TOP ACTIVATIONS
MAX = 16.643

performance , Hein rich H imm ler declared the unit to
6 7 8 9 10 11 12 13 14 15 16
16 17 18 19 20 21 22 23 24 SELECT REG
2011 Matt Le Bl anc 2012 Jon Cry er
6 7 8 9 10 11 12 13 14 15 --
duck - b illed Hyp ac ros aurus st eb inger
6 7 8 9 10 11 12 13 14 15 16
from Islamic State in Iraq and Syria forces . He said
of Merc ia , Mor car former Earl of North umb
on the conflicts in Iraq and Afghanistan . Ass
conduct seismic testing in B aff in Bay and Davis Strait
with a lady , should pay almost exclusive attention to her
16 17 18 19 20 21 22 23 24 25 26
R upp e Award Nom ination Pack et and submit all
dug in . P es kin calls it Division
on the convention J umb ot ron for donations . It
comedian / author Sara Ben inc asa ), was strangely judged
list . From Edward Has b rou ck 's transcript of
. WHO spokesman Gregory Hart l said it had been expecting
norm ally protective lact ob ac illi ( S

MIN ACTIVATIONS
MIN = -15.052

4 Comments Print This Post P CC Natural
speech . ACLU of Oregon (@ AC LU _ OR
gather with ACLU of Oregon (@ AC LU _ OR
his head ). ( Example : Because of a
in Allen Robinson , Allen H urn s and Julius Thomas
Irvine , California . Hide Caption 9 of 15 Photos :
] General Ge or gy Zh uk ov speaking
States . ACLU of Oregon (@ AC LU _ OR
scientists at the American Museum of Natural History ( which houses
Ren aud Lav o ie (@ ren lav o iet
# == " E " || # == " A "
P 217 Gibson of United Aut os ports in fifth .
the NFL Commissioner as judge , jury , execution or ,
know choose ) ( Example : Your + 1
from the National Ocean ic and Atmospheric Administration s
but ACLU of Oregon (@ AC LU _ OR
line . ACLU of Oregon (@ AC LU _ OR
) ( Example : Your + 1 shield keeps
Ad ept Eye of Doom vs Moment ous Fall
on Ubuntu above and lo and behold , the problem isn

INTERVAL 8.719 - 16.643
CONTAINS 0.106%

" Some may qu ibble that this doesn 't
O & A - J imm ys 3 way Dream -
(@ m f lynn JR )
Marshall intercepted a pass over the middle by Siem ian .
a bit safer than they otherwise might be . So let

INTERVAL 0.795 - 8.719
CONTAINS 36.434%

as long as it wasn 't the el che apo method
of the building , seeing the handheld bomb go off in
of satellite - based temperature estimates to reach their conclusion .
Color lines ) September 26 , 2016 G otte
him because they belonged to the Atlanta Hawks .

INTERVAL -7.128 - 0.795
CONTAINS 63.084%

Collection , replacing Confederate General Edmund Kirby Smith .[ 7 ]
that culminated in this month 's release of version 57 ,
apolog etic intent , the late English scholar Martin L ings
, a 1982 V itus 9 79 road bike , made
Damian Allow ay committed to UCLA on Friday via Ble acher

INTERVAL -15.052 - -7.128
CONTAINS 0.376%

press conference , EV O Japan 's organizers stated that the
by : NO VA . TV On a dramatic
): [ email protected ] Luke , I know
of Virginia . Del . Todd Gilbert ( R
, and the application of established theory to the results .
Token performance
Token ID2854
Feature activation-4.06e+00

Pos logit contributions
��+1.935
ット+1.419
Line+1.418
uez+1.393
 Younger+1.374
Neg logit contributions
iaries-1.953
acas-1.898
OTOS-1.815
ruary-1.786
mitt-1.754
Token,
Token ID11
Feature activation+7.73e-01

Pos logit contributions
��+3.101
Line+2.328
ット+2.303
uez+2.274
 Younger+2.267
Neg logit contributions
iaries-2.968
acas-2.855
OTOS-2.734
ruary-2.680
aceae-2.652
Token Hein
Token ID26431
Feature activation-1.37e+00

Pos logit contributions
iaries+0.520
acas+0.506
OTOS+0.482
ruary+0.473
mitt+0.466
Neg logit contributions
��-0.650
ット-0.489
Line-0.484
�醒-0.482
uez-0.476
Tokenrich
Token ID7527
Feature activation+2.45e+00

