2.027
Token condo
Token ID32119
Feature activation-9.20e-01

Pos logit contributions
 Samar+0.133
 amy+0.118
olicy+0.112
format+0.111
oker+0.110
Neg logit contributions
race-0.165
Redd-0.164
Wiki-0.151
ERA-0.146
Stack-0.144
Token developments
Token ID13312
Feature activation-3.58e+00

Pos logit contributions
 Samar+0.677
 amy+0.611
olicy+0.578
format+0.577
oker+0.569
Neg logit contributions
race-0.663
Redd-0.657
Wiki-0.601
ERA-0.576
Stack-0.564
Token are
Token ID389
Feature activation+1.82e+00

Pos logit contributions
 Samar+2.512
 amy+2.256
format+2.126
oker+2.080
 Hug+2.077
Neg logit contributions
Redd-2.708
race-2.644
Wiki-2.460
ERA-2.399
Stack-2.296
Token knee
Token ID10329
Feature activation-7.61e+00

Pos logit contributions
race+1.360
Redd+1.345
Wiki+1.235
ERA+1.184
Stack+1.168
Neg logit contributions
 Samar-1.293
 amy-1.155
olicy-1.102
format-1.092
oker-1.086
Token-
Token ID12
Feature activation-1.48e+01

Pos logit contributions
 Samar+4.398
 amy+3.913
format+3.671
oker+3.640
 Hug+3.584
Neg logit contributions
Redd-6.434
race-6.331
Wiki-5.875
ERA-5.780
idon-5.723
Tokenj
Token ID73
Feature activation-1.33e+01

Pos logit contributions
 Samar+7.126
format+6.485
 amy+6.398
 Hug+6.148
bm+6.086
Neg logit contributions
Redd-12.239
idon-11.536
race-11.508
 waivers-11.390
ERA-11.249
Tokenerk
Token ID9587
Feature activation+4.77e-01

Pos logit contributions
oker+9.285
 Samar+9.029
 amy+8.483
bm+8.374
format+8.358
Neg logit contributions
Redd-9.167
race-7.948
Wiki-7.761
ERA-7.535
 waivers-7.505
Token.
Token ID13
Feature activation-4.64e-01

Pos logit contributions
race+0.360
Redd+0.356
Wiki+0.327
ERA+0.315
Stack+0.310
Neg logit contributions
 Samar-0.336
 amy-0.300
olicy-0.284
format-0.282
oker-0.280
Token They
Token ID1119
Feature activation+2.02e+00

Pos logit contributions
 Samar+0.339
 amy+0.305
olicy+0.290
format+0.287
oker+0.285
Neg logit contributions
race-0.338
Redd-0.335
Wiki-0.307
ERA-0.295
Stack-0.289
Token're
Token ID821
Feature activation+1.27e+00

Pos logit contributions
race+1.456
Redd+1.403
Wiki+1.302
ERA+1.247
Stack+1.234
Neg logit contributions
 Samar-1.492
 amy-1.337
olicy-1.290
format-1.269
oker-1.259
Token only
Token ID691
Feature activation+3.63e+00

Pos logit contributions
 Samar+0.489
 amy+0.438
olicy+0.413
format+0.411
oker+0.407
Neg logit contributions
race-0.515
Redd-0.511
Wiki-0.469
ERA-0.451
Stack-0.443
Token to
Token ID284
Feature activation-1.12e-01

Pos logit contributions
race+2.651
Redd+2.631
Wiki+2.416
ERA+2.312
Stack+2.282
Neg logit contributions
 Samar-2.556
 amy-2.293
olicy-2.243
format-2.218
oker-2.180
Token stand
Token ID1302
Feature activation+1.47e+00

Pos logit contributions
 Samar+0.084
 amy+0.076
olicy+0.072
format+0.072
oker+0.071
Neg logit contributions
race-0.080
Redd-0.079
Wiki-0.072
ERA-0.069
Stack-0.068
Token up
Token ID510
Feature activation+3.90e+00

Pos logit contributions
race+1.094
Redd+1.077
Wiki+0.988
ERA+0.950
Stack+0.936
Neg logit contributions
 Samar-1.043
 amy-0.932
olicy-0.896
format-0.886
oker-0.876
Token ankle
Token ID19847
Feature activation-5.47e+00

Pos logit contributions
race+2.723
Redd+2.663
Wiki+2.396
ERA+2.316
Stack+2.294
Neg logit contributions
 Samar-2.892
 amy-2.634
olicy-2.547
format-2.500
oker-2.470
Token-
Token ID12
Feature activation-1.37e+01

Pos logit contributions
 Samar+3.529
 amy+3.115
format+2.955
 Hug+2.897
olicy+2.887
Neg logit contributions
Redd-4.387
race-4.321
Wiki-4.034
ERA-3.887
Stack-3.866
Tokendeep
Token ID22089
Feature activation+2.98e+00

Pos logit contributions
 Samar+7.577
format+6.704
 amy+6.567
 Hug+6.385
bm+6.165
Neg logit contributions
Redd-11.059
race-10.257
idon-10.044
Wiki-9.947
ERA-9.844
Token in
Token ID287
Feature activation+1.44e+00

Pos logit contributions
race+2.174
Redd+2.126
Wiki+1.944
ERA+1.873
Stack+1.854
Neg logit contributions
 Samar-2.152
 amy-1.925
olicy-1.873
oker-1.828
format-1.827
Token water
Token ID1660
Feature activation+2.69e+00

Pos logit contributions
race+1.095
Redd+1.083
Wiki+0.996
ERA+0.958
Stack+0.943
Neg logit contributions
 Samar-1.011
 amy-0.904
olicy-0.859
format-0.853
oker-0.845
Token.
Token ID13
Feature activation+4.04e-02

Pos logit contributions
race+1.978
Redd+1.934
Wiki+1.755
ERA+1.698
Stack+1.677
Neg logit contributions
 Samar-1.948
 amy-1.745
olicy-1.681
format-1.655
oker-1.642
Token
Token ID198
Feature activation+1.36e+00

Pos logit contributions
race+0.031
Redd+0.031
Wiki+0.028
ERA+0.027
Stack+0.027
Neg logit contributions
 Samar-0.028
 amy-0.025
olicy-0.023
format-0.023
oker-0.023
Token paper
Token ID3348
Feature activation-1.38e+00

Pos logit contributions
 Samar+0.780
 amy+0.692
olicy+0.649
format+0.646
oker+0.640
Neg logit contributions
race-0.935
Redd-0.930
Wiki-0.857
ERA-0.826
Stack-0.814
Token from
Token ID422
Feature activation-1.25e+00

Pos logit contributions
 Samar+0.942
 amy+0.839
olicy+0.792
format+0.788
oker+0.778
Neg logit contributions
race-1.067
Redd-1.060
Wiki-0.976
ERA-0.940
Stack-0.924
Token publication
Token ID9207
Feature activation+9.53e-01

Pos logit contributions
 Samar+0.908
 amy+0.816
olicy+0.772
format+0.766
oker+0.759
Neg logit contributions
race-0.918
Redd-0.911
Wiki-0.834
ERA-0.799
Stack-0.787
Token in
Token ID287
Feature activation-3.69e+00

Pos logit contributions
race+0.723
Redd+0.711
Wiki+0.657
ERA+0.631
Stack+0.622
Neg logit contributions
 Samar-0.666
 amy-0.596
olicy-0.566
format-0.559
oker-0.558
Token J
Token ID449
Feature activation-6.44e+00

Pos logit contributions
 Samar+2.464
 amy+2.186
format+2.032
olicy+2.018
oker+2.002
Neg logit contributions
Redd-2.924
race-2.913
Wiki-2.683
ERA-2.560
Stack-2.548
TokenAMA
Token ID25087
Feature activation-1.35e+01

Pos logit contributions
 Samar+4.623
 amy+4.127
oker+3.958
format+3.950
bm+3.896
Neg logit contributions
Redd-4.653
race-4.521
Wiki-4.153
Stack-4.022
idon-3.949
Token showing
Token ID4478
Feature activation-1.56e+00

Pos logit contributions
 Samar+8.244
 amy+7.134
format+6.692
oker+6.622
 BJ+6.535
Neg logit contributions
Redd-10.465
race-10.194
Wiki-9.372
Stack-9.268
rame-8.818
Token that
Token ID326
Feature activation+1.94e+00

Pos logit contributions
 Samar+1.109
 amy+0.998
olicy+0.935
format+0.927
oker+0.921
Neg logit contributions
race-1.169
Redd-1.164
Wiki-1.068
ERA-1.029
Stack-1.010
Token its
Token ID663
Feature activation-3.18e-01

Pos logit contributions
race+1.508
Redd+1.478
Wiki+1.374
ERA+1.314
Stack+1.294
Neg logit contributions
 Samar-1.310
 amy-1.151
olicy-1.128
format-1.114
oker-1.100
Token drug
Token ID2563
Feature activation+4.38e-01

Pos logit contributions
 Samar+0.215
 amy+0.191
olicy+0.181
format+0.179
oker+0.178
Neg logit contributions
race-0.249
Redd-0.247
Wiki-0.227
ERA-0.219
Stack-0.215
Token,
Token ID11
Feature activation+8.78e-01

Pos logit contributions
race+0.333
Redd+0.329
Wiki+0.303
ERA+0.292
Stack+0.287
Neg logit contributions
 Samar-0.304
 amy-0.272
olicy-0.259
format-0.257
oker-0.255
Token condo
Token ID32119
Feature activation-9.20e-01

Pos logit contributions
 Samar+0.133
 amy+0.118
olicy+0.112
format+0.111
oker+0.110
Neg logit contributions
race-0.165
Redd-0.164
Wiki-0.151
ERA-0.146
Stack-0.144
Token developments
Token ID13312
Feature activation-3.58e+00

Pos logit contributions
 Samar+0.677
 amy+0.611
olicy+0.578
format+0.577
oker+0.569
Neg logit contributions
race-0.663
Redd-0.657
Wiki-0.601
ERA-0.576
Stack-0.564
Token are
Token ID389
Feature activation+1.82e+00

Pos logit contributions
 Samar+2.512
 amy+2.256
format+2.126
oker+2.080
 Hug+2.077
Neg logit contributions
Redd-2.708
race-2.644
Wiki-2.460
ERA-2.399
Stack-2.296
Token knee
Token ID10329
Feature activation-7.61e+00

Pos logit contributions
race+1.360
Redd+1.345
Wiki+1.235
ERA+1.184
Stack+1.168
Neg logit contributions
 Samar-1.293
 amy-1.155
olicy-1.102
format-1.092
oker-1.086
Token-
Token ID12
Feature activation-1.48e+01

Pos logit contributions
 Samar+4.398
 amy+3.913
format+3.671
oker+3.640
 Hug+3.584
Neg logit contributions
Redd-6.434
race-6.331
Wiki-5.875
ERA-5.780
idon-5.723
Tokenj
Token ID73
Feature activation-1.33e+01

Pos logit contributions
 Samar+7.126
format+6.485
 amy+6.398
 Hug+6.148
bm+6.086
Neg logit contributions
Redd-12.239
idon-11.536
race-11.508
 waivers-11.390
ERA-11.249
Tokenerk
Token ID9587
Feature activation+4.77e-01

Pos logit contributions
oker+9.285
 Samar+9.029
 amy+8.483
bm+8.374
format+8.358
Neg logit contributions
Redd-9.167
race-7.948
Wiki-7.761
ERA-7.535
 waivers-7.505
Token.
Token ID13
Feature activation-4.64e-01

Pos logit contributions
race+0.360
Redd+0.356
Wiki+0.327
ERA+0.315
Stack+0.310
Neg logit contributions
 Samar-0.336
 amy-0.300
olicy-0.284
format-0.282
oker-0.280
Token They
Token ID1119
Feature activation+2.02e+00

Pos logit contributions
 Samar+0.339
 amy+0.305
olicy+0.290
format+0.287
oker+0.285
Neg logit contributions
race-0.338
Redd-0.335
Wiki-0.307
ERA-0.295
Stack-0.289
Token're
Token ID821
Feature activation+1.27e+00

Pos logit contributions
race+1.456
Redd+1.403
Wiki+1.302
ERA+1.247
Stack+1.234
Neg logit contributions
 Samar-1.492
 amy-1.337
olicy-1.290
format-1.269
oker-1.259
Token often
Token ID1690
Feature activation+2.99e+00

Pos logit contributions
race+0.985
Redd+0.975
Wiki+0.897
ERA+0.862
Stack+0.850
Neg logit contributions
 Samar-0.870
 amy-0.774
olicy-0.738
format-0.732
oker-0.727
Token as
Token ID355
Feature activation+2.27e+00

Pos logit contributions
 Samar+0.527
 amy+0.474
olicy+0.454
format+0.444
oker+0.443
Neg logit contributions
race-0.572
Redd-0.565
Wiki-0.523
ERA-0.500
Stack-0.493
Token Visa
Token ID27645
Feature activation+9.48e-01

Pos logit contributions
race+1.764
Redd+1.736
Wiki+1.608
ERA+1.550
Stack+1.532
Neg logit contributions
 Samar-1.500
 amy-1.359
olicy-1.303
format-1.288
oker-1.275
Token,
Token ID11
Feature activation-2.26e+00

Pos logit contributions
race+0.713
Redd+0.705
Wiki+0.650
ERA+0.624
Stack+0.613
Neg logit contributions
 Samar-0.669
 amy-0.599
olicy-0.568
format-0.563
oker-0.559
Token Pro
Token ID1041
Feature activation+5.57e-01

Pos logit contributions
 Samar+1.422
 amy+1.249
olicy+1.170
format+1.163
oker+1.150
Neg logit contributions
race-1.876
Redd-1.865
Wiki-1.724
ERA-1.668
Stack-1.639
Tokenctor
Token ID2715
Feature activation+5.61e-01

Pos logit contributions
race+0.463
Redd+0.458
Wiki+0.425
ERA+0.411
Stack+0.404
Neg logit contributions
 Samar-0.350
 amy-0.310
olicy-0.291
format-0.288
oker-0.285
Token &
Token ID1222
Feature activation-1.27e+01

Pos logit contributions
race+0.405
Redd+0.400
Wiki+0.367
ERA+0.352
Stack+0.346
Neg logit contributions
 Samar-0.413
 amy-0.372
olicy-0.353
format-0.350
oker-0.347
Token Gamble
Token ID49318
Feature activation-3.38e+00

Pos logit contributions
 Samar+5.939
 amy+4.806
 Hug+4.641
format+4.541
 Volvo+4.304
Neg logit contributions
race-12.121
Redd-11.927
idon-11.244
Wiki-11.177
ERA-10.941
Token,
Token ID11
Feature activation+5.55e-01

Pos logit contributions
 Samar+2.256
 amy+1.981
format+1.855
olicy+1.852
 Volvo+1.835
Neg logit contributions
Redd-2.654
race-2.650
Wiki-2.426
ERA-2.356
Stack-2.312
Token Coca
Token ID29803
Feature activation-6.31e-01

Pos logit contributions
race+0.429
Redd+0.422
Wiki+0.391
ERA+0.376
Stack+0.370
Neg logit contributions
 Samar-0.376
 amy-0.338
olicy-0.323
format-0.319
oker-0.317
Token-
Token ID12
Feature activation-2.41e+00

Pos logit contributions
 Samar+0.434
 amy+0.386
olicy+0.365
format+0.363
oker+0.360
Neg logit contributions
race-0.487
Redd-0.482
Wiki-0.444
ERA-0.428
Stack-0.420
TokenCola
Token ID28635
Feature activation+6.31e-01