Pos logit contributions
��+1.238
ット+0.969
Line+0.963
uez+0.951
�醒+0.950
Neg logit contributions
iaries-0.820
acas-0.795
OTOS-0.744
ruary-0.732
 "$:/-0.710
Token H
Token ID367
Feature activation-8.93e-01

Pos logit contributions
iaries+1.658
acas+1.617
OTOS+1.543
ruary+1.511
mitt+1.502
Neg logit contributions
��-2.051
ット-1.535
�醒-1.518
Line-1.513
uez-1.492
Tokenimm
Token ID8608
Feature activation+1.66e+01

Pos logit contributions
��+0.929
Line+0.753
uez+0.749
ット+0.748
�醒+0.738
Neg logit contributions
iaries-0.408
acas-0.390
OTOS-0.365
ruary-0.355
 "$:/-0.342
Tokenler
Token ID1754
Feature activation+2.53e+00

Pos logit contributions
mitt+5.977
acas+5.336
dom+5.012
dan+4.909
sm+4.856
Neg logit contributions
��-18.090
-14.946
���-14.906
�醒-14.143
ーテ-13.949
Token declared
Token ID6875
Feature activation-6.31e-01

Pos logit contributions
iaries+1.555
acas+1.506
OTOS+1.418
ruary+1.412
mitt+1.397
Neg logit contributions
��-2.272
ット-1.735
�醒-1.735
Line-1.712
���-1.687
Token the
Token ID262
Feature activation-1.39e+00

Pos logit contributions
��+0.504
ット+0.377
Line+0.374
uez+0.369
�醒+0.365
Neg logit contributions
iaries-0.446
acas-0.437
OTOS-0.417
ruary-0.407
mitt-0.402
Token unit
Token ID4326
Feature activation-6.64e-01

Pos logit contributions
��+1.090
ット+0.814
Line+0.810
uez+0.796
�醒+0.790
Neg logit contributions
iaries-0.993
acas-0.972
OTOS-0.924
ruary-0.905
mitt-0.893
Token to
Token ID284
Feature activation+1.99e+00

Pos logit contributions
��+0.545
ット+0.410
Line+0.407
uez+0.400
�醒+0.399
Neg logit contributions
iaries-0.456
acas-0.446
OTOS-0.424
ruary-0.416
mitt-0.410
Token 6
Token ID718
Feature activation+2.64e+00

Pos logit contributions
iaries+2.047
acas+1.992
OTOS+1.926
ruary+1.837
 "$:/+1.807
Neg logit contributions
��-2.985
�醒-2.288
ット-2.286
Line-2.278
-2.268
Token 7
Token ID767
Feature activation+7.52e+00

Pos logit contributions
iaries+1.658
acas+1.637
OTOS+1.551
ruary+1.509
mitt+1.487
Neg logit contributions
��-2.310
ット-1.748
Line-1.736
uez-1.722
�醒-1.717
Token 8
Token ID807
Feature activation+4.78e+00

Pos logit contributions
iaries+3.959
acas+3.839
OTOS+3.721
 "$:/+3.482
ruary+3.451
Neg logit contributions
��-7.060
ット-5.567
���-5.539
�醒-5.517
uez-5.494
Token 9
Token ID860
Feature activation+7.49e+00

Pos logit contributions
iaries+3.188
acas+3.106
OTOS+3.002
ruary+2.883
 "$:/+2.871
Neg logit contributions
��-3.979
ット-3.034
uez-2.981
ーテ-2.893
Line-2.887
Token 10
Token ID838
Feature activation+6.81e+00

Pos logit contributions
iaries+4.317
acas+4.122
OTOS+4.077
 "$:/+3.856
aceae+3.798
Neg logit contributions
��-6.575
uez-5.198
ット-5.131
-5.127
���-5.095
Token 11
Token ID1367
Feature activation+1.65e+01

Pos logit contributions
iaries+3.364
acas+3.296
OTOS+3.139
ruary+2.945
mitt+2.940
Neg logit contributions
��-6.632
ット-5.270
uez-5.238
ーテ-5.197
Line-5.182
Token 12
Token ID1105
Feature activation+6.85e+00

Pos logit contributions
iaries+6.286
OTOS+6.107
acas+5.927
 "$:/+5.676
 PROT+5.598
Neg logit contributions
��-15.338
uez-12.629
���-12.621
-12.499
igham-12.434
Token 13
Token ID1511
Feature activation+6.02e+00

Pos logit contributions
iaries+3.505
acas+3.431
OTOS+3.287
 "$:/+3.128
imore+3.080
Neg logit contributions
��-6.591
uez-5.181
ット-5.162
-5.106
���-5.050
Token 14
Token ID1478
Feature activation+7.81e+00