Pos logit contributions
 Samar+2.163
 amy+1.984
olicy+1.901
format+1.900
oker+1.883
Neg logit contributions
race-1.340
Redd-1.323
Wiki-1.171
ERA-1.118
Stack-1.086
Token people
Token ID661
Feature activation-7.53e-01

Pos logit contributions
race+2.657
Redd+2.602
Wiki+2.411
ERA+2.259
Stack+2.226
Neg logit contributions
 Samar-3.329
 amy-3.010
olicy-2.920
format-2.884
oker-2.879
Token,
Token ID11
Feature activation+1.54e+00

Pos logit contributions
 Samar+0.526
 amy+0.471
olicy+0.444
format+0.442
oker+0.437
Neg logit contributions
race-0.573
Redd-0.568
Wiki-0.522
ERA-0.503
Stack-0.494
Token this
Token ID428
Feature activation+6.93e-01

Pos logit contributions
race+1.138
Redd+1.120
Wiki+1.030
ERA+0.992
Stack+0.971
Neg logit contributions
 Samar-1.103
 amy-0.988
olicy-0.943
format-0.937
oker-0.930
Token
Token ID39073
Feature activation-3.55e+00

Pos logit contributions
race+0.530
Redd+0.523
Wiki+0.482
ERA+0.465
Stack+0.456
Neg logit contributions
 Samar-0.481
 amy-0.429
olicy-0.410
format-0.405
oker-0.402
Tokenj
Token ID73
Feature activation-5.57e+00

Pos logit contributions
 Samar+2.350
 amy+2.063
format+2.010
olicy+1.973
oker+1.943
Neg logit contributions
Redd-2.817
race-2.729
Wiki-2.522
ERA-2.486
Stack-2.432
Tokenà
Token ID24247
Feature activation-1.27e+01

Pos logit contributions
 Samar+3.477
 amy+3.028
oker+3.002
format+2.945
olicy+2.935
Neg logit contributions
Redd-4.632
race-4.466
Wiki-4.135
Stack-3.967
ERA-3.934
Token v
Token ID410
Feature activation-3.66e+00

Pos logit contributions
 Samar+4.948
 amy+4.358
format+4.110
 Volvo+3.846
oker+3.799
Neg logit contributions
Redd-12.466
race-12.405
idon-11.546
Wiki-11.315
Stack-11.129
Tokenu
Token ID84
Feature activation-1.06e+00

Pos logit contributions
 Samar+2.802
 amy+2.542
format+2.427
olicy+2.424
oker+2.396
Neg logit contributions
Redd-2.509
race-2.501
Wiki-2.271
ERA-2.159
Stack-2.130
Token isn
Token ID2125
Feature activation+1.06e+00

Pos logit contributions
 Samar+0.748
 amy+0.669
olicy+0.634
format+0.630
oker+0.624
Neg logit contributions
race-0.805
Redd-0.797
Wiki-0.733
ERA-0.706
Stack-0.693
Token
Token ID447
Feature activation+2.47e+00

Pos logit contributions
race+0.777
Redd+0.769
Wiki+0.711
ERA+0.685
Stack+0.673
Neg logit contributions
 Samar-0.776
 amy-0.702
olicy-0.670
mble-0.656
format-0.645
Token
Token ID247
Feature activation-3.50e-02

Pos logit contributions
race+1.492
Redd+1.479
Wiki+1.323
ERA+1.275
Stack+1.238
Neg logit contributions
 Samar-2.113
 amy-1.917
olicy-1.841
format-1.824
oker-1.808
Token08
Token ID2919
Feature activation+3.58e-01

Pos logit contributions
race+0.238
Redd+0.235
Wiki+0.217
ERA+0.209
Stack+0.205
Neg logit contributions
 Samar-0.215
 amy-0.193
olicy-0.183
format-0.181
oker-0.180
Token Rating
Token ID12028
Feature activation-5.83e+00

Pos logit contributions
race+0.307
Redd+0.304
Wiki+0.283
ERA+0.274
Stack+0.270
Neg logit contributions
 Samar-0.215
 amy-0.189
olicy-0.177
format-0.175
oker-0.174
Token:
Token ID25
Feature activation-5.53e+00

Pos logit contributions
 Samar+3.859
 amy+3.357
format+3.282
 Hug+3.186
bm+3.173
Neg logit contributions
race-4.531
Redd-4.493
Wiki-4.060
ERA-4.016
idon-3.931
Token 5
Token ID642
Feature activation-7.21e+00

Pos logit contributions
 Samar+3.586
 amy+3.111
format+2.960
 Hug+2.944
bm+2.901
Neg logit contributions
race-4.417
Redd-4.374
Wiki-4.023
ERA-3.919
idon-3.794
Token
Token ID198
Feature activation-8.63e+00

Pos logit contributions
 Samar+4.239
 amy+3.743
 Hug+3.505
olicy+3.485
format+3.444
Neg logit contributions
race-5.968
Redd-5.965
Wiki-5.459
ERA-5.366
idon-5.221
Token
Token ID198
Feature activation-1.25e+01

Pos logit contributions
 Samar+4.658
format+3.955
bm+3.809
 Hug+3.760
 amy+3.757
Neg logit contributions
race-7.442
Redd-7.362
Wiki-6.732
idon-6.695
ERA-6.661
TokenCrit
Token ID18559
Feature activation-3.25e+00

Pos logit contributions
format+6.567
 Samar+6.559
bm+6.345
cs+6.269
cz+5.919
Neg logit contributions
race-9.044
Redd-8.760
idon-8.270
 waivers-8.151
 Doodle-8.084
Tokenique
Token ID2350
Feature activation-3.43e+00

Pos logit contributions
 Samar+3.103
 amy+2.856
format+2.777
olicy+2.762
oker+2.759
Neg logit contributions
Redd-1.606
race-1.591
Wiki-1.378
ERA-1.317
Stack-1.262
Token:
Token ID25
Feature activation-3.80e+00

Pos logit contributions
 Samar+2.403
 amy+2.119
format+2.045
oker+2.003
bm+1.992
Neg logit contributions
race-2.572
Redd-2.556
Wiki-2.332
ERA-2.264
Stack-2.203
Token Three
Token ID7683
Feature activation-6.40e+00

Pos logit contributions
 Samar+2.590
 amy+2.275
 Hug+2.142
format+2.130
olicy+2.119
Neg logit contributions
race-2.939
Redd-2.930
Wiki-2.701
ERA-2.607
Stack-2.547
Token of
Token ID286
Feature activation-6.68e-01

Pos logit contributions
 Samar+4.283
 amy+3.746
 Hug+3.506
oker+3.460
ults+3.452
Neg logit contributions
race-4.930
Redd-4.912
Wiki-4.566
ERA-4.469
Stack-4.298
TokenR
Token ID49
Feature activation+1.32e+00

Pos logit contributions
race+0.957
Redd+0.952
Wiki+0.865
ERA+0.828
Stack+0.811
Neg logit contributions
 Samar-1.137
 amy-1.034
olicy-0.982
format-0.969
oker-0.966
Tokeneed
Token ID2308
Feature activation+1.12e+00

Pos logit contributions
race+0.812
Redd+0.797
Wiki+0.719
ERA+0.692
Stack+0.669
Neg logit contributions
 Samar-1.117
 amy-1.017
olicy-0.965
format-0.964
 Volvo-0.951
Token argues
Token ID11673
Feature activation-1.13e+00

Pos logit contributions
race+0.871
Redd+0.861
Wiki+0.797
ERA+0.766
Stack+0.754
Neg logit contributions
 Samar-0.758
 amy-0.675
olicy-0.639
format-0.634
oker-0.627
Token,
Token ID11
Feature activation+3.47e-01

Pos logit contributions
 Samar+0.804
 amy+0.721
olicy+0.683
format+0.676
oker+0.670
Neg logit contributions
race-0.844
Redd-0.839
Wiki-0.770
ERA-0.741
Stack-0.727
Token persu
Token ID10722
Feature activation-4.43e+00

Pos logit contributions
race+0.263
Redd+0.260
Wiki+0.240
ERA+0.231
Stack+0.227
Neg logit contributions
 Samar-0.242
 amy-0.217
olicy-0.206
format-0.204
oker-0.202
Tokenas
Token ID292
Feature activation-1.20e+01

Pos logit contributions
 Samar+2.710
 amy+2.378
format+2.251
olicy+2.248
oker+2.240
Neg logit contributions
race-3.707
Redd-3.698
Wiki-3.411
ERA-3.306
Stack-3.256
Tokenively
Token ID2280
Feature activation-2.25e+00

Pos logit contributions
 Samar+5.423
 amy+4.491
bm+4.387
format+4.275
ults+4.108
Neg logit contributions
Redd-11.179
race-11.082
Wiki-10.377
ERA-10.332
 waivers-10.075
Token,
Token ID11
Feature activation-2.74e+00

Pos logit contributions
 Samar+1.459
 amy+1.293
format+1.209
olicy+1.208
oker+1.195
Neg logit contributions
race-1.821
Redd-1.812
Wiki-1.662
ERA-1.614
Stack-1.585
Token that
Token ID326
Feature activation+1.13e+00

Pos logit contributions
 Samar+1.920
 amy+1.721
olicy+1.625
format+1.615
oker+1.596
Neg logit contributions
Redd-2.063
race-2.058
Wiki-1.891
ERA-1.821
Stack-1.789
Token a
Token ID257
Feature activation+1.22e+00

Pos logit contributions
race+0.838
Redd+0.825
Wiki+0.763
ERA+0.732
Stack+0.717
Neg logit contributions
 Samar-0.805
 amy-0.721
olicy-0.689
format-0.685
oker-0.681
Token vibrant
Token ID21266
Feature activation-9.34e-01

Pos logit contributions
race+0.939
Redd+0.928
Wiki+0.854
ERA+0.825
Stack+0.809
Neg logit contributions
 Samar-0.844
 amy-0.754
olicy-0.717
format-0.710
oker-0.705
Token heat
Token ID4894
Feature activation-3.24e+00

Pos logit contributions
race+0.084
Redd+0.082
Wiki+0.071
ERA+0.066
Stack+0.064
Neg logit contributions
 Samar-0.181
 amy-0.168
olicy-0.163
format-0.161
oker-0.160
Token to
Token ID284
Feature activation+1.89e+00

Pos logit contributions
 Samar+2.059
 amy+1.801
format+1.710
olicy+1.673
oker+1.665
Neg logit contributions
race-2.653
Redd-2.636
Wiki-2.430
ERA-2.352
Stack-2.316
Token low
Token ID1877
Feature activation+3.21e+00

Pos logit contributions
race+1.561
Redd+1.542
Wiki+1.415
ERA+1.369
Stack+1.346
Neg logit contributions
 Samar-1.200
 amy-1.059
olicy-1.030
format-0.997
oker-0.992
Token and
Token ID290
Feature activation+6.83e-01

Pos logit contributions
race+2.083
Redd+2.027
Wiki+1.857
ERA+1.755
Stack+1.739
Neg logit contributions
 Samar-2.567
 amy-2.355
olicy-2.337
mble-2.290
 rul-2.254
Token cook
Token ID4255
Feature activation-4.42e+00

Pos logit contributions
race+0.369
Redd+0.358
Wiki+0.317
ERA+0.302
Stack+0.294
Neg logit contributions
 Samar-0.631
 amy-0.576
olicy-0.563
format-0.552
oker-0.548
Token f
Token ID277
Feature activation-1.20e+01

Pos logit contributions
 Samar+1.956
 amy+1.686
format+1.491
oker+1.460
 Hug+1.454
Neg logit contributions
race-4.453
Redd-4.418
Wiki-4.154
ERA-4.048
Stack-3.999
Tokenrit
Token ID799
Feature activation+1.94e-01

Pos logit contributions
format+5.844
 Samar+5.818
cs+5.545
ults+5.534
bm+5.346
Neg logit contributions
Redd-10.116
race-9.556
Wiki-9.288
ERA-9.286
 Doodle-9.090
Tokenters
Token ID1010
Feature activation-5.27e+00

Pos logit contributions
race+0.163
Redd+0.161
Wiki+0.149
ERA+0.144
Stack+0.142
Neg logit contributions
 Samar-0.123
 amy-0.108
olicy-0.102
format-0.099
oker-0.098
Token on
Token ID319
Feature activation-3.17e+00

Pos logit contributions
 Samar+3.218
 amy+2.805
format+2.652
oker+2.603
 Hug+2.597
Neg logit contributions
Redd-4.375
race-4.336
Wiki-4.048
ERA-3.923
idon-3.850
Token each
Token ID1123
Feature activation+3.17e+00

Pos logit contributions
 Samar+1.521
 amy+1.302
format+1.181
olicy+1.169
oker+1.166
Neg logit contributions
race-3.080
Redd-3.058
Wiki-2.869
ERA-2.780
Stack-2.752
Token side
Token ID1735
Feature activation-1.38e+00

Pos logit contributions
race+2.184
Redd+2.131
Wiki+1.941
ERA+1.879
Stack+1.854
Neg logit contributions
 Samar-2.404
 amy-2.177
olicy-2.156
mble-2.066
oker-2.043
Token b
Token ID275
Feature activation-1.91e+00

Pos logit contributions
race+0.515
Redd+0.510
Wiki+0.466
ERA+0.449
Stack+0.440
Neg logit contributions
 Samar-0.516
 amy-0.464
olicy-0.443
format-0.440
oker-0.436
Tokeniz
Token ID528
Feature activation-3.22e+00

Pos logit contributions
 Samar+1.245
 amy+1.103
olicy+1.042
format+1.039
oker+1.034
Neg logit contributions
race-1.526
Redd-1.525
Wiki-1.403
ERA-1.352
Stack-1.325
Tokenarro
Token ID34852
Feature activation-2.16e+00

Pos logit contributions
 Samar+2.675
 amy+2.432
olicy+2.319
format+2.316
oker+2.315
Neg logit contributions
race-2.004
Redd-1.998
Wiki-1.796
ERA-1.691
Stack-1.675
Token
Token ID39073
Feature activation-3.09e+00

Pos logit contributions
 Samar+1.481
 amy+1.321
olicy+1.235
format+1.232
oker+1.226
Neg logit contributions
race-1.672
Redd-1.658
Wiki-1.534
ERA-1.470
Stack-1.450
Tokenj
Token ID73
Feature activation-4.84e+00

Pos logit contributions
 Samar+2.547
 amy+2.284
format+2.238
olicy+2.211
bm+2.188
Neg logit contributions
Redd-1.945
race-1.903
Wiki-1.724
ERA-1.670
Stack-1.622
Tokenà
Token ID24247
Feature activation-1.20e+01

Pos logit contributions
 Samar+3.141
 amy+2.745
oker+2.688
format+2.650
olicy+2.637
Neg logit contributions
Redd-3.904
race-3.825
Wiki-3.533
Stack-3.386
ERA-3.364
Token v
Token ID410
Feature activation-3.58e+00

Pos logit contributions
 Samar+5.064
 amy+4.395
format+4.362
cs+4.118
oker+3.935
Neg logit contributions
race-11.449
Redd-11.401
idon-10.625
Wiki-10.498
Stack-10.279
Tokenu
Token ID84
Feature activation-1.96e+00

Pos logit contributions
 Samar+2.759
 amy+2.504
format+2.393
olicy+2.387
oker+2.364
Neg logit contributions
Redd-2.441
race-2.440
Wiki-2.209
ERA-2.104
Stack-2.069
Token
Token ID960
Feature activation-1.71e+00

Pos logit contributions
 Samar+1.368
 amy+1.223
olicy+1.151
format+1.147
oker+1.140
Neg logit contributions
race-1.488
Redd-1.476
Wiki-1.361
ERA-1.303
Stack-1.282
Tokenthat
Token ID5562
Feature activation+1.56e+00