Pos logit contributions
iaries+3.518
acas+3.353
OTOS+3.268
 "$:/+3.129
mitt+3.032
Neg logit contributions
��-5.413
-4.251
ット-4.233
uez-4.206
�醒-4.184
Token 15
Token ID1315
Feature activation+7.14e+00

Pos logit contributions
iaries+4.170
acas+3.956
OTOS+3.758
 "$:/+3.617
ruary+3.559
Neg logit contributions
��-7.278
uez-5.937
ット-5.876
-5.805
���-5.751
Token 16
Token ID1467
Feature activation+5.69e+00

Pos logit contributions
iaries+3.827
acas+3.666
OTOS+3.508
ruary+3.353
 "$:/+3.275
Neg logit contributions
��-6.669
ット-5.302
���-5.283
�醒-5.278
-5.255
Token 16
Token ID1467
Feature activation+5.69e+00

Pos logit contributions
iaries+3.827
acas+3.666
OTOS+3.508
ruary+3.353
 "$:/+3.275
Neg logit contributions
��-6.669
ット-5.302
���-5.283
�醒-5.278
-5.255
Token 17
Token ID1596
Feature activation+7.48e+00

Pos logit contributions
iaries+3.244
acas+3.166
OTOS+3.011
ruary+2.920
 "$:/+2.853
Neg logit contributions
��-5.281
ット-4.080
uez-4.049
���-4.003
Line-3.998
Token 18
Token ID1248
Feature activation+3.94e+00

Pos logit contributions
iaries+4.012
acas+3.878
OTOS+3.771
obin+3.470
 "$:/+3.451
Neg logit contributions
��-6.965
�醒-5.564
���-5.489
uez-5.473
Line-5.461
Token 19
Token ID678
Feature activation+1.22e+01

Pos logit contributions
iaries+2.473
acas+2.421
OTOS+2.310
ruary+2.217
 "$:/+2.186
Neg logit contributions
��-3.438
ット-2.629
uez-2.606
�醒-2.588
Line-2.588
Token 20
Token ID1160
Feature activation+9.50e+00

Pos logit contributions
iaries+6.111
acas+5.953
OTOS+5.878
obin+5.539
 "$:/+5.385
Neg logit contributions
��-10.958
uez-8.716
-8.710
���-8.700
�醒-8.658
Token 21
Token ID2310
Feature activation+1.63e+01

Pos logit contributions
iaries+5.562
acas+5.510
OTOS+5.338
ruary+5.039
obin+5.016
Neg logit contributions
��-8.131
uez-6.169
ット-6.169
-6.133
ーテ-6.115
Token 22
Token ID2534
Feature activation+1.02e+01

Pos logit contributions
iaries+7.776
acas+7.331
OTOS+7.092
ruary+6.851
 PROT+6.772
Neg logit contributions
��-13.804
igham-11.317
uez-11.283
���-11.225
ーテ-11.117
Token 23
Token ID2242
Feature activation+9.85e+00

Pos logit contributions
iaries+5.588
acas+5.313
OTOS+5.090
ruary+4.911
 "$:/+4.882
Neg logit contributions
��-9.113
uez-7.180
ット-7.180
ーテ-7.045
���-6.999
Token 24
Token ID1987
Feature activation+5.94e+00

Pos logit contributions
iaries+5.227
OTOS+4.801
acas+4.784
 "$:/+4.533
ruary+4.371
Neg logit contributions
��-8.973
-7.282
ット-7.229
uez-7.161
���-7.128
Token SELECT
Token ID33493
Feature activation-3.18e+00

Pos logit contributions
iaries+3.673
acas+3.519
OTOS+3.356
ruary+3.277
 "$:/+3.238
Neg logit contributions
��-5.166
ット-4.024
uez-4.007
-3.932
ーテ-3.925
Token REG
Token ID23337
Feature activation-2.16e+00

Pos logit contributions
��+2.789
Line+2.150
ット+2.143
�醒+2.118
uez+2.117
Neg logit contributions
iaries-1.969
acas-1.905
ruary-1.787
OTOS-1.786
mitt-1.759
Token
Token ID198
Feature activation+6.50e+00

Pos logit contributions
iaries+2.112
acas+2.066
OTOS+1.971
mitt+1.918
flush+1.899
Neg logit contributions
��-3.765
���-3.017
�醒-2.931
ット-2.841
ーテ-2.837
Token2011
Token ID9804
Feature activation-3.89e+00