Pos logit contributions
 Samar+1.258
 amy+1.133
format+1.071
olicy+1.070
oker+1.061
Neg logit contributions
race-1.219
Redd-1.209
Wiki-1.110
ERA-1.063
Stack-1.045
Token rare
Token ID4071
Feature activation+5.28e+00

Pos logit contributions
race+1.194
Redd+1.170
Wiki+1.078
ERA+1.044
Stack+1.023
Neg logit contributions
 Samar-1.084
 amy-0.963
olicy-0.927
format-0.914
oker-0.904
Token short
Token ID1790
Feature activation+8.44e-01

Pos logit contributions
 Samar+2.766
 amy+2.324
olicy+2.118
format+2.099
 Hug+2.092
Neg logit contributions
Redd-6.157
race-6.043
Wiki-5.752
ERA-5.562
idon-5.476
Token limit
Token ID4179
Feature activation-2.27e+00

Pos logit contributions
race+0.445
Redd+0.431
Wiki+0.384
ERA+0.360
Stack+0.353
Neg logit contributions
 Samar-0.791
 amy-0.726
olicy-0.702
oker-0.693
format-0.693
Token:
Token ID25
Feature activation-1.02e-01

Pos logit contributions
 Samar+1.636
 amy+1.461
format+1.392
olicy+1.384
oker+1.374
Neg logit contributions
race-1.665
Redd-1.651
Wiki-1.509
ERA-1.454
Stack-1.421
Token7
Token ID22
Feature activation-4.80e-01

Pos logit contributions
 Samar+0.077
 amy+0.070
olicy+0.067
format+0.066
oker+0.066
Neg logit contributions
race-0.072
Redd-0.071
Wiki-0.065
ERA-0.062
Stack-0.061
Token R
Token ID371
Feature activation-8.41e+00

Pos logit contributions
 Samar+0.314
 amy+0.278
olicy+0.263
format+0.261
oker+0.257
Neg logit contributions
race-0.386
Redd-0.384
Wiki-0.354
ERA-0.341
Stack-0.335
TokenTS
Token ID4694
Feature activation-1.16e+01

Pos logit contributions
 Samar+2.755
format+2.165
cs+2.125
 amy+2.090
bm+2.043
Neg logit contributions
race-8.958
Redd-8.917
Wiki-8.296
idon-8.231
 waivers-7.967
Token thr
Token ID5636
Feature activation-1.39e+00

Pos logit contributions
 Samar+4.022
 amy+3.393
 Hug+2.818
bm+2.643
format+2.550
Neg logit contributions
Redd-12.446
race-12.104
Wiki-11.708
ERA-11.283
idon-11.247
Token:
Token ID25
Feature activation-5.70e+00

Pos logit contributions
 Samar+1.025
 amy+0.921
olicy+0.876
format+0.870
oker+0.862
Neg logit contributions
race-1.005
Redd-0.995
Wiki-0.911
ERA-0.875
Stack-0.858
Tokenoff
Token ID2364
Feature activation-1.13e+01

Pos logit contributions
 Samar+4.798
 amy+4.371
format+4.302
oker+4.213
bm+4.207
Neg logit contributions
Redd-3.382
race-3.253
Wiki-3.024
ERA-2.840
Stack-2.776
Token Frag
Token ID24229
Feature activation-7.16e+00

Pos logit contributions
 Samar+7.846
 Hug+6.720
 amy+6.697
olicy+6.580
format+6.456
Neg logit contributions
Redd-8.302
race-7.773
Wiki-7.408
ERA-7.057
 waivers-7.054
Tokenment
Token ID434
Feature activation-1.08e+01

Pos logit contributions
 Samar+4.465
 amy+3.871
format+3.847
bm+3.758
olicy+3.695
Neg logit contributions
Redd-5.735
race-5.501
Wiki-5.270
ERA-5.075
idon-5.002
Token ALL
Token ID11096
Feature activation+1.03e-01

Pos logit contributions
 Samar+1.503
 amy+1.321
format+1.249
olicy+1.243
oker+1.231
Neg logit contributions
race-1.832
Redd-1.814
Wiki-1.671
ERA-1.602
Stack-1.586
Token PERSON
Token ID46740
Feature activation-1.46e+00

Pos logit contributions
race+0.075
Redd+0.074
Wiki+0.068
ERA+0.066
Stack+0.064
Neg logit contributions
 Samar-0.075
 amy-0.067
olicy-0.064
format-0.064
oker-0.063
TokenEL
Token ID3698
Feature activation+3.99e+00

Pos logit contributions
 Samar+1.027
 amy+0.915
format+0.868
olicy+0.867
oker+0.853
Neg logit contributions
race-1.100
Redd-1.090
Wiki-0.999
ERA-0.949
Stack-0.943
Token UPDATE
Token ID35717
Feature activation-2.39e+00

Pos logit contributions
race+2.996
Redd+2.990
Wiki+2.786
ERA+2.713
Stack+2.622
Neg logit contributions
 Samar-2.698
 amy-2.438
olicy-2.370
mble-2.298
format-2.279
Token:
Token ID25
Feature activation-6.47e-01

Pos logit contributions
 Samar+1.666
 amy+1.483
format+1.405
oker+1.388
olicy+1.387
Neg logit contributions
race-1.820
Redd-1.801
Wiki-1.642
ERA-1.571
Stack-1.555
Token 05
Token ID8870
Feature activation-1.16e+01

Pos logit contributions
 Samar+0.450
 amy+0.398
olicy+0.377
format+0.375
oker+0.372
Neg logit contributions
race-0.499
Redd-0.491
Wiki-0.451
ERA-0.434
Stack-0.426
Token45
Token ID2231
Feature activation-6.04e+00

Pos logit contributions
 Samar+4.665
format+3.604
bm+3.595
 amy+3.450
cs+3.329
Neg logit contributions
race-11.245
Redd-11.092
Wiki-10.419
idon-10.332
 waivers-10.134
Tokenz
Token ID89
Feature activation+9.78e-01

Pos logit contributions
 Samar+3.903
 amy+3.445
format+3.331
bm+3.312
oker+3.283
Neg logit contributions
Redd-4.724
race-4.654
Wiki-4.348
ERA-4.190
Stack-4.092
Token K
Token ID509
Feature activation-2.15e+00

Pos logit contributions
race+0.774
Redd+0.766
Wiki+0.709
ERA+0.684
Stack+0.671
Neg logit contributions
 Samar-0.648
 amy-0.578
olicy-0.549
format-0.542
oker-0.538
TokenUSH
Token ID27143
Feature activation-5.51e+00

Pos logit contributions
 Samar+1.631
 amy+1.474
olicy+1.406
oker+1.401
format+1.399
Neg logit contributions
race-1.487
Redd-1.475
Wiki-1.332
Stack-1.257
ERA-1.252
TokenAM
Token ID2390
Feature activation-2.27e+00

Pos logit contributions
 Samar+4.445
 amy+3.930
format+3.742
oker+3.713
 Hug+3.711
Neg logit contributions
race-3.569
Redd-3.517
Wiki-3.124
idon-2.928
Stack-2.921
Token young
Token ID1862
Feature activation-1.42e-01

Pos logit contributions
 Samar+2.851
 amy+2.530
 Hug+2.294
format+2.287
olicy+2.281
Neg logit contributions
race-3.361
Redd-3.334
Wiki-3.059
ERA-2.974
Stack-2.921
Token voters
Token ID4446
Feature activation-3.00e+00

Pos logit contributions
 Samar+0.115
 amy+0.104
olicy+0.099
format+0.099
oker+0.098
Neg logit contributions
race-0.092
Redd-0.091
Wiki-0.082
ERA-0.079
Stack-0.077
Token,
Token ID11
Feature activation+1.92e+00

Pos logit contributions
 Samar+2.039
 amy+1.808
format+1.696
olicy+1.678
oker+1.671
Neg logit contributions
Redd-2.344
race-2.343
Wiki-2.149
ERA-2.080
Stack-2.029
Token says
Token ID1139
Feature activation-1.77e+00

Pos logit contributions
race+1.354
Redd+1.340
Wiki+1.227
ERA+1.173
Stack+1.154
Neg logit contributions
 Samar-1.430
 amy-1.289
olicy-1.233
format-1.223
oker-1.215
Token D
Token ID360
Feature activation-1.91e+00

Pos logit contributions
 Samar+1.255
 amy+1.116
olicy+1.041
format+1.035
oker+1.027
Neg logit contributions
race-1.333
Redd-1.326
Wiki-1.219
ERA-1.176
Stack-1.153
Tokenella
Token ID12627
Feature activation-1.15e+01

Pos logit contributions
 Samar+1.001
 amy+0.863
olicy+0.800
format+0.799
oker+0.792
Neg logit contributions
race-1.771
Redd-1.766
Wiki-1.647
ERA-1.589
Stack-1.575
Token Vol
Token ID4709
Feature activation-5.10e+00

Pos logit contributions
 Samar+3.631
 Volvo+2.555
 Hug+2.280
 amy+2.182
format+1.982
Neg logit contributions
Redd-12.599
race-12.528
Wiki-11.955
ERA-11.694
idon-11.595
Tokenpe
Token ID431
Feature activation+2.25e-01

Pos logit contributions
 Samar+3.340
format+2.969
 amy+2.948
oker+2.922
bm+2.897
Neg logit contributions
Redd-3.970
race-3.810
Wiki-3.597
ERA-3.478
Stack-3.413
Token.
Token ID13
Feature activation+4.98e+00

Pos logit contributions
race+0.181
Redd+0.180
Wiki+0.166
ERA+0.161
Stack+0.158
Neg logit contributions
 Samar-0.147
 amy-0.131
olicy-0.123
format-0.122
oker-0.121
Token At
Token ID1629
Feature activation+2.57e+00

Pos logit contributions
race+3.374
Redd+3.364
Wiki+3.117
ERA+2.939
Stack+2.924
Neg logit contributions
 Samar-3.694
 amy-3.457
mble-3.311
olicy-3.303
oker-3.228
Token worse
Token ID4785
Feature activation-1.65e+00

Pos logit contributions
race+2.218
Redd+2.188
Wiki+2.051
ERA+1.982
Stack+1.951
Neg logit contributions
 Samar-1.509
 amy-1.319
olicy-1.242
format-1.239
oker-1.219
Token for
Token ID329
Feature activation+4.28e+00

Pos logit contributions
 Samar+1.143
 amy+1.023
olicy+0.965
format+0.958
oker+0.946
Neg logit contributions
race-1.225
Redd-1.215
Wiki-1.119
ERA-1.073
Stack-1.054
Token public
Token ID1171
Feature activation+2.19e+00

Pos logit contributions
race+3.075
Redd+3.023
Wiki+2.762
ERA+2.711
 waivers+2.678
Neg logit contributions
 Samar-3.064
 amy-2.731
olicy-2.632
format-2.629
oker-2.627
Token monitoring
Token ID9904
Feature activation+1.89e+00

Pos logit contributions
race+1.755
Redd+1.735
Wiki+1.602
ERA+1.554
Stack+1.533
Neg logit contributions
 Samar-1.425
 amy-1.258
olicy-1.195
format-1.194
oker-1.177
Token and
Token ID290
Feature activation+5.06e+00

Pos logit contributions
race+1.330
Redd+1.314
Wiki+1.201
ERA+1.154
Stack+1.133
Neg logit contributions
 Samar-1.422
 amy-1.281
olicy-1.224
format-1.217
oker-1.207
Token accountability
Token ID18241
Feature activation+2.49e+00

Pos logit contributions
race+3.776
Redd+3.669
Wiki+3.407
 waivers+3.306
ERA+3.304
Neg logit contributions
 Samar-3.466
 amy-3.085
oker-2.954
olicy-2.952
format-2.948
Token;
Token ID26
Feature activation-1.14e+01

Pos logit contributions
race+1.791
Redd+1.768
Wiki+1.623
ERA+1.557
Stack+1.530
Neg logit contributions
 Samar-1.823
 amy-1.640
olicy-1.561
format-1.551
oker-1.545
Token and
Token ID290
Feature activation-1.13e+01

Pos logit contributions
 Samar+6.071
 amy+5.484
format+5.153
olicy+5.023
 Volvo+4.840
Neg logit contributions
race-9.562
Redd-9.484
Wiki-8.781
ERA-8.609
Stack-8.316
Token iv
Token ID21628
Feature activation-6.40e+00

Pos logit contributions
 Samar+3.970
 amy+3.446
format+3.099
olicy+2.957
bm+2.837
Neg logit contributions
race-11.663
Redd-11.490
Wiki-10.773
ERA-10.596
Stack-10.246
Token)
Token ID8
Feature activation-5.14e+00

Pos logit contributions
 Samar+3.997
 amy+3.490
format+3.358
bm+3.326
oker+3.291
Neg logit contributions
Redd-5.225
race-5.155
Wiki-4.772
ERA-4.577
Stack-4.507
Token mandate
Token ID14598
Feature activation+6.23e-01

Pos logit contributions
 Samar+3.647
 amy+3.302
format+3.104
olicy+3.089
bm+3.016
Neg logit contributions
Redd-3.809
race-3.751
Wiki-3.464
ERA-3.309
Stack-3.253
Token that
Token ID326
Feature activation+4.43e+00

Pos logit contributions
race+0.446
Redd+0.441
Wiki+0.404
ERA+0.388
Stack+0.381
Neg logit contributions
 Samar-0.461
 amy-0.415
olicy-0.396
format-0.393
oker-0.390
Token for
Token ID329
Feature activation+3.76e+00

Pos logit contributions
race+1.953
Redd+1.912
Wiki+1.746
ERA+1.687
Stack+1.659
Neg logit contributions
 Samar-1.848
 amy-1.675
olicy-1.611
format-1.585
oker-1.554
Token a
Token ID257
Feature activation-8.41e-02

Pos logit contributions
race+2.766
Redd+2.732
Wiki+2.445
ERA+2.369
Stack+2.353
Neg logit contributions
 Samar-2.588
 amy-2.352
olicy-2.300
format-2.271
mble-2.229
Token heavy
Token ID4334
Feature activation-1.30e+00

Pos logit contributions
 Samar+0.056
 amy+0.050
olicy+0.047
format+0.047
oker+0.046
Neg logit contributions
race-0.067
Redd-0.066
Wiki-0.061
ERA-0.059
Stack-0.058
Token,
Token ID11
Feature activation-2.44e+00

Pos logit contributions
 Samar+0.976
 amy+0.875
olicy+0.831
format+0.825
oker+0.821
Neg logit contributions
race-0.922
Redd-0.913
Wiki-0.838
ERA-0.803
Stack-0.786
Token knee
Token ID10329
Feature activation-4.21e+00

Pos logit contributions
 Samar+1.679
 amy+1.489
format+1.386
olicy+1.383
 Hug+1.371
Neg logit contributions
race-1.881
Redd-1.867
Wiki-1.741
ERA-1.668
Stack-1.632
Token-
Token ID12
Feature activation-1.14e+01

Pos logit contributions
 Samar+2.685
 amy+2.349
format+2.233
oker+2.220
olicy+2.208
Neg logit contributions
Redd-3.429
race-3.416
Wiki-3.168
ERA-3.059
Stack-2.991
Tokenhigh
Token ID8929
Feature activation+1.78e-01

Pos logit contributions
 Samar+7.552
format+6.782
 amy+6.647
bm+6.523
oker+6.500
Neg logit contributions
Redd-8.161
race-7.668
ERA-7.292
Wiki-7.276
 waivers-7.096
Token,
Token ID11
Feature activation-2.36e+00

Pos logit contributions
race+0.134
Redd+0.132
Wiki+0.121
ERA+0.117
Stack+0.115
Neg logit contributions
 Samar-0.126
 amy-0.113
olicy-0.107
format-0.107
oker-0.105
Token tackle
Token ID9761
Feature activation+1.07e+00

Pos logit contributions
 Samar+1.664
 amy+1.480
olicy+1.382
format+1.378
oker+1.369
Neg logit contributions
race-1.783
Redd-1.771
Wiki-1.642
ERA-1.572
Stack-1.543
Token on
Token ID319
Feature activation-2.86e+00

Pos logit contributions
race+0.813
Redd+0.797
Wiki+0.728
ERA+0.705
Stack+0.695
Neg logit contributions
 Samar-0.746
 amy-0.675
olicy-0.637
format-0.634
oker-0.623
Token Vladimir
Token ID14840
Feature activation-1.97e+00

Pos logit contributions
 Samar+2.072
 amy+1.835
 Hug+1.726
olicy+1.717
oker+1.710
Neg logit contributions
race-2.114
Redd-2.086
Wiki-1.924
ERA-1.857
Stack-1.816
Tokenangle
Token ID9248
Feature activation+1.21e+00

Pos logit contributions
race+1.407
Redd+1.370
Wiki+1.299
ERA+1.265
Stack+1.259
Neg logit contributions
 Samar-0.575
 amy-0.479
olicy-0.427
oker-0.403
format-0.401
TokenF
Token ID37
Feature activation-1.39e+00

Pos logit contributions
race+1.027
Redd+1.016
Wiki+0.941
ERA+0.911
Stack+0.895
Neg logit contributions
 Samar-0.744
 amy-0.654
olicy-0.616
format-0.614
oker-0.604
Token (
Token ID357
Feature activation+2.26e+00

Pos logit contributions
 Samar+1.223
 amy+1.113
format+1.073
olicy+1.069
oker+1.062
Neg logit contributions
race-0.806
Redd-0.796
Wiki-0.709
ERA-0.673
Stack-0.655
Token0
Token ID15
Feature activation+9.21e-01

Pos logit contributions
race+1.581
Redd+1.563
Wiki+1.430
ERA+1.371
Stack+1.346
Neg logit contributions
 Samar-1.722
 amy-1.554
olicy-1.476
format-1.462
oker-1.456
Token,
Token ID11
Feature activation+3.13e-01

Pos logit contributions
race+0.683
Redd+0.673
Wiki+0.621
ERA+0.594
Stack+0.589
Neg logit contributions
 Samar-0.663
 amy-0.603
olicy-0.576
mble-0.562
oker-0.555
Token($
Token ID16763
Feature activation-1.13e+01

Pos logit contributions
race+0.253
Redd+0.251
Wiki+0.231
ERA+0.224
Stack+0.219
Neg logit contributions
 Samar-0.203
 amy-0.180
olicy-0.170
format-0.170
oker-0.167
Tokeni
Token ID72
Feature activation+4.11e+00

Pos logit contributions
 Samar+5.842
format+5.522
cs+5.510
bm+5.293
 amy+5.034
Neg logit contributions
Redd-9.173
race-8.911
Wiki-8.441
 waivers-8.299
ERA-8.267
Token*
Token ID9
Feature activation-2.56e+00

Pos logit contributions
race+3.108
Redd+3.071
Wiki+2.833
ERA+2.713
Stack+2.692
Neg logit contributions
 Samar-2.893
 amy-2.575
olicy-2.433
oker-2.393
format-2.391
Token$
Token ID3
Feature activation-1.44e+00

Pos logit contributions
 Samar+1.750
 amy+1.561
format+1.523
olicy+1.492
bm+1.476
Neg logit contributions
race-1.938
Redd-1.931
Wiki-1.758
ERA-1.700
idon-1.671
TokenFontSize
Token ID38160
Feature activation-5.23e-01

Pos logit contributions
 Samar+1.054
 amy+0.948
format+0.910
olicy+0.906
oker+0.892
Neg logit contributions
race-1.030
Redd-1.024
Wiki-0.934
ERA-0.899
Stack-0.877
Token*
Token ID9
Feature activation+6.44e-01

Pos logit contributions
 Samar+0.371
 amy+0.332
olicy+0.316
format+0.316
oker+0.311
Neg logit contributions
race-0.390
Redd-0.386
Wiki-0.354
ERA-0.341
Stack-0.333
Token public
Token ID1171
Feature activation+2.19e+00

Pos logit contributions
race+3.075
Redd+3.023
Wiki+2.762
ERA+2.711
 waivers+2.678
Neg logit contributions
 Samar-3.064
 amy-2.731
olicy-2.632
format-2.629
oker-2.627
Token monitoring
Token ID9904
Feature activation+1.89e+00

Pos logit contributions
race+1.755
Redd+1.735
Wiki+1.602
ERA+1.554
Stack+1.533
Neg logit contributions
 Samar-1.425
 amy-1.258
olicy-1.195
format-1.194
oker-1.177
Token and
Token ID290
Feature activation+5.06e+00

Pos logit contributions
race+1.330
Redd+1.314
Wiki+1.201
ERA+1.154
Stack+1.133
Neg logit contributions
 Samar-1.422
 amy-1.281
olicy-1.224
format-1.217
oker-1.207
Token accountability
Token ID18241
Feature activation+2.49e+00

Pos logit contributions
race+3.776
Redd+3.669
Wiki+3.407
 waivers+3.306
ERA+3.304
Neg logit contributions
 Samar-3.466
 amy-3.085
oker-2.954
olicy-2.952
format-2.948
Token;
Token ID26
Feature activation-1.14e+01

Pos logit contributions
race+1.791
Redd+1.768
Wiki+1.623
ERA+1.557
Stack+1.530
Neg logit contributions
 Samar-1.823
 amy-1.640
olicy-1.561
format-1.551
oker-1.545
Token and
Token ID290
Feature activation-1.13e+01

Pos logit contributions
 Samar+6.071
 amy+5.484
format+5.153
olicy+5.023
 Volvo+4.840
Neg logit contributions
race-9.562
Redd-9.484
Wiki-8.781
ERA-8.609
Stack-8.316
Token iv
Token ID21628
Feature activation-6.40e+00

Pos logit contributions
 Samar+3.970
 amy+3.446
format+3.099
olicy+2.957
bm+2.837
Neg logit contributions
race-11.663
Redd-11.490
Wiki-10.773
ERA-10.596
Stack-10.246
Token)
Token ID8
Feature activation-5.14e+00

Pos logit contributions
 Samar+3.997
 amy+3.490
format+3.358
bm+3.326
oker+3.291
Neg logit contributions
Redd-5.225
race-5.155
Wiki-4.772
ERA-4.577
Stack-4.507
Token mandate
Token ID14598
Feature activation+6.23e-01

Pos logit contributions
 Samar+3.647
 amy+3.302
format+3.104
olicy+3.089
bm+3.016
Neg logit contributions
Redd-3.809
race-3.751
Wiki-3.464
ERA-3.309
Stack-3.253
Token that
Token ID326
Feature activation+4.43e+00

Pos logit contributions
race+0.446
Redd+0.441
Wiki+0.404
ERA+0.388
Stack+0.381
Neg logit contributions
 Samar-0.461
 amy-0.415
olicy-0.396
format-0.393
oker-0.390
Token pictures
Token ID5986
Feature activation+6.60e-01

Pos logit contributions
race+3.168
Redd+3.098
Wiki+2.878
 waivers+2.771
ERA+2.767
Neg logit contributions
 Samar-3.152
 amy-2.810
olicy-2.783
format-2.748
oker-2.732
Token7
Token ID22
Feature activation-4.80e-01

Pos logit contributions
 Samar+0.077
 amy+0.070
olicy+0.067
format+0.066
oker+0.066
Neg logit contributions
race-0.072
Redd-0.071
Wiki-0.065
ERA-0.062
Stack-0.061
Token R
Token ID371
Feature activation-8.41e+00

Pos logit contributions
 Samar+0.314
 amy+0.278
olicy+0.263
format+0.261
oker+0.257
Neg logit contributions
race-0.386
Redd-0.384
Wiki-0.354
ERA-0.341
Stack-0.335
TokenTS
Token ID4694
Feature activation-1.16e+01

Pos logit contributions
 Samar+2.755
format+2.165
cs+2.125
 amy+2.090
bm+2.043
Neg logit contributions
race-8.958
Redd-8.917
Wiki-8.296
idon-8.231
 waivers-7.967
Token thr
Token ID5636
Feature activation-1.39e+00

Pos logit contributions
 Samar+4.022
 amy+3.393
 Hug+2.818
bm+2.643
format+2.550
Neg logit contributions
Redd-12.446
race-12.104
Wiki-11.708
ERA-11.283
idon-11.247
Token:
Token ID25
Feature activation-5.70e+00

Pos logit contributions
 Samar+1.025
 amy+0.921
olicy+0.876
format+0.870
oker+0.862
Neg logit contributions
race-1.005
Redd-0.995
Wiki-0.911
ERA-0.875
Stack-0.858
Tokenoff
Token ID2364
Feature activation-1.13e+01

Pos logit contributions
 Samar+4.798
 amy+4.371
format+4.302
oker+4.213
bm+4.207
Neg logit contributions
Redd-3.382
race-3.253
Wiki-3.024
ERA-2.840
Stack-2.776
Token Frag
Token ID24229
Feature activation-7.16e+00

Pos logit contributions
 Samar+7.846
 Hug+6.720
 amy+6.697
olicy+6.580
format+6.456
Neg logit contributions
Redd-8.302
race-7.773
Wiki-7.408
ERA-7.057
 waivers-7.054
Tokenment
Token ID434
Feature activation-1.08e+01

Pos logit contributions
 Samar+4.465
 amy+3.871
format+3.847
bm+3.758
olicy+3.695
Neg logit contributions
Redd-5.735
race-5.501
Wiki-5.270
ERA-5.075
idon-5.002
Token thr
Token ID5636
Feature activation-9.80e-01

Pos logit contributions
 Samar+3.961
 amy+3.218
 Hug+2.758
bm+2.628
format+2.566
Neg logit contributions
Redd-11.398
race-11.200
Wiki-10.893
idon-10.430
ERA-10.410
Token:
Token ID25
Feature activation-7.54e+00

Pos logit contributions
 Samar+0.723
 amy+0.651
olicy+0.619
format+0.614
oker+0.609
Neg logit contributions
race-0.707
Redd-0.700
Wiki-0.641
ERA-0.615
Stack-0.604
Tokenoff
Token ID2364
Feature activation-8.93e+00

Pos logit contributions
 Samar+5.993
format+5.482
 amy+5.412
bm+5.330
oker+5.278
Neg logit contributions
Redd-4.669
race-4.372
Wiki-4.253
ERA-3.930
 waivers-3.863
Token the
Token ID262
Feature activation+4.69e-01

Pos logit contributions
 Samar+2.737
 amy+2.398
format+2.280
oker+2.233
 Hug+2.228
Neg logit contributions
race-3.325
Redd-3.301
Wiki-3.016
ERA-2.945
Stack-2.865
Token input
Token ID5128
Feature activation-3.95e+00

Pos logit contributions
race+0.414
Redd+0.411
Wiki+0.386
ERA+0.371
Stack+0.367
Neg logit contributions
 Samar-0.268
 amy-0.233
olicy-0.222
format-0.213
oker-0.212
Token image
Token ID2939
Feature activation-9.72e+00

Pos logit contributions
 Samar+2.614
 amy+2.313
format+2.169
oker+2.133
olicy+2.128
Neg logit contributions
Redd-3.153
race-3.148
Wiki-2.876
ERA-2.798
Stack-2.731
Token paths
Token ID13532
Feature activation-4.10e+00

Pos logit contributions
 Samar+3.875
 amy+3.216
format+2.789
cs+2.687
 Hug+2.668
Neg logit contributions
race-10.001
Redd-9.780
ERA-9.198
Wiki-9.164
idon-9.091
Token for
Token ID329
Feature activation-2.99e+00

Pos logit contributions
 Samar+2.524
 amy+2.232
format+2.113
bm+2.056
oker+2.051
Neg logit contributions
Redd-3.419
race-3.395
Wiki-3.132
ERA-3.059
Stack-2.981
Token image
Token ID2939
Feature activation-1.13e+01

Pos logit contributions
 Samar+2.003
 amy+1.789
format+1.677
olicy+1.657
oker+1.653
Neg logit contributions
Redd-2.355
race-2.351
Wiki-2.154
ERA-2.083
Stack-2.037
TokenPath
Token ID15235
Feature activation-5.71e+00

Pos logit contributions
 Samar+3.991
format+3.187
bm+2.920
cs+2.909
 Hug+2.905
Neg logit contributions
race-11.331
Redd-10.831
idon-10.694
 waivers-10.249
 Doodle-10.150
Token in
Token ID287
Feature activation-7.16e+00

Pos logit contributions
 Samar+3.454
 amy+3.018
format+2.934
bm+2.818
oker+2.801
Neg logit contributions
Redd-4.741
race-4.688
Wiki-4.323
ERA-4.268
idon-4.122
Token paths
Token ID13532
Feature activation-2.76e+00

Pos logit contributions
 Samar+2.991
 amy+2.532
format+2.279
ults+2.187
oker+2.170
Neg logit contributions
race-7.277
Redd-7.245
Wiki-6.748
ERA-6.738
idon-6.557
Token.
Token ID13
Feature activation-8.62e-01

Pos logit contributions
 Samar+1.790
 amy+1.582
format+1.489
olicy+1.486
oker+1.469
Neg logit contributions
race-2.233
Redd-2.222
Wiki-2.048
ERA-1.982
Stack-1.944
Tokenlist
Token ID4868
Feature activation-3.02e+00

Pos logit contributions
 Samar+0.648
 amy+0.583
olicy+0.555
format+0.544
oker+0.543
Neg logit contributions
race-0.617
Redd-0.605
Wiki-0.556
ERA-0.531
Stack-0.524
Token
Token ID447
Feature activation+1.89e+00

Pos logit contributions
race+1.719
Redd+1.707
Wiki+1.586
ERA+1.535
Stack+1.513
Neg logit contributions
 Samar-1.141
 amy-0.994
olicy-0.934
format-0.921
oker-0.913
Token
Token ID247
Feature activation+1.07e+00

Pos logit contributions
race+1.528
Redd+1.513
Wiki+1.383
ERA+1.347
Stack+1.314
Neg logit contributions
 Samar-1.236
 amy-1.096
olicy-1.030
format-1.020
oker-1.010
Tokens
Token ID82
Feature activation+7.67e+00

Pos logit contributions
race+0.765
Redd+0.743
Wiki+0.678
ERA+0.648
Stack+0.642
Neg logit contributions
 Samar-0.810
 amy-0.734
olicy-0.702
mble-0.690
oker-0.682
Token past
Token ID1613
Feature activation+2.30e+00

Pos logit contributions
race+4.481
Redd+4.268
Wiki+4.042
ERA+3.773
Stack+3.740
Neg logit contributions
 Samar-6.317
olicy-5.754
 amy-5.726
mble-5.648
oker-5.546
Token the
Token ID262
Feature activation+4.94e+00

Pos logit contributions
race+1.579
Redd+1.553
Wiki+1.433
ERA+1.370
Stack+1.352
Neg logit contributions
 Samar-1.757
 amy-1.605
olicy-1.552
mble-1.517
format-1.504
Token edge
Token ID5743
Feature activation+8.28e+00

Pos logit contributions
race+2.703
Redd+2.629
Wiki+2.354
ERA+2.261
Stack+2.247
Neg logit contributions
 Samar-4.421
 amy-4.077
mble-3.897
olicy-3.894
oker-3.826
Token of
Token ID286
Feature activation+3.70e-01