Pos logit contributions
iaries+3.510
acas+3.493
mitt+3.318
OTOS+3.238
dan+3.208
Neg logit contributions
��-6.140
�醒-4.812
ーテ-4.755
ット-4.755
���-4.722
Token Matt
Token ID4705
Feature activation+2.17e+00

Pos logit contributions
��+3.034
Line+2.328
ット+2.284
 Younger+2.269
 Lines+2.254
Neg logit contributions
iaries-2.780
acas-2.676
OTOS-2.529
ruary-2.499
imore-2.462
Token Le
Token ID1004
Feature activation+1.71e+00

Pos logit contributions
iaries+1.483
acas+1.444
OTOS+1.375
ruary+1.351
mitt+1.332
Neg logit contributions
��-1.800
ット-1.348
Line-1.333
�醒-1.325
uez-1.312
TokenBl
Token ID3629
Feature activation+7.80e+00

Pos logit contributions
iaries+0.924
acas+0.894
OTOS+0.839
ruary+0.819
mitt+0.808
Neg logit contributions
��-1.661
ット-1.308
�醒-1.290
Line-1.289
uez-1.275
Tokenanc
Token ID1192
Feature activation+1.63e+01

Pos logit contributions
acas+3.853
iaries+3.664
imore+3.324
aceae+3.279
obin+3.257
Neg logit contributions
��-8.399
���-6.838
ーテ-6.755
�醒-6.636
ット-6.502
Token 2012
Token ID2321
Feature activation+1.70e+00

Pos logit contributions
acas+7.135
iaries+7.050
imore+6.911
mitt+6.815
ruary+6.696
Neg logit contributions
��-14.801
ーテ-11.982
ット-11.617
�醒-11.581
��-11.446
Token Jon
Token ID5966
Feature activation-6.79e+00

Pos logit contributions
iaries+1.139
acas+1.113
OTOS+1.064
ruary+1.040
mitt+1.031
Neg logit contributions
��-1.423
ット-1.068
�醒-1.055
Line-1.048
���-1.039
Token Cry
Token ID8152
Feature activation+4.37e-01

Pos logit contributions
��+4.866
Line+3.673
 Younger+3.661
 Lines+3.643
uez+3.576
Neg logit contributions
iaries-5.121
acas-4.899
ruary-4.699
OTOS-4.686
flush-4.656
Tokener
Token ID263
Feature activation+3.44e+00

Pos logit contributions
iaries+0.313
acas+0.305
OTOS+0.293
ruary+0.286
mitt+0.280
Neg logit contributions
��-0.347
Line-0.256
ット-0.252
�醒-0.252
uez-0.252
Token
Token ID198
Feature activation+2.66e+00

Pos logit contributions
iaries+2.052
acas+2.007
OTOS+1.904
ruary+1.854
mitt+1.842
Neg logit contributions
��-3.125
ット-2.402
Line-2.368
�醒-2.360
uez-2.341
Token 6
Token ID718
Feature activation+2.59e+00

Pos logit contributions
iaries+1.302
acas+1.265
OTOS+1.208
ruary+1.176
mitt+1.156
Neg logit contributions
��-1.763
ット-1.340
�醒-1.333
Line-1.332
���-1.312
Token 7
Token ID767
Feature activation+7.73e+00

Pos logit contributions
iaries+1.663
acas+1.635
OTOS+1.543
ruary+1.514
mitt+1.490
Neg logit contributions
��-2.238
ット-1.691
Line-1.677
�醒-1.660
uez-1.655
Token 8
Token ID807
Feature activation+4.32e+00

Pos logit contributions
iaries+4.242
acas+4.136
OTOS+3.882
ruary+3.755
 "$:/+3.750
Neg logit contributions
��-7.091
�醒-5.538
ット-5.538
���-5.480
Line-5.473
Token 9
Token ID860
Feature activation+7.62e+00

Pos logit contributions
iaries+2.967
acas+2.893
OTOS+2.763
ruary+2.702
 "$:/+2.663
Neg logit contributions
��-3.523
ット-2.663
uez-2.599
Line-2.545
�醒-2.544
Token 10
Token ID838
Feature activation+5.74e+00

Pos logit contributions
iaries+4.559
acas+4.368
OTOS+4.213
 "$:/+4.054
mitt+4.022
Neg logit contributions
��-6.579
uez-5.097
ット-5.091
�醒-5.054
���-5.029
Token 11
Token ID1367
Feature activation+1.54e+01