Pos logit contributions
race+4.365
Redd+4.219
Wiki+3.744
Stack+3.606
ERA+3.545
Neg logit contributions
 Samar-7.206
 eleph-7.117
mble-7.112
olicy-6.993
 rul-6.992
Token the
Token ID262
Feature activation-6.32e-01

Pos logit contributions
race+0.265
Redd+0.263
Wiki+0.242
ERA+0.232
Stack+0.229
Neg logit contributions
 Samar-0.272
 amy-0.248
olicy-0.238
format-0.232
mble-0.231
Token Universe
Token ID11950
Feature activation+2.23e+00

Pos logit contributions
 Samar+0.306
 amy+0.259
olicy+0.238
format+0.236
oker+0.232
Neg logit contributions
race-0.616
Redd-0.611
Wiki-0.573
ERA-0.556
Stack-0.549
Token?
Token ID30
Feature activation-2.13e+00

Pos logit contributions
race+1.297
Redd+1.267
Wiki+1.156
ERA+1.093
Stack+1.083
Neg logit contributions
 Samar-1.943
 amy-1.794
olicy-1.731
mble-1.702
format-1.671
Token Y
Token ID575
Feature activation-7.28e+00

Pos logit contributions
 Samar+1.522
 amy+1.359
olicy+1.268
format+1.267
 Hug+1.256
Neg logit contributions
race-1.596
Redd-1.586
Wiki-1.449
ERA-1.404
Stack-1.375
Token
Token ID109
Feature activation-1.29e+00

Pos logit contributions
race+1.701
Redd+1.670
Wiki+1.494
ERA+1.417
Stack+1.384
Neg logit contributions
 Samar-2.559
 amy-2.341
olicy-2.240
format-2.224
oker-2.212
Tokenо
Token ID15166
Feature activation-3.09e-01

Pos logit contributions
 Samar+0.945
 amy+0.849
olicy+0.806
format+0.804
oker+0.795
Neg logit contributions
race-0.931
Redd-0.923
Wiki-0.842
ERA-0.810
Stack-0.796
Tokenе
Token ID16843
Feature activation-2.05e+00

Pos logit contributions
 Samar+0.214
 amy+0.191
olicy+0.181
format+0.180
oker+0.178
Neg logit contributions
race-0.237
Redd-0.235
Wiki-0.216
ERA-0.208
Stack-0.204
Tokenв
Token ID38857
Feature activation+1.71e+00

Pos logit contributions
 Samar+1.401
 amy+1.245
format+1.179
olicy+1.169
oker+1.157
Neg logit contributions
race-1.593
Redd-1.576
Wiki-1.443
ERA-1.395
Stack-1.368
Tokenы
Token ID45035
Feature activation+1.99e-01

Pos logit contributions
race+1.249
Redd+1.228
Wiki+1.139
ERA+1.092
Stack+1.068
Neg logit contributions
 Samar-1.239
 amy-1.114
olicy-1.067
format-1.046
oker-1.040
Token
Token ID141
Feature activation+8.92e+00

Pos logit contributions
race+0.155
Redd+0.154
Wiki+0.142
ERA+0.137
Stack+0.134
Neg logit contributions
 Samar-0.135
 amy-0.120
olicy-0.114
format-0.113
oker-0.112
Token
Token ID227
Feature activation+1.06e-01

Pos logit contributions
race+3.753
Redd+3.516
Wiki+3.270
ERA+3.102
Stack+2.889
Neg logit contributions
 Samar-8.807
 amy-8.238
olicy-7.834
format-7.742
oker-7.655
Token
Token ID12466
Feature activation+4.15e+00

Pos logit contributions
race+0.078
Redd+0.077
Wiki+0.071
ERA+0.068
Stack+0.067
Neg logit contributions
 Samar-0.076
 amy-0.068
olicy-0.065
format-0.064
oker-0.064
Token
Token ID112
Feature activation+2.74e+00

Pos logit contributions
race+2.478
Redd+2.438
Wiki+2.181
ERA+2.076
Stack+2.024
Neg logit contributions
 Samar-3.554
 amy-3.248
olicy-3.104
format-3.075
oker-3.061
Tokenе
Token ID16843
Feature activation-2.33e+00

Pos logit contributions
race+1.912
Redd+1.888
Wiki+1.739
ERA+1.658
Stack+1.624
Neg logit contributions
 Samar-2.064
 amy-1.865
olicy-1.793
format-1.750
oker-1.748
Token
Token ID140
Feature activation+2.86e+00

Pos logit contributions
 Samar+1.593
 amy+1.417
format+1.349
olicy+1.327
oker+1.316
Neg logit contributions
race-1.806
Redd-1.780
Wiki-1.630
ERA-1.580
Stack-1.547
Token and
Token ID290
Feature activation+1.42e+00

Pos logit contributions
race+0.304
Redd+0.300
Wiki+0.276
ERA+0.266
Stack+0.261
Neg logit contributions
 Samar-0.286
 amy-0.256
olicy-0.243
format-0.240
oker-0.238
Token the
Token ID262
Feature activation+1.20e+00

Pos logit contributions
race+1.067
Redd+1.054
Wiki+0.969
ERA+0.932
Stack+0.920
Neg logit contributions
 Samar-0.999
 amy-0.895
olicy-0.861
format-0.852
oker-0.844
Token Cuban
Token ID18147
Feature activation+2.99e+00

Pos logit contributions
race+0.896
Redd+0.883
Wiki+0.810
ERA+0.780
Stack+0.766
Neg logit contributions
 Samar-0.847
 amy-0.759
olicy-0.730
format-0.722
oker-0.715
Token flag
Token ID6056
Feature activation+1.05e+00

Pos logit contributions
race+2.285
Redd+2.253
Wiki+2.087
ERA+2.003
Stack+1.966
Neg logit contributions
 Samar-2.049
 amy-1.836
olicy-1.755
format-1.742
oker-1.714
Token was
Token ID373
Feature activation-1.44e+00

Pos logit contributions
race+0.824
Redd+0.814
Wiki+0.749
ERA+0.725
Stack+0.715
Neg logit contributions
 Samar-0.711
 amy-0.633
olicy-0.602
format-0.594
oker-0.587
Token flying
Token ID7348
Feature activation+8.23e+00

Pos logit contributions
 Samar+0.944
 amy+0.837
format+0.782
olicy+0.782
oker+0.774
Neg logit contributions
race-1.154
Redd-1.143
Wiki-1.059
ERA-1.019
Stack-0.999
Token over
Token ID625
Feature activation+3.57e+00

Pos logit contributions
race+5.569
Redd+5.345
Wiki+4.783
Stack+4.716
ERA+4.690
Neg logit contributions
 Samar-5.967
olicy-5.465
 amy-5.410
oker-5.238
bm-5.167
Token the
Token ID262
Feature activation+2.29e+00

Pos logit contributions
race+2.573
Redd+2.538
Wiki+2.328
ERA+2.239
Stack+2.206
Neg logit contributions
 Samar-2.574
 amy-2.346
olicy-2.235
format-2.222
oker-2.192
Token radio
Token ID5243
Feature activation+3.73e+00

Pos logit contributions
race+1.747
Redd+1.720
Wiki+1.582
ERA+1.521
Stack+1.498
Neg logit contributions
 Samar-1.570
 amy-1.410
olicy-1.356
format-1.339
oker-1.321
Token shack
Token ID32772
Feature activation+3.21e+00

Pos logit contributions
race+2.780
Redd+2.708
Wiki+2.487
ERA+2.442
Stack+2.398
Neg logit contributions
 Samar-2.658
 amy-2.357
olicy-2.292
format-2.213
oker-2.206
Token and
Token ID290
Feature activation-1.50e+00

Pos logit contributions
race+2.387
Redd+2.333
Wiki+2.113
ERA+2.072
Stack+2.037
Neg logit contributions
 Samar-2.304
 amy-2.057
olicy-1.969
format-1.927
oker-1.922
TokenS
Token ID50
Feature activation+2.33e+00

Pos logit contributions
race+3.061
Redd+3.047
Wiki+2.831
ERA+2.688
Stack+2.645
Neg logit contributions
 Samar-4.753
 amy-4.559
mble-4.480
olicy-4.426
 rul-4.392
Token.
Token ID13
Feature activation+7.04e+00

Pos logit contributions
race+1.711
Redd+1.684
Wiki+1.573
ERA+1.533
Stack+1.482
Neg logit contributions
 Samar-1.652
 amy-1.524
olicy-1.457
mble-1.436
 rul-1.426
TokenA
Token ID32
Feature activation+8.07e-01

Pos logit contributions
race+3.794
Redd+3.731
Wiki+3.460
ERA+3.376
Stack+3.171
Neg logit contributions
 Samar-6.182
mble-5.917
 rul-5.877
 amy-5.828
staking-5.810
Token.
Token ID13
Feature activation+7.55e+00

Pos logit contributions
race+0.649
Redd+0.644
Wiki+0.595
ERA+0.573
Stack+0.565
Neg logit contributions
 Samar-0.529
 amy-0.469
olicy-0.442
format-0.439
oker-0.434
TokenI
Token ID40
Feature activation+2.54e+00

Pos logit contributions
race+3.818
Redd+3.688
Wiki+3.492
ERA+3.287
Stack+3.230
Neg logit contributions
 Samar-6.831
 amy-6.378
mble-6.275
olicy-6.244
staking-6.176
Token.
Token ID13
Feature activation+7.96e+00

Pos logit contributions
race+1.868
Redd+1.824
Wiki+1.693
ERA+1.653
Stack+1.598
Neg logit contributions
 Samar-1.825
 amy-1.711
olicy-1.630
 rul-1.598
mble-1.594
TokenR
Token ID49
Feature activation+6.43e-01

Pos logit contributions
race+3.577
Redd+3.516
Wiki+3.051
ERA+2.967
Stack+2.858
Neg logit contributions
 Samar-7.826
 amy-7.604
mble-7.418
staking-7.376
 eleph-7.363
Token.
Token ID764
Feature activation-2.75e+00

Pos logit contributions
race+0.501
Redd+0.495
Wiki+0.457
ERA+0.441
Stack+0.433
Neg logit contributions
 Samar-0.437
 amy-0.388
olicy-0.369
format-0.365
oker-0.362
TokenDes
Token ID5960
Feature activation-9.69e-01

Pos logit contributions
 Samar+1.972
 amy+1.771
format+1.673
olicy+1.662
oker+1.641
Neg logit contributions
race-2.020
Redd-2.002
Wiki-1.824
ERA-1.757
Stack-1.725
Token ren
Token ID8851
Feature activation-7.58e-01

Pos logit contributions
 Samar+0.652
 amy+0.581
olicy+0.548
format+0.545
oker+0.539
Neg logit contributions
race-0.762
Redd-0.756
Wiki-0.697
ERA-0.672
Stack-0.661
Tokense
Token ID325
Feature activation-1.01e+00

Pos logit contributions
 Samar+0.532
 amy+0.476
olicy+0.451
format+0.448
oker+0.444
Neg logit contributions
race-0.574
Redd-0.569
Wiki-0.523
ERA-0.503
Stack-0.494
Token down
Token ID866
Feature activation+3.38e+00

Pos logit contributions
race+0.898
Redd+0.889
Wiki+0.821
ERA+0.790
Stack+0.779
Neg logit contributions
 Samar-0.764
 amy-0.682
olicy-0.652
format-0.645
oker-0.637
Token clues
Token ID20195
Feature activation+1.42e+00

Pos logit contributions
race+2.573
Redd+2.522
Wiki+2.354
Stack+2.227
ERA+2.225
Neg logit contributions
 Samar-2.327
 amy-2.086
olicy-1.977
oker-1.928
mble-1.918
Token
Token ID198
Feature activation+1.21e+00

Pos logit contributions
race+1.047
Redd+1.029
Wiki+0.951
ERA+0.913
Stack+0.899
Neg logit contributions
 Samar-1.020
 amy-0.913
olicy-0.877
format-0.864
oker-0.858
Token
Token ID198
Feature activation-1.51e+00

Pos logit contributions
race+0.891
Redd+0.877
Wiki+0.811
ERA+0.773
Stack+0.766
Neg logit contributions
 Samar-0.884
 amy-0.808
olicy-0.780
mble-0.764
 rul-0.755
Token8
Token ID23
Feature activation+1.36e+00

Pos logit contributions
 Samar+0.830
 amy+0.721
format+0.690
olicy+0.669
bm+0.658
Neg logit contributions
race-1.345
Redd-1.336
Wiki-1.241
ERA-1.212
idon-1.188
Tokend
Token ID67
Feature activation+8.26e+00

Pos logit contributions
race+0.942
Redd+0.929
Wiki+0.851
ERA+0.814
Stack+0.802
Neg logit contributions
 Samar-1.039
 amy-0.936
olicy-0.896
format-0.888
oker-0.883
Token 8
Token ID807
Feature activation+3.84e+00

Pos logit contributions
race+5.429
Redd+5.149
Wiki+4.887
Stack+4.652
ERA+4.604
Neg logit contributions
 Samar-6.088
 amy-5.498
olicy-5.389
format-5.273
mble-5.228
Token.
Token ID13
Feature activation+4.98e-01

Pos logit contributions
race+2.972
Redd+2.926
Wiki+2.707
ERA+2.595
Stack+2.573
Neg logit contributions
 Samar-2.602
 amy-2.300
olicy-2.195
format-2.173
oker-2.156
Token Euro
Token ID1898
Feature activation+1.85e+00

Pos logit contributions
race+0.382
Redd+0.379
Wiki+0.349
ERA+0.336
Stack+0.330
Neg logit contributions
 Samar-0.343
 amy-0.307
olicy-0.291
format-0.288
oker-0.286
Token
Token ID1906
Feature activation-4.17e-01

Pos logit contributions
race+1.393
Redd+1.375
Wiki+1.269
ERA+1.210
Stack+1.190
Neg logit contributions
 Samar-1.295
 amy-1.171
olicy-1.115
format-1.095
oker-1.088
Tokenlist
Token ID4868
Feature activation-3.25e-01

Pos logit contributions
 Samar+0.305
 amy+0.274
olicy+0.260
format+0.258
oker+0.256
Neg logit contributions
race-0.304
Redd-0.301
Wiki-0.276
ERA-0.265
Stack-0.260
Token a
Token ID257
Feature activation+9.14e-01

Pos logit contributions
 Samar+1.248
 amy+1.117
olicy+1.051
format+1.047
oker+1.040
Neg logit contributions
race-1.313
Redd-1.302
Wiki-1.198
ERA-1.149
Stack-1.131
Token 405
Token ID36966
Feature activation-6.75e-01

Pos logit contributions
race+0.689
Redd+0.678
Wiki+0.621
ERA+0.601
Stack+0.591
Neg logit contributions
 Samar-0.642
 amy-0.575
olicy-0.554
format-0.544
oker-0.538
Token
Token ID1906
Feature activation+1.55e-01

Pos logit contributions
 Samar+0.490
 amy+0.440
olicy+0.418
format+0.416
oker+0.413
Neg logit contributions
race-0.492
Redd-0.491
Wiki-0.450
ERA-0.431
Stack-0.423
Token1
Token ID16
Feature activation+5.47e+00

Pos logit contributions
race+0.123
Redd+0.122
Wiki+0.113
ERA+0.109
Stack+0.107
Neg logit contributions
 Samar-0.104
 amy-0.092
olicy-0.087
format-0.086
oker-0.085
Token against
Token ID1028
Feature activation-1.18e+00

Pos logit contributions
race+3.909
Redd+3.741
Wiki+3.423
ERA+3.385
Stack+3.287
Neg logit contributions
 Samar-3.976
 amy-3.606
olicy-3.474
format-3.402
 Hug-3.340
Token shot
Token ID2823
Feature activation+1.98e+00

Pos logit contributions
 Samar+0.868
 amy+0.780
olicy+0.740
format+0.736
oker+0.729
Neg logit contributions
race-0.849
Redd-0.841
Wiki-0.770
ERA-0.739
Stack-0.725
Token.
Token ID13
Feature activation-3.76e+00

Pos logit contributions
race+1.510
Redd+1.491
Wiki+1.371
ERA+1.324
Stack+1.300
Neg logit contributions
 Samar-1.379
 amy-1.234
olicy-1.169
format-1.158
oker-1.147
Token
Token ID198
Feature activation-2.12e+00

Pos logit contributions
 Samar+2.591
 amy+2.246
format+2.152
oker+2.126
 Hug+2.112
Neg logit contributions
race-2.893
Redd-2.861
Wiki-2.621
ERA-2.520
idon-2.488
Token
Token ID198
Feature activation-1.86e+00

Pos logit contributions
 Samar+1.390
 amy+1.222
format+1.163
olicy+1.145
oker+1.141
Neg logit contributions
race-1.692
Redd-1.681
Wiki-1.546
ERA-1.497
Stack-1.467
TokenTo
Token ID2514
Feature activation-5.20e+00

Pos logit contributions
 Samar+1.441
 amy+1.302
format+1.250
olicy+1.237
oker+1.231
Neg logit contributions
race-1.258
Redd-1.238
Wiki-1.125
ERA-1.076
idon-1.055
Token put
Token ID1234
Feature activation-1.52e+00

Pos logit contributions
 Samar+3.765
 amy+3.393
format+3.186
oker+3.165
olicy+3.138
Neg logit contributions
Redd-3.750
race-3.741
Wiki-3.397
ERA-3.268
Stack-3.202
Token,
Token ID11
Feature activation-1.93e+00

Pos logit contributions
race+1.660
Redd+1.634
Wiki+1.492
ERA+1.433
Stack+1.421
Neg logit contributions
 Samar-1.706
 amy-1.534
olicy-1.475
format-1.451
oker-1.445
Token keeps
Token ID7622
Feature activation-6.13e-01

Pos logit contributions
 Samar+1.362
 amy+1.225
format+1.144
olicy+1.140
oker+1.133
Neg logit contributions
race-1.443
Redd-1.440
Wiki-1.323
ERA-1.274
Stack-1.249
Token honey
Token ID12498
Feature activation-4.39e+00

Pos logit contributions
 Samar+0.433
 amy+0.387
olicy+0.366
format+0.364
oker+0.360
Neg logit contributions
race-0.462
Redd-0.458
Wiki-0.421
ERA-0.405
Stack-0.397
Tokenbees
Token ID41712
Feature activation+5.82e-01

Pos logit contributions
 Samar+2.940
 amy+2.658
format+2.498
olicy+2.483
oker+2.434
Neg logit contributions
race-3.392
Redd-3.369
Wiki-3.101
ERA-2.989
idon-2.896
Token,
Token ID11
Feature activation+6.18e-01

Pos logit contributions
race+0.427
Redd+0.423
Wiki+0.388
ERA+0.373
Stack+0.366
Neg logit contributions
 Samar-0.421
 amy-0.378
olicy-0.359
format-0.357
oker-0.354
Token cultiv
Token ID11229
Feature activation+3.87e+00

Pos logit contributions
race+0.448
Redd+0.444
Wiki+0.407
ERA+0.391
Stack+0.384
Neg logit contributions
 Samar-0.453
 amy-0.407
olicy-0.386
format-0.384
oker-0.380
Tokenates
Token ID689
Feature activation-1.84e-01

Pos logit contributions
race+3.100
Redd+3.066
Wiki+2.826
ERA+2.720
Stack+2.681
Neg logit contributions
 Samar-2.524
 amy-2.241
olicy-2.124
format-2.075
mble-2.062
Token mushrooms
Token ID23452
Feature activation-1.84e+00

Pos logit contributions
 Samar+0.125
 amy+0.111
olicy+0.105
format+0.104
oker+0.103
Neg logit contributions
race-0.144
Redd-0.143
Wiki-0.132
ERA-0.127
Stack-0.125
Token,
Token ID11
Feature activation+6.06e-01

Pos logit contributions
 Samar+1.229
 amy+1.103
olicy+1.034
format+1.031
oker+1.017
Neg logit contributions
race-1.433
Redd-1.431
Wiki-1.319
ERA-1.278
Stack-1.235
Token b
Token ID275
Feature activation-8.56e-01

Pos logit contributions
race+0.452
Redd+0.448
Wiki+0.411
ERA+0.396
Stack+0.389
Neg logit contributions
 Samar-0.431
 amy-0.386
olicy-0.367
format-0.364
oker-0.361
Tokenakes
Token ID1124
Feature activation+3.24e-01

Pos logit contributions
 Samar+0.625
 amy+0.561
olicy+0.533
format+0.530
oker+0.527
Neg logit contributions
race-0.622
Redd-0.618
Wiki-0.565
ERA-0.543
Stack-0.532
Token The
Token ID383
Feature activation+4.70e+00

Pos logit contributions
race+2.478
Redd+2.456
Wiki+2.267
ERA+2.187
Stack+2.122
Neg logit contributions
 Samar-2.531
 amy-2.318
olicy-2.239
format-2.198
mble-2.176
Token
Token ID564
Feature activation-1.33e+00

Pos logit contributions
race+3.565
Redd+3.510
Wiki+3.233
ERA+3.125
Stack+3.051
Neg logit contributions
 Samar-3.143
 amy-2.843
olicy-2.764
format-2.721
oker-2.667
Token
Token ID250
Feature activation+2.53e+00

Pos logit contributions
 Samar+1.223
 amy+1.124
olicy+1.082
oker+1.075
format+1.075
Neg logit contributions
race-0.706
Redd-0.699
Wiki-0.624
ERA-0.581
Stack-0.571
Tokenone
Token ID505
Feature activation+3.54e+00

Pos logit contributions
race+1.799
Redd+1.778
Wiki+1.625
ERA+1.563
Stack+1.529
Neg logit contributions
 Samar-1.902
 amy-1.716
olicy-1.630
format-1.603
oker-1.589
Token time
Token ID640
Feature activation+1.34e+00

Pos logit contributions
race+2.436
Redd+2.386
Wiki+2.179
ERA+2.117
Stack+2.050
Neg logit contributions
 Samar-2.663
 amy-2.438
olicy-2.335
format-2.313
oker-2.268
Token
Token ID447
Feature activation+2.51e+00

Pos logit contributions
race+0.968
Redd+0.953
Wiki+0.873
ERA+0.845
Stack+0.824
Neg logit contributions
 Samar-0.974
 amy-0.881
olicy-0.841
format-0.835
oker-0.822
Token
Token ID251
Feature activation+1.95e+00

Pos logit contributions
race+1.377
Redd+1.357
Wiki+1.202
ERA+1.142
Stack+1.109
Neg logit contributions
 Samar-2.286
 amy-2.096
olicy-2.016
format-2.004
oker-1.989
Token that
Token ID326
Feature activation+3.84e+00

Pos logit contributions
race+1.451
Redd+1.434
Wiki+1.317
ERA+1.274
Stack+1.241
Neg logit contributions
 Samar-1.388
 amy-1.247
olicy-1.189
format-1.180
oker-1.166
Token O
Token ID440
Feature activation+1.39e+00

Pos logit contributions
race+2.862
Redd+2.794
Wiki+2.572
ERA+2.513
Stack+2.424
Neg logit contributions
 Samar-2.659
 amy-2.413
olicy-2.317
format-2.290
oker-2.257
Tokenma
Token ID2611
Feature activation+5.67e+00

Pos logit contributions
race+1.056
Redd+1.045
Wiki+0.961
ERA+0.926
Stack+0.908
Neg logit contributions
 Samar-0.973
 amy-0.869
olicy-0.824
format-0.818
oker-0.810
Tokeneda
Token ID18082
Feature activation+4.62e+00

Pos logit contributions
race+3.270
Redd+3.200
ERA+2.889
Wiki+2.874
idon+2.688
Neg logit contributions
 Samar-4.843
 amy-4.471
olicy-4.327
mble-4.245
 Hug-4.215
Token out
Token ID503
Feature activation+3.37e+00

Pos logit contributions
race+2.200
Redd+2.148
Wiki+2.011
ERA+1.903
Stack+1.889
Neg logit contributions
 Samar-2.228
 amy-2.027
olicy-1.936
format-1.918
oker-1.898
Token.
Token ID13
Feature activation-1.48e+00

Pos logit contributions
race+2.319
Redd+2.261
Wiki+2.083
ERA+1.975
Stack+1.961
Neg logit contributions
 Samar-2.566
 amy-2.349
olicy-2.249
format-2.218
oker-2.201
Token I
Token ID314
Feature activation+2.43e+00

Pos logit contributions
 Samar+1.050
 amy+0.931
olicy+0.881
format+0.880
oker+0.870
Neg logit contributions
race-1.115
Redd-1.103
Wiki-1.009
ERA-0.975
Stack-0.955
Token mean
Token ID1612
Feature activation-2.70e+00

Pos logit contributions
race+1.641
Redd+1.572
Wiki+1.445
ERA+1.420
Stack+1.367
Neg logit contributions
 Samar-1.883
 amy-1.691
olicy-1.645
format-1.622
oker-1.594
Token,
Token ID11
Feature activation-2.04e+00

Pos logit contributions
 Samar+1.780
 amy+1.565
olicy+1.457
format+1.446
 Hug+1.444
Neg logit contributions
Redd-2.167
race-2.156
Wiki-1.965
ERA-1.917
Stack-1.877
Token I
Token ID314
Feature activation+1.88e+00

Pos logit contributions
 Samar+1.427
 amy+1.272
olicy+1.190
format+1.186
oker+1.178
Neg logit contributions
race-1.546
Redd-1.545
Wiki-1.404
ERA-1.363
Stack-1.335
Token guess
Token ID4724
Feature activation+3.93e-01

Pos logit contributions
race+1.277
Redd+1.221
Wiki+1.124
ERA+1.098
Stack+1.064
Neg logit contributions
 Samar-1.456
 amy-1.308
olicy-1.281
format-1.261
oker-1.237
Token we
Token ID356
Feature activation-1.67e+00

Pos logit contributions
race+0.292
Redd+0.288
Wiki+0.266
ERA+0.254
Stack+0.251
Neg logit contributions
 Samar-0.280
 amy-0.252
olicy-0.241
format-0.239
oker-0.236
Token
Token ID447
Feature activation+7.07e-01

Pos logit contributions
 Samar+1.223
 amy+1.099
olicy+1.042
format+1.036
oker+1.028
Neg logit contributions
race-1.213
Redd-1.204
Wiki-1.101
ERA-1.058
Stack-1.037
Token
Token ID247
Feature activation+5.91e-02

Pos logit contributions
race+0.546
Redd+0.541
Wiki+0.497
ERA+0.479
Stack+0.472
Neg logit contributions
 Samar-0.488
 amy-0.435
olicy-0.411
format-0.408
oker-0.404
Tokenre
Token ID260
Feature activation+3.43e+00

Pos logit contributions
race+0.043
Redd+0.043
Wiki+0.039
ERA+0.038
Stack+0.037
Neg logit contributions
 Samar-0.043
 amy-0.038
olicy-0.037
format-0.036
oker-0.036
Token and
Token ID290
Feature activation+7.50e-02

Pos logit contributions
race+1.758
Redd+1.721
Wiki+1.577
ERA+1.522
Stack+1.489
Neg logit contributions
 Samar-1.750
 amy-1.575
olicy-1.501
format-1.488
oker-1.468
Token England
Token ID4492
Feature activation-1.30e+00

Pos logit contributions
race+0.056
Redd+0.055
Wiki+0.051
ERA+0.049
Stack+0.048
Neg logit contributions
 Samar-0.053
 amy-0.048
olicy-0.046
format-0.045
oker-0.045
Token on
Token ID319
Feature activation-4.01e+00

Pos logit contributions
 Samar+0.882
 amy+0.781
olicy+0.735
format+0.732
oker+0.729
Neg logit contributions
race-1.010
Redd-1.004
Wiki-0.929
ERA-0.890
Stack-0.878
Token October
Token ID3267
Feature activation+1.02e+00

Pos logit contributions
 Samar+2.807
 amy+2.481
format+2.311
oker+2.279
 Hug+2.279
Neg logit contributions
Redd-3.059
race-3.006
Wiki-2.798
ERA-2.696
Stack-2.633
Token 29
Token ID2808
Feature activation+3.64e+00

Pos logit contributions
race+0.603
Redd+0.595
Wiki+0.539
ERA+0.506
Stack+0.498
Neg logit contributions
 Samar-0.873
 amy-0.813
olicy-0.791
format-0.771
oker-0.769
Token.
Token ID13
Feature activation+1.88e+00

Pos logit contributions
race+2.714
Redd+2.646
Wiki+2.432
ERA+2.364
Stack+2.307
Neg logit contributions
 Samar-2.538
 amy-2.285
olicy-2.172
format-2.145
mble-2.116
Token
Token ID198
Feature activation-1.35e+00

Pos logit contributions
race+1.431
Redd+1.418
Wiki+1.306
ERA+1.257
Stack+1.235
Neg logit contributions
 Samar-1.301
 amy-1.169
olicy-1.105
format-1.097
oker-1.086
Token
Token ID198
Feature activation-7.29e-01

Pos logit contributions
 Samar+0.917
 amy+0.816
olicy+0.772
format+0.766
oker+0.759
Neg logit contributions
race-1.056
Redd-1.047
Wiki-0.965
ERA-0.930
Stack-0.914
TokenRepublic
Token ID15431
Feature activation+1.77e+00

Pos logit contributions
 Samar+0.579
 amy+0.525
olicy+0.502
format+0.501
oker+0.496
Neg logit contributions
race-0.482
Redd-0.475
Wiki-0.431
ERA-0.413
Stack-0.404
Token Of
Token ID3226
Feature activation-1.22e-01

Pos logit contributions
race+1.263
Redd+1.251
Wiki+1.144
ERA+1.098
Stack+1.077
Neg logit contributions
 Samar-1.322
 amy-1.190
olicy-1.132
format-1.125
oker-1.116
Token Ireland
Token ID7517
Feature activation+5.54e-02

Pos logit contributions
 Samar+0.109
 amy+0.100
olicy+0.096
format+0.095
oker+0.095
Neg logit contributions
race-0.069
Redd-0.068
Wiki-0.061
ERA-0.058
Stack-0.057
Token future
Token ID2003
Feature activation-5.05e-02

Pos logit contributions
race+0.030
Redd+0.030
Wiki+0.028
ERA+0.027
Stack+0.026
Neg logit contributions
 Samar-0.029
 amy-0.026
olicy-0.025
format-0.024
oker-0.024
Token tra
Token ID1291
Feature activation+2.07e+00

Pos logit contributions
 Samar+0.035
 amy+0.032
olicy+0.030
format+0.030
oker+0.029
Neg logit contributions
race-0.038
Redd-0.038
Wiki-0.035
ERA-0.034
Stack-0.033
Tokenitors
Token ID6742
Feature activation+2.32e+00

Pos logit contributions
race+1.504
Redd+1.481
Wiki+1.354
ERA+1.301
Stack+1.280
Neg logit contributions
 Samar-1.513
 amy-1.364
olicy-1.291
format-1.274
oker-1.263
Token and
Token ID290
Feature activation+1.13e+00