Pos logit contributions
iaries+3.017
acas+2.946
OTOS+2.776
ruary+2.680
mitt+2.642
Neg logit contributions
��-5.467
ット-4.314
uez-4.283
�醒-4.234
Line-4.226
Token 12
Token ID1105
Feature activation+6.29e+00

Pos logit contributions
iaries+7.065
acas+6.675
OTOS+6.614
 "$:/+6.339
mitt+6.261
Neg logit contributions
��-13.563
uez-11.031
���-10.860
-10.816
ット-10.810
Token 13
Token ID1511
Feature activation+4.33e+00

Pos logit contributions
iaries+3.386
acas+3.292
OTOS+3.135
 "$:/+3.007
ruary+2.976
Neg logit contributions
��-5.944
ット-4.633
uez-4.615
-4.556
���-4.500
Token 14
Token ID1478
Feature activation+7.02e+00

Pos logit contributions
iaries+2.648
acas+2.528
OTOS+2.450
 "$:/+2.342
ruary+2.311
Neg logit contributions
��-3.848
ット-2.988
�醒-2.962
-2.952
uez-2.944
Token 15
Token ID1315
Feature activation+5.88e+00

Pos logit contributions
iaries+3.999
acas+3.781
OTOS+3.567
 "$:/+3.491
ruary+3.441
Neg logit contributions
��-6.381
uez-5.112
ット-5.064
-4.992
���-4.921
Token --
Token ID1377
Feature activation-2.80e+00

Pos logit contributions
iaries+3.222
acas+3.053
OTOS+2.910
ruary+2.835
flush+2.742
Neg logit contributions
��-5.511
ット-4.347
�醒-4.332
uez-4.314
Line-4.303
Token duck
Token ID22045
Feature activation-1.55e+00

Pos logit contributions
iaries+1.308
acas+1.275
OTOS+1.216
ruary+1.198
mitt+1.185
Neg logit contributions
��-1.448
ット-1.067
�醒-1.049
Line-1.049
���-1.034
Token-
Token ID12
Feature activation+6.27e+00

Pos logit contributions
��+1.253
ット+0.934
Line+0.929
�醒+0.916
uez+0.911
Neg logit contributions
iaries-1.087
acas-1.055
OTOS-1.013
ruary-0.989
mitt-0.973
Tokenb
Token ID65
Feature activation+2.88e+00

Pos logit contributions
iaries+3.791
acas+3.716
mitt+3.515
flush+3.469
OTOS+3.385
Neg logit contributions
��-5.653
���-4.317
�醒-4.286
ット-4.277
ーテ-4.230
Tokenilled
Token ID2967
Feature activation+1.32e+00

Pos logit contributions
iaries+1.801
acas+1.759
ruary+1.641
OTOS+1.636
mitt+1.606
Neg logit contributions
��-2.556
ット-1.966
�醒-1.933
���-1.933
Line-1.931
Token Hyp
Token ID21209
Feature activation+1.14e+00

Pos logit contributions
iaries+1.001
acas+0.978
OTOS+0.933
ruary+0.916
mitt+0.911
Neg logit contributions
��-0.991
ット-0.717
�醒-0.707
Line-0.703
���-0.696
Tokenac
Token ID330
Feature activation+1.49e+01

Pos logit contributions
iaries+0.750
acas+0.729
OTOS+0.692
ruary+0.679
mitt+0.671
Neg logit contributions
��-0.971
ット-0.736
Line-0.728
�醒-0.724
uez-0.716
Tokenros
Token ID4951
Feature activation-4.47e-01

Pos logit contributions
acas+9.670
iaries+9.614
aceae+9.235
dan+9.077
imore+9.018
Neg logit contributions
��-11.094
ット-8.531
ーテ-8.235
���-8.212
�醒-8.171
Tokenaurus
Token ID22302
Feature activation+1.07e+00

Pos logit contributions
��+0.377
ット+0.285
Line+0.282
�醒+0.279
uez+0.278
Neg logit contributions
iaries-0.300
acas-0.290
OTOS-0.277
ruary-0.272
mitt-0.266
Token st
Token ID336
Feature activation-1.95e+00

Pos logit contributions
iaries+0.769
acas+0.750
OTOS+0.716
ruary+0.702
mitt+0.695
Neg logit contributions
��-0.850
ット-0.628
Line-0.620
�醒-0.618
uez-0.610
Tokeneb
Token ID1765
Feature activation-3.76e-01

Pos logit contributions
��+1.697
Line+1.307
ット+1.305
uez+1.303
�醒+1.277
Neg logit contributions
iaries-1.200
acas-1.172
OTOS-1.118
ruary-1.094
 "$:/-1.076
Tokeninger
Token ID3889
Feature activation+2.99e+00