Pos logit contributions
race+1.732
Redd+1.692
Wiki+1.569
ERA+1.497
Stack+1.486
Neg logit contributions
 Samar-1.641
 amy-1.473
olicy-1.419
format-1.390
oker-1.384
Token supported
Token ID4855
Feature activation+1.06e+00

Pos logit contributions
race+0.867
Redd+0.856
Wiki+0.790
ERA+0.758
Stack+0.748
Neg logit contributions
 Samar-0.780
 amy-0.697
olicy-0.663
format-0.657
oker-0.652
Token locking
Token ID22656
Feature activation-3.27e+00

Pos logit contributions
race+0.791
Redd+0.780
Wiki+0.721
ERA+0.691
Stack+0.680
Neg logit contributions
 Samar-0.746
 amy-0.669
olicy-0.638
format-0.632
oker-0.626
Token them
Token ID606
Feature activation-4.49e+00

Pos logit contributions
 Samar+2.245
 amy+2.000
 Hug+1.848
format+1.835
olicy+1.834
Neg logit contributions
race-2.523
Redd-2.505
Wiki-2.293
ERA-2.240
idon-2.169
Token up
Token ID510
Feature activation-1.96e+00

Pos logit contributions
 Samar+2.757
 amy+2.460
format+2.268
 Hug+2.242
olicy+2.226
Neg logit contributions
race-3.741
Redd-3.729
Wiki-3.442
ERA-3.385
idon-3.274
Token in
Token ID287
Feature activation+1.06e+00

Pos logit contributions
 Samar+1.317
 amy+1.170
olicy+1.099
format+1.094
oker+1.081
Neg logit contributions
race-1.540
Redd-1.533
Wiki-1.406
ERA-1.363
Stack-1.330
Token intern
Token ID1788
Feature activation+2.44e+00

Pos logit contributions
race+0.787
Redd+0.782
Wiki+0.720
ERA+0.687
Stack+0.680
Neg logit contributions
 Samar-0.756
 amy-0.675
olicy-0.647
format-0.641
oker-0.639
Tokenment
Token ID434
Feature activation+1.18e+00

Pos logit contributions
race+1.641
Redd+1.627
Wiki+1.481
ERA+1.400
Stack+1.384
Neg logit contributions
 Samar-1.911
 amy-1.720
olicy-1.660
format-1.639
oker-1.615
Tokenuably
Token ID14632
Feature activation+2.72e+00

Pos logit contributions
race+1.391
Redd+1.372
Wiki+1.249
ERA+1.195
Stack+1.174
Neg logit contributions
 Samar-1.565
 amy-1.415
olicy-1.346
format-1.336
oker-1.327
Token,
Token ID11
Feature activation+2.73e+00

Pos logit contributions
race+2.060
Redd+2.038
Wiki+1.876
ERA+1.805
Stack+1.773
Neg logit contributions
 Samar-1.889
 amy-1.688
olicy-1.610
format-1.594
oker-1.576
Token were
Token ID547
Feature activation+2.52e+00

Pos logit contributions
race+1.854
Redd+1.814
Wiki+1.661
ERA+1.583
Stack+1.552
Neg logit contributions
 Samar-2.099
 amy-1.905
olicy-1.838
format-1.816
oker-1.803
Token 10
Token ID838
Feature activation+3.07e+00

Pos logit contributions
race+1.853
Redd+1.820
Wiki+1.682
ERA+1.611
Stack+1.573
Neg logit contributions
 Samar-1.778
 amy-1.605
olicy-1.544
format-1.532
oker-1.521
Token years
Token ID812
Feature activation+1.30e+00

Pos logit contributions
race+2.316
Redd+2.274
Wiki+2.102
ERA+2.030
Stack+1.994
Neg logit contributions
 Samar-2.117
 amy-1.895
olicy-1.813
format-1.789
oker-1.779
Token,
Token ID11
Feature activation-2.30e+00

Pos logit contributions
race+0.953
Redd+0.934
Wiki+0.860
ERA+0.830
Stack+0.814
Neg logit contributions
 Samar-0.930
 amy-0.835
olicy-0.803
format-0.791
oker-0.783
Token loaded
Token ID9639
Feature activation-3.49e-01

Pos logit contributions
 Samar+1.630
 amy+1.456
olicy+1.369
format+1.368
oker+1.351
Neg logit contributions
race-1.729
Redd-1.722
Wiki-1.578
ERA-1.515
Stack-1.488
Token up
Token ID510
Feature activation-4.43e-01

Pos logit contributions
 Samar+0.242
 amy+0.216
olicy+0.205
format+0.203
oker+0.201
Neg logit contributions
race-0.267
Redd-0.265
Wiki-0.244
ERA-0.235
Stack-0.231
Token with
Token ID351
Feature activation+2.60e+00

Pos logit contributions
 Samar+0.307
 amy+0.274
olicy+0.260
format+0.258
oker+0.256
Neg logit contributions
race-0.340
Redd-0.336
Wiki-0.310
ERA-0.298
Stack-0.293
Token many
Token ID867
Feature activation-4.75e-02

Pos logit contributions
race+1.990
Redd+1.959
Wiki+1.810
ERA+1.746
Stack+1.720
Neg logit contributions
 Samar-1.769
 amy-1.577
olicy-1.514
format-1.495
oker-1.494
Token expectations
Token ID9027
Feature activation-6.50e-01

Pos logit contributions
 Samar+0.032
 amy+0.028
olicy+0.027
format+0.027
oker+0.026
Neg logit contributions
race-0.037
Redd-0.037
Wiki-0.034
ERA-0.033
Stack-0.032
Tokenito
Token ID10094
Feature activation+1.13e+00

Pos logit contributions
 Samar+0.807
 amy+0.734
olicy+0.701
oker+0.697
format+0.696
Neg logit contributions
race-0.658
Redd-0.650
Wiki-0.586
ERA-0.561
Stack-0.550
Token.
Token ID13
Feature activation+1.22e+00

Pos logit contributions
race+0.852
Redd+0.843
Wiki+0.776
ERA+0.746
Stack+0.735
Neg logit contributions
 Samar-0.790
 amy-0.708
olicy-0.676
format-0.669
oker-0.662
Token
Token ID198
Feature activation+4.53e-01

Pos logit contributions
race+0.925
Redd+0.916
Wiki+0.844
ERA+0.811
Stack+0.797
Neg logit contributions
 Samar-0.847
 amy-0.758
olicy-0.719
format-0.712
oker-0.706
Token
Token ID198
Feature activation+1.26e+00

Pos logit contributions
race+0.340
Redd+0.335
Wiki+0.309
ERA+0.296
Stack+0.293
Neg logit contributions
 Samar-0.322
 amy-0.291
olicy-0.280
mble-0.273
oker-0.270
TokenFor
Token ID1890
Feature activation+6.15e-01

Pos logit contributions
race+0.879
Redd+0.872
Wiki+0.797
ERA+0.762
Stack+0.749
Neg logit contributions
 Samar-0.958
 amy-0.865
olicy-0.826
format-0.812
oker-0.808
Token photographic
Token ID35788
Feature activation-1.84e+00

Pos logit contributions
race+0.463
Redd+0.459
Wiki+0.422
ERA+0.406
Stack+0.398
Neg logit contributions
 Samar-0.434
 amy-0.388
olicy-0.369
format-0.366
oker-0.362
Token evidence
Token ID2370
Feature activation-2.95e+00

Pos logit contributions
 Samar+1.213
 amy+1.079
olicy+1.003
format+1.001
oker+0.991
Neg logit contributions
race-1.477
Redd-1.463
Wiki-1.347
ERA-1.307
Stack-1.283
Token of
Token ID286
Feature activation-1.71e+00

Pos logit contributions
 Samar+2.030
 amy+1.801
oker+1.677
format+1.675
olicy+1.659
Neg logit contributions
Redd-2.282
race-2.279
Wiki-2.082
ERA-2.017
Stack-1.974
Token Manson
Token ID41645
Feature activation+8.80e-02

Pos logit contributions
 Samar+1.138
 amy+1.008
olicy+0.936
format+0.934
oker+0.928
Neg logit contributions
race-1.367
Redd-1.359
Wiki-1.250
ERA-1.213
Stack-1.190
Token's
Token ID338
Feature activation+1.17e+00

Pos logit contributions
race+0.064
Redd+0.063
Wiki+0.058
ERA+0.056
Stack+0.055
Neg logit contributions
 Samar-0.064
 amy-0.058
olicy-0.055
format-0.055
oker-0.054
Token chi
Token ID33166
Feature activation-3.43e+00

Pos logit contributions
race+0.895
Redd+0.884
Wiki+0.812
ERA+0.784
Stack+0.770
Neg logit contributions
 Samar-0.798
 amy-0.713
olicy-0.684
format-0.678
oker-0.669
Token.
Token ID13
Feature activation-1.17e+00

Pos logit contributions
 Samar+3.004
 amy+2.620
format+2.443
 Hug+2.410
olicy+2.387
Neg logit contributions
Redd-3.827
race-3.827
Wiki-3.520
ERA-3.414
Stack-3.362
Token
Token ID447
Feature activation-8.79e-01

Pos logit contributions
 Samar+0.797
 amy+0.702
format+0.660
olicy+0.660
oker+0.650
Neg logit contributions
race-0.914
Redd-0.902
Wiki-0.831
ERA-0.804
Stack-0.789
Token
Token ID251
Feature activation+6.29e-01

Pos logit contributions
 Samar+0.798
 amy+0.736
olicy+0.704
format+0.703
oker+0.697
Neg logit contributions
race-0.480
Redd-0.473
Wiki-0.421
ERA-0.396
Stack-0.389
Token
Token ID198
Feature activation-1.29e+00

Pos logit contributions
race+0.486
Redd+0.481
Wiki+0.443
ERA+0.427
Stack+0.420
Neg logit contributions
 Samar-0.431
 amy-0.384
olicy-0.364
format-0.361
oker-0.358
Token
Token ID198
Feature activation-1.33e+00

Pos logit contributions
 Samar+0.877
 amy+0.781
olicy+0.739
format+0.733
oker+0.726
Neg logit contributions
race-1.008
Redd-0.999
Wiki-0.921
ERA-0.887
Stack-0.872
TokenJim
Token ID18050
Feature activation-7.40e-01

Pos logit contributions
 Samar+1.008
 amy+0.908
format+0.872
olicy+0.862
oker+0.857
Neg logit contributions
race-0.918
Redd-0.897
Wiki-0.821
ERA-0.788
Stack-0.773
Token Do
Token ID2141
Feature activation+4.35e-01

Pos logit contributions
 Samar+0.541
 amy+0.481
olicy+0.456
format+0.452
oker+0.452
Neg logit contributions
race-0.540
Redd-0.537
Wiki-0.492
ERA-0.473
Stack-0.464
Tokenoley
Token ID48437
Feature activation+1.64e+00

Pos logit contributions
race+0.279
Redd+0.276
Wiki+0.250
ERA+0.238
Stack+0.233
Neg logit contributions
 Samar-0.356
 amy-0.324
olicy-0.310
format-0.308
oker-0.306
Token,
Token ID11
Feature activation-2.28e-01

Pos logit contributions
race+1.200
Redd+1.185
Wiki+1.085
ERA+1.047
Stack+1.026
Neg logit contributions
 Samar-1.178
 amy-1.057
olicy-1.012
format-1.005
oker-0.992
Token director
Token ID3437
Feature activation+1.49e+00

Pos logit contributions
 Samar+0.168
 amy+0.150
olicy+0.143
format+0.141
oker+0.140
Neg logit contributions
race-0.166
Redd-0.165
Wiki-0.151
ERA-0.145
Stack-0.142
Token of
Token ID286
Feature activation+2.34e+00

Pos logit contributions
race+1.077
Redd+1.068
Wiki+0.978
ERA+0.941
Stack+0.922
Neg logit contributions
 Samar-1.106
 amy-0.995
olicy-0.943
format-0.937
oker-0.929
Token always
Token ID1464
Feature activation+1.36e+00

Pos logit contributions
 Samar+1.210
 amy+1.081
olicy+1.014
format+1.011
oker+0.997
Neg logit contributions
race-1.336
Redd-1.326
Wiki-1.217
ERA-1.173
Stack-1.150
Token had
Token ID550
Feature activation-5.16e-01

Pos logit contributions
race+0.918
Redd+0.903
Wiki+0.826
ERA+0.792
Stack+0.778
Neg logit contributions
 Samar-1.051
 amy-0.953
olicy-0.924
format-0.908
oker-0.904
Token it
Token ID340
Feature activation-1.54e+00

Pos logit contributions
 Samar+0.376
 amy+0.337
olicy+0.321
format+0.318
oker+0.316
Neg logit contributions
race-0.377
Redd-0.373
Wiki-0.342
ERA-0.329
Stack-0.323
Token.
Token ID13
Feature activation-3.55e+00

Pos logit contributions
 Samar+1.015
 amy+0.902
olicy+0.845
format+0.844
oker+0.835
Neg logit contributions
race-1.227
Redd-1.221
Wiki-1.126
ERA-1.084
Stack-1.066
Token
Token ID198
Feature activation+2.31e+00

Pos logit contributions
 Samar+2.489
 amy+2.184
format+2.074
 Hug+2.067
olicy+2.042
Neg logit contributions
race-2.703
Redd-2.672
Wiki-2.434
ERA-2.351
Stack-2.306
Token
Token ID198
Feature activation-7.74e-01

Pos logit contributions
race+1.641
Redd+1.614
Wiki+1.495
ERA+1.421
Stack+1.417
Neg logit contributions
 Samar-1.722
 amy-1.587
olicy-1.547
mble-1.532
 rul-1.523
TokenIn
Token ID818
Feature activation-3.05e+00

Pos logit contributions
 Samar+0.617
 amy+0.560
olicy+0.534
format+0.531
oker+0.527
Neg logit contributions
race-0.511
Redd-0.505
Wiki-0.459
ERA-0.439
Stack-0.429
Token this
Token ID428
Feature activation-3.23e+00

Pos logit contributions
 Samar+2.096
 amy+1.861
format+1.764
olicy+1.747
oker+1.729
Neg logit contributions
race-2.347
Redd-2.333
Wiki-2.145
ERA-2.066
Stack-2.027
Token moment
Token ID2589
Feature activation+1.52e+00

Pos logit contributions
 Samar+2.023
 amy+1.786
format+1.647
olicy+1.638
 Hug+1.621
Neg logit contributions
race-2.695
Redd-2.677
Wiki-2.466
ERA-2.386
Stack-2.353
Token and
Token ID290
Feature activation-3.65e+00

Pos logit contributions
race+1.138
Redd+1.122
Wiki+1.034
ERA+0.994
Stack+0.977
Neg logit contributions
 Samar-1.080
 amy-0.967
olicy-0.925
format-0.915
oker-0.903
Token in
Token ID287
Feature activation-4.26e+00

Pos logit contributions
 Samar+2.384
 amy+2.110
format+1.956
olicy+1.942
 Hug+1.932
Neg logit contributions
Redd-2.932
race-2.919
Wiki-2.692
ERA-2.585
Stack-2.548
Token December
Token ID3426
Feature activation-2.76e+00

Pos logit contributions
 Samar+0.074
 amy+0.067
olicy+0.064
format+0.064
oker+0.063
Neg logit contributions
race-0.061
Redd-0.060
Wiki-0.055
ERA-0.052
Stack-0.051
Token 2009
Token ID3717
Feature activation-1.89e+00