Pos logit contributions
��+0.320
ット+0.242
Line+0.240
�醒+0.238
uez+0.237
Neg logit contributions
iaries-0.248
acas-0.240
OTOS-0.230
ruary-0.224
mitt-0.221
Token 6
Token ID718
Feature activation+2.25e+00

Pos logit contributions
iaries+1.702
acas+1.663
OTOS+1.604
ruary+1.534
 "$:/+1.503
Neg logit contributions
��-2.401
ット-1.821
�醒-1.815
Line-1.811
uez-1.799
Token 7
Token ID767
Feature activation+5.15e+00

Pos logit contributions
iaries+1.437
acas+1.419
OTOS+1.349
ruary+1.310
mitt+1.286
Neg logit contributions
��-1.948
ット-1.467
Line-1.454
�醒-1.446
uez-1.444
Token 8
Token ID807
Feature activation+3.33e+00

Pos logit contributions
iaries+3.052
acas+3.009
OTOS+2.874
ruary+2.733
 "$:/+2.705
Neg logit contributions
��-4.656
ット-3.561
�醒-3.526
uez-3.518
���-3.508
Token 9
Token ID860
Feature activation+5.60e+00

Pos logit contributions
iaries+2.307
acas+2.264
OTOS+2.175
ruary+2.101
 "$:/+2.076
Neg logit contributions
��-2.720
ット-2.028
uez-1.987
�醒-1.963
Line-1.958
Token 10
Token ID838
Feature activation+5.03e+00

Pos logit contributions
iaries+3.426
acas+3.346
OTOS+3.249
 "$:/+3.073
ruary+3.036
Neg logit contributions
��-4.888
uez-3.753
ット-3.735
�醒-3.707
-3.704
Token 11
Token ID1367
Feature activation+1.46e+01

Pos logit contributions
iaries+2.621
acas+2.580
OTOS+2.455
ruary+2.315
mitt+2.281
Neg logit contributions
��-4.869
ット-3.810
uez-3.790
�醒-3.754
Line-3.753
Token 12
Token ID1105
Feature activation+5.92e+00

Pos logit contributions
iaries+5.676
OTOS+5.609
acas+5.499
 "$:/+5.035
 PROT+4.946
Neg logit contributions
��-14.110
uez-11.401
���-11.335
-11.313
igham-11.216
Token 13
Token ID1511
Feature activation+4.28e+00

Pos logit contributions
iaries+3.120
acas+3.062
OTOS+2.942
 "$:/+2.755
imore+2.728
Neg logit contributions
��-5.695
uez-4.426
ット-4.425
-4.369
ーテ-4.321
Token 14
Token ID1478
Feature activation+6.02e+00

Pos logit contributions
iaries+2.592
acas+2.506
OTOS+2.420
 "$:/+2.295
ruary+2.263
Neg logit contributions
��-3.834
ット-2.949
-2.934
uez-2.924
�醒-2.920
Token 15
Token ID1315
Feature activation+5.23e+00

Pos logit contributions
iaries+3.337
acas+3.225
OTOS+3.065
 "$:/+2.908
ruary+2.901
Neg logit contributions
��-5.611
uez-4.469
ット-4.439
-4.385
���-4.337
Token 16
Token ID1467
Feature activation+4.11e+00

Pos logit contributions
iaries+2.830
acas+2.731
OTOS+2.621
ruary+2.495
 "$:/+2.423
Neg logit contributions
��-4.965
ット-3.898
uez-3.874
�醒-3.871
-3.859
Token from
Token ID422
Feature activation+1.08e+00

Pos logit contributions
iaries+1.031
acas+1.002
OTOS+0.951
ruary+0.934
mitt+0.920
Neg logit contributions
��-1.421
ット-1.079
Line-1.071
�醒-1.069
���-1.057
Token Islamic
Token ID5533
Feature activation+4.93e+00

Pos logit contributions
iaries+0.757
acas+0.738
OTOS+0.704
ruary+0.691
mitt+0.684
Neg logit contributions
��-0.879
ット-0.654
Line-0.646
�醒-0.643
uez-0.635
Token State
Token ID1812
Feature activation-1.44e+00

Pos logit contributions
iaries+2.233
acas+2.139
OTOS+1.960
mitt+1.916
flush+1.863
Neg logit contributions
��-5.169
�醒-4.172
ット-4.128
-4.094
Line-4.084
Token in
Token ID287
Feature activation+7.31e-01

Pos logit contributions
��+1.238
ット+0.948
Line+0.944
uez+0.921
�醒+0.921
Neg logit contributions
iaries-0.922
acas-0.904
OTOS-0.851
ruary-0.840
imore-0.820
Token Iraq
Token ID3908
Feature activation-1.28e+00

Pos logit contributions
iaries+0.458
acas+0.446
OTOS+0.421
ruary+0.414
mitt+0.409
Neg logit contributions
��-0.649
ット-0.494
Line-0.490
�醒-0.489
uez-0.485
Token and
Token ID290
Feature activation+1.46e+01

Pos logit contributions
��+1.042
ット+0.782
Line+0.775
�醒+0.763
uez+0.755
Neg logit contributions
iaries-0.897
acas-0.873
OTOS-0.830
ruary-0.813
mitt-0.806
Token Syria
Token ID4392
Feature activation+1.87e+00

Pos logit contributions
iaries+7.080
acas+6.306
ashtra+6.170
ruary+6.022
OTOS+5.985
Neg logit contributions
��-13.303
���-10.691
-10.684
�醒-10.639
Line-10.134
Token forces
Token ID3386
Feature activation-1.28e+00

Pos logit contributions
iaries+1.161
acas+1.126
OTOS+1.070
ruary+1.047
mitt+1.031
Neg logit contributions
��-1.669
ット-1.280
Line-1.267
�醒-1.265
uez-1.251
Token.
Token ID13
Feature activation-2.55e+00

Pos logit contributions
��+1.053
ット+0.798
Line+0.790
�醒+0.776
uez+0.773
Neg logit contributions
iaries-0.870
acas-0.843
OTOS-0.806
ruary-0.786
mitt-0.772
Token He
Token ID679
Feature activation-2.07e+00

Pos logit contributions
��+2.017
ット+1.523
Line+1.522
 Younger+1.498
 Lines+1.489
Neg logit contributions
iaries-1.824
acas-1.764
OTOS-1.670
ruary-1.641
imore-1.624
Token said
Token ID531
Feature activation-2.02e+00

Pos logit contributions
��+1.718
ット+1.299
Line+1.295
uez+1.287
�醒+1.268
Neg logit contributions
iaries-1.377
acas-1.344
OTOS-1.305
ruary-1.253
mitt-1.236
Token of
Token ID286
Feature activation-9.48e-01

Pos logit contributions
��+2.538
ット+1.866
Line+1.859
 Younger+1.854
+1.838
Neg logit contributions
iaries-2.137
acas-2.057
OTOS-1.981
ruary-1.921
mitt-1.896
Token Merc
Token ID12185
Feature activation+2.16e+00

Pos logit contributions
��+0.753
ット+0.556
Line+0.553
�醒+0.543
uez+0.543
Neg logit contributions
iaries-0.680
acas-0.660
OTOS-0.635
ruary-0.620
mitt-0.612
Tokenia
Token ID544
Feature activation+1.52e-01

Pos logit contributions
iaries+1.456
acas+1.426
OTOS+1.343
ruary+1.337
mitt+1.310
Neg logit contributions
��-1.815
ット-1.362
Line-1.341
�醒-1.339
���-1.323
Token,
Token ID11
Feature activation+5.47e-01

Pos logit contributions
iaries+0.099
acas+0.096
OTOS+0.092
ruary+0.089
mitt+0.088
Neg logit contributions
��-0.132
ット-0.100
Line-0.099
�醒-0.098
uez-0.098
Token Mor
Token ID3461
Feature activation-1.24e+00

Pos logit contributions
iaries+0.378
acas+0.368
OTOS+0.351
ruary+0.345
mitt+0.340
Neg logit contributions
��-0.449
ット-0.335
Line-0.332
�醒-0.330
uez-0.326
Tokencar
Token ID7718
Feature activation+1.39e+01

Pos logit contributions
��+0.993
ット+0.748
Line+0.743
uez+0.736
�醒+0.730
Neg logit contributions
iaries-0.873
acas-0.836
OTOS-0.817
ruary-0.789
 "$:/-0.775
Token former
Token ID1966
Feature activation+3.29e+00

Pos logit contributions
acas+9.203
iaries+8.539
imore+8.512
dan+8.512
ón+8.504
Neg logit contributions
��-10.222
ット-7.851
���-7.604
�醒-7.563
ーテ-7.434
Token Earl
Token ID21647
Feature activation+9.00e-01