Pos logit contributions
 Samar+1.689
 amy+1.470
format+1.373
olicy+1.358
oker+1.349
Neg logit contributions
race-2.344
Redd-2.334
Wiki-2.150
ERA-2.091
Stack-2.047
Token 10
Token ID838
Feature activation-1.12e+00

Pos logit contributions
 Samar+1.287
 amy+1.144
olicy+1.075
format+1.075
oker+1.060
Neg logit contributions
race-1.467
Redd-1.456
Wiki-1.335
ERA-1.292
Stack-1.266
Token:
Token ID25
Feature activation-1.89e+00

Pos logit contributions
 Samar+0.810
 amy+0.727
format+0.684
olicy+0.683
oker+0.675
Neg logit contributions
race-0.827
Redd-0.823
Wiki-0.749
ERA-0.724
Stack-0.709
Token31
Token ID3132
Feature activation-8.67e+00

Pos logit contributions
 Samar+1.143
 amy+0.999
format+0.936
olicy+0.933
oker+0.921
Neg logit contributions
race-1.617
Redd-1.605
Wiki-1.488
ERA-1.440
Stack-1.417
Token,
Token ID837
Feature activation-8.01e+00

Pos logit contributions
 Samar+5.827
 amy+5.155
 Hug+4.833
format+4.753
 Volvo+4.741
Neg logit contributions
Redd-6.691
race-6.516
Wiki-5.845
ERA-5.839
Stack-5.700
Token e
Token ID304
Feature activation-3.02e+00

Pos logit contributions
 Samar+4.706
 amy+3.988
 Hug+3.720
format+3.697
 Volvo+3.629
Neg logit contributions
Redd-7.080
race-6.868
Wiki-6.216
ERA-6.152
Stack-6.051
Tokenu
Token ID84
Feature activation+2.90e-02

Pos logit contributions
 Samar+2.091
 amy+1.853
format+1.786
olicy+1.775
oker+1.754
Neg logit contributions
race-2.284
Redd-2.265
Wiki-2.086
ERA-2.011
Stack-1.973
Tokeninside
Token ID48787
Feature activation-2.92e+00

Pos logit contributions
race+0.022
Redd+0.022
Wiki+0.020
ERA+0.019
Stack+0.019
Neg logit contributions
 Samar-0.020
 amy-0.018
olicy-0.017
format-0.017
oker-0.017
Token,
Token ID837
Feature activation-2.52e+00

Pos logit contributions
 Samar+2.031
 amy+1.803
format+1.712
olicy+1.710
oker+1.679
Neg logit contributions
race-2.220
Redd-2.213
Wiki-2.013
ERA-1.946
Stack-1.918
Token Sof
Token ID41427
Feature activation-5.83e-01

Pos logit contributions
 Samar+1.795
 amy+1.606
format+1.498
olicy+1.491
 Hug+1.477
Neg logit contributions
race-1.889
Redd-1.883
Wiki-1.708
ERA-1.658
Stack-1.624
Token looks
Token ID3073
Feature activation+4.28e-01

Pos logit contributions
race+2.785
Redd+2.598
Wiki+2.444
Stack+2.399
ERA+2.360
Neg logit contributions
 Samar-3.091
 amy-2.801
olicy-2.626
bm-2.596
format-2.589
Token like
Token ID588
Feature activation+3.26e+00

Pos logit contributions
race+0.329
Redd+0.325
Wiki+0.300
ERA+0.289
Stack+0.286
Neg logit contributions
 Samar-0.294
 amy-0.262
olicy-0.249
format-0.246
oker-0.245
Token immediately
Token ID3393
Feature activation+3.65e+00

Pos logit contributions
race+2.063
Redd+1.981
Wiki+1.814
Stack+1.732
ERA+1.728
Neg logit contributions
 Samar-2.648
 amy-2.410
olicy-2.345
format-2.292
oker-2.289
Token after
Token ID706
Feature activation-4.00e+00

Pos logit contributions
race+2.207
Redd+2.126
Wiki+1.940
ERA+1.826
Stack+1.823
Neg logit contributions
 Samar-3.062
 amy-2.796
olicy-2.717
format-2.665
oker-2.651
Token read
Token ID1100
Feature activation-2.65e+00

Pos logit contributions
 Samar+2.540
 amy+2.221
format+2.087
olicy+2.087
oker+2.066
Neg logit contributions
Redd-3.301
race-3.278
Wiki-3.029
ERA-2.927
idon-2.836
Token()
Token ID3419
Feature activation-7.35e+00

Pos logit contributions
 Samar+1.921
 amy+1.723
format+1.653
olicy+1.633
oker+1.631
Neg logit contributions
Redd-1.932
race-1.911
Wiki-1.749
ERA-1.670
idon-1.628
Token returns
Token ID5860
Feature activation-5.87e+00

Pos logit contributions
 Samar+4.843
 amy+4.233
oker+4.082
format+4.048
olicy+3.961
Neg logit contributions
Redd-5.794
race-5.615
Wiki-5.257
ERA-5.059
idon-4.887
Token to
Token ID284
Feature activation+2.89e+00

Pos logit contributions
 Samar+3.877
 amy+3.412
format+3.228
oker+3.203
olicy+3.178
Neg logit contributions
Redd-4.665
race-4.531
Wiki-4.255
ERA-4.033
idon-3.895
Token a
Token ID257
Feature activation+7.39e-01

Pos logit contributions
race+2.111
Redd+2.050
Wiki+1.892
Stack+1.826
ERA+1.819
Neg logit contributions
 Samar-2.080
 amy-1.876
olicy-1.802
format-1.767
oker-1.753
Token pop
Token ID1461
Feature activation+3.42e-01

Pos logit contributions
race+0.575
Redd+0.564
Wiki+0.521
ERA+0.503
Stack+0.501
Neg logit contributions
 Samar-0.502
 amy-0.449
olicy-0.428
format-0.420
oker-0.416
Token/
Token ID14
Feature activation-4.23e+00

Pos logit contributions
race+0.255
Redd+0.253
Wiki+0.232
ERA+0.224
Stack+0.220
Neg logit contributions
 Samar-0.243
 amy-0.217
olicy-0.206
format-0.205
oker-0.203
Token so
Token ID523
Feature activation-1.71e+00

Pos logit contributions
 Samar+2.723
 amy+2.422
olicy+2.250
format+2.243
oker+2.235
Neg logit contributions
Redd-3.316
race-3.314
Wiki-3.050
ERA-2.927
Stack-2.887
Token sad
Token ID6507
Feature activation-2.78e+00

Pos logit contributions
 Samar+1.107
 amy+0.979
olicy+0.923
format+0.912
oker+0.911
Neg logit contributions
race-1.383
Redd-1.377
Wiki-1.276
ERA-1.228
Stack-1.211
Token to
Token ID284
Feature activation-3.94e+00

Pos logit contributions
 Samar+1.874
 amy+1.673
format+1.569
olicy+1.562
oker+1.558
Neg logit contributions
race-2.175
Redd-2.163
Wiki-1.996
ERA-1.916
Stack-1.891
Token watch
Token ID2342
Feature activation-2.98e+00

Pos logit contributions
 Samar+2.949
 amy+2.671
format+2.503
olicy+2.483
 Hug+2.476
Neg logit contributions
race-2.781
Redd-2.780
Wiki-2.526
ERA-2.435
Stack-2.384
Token.
Token ID13
Feature activation-1.22e+00

Pos logit contributions
 Samar+1.973
 amy+1.758
format+1.635
olicy+1.633
oker+1.627
Neg logit contributions
race-2.363
Redd-2.356
Wiki-2.166
ERA-2.081
Stack-2.049
Token James
Token ID3700
Feature activation-8.14e+00

Pos logit contributions
 Samar+0.860
 amy+0.765
olicy+0.724
format+0.721
oker+0.714
Neg logit contributions
race-0.917
Redd-0.907
Wiki-0.832
ERA-0.800
Stack-0.787
Token Comey
Token ID12388
Feature activation-4.19e+00

Pos logit contributions
 Samar+6.131
 amy+5.510
oker+5.206
 Hug+5.157
olicy+5.141
Neg logit contributions
race-5.530
Redd-5.514
Wiki-4.903
idon-4.829
ERA-4.791
Token
Token ID447
Feature activation+5.26e-03

Pos logit contributions
 Samar+2.885
 amy+2.582
format+2.392
olicy+2.391
oker+2.390
Neg logit contributions
Redd-3.217
race-3.206
Wiki-2.920
ERA-2.792
Stack-2.761
Token
Token ID247
Feature activation-3.32e+00

Pos logit contributions
race+0.004
Redd+0.004
Wiki+0.004
ERA+0.004
Stack+0.004
Neg logit contributions
 Samar-0.004
 amy-0.003
olicy-0.003
format-0.003
oker-0.003
Tokens
Token ID82
Feature activation-2.78e+00

Pos logit contributions
 Samar+2.326
 amy+2.084
format+1.961
olicy+1.957
oker+1.947
Neg logit contributions
Redd-2.492
race-2.490
Wiki-2.273
ERA-2.178
Stack-2.150
Token leadership
Token ID5531
Feature activation-1.31e+00

Pos logit contributions
 Samar+1.967
 amy+1.768
olicy+1.658
format+1.652
oker+1.646
Neg logit contributions
Redd-2.075
race-2.070
Wiki-1.894
ERA-1.817
Stack-1.786
Token,
Token ID11
Feature activation-3.67e+00

Pos logit contributions
 Samar+1.623
 amy+1.429
format+1.353
olicy+1.337
oker+1.337
Neg logit contributions
race-1.972
Redd-1.969
Wiki-1.807
ERA-1.714
Stack-1.708
Token IT
Token ID7283
Feature activation-2.88e+00

Pos logit contributions
 Samar+2.351
 amy+2.068
format+1.962
oker+1.921
 Volvo+1.919
Neg logit contributions
Redd-2.979
race-2.971
Wiki-2.726
Stack-2.599
ERA-2.580
Token GO
Token ID10351
Feature activation-7.66e+00

Pos logit contributions
 Samar+1.801
 amy+1.572
format+1.476
olicy+1.454
oker+1.452
Neg logit contributions
race-2.401
Redd-2.384
Wiki-2.192
Stack-2.086
ERA-2.083
TokenES
Token ID1546
Feature activation-2.98e+00

Pos logit contributions
 Samar+4.117
 amy+3.343
format+3.234
 Volvo+3.204
cs+3.185
Neg logit contributions
race-7.039
Redd-6.773
Wiki-6.307
Stack-6.062
idon-6.022
Token ST
Token ID3563
Feature activation-3.46e+00

Pos logit contributions
 Samar+1.855
 amy+1.617
format+1.523
olicy+1.504
oker+1.488
Neg logit contributions
race-2.498
Redd-2.473
Wiki-2.286
ERA-2.190
Stack-2.173
TokenRA
Token ID3861
Feature activation-7.89e+00

Pos logit contributions
 Samar+2.554
 amy+2.269
oker+2.175
olicy+2.170
format+2.154
Neg logit contributions
race-2.472
Redd-2.450
Wiki-2.235
ERA-2.107
idon-2.106
TokenIGHT
Token ID9947
Feature activation-3.51e-01

Pos logit contributions
 Samar+5.553
 amy+4.886
format+4.838
bm+4.805
 Hug+4.774
Neg logit contributions
race-5.509
Redd-5.342
Wiki-4.887
idon-4.654
ERA-4.604
Token TO
Token ID5390
Feature activation-3.97e-01

Pos logit contributions
 Samar+0.238
 amy+0.212
olicy+0.200
format+0.199
oker+0.197
Neg logit contributions
race-0.274
Redd-0.272
Wiki-0.250
ERA-0.240
Stack-0.237
Token THE
Token ID3336
Feature activation-3.20e+00

Pos logit contributions
 Samar+0.267
 amy+0.237
olicy+0.224
format+0.223
oker+0.221
Neg logit contributions
race-0.312
Redd-0.309
Wiki-0.285
ERA-0.275
Stack-0.271
Token GEAR
Token ID43790
Feature activation-2.81e-01

Pos logit contributions
 Samar+2.069
 amy+1.823
format+1.732
oker+1.707
olicy+1.703
Neg logit contributions
race-2.578
Redd-2.565
Wiki-2.361
ERA-2.247
Stack-2.235
Token S
Token ID311
Feature activation-2.35e+00

Pos logit contributions
 Samar+0.201
 amy+0.180
olicy+0.171
format+0.170
oker+0.168
Neg logit contributions
race-0.209
Redd-0.207
Wiki-0.190
ERA-0.182
Stack-0.179
Tokenz
Token ID89
Feature activation-1.59e+00

Pos logit contributions
 Samar+0.306
 amy+0.275
olicy+0.261
format+0.257
oker+0.255
Neg logit contributions
race-0.305
Redd-0.302
Wiki-0.277
ERA-0.266
Stack-0.262
Token1
Token ID16
Feature activation-1.49e+00

Pos logit contributions
 Samar+0.998
 amy+0.891
format+0.856
olicy+0.843
oker+0.827
Neg logit contributions
Redd-1.286
race-1.282
Wiki-1.171
ERA-1.145
 waivers-1.115
Token.
Token ID13
Feature activation+2.30e+00

Pos logit contributions
 Samar+1.007
 amy+0.902
format+0.856
olicy+0.853
oker+0.837
Neg logit contributions
race-1.147
Redd-1.145
Wiki-1.048
ERA-1.016
Stack-0.989
TokenHeight
Token ID23106
Feature activation-2.64e+00

Pos logit contributions
race+1.111
Redd+1.103
Wiki+0.963
ERA+0.898
Stack+0.889
Neg logit contributions
 Samar-2.259
 amy-2.086
olicy-2.008
oker-1.983
format-1.969
Token),
Token ID828
Feature activation+1.04e+00

Pos logit contributions
 Samar+1.762
 amy+1.571
format+1.525
olicy+1.494
oker+1.470
Neg logit contributions
race-2.034
Redd-2.010
Wiki-1.855
ERA-1.803
idon-1.754
Token$
Token ID3
Feature activation-7.43e+00

Pos logit contributions
race+0.789
Redd+0.781
Wiki+0.718
ERA+0.691
Stack+0.678
Neg logit contributions
 Samar-0.731
 amy-0.653
olicy-0.619
format-0.616
oker-0.609
TokenSR
Token ID12562
Feature activation-4.05e+00

Pos logit contributions
 Samar+4.913
format+4.491
bm+4.356
cs+4.341
 amy+4.328
Neg logit contributions
Redd-5.406
race-5.372
Wiki-4.903
 waivers-4.774
idon-4.743
Token.
Token ID13
Feature activation-1.51e-01

Pos logit contributions
 Samar+2.384
 amy+2.116
format+2.050
olicy+2.046
bm+1.984
Neg logit contributions
Redd-3.387
race-3.368
Wiki-3.095
ERA-3.023
 waivers-2.962
TokenWidth
Token ID30916
Feature activation-3.23e+00

Pos logit contributions
 Samar+0.158
 amy+0.146
format+0.142
olicy+0.142
oker+0.140
Neg logit contributions
race-0.062
Redd-0.061
Wiki-0.052
ERA-0.048
Stack-0.046
Token,
Token ID11
Feature activation-1.64e+00

Pos logit contributions
 Samar+2.079
 amy+1.855
format+1.784
olicy+1.764
oker+1.730
Neg logit contributions
race-2.555
Redd-2.546
Wiki-2.353
ERA-2.280
Stack-2.217
Token$
Token ID3
Feature activation-7.09e+00

Pos logit contributions
 Samar+1.108
 amy+0.982
format+0.945
olicy+0.937
oker+0.920
Neg logit contributions
race-1.273
Redd-1.262
Wiki-1.157
ERA-1.114
idon-1.100