Pos logit contributions
iaries+2.204
acas+2.144
OTOS+2.023
ruary+1.991
mitt+1.967
Neg logit contributions
��-2.749
ット-2.078
�醒-2.061
Line-2.040
���-2.028
Token of
Token ID286
Feature activation+4.91e-01

Pos logit contributions
iaries+0.576
acas+0.560
OTOS+0.532
ruary+0.522
mitt+0.514
Neg logit contributions
��-0.783
ット-0.597
Line-0.592
�醒-0.588
uez-0.583
Token North
Token ID2258
Feature activation+5.77e-01

Pos logit contributions
iaries+0.348
acas+0.339
OTOS+0.324
ruary+0.318
mitt+0.314
Neg logit contributions
��-0.395
ット-0.293
Line-0.290
�醒-0.288
uez-0.285
Tokenumb
Token ID2178
Feature activation+2.47e+00

Pos logit contributions
iaries+0.389
acas+0.378
OTOS+0.362
ruary+0.353
mitt+0.348
Neg logit contributions
��-0.483
ット-0.363
Line-0.360
�醒-0.357
uez-0.355
Token on
Token ID319
Feature activation+1.79e-01

Pos logit contributions
iaries+0.370
acas+0.360
OTOS+0.343
ruary+0.336
mitt+0.331
Neg logit contributions
��-0.459
ット-0.346
Line-0.342
�醒-0.340
uez-0.337
Token the
Token ID262
Feature activation-1.41e+00

Pos logit contributions
iaries+0.124
acas+0.121
OTOS+0.115
ruary+0.113
mitt+0.111
Neg logit contributions
��-0.147
ット-0.110
Line-0.109
�醒-0.108
uez-0.107
Token conflicts
Token ID12333
Feature activation+5.11e-01

Pos logit contributions
��+1.109
ット+0.824
Line+0.820
uez+0.810
�醒+0.800
Neg logit contributions
iaries-1.015
acas-0.984
OTOS-0.946
ruary-0.930
mitt-0.913
Token in
Token ID287
Feature activation+3.95e+00

Pos logit contributions
iaries+0.344
acas+0.335
OTOS+0.319
ruary+0.313
mitt+0.309
Neg logit contributions
��-0.429
ット-0.323
Line-0.320
�醒-0.318
uez-0.315
Token Iraq
Token ID3908
Feature activation-9.19e-01

Pos logit contributions
acas+2.260
iaries+2.230
OTOS+2.039
ruary+2.020
mitt+1.991
Neg logit contributions
��-3.756
�醒-2.885
ット-2.860
���-2.852
ーテ-2.800
Token and
Token ID290
Feature activation+1.39e+01

Pos logit contributions
��+0.750
ット+0.559
Line+0.556
�醒+0.549
uez+0.546
Neg logit contributions
iaries-0.641
acas-0.620
OTOS-0.593
ruary-0.579
mitt-0.573
Token Afghanistan
Token ID8037
Feature activation-4.08e-01

Pos logit contributions
acas+5.268
iaries+5.099
OTOS+4.846
ruary+4.759
mitt+4.582
Neg logit contributions
��-14.499
�醒-12.086
���-12.011
-11.352
 partName-11.065
Token.
Token ID13
Feature activation-1.65e+00

Pos logit contributions
��+0.351
ット+0.267
Line+0.266
�醒+0.262
uez+0.261
Neg logit contributions
iaries-0.266
acas-0.257
OTOS-0.245
ruary-0.239
mitt-0.236
Token
Token ID198
Feature activation+2.17e+00

Pos logit contributions
��+1.397
ット+1.064
Line+1.060
�醒+1.049
uez+1.045
Neg logit contributions
iaries-1.081
acas-1.046
OTOS-1.000
ruary-0.979
mitt-0.973
Token
Token ID198
Feature activation-3.42e+00

Pos logit contributions
iaries+1.282
acas+1.251
OTOS+1.188
ruary+1.152
mitt+1.150
Neg logit contributions
��-2.027
���-1.565
�醒-1.553
ット-1.541
ーテ-1.511
TokenAss
Token ID8021
Feature activation+2.38e+00

Pos logit contributions
��+2.705
Line+2.151
ット+2.062
uez+2.048
+1.999
Neg logit contributions
iaries-2.380
acas-2.290
ruary-2.167
OTOS-2.152
imore-2.110
Token conduct
Token ID3189
Feature activation-6.29e-01

Pos logit contributions
iaries+0.072
acas+0.070
OTOS+0.067
ruary+0.066
mitt+0.065
Neg logit contributions
��-0.070
ット-0.050
Line-0.050
�醒-0.049
uez-0.049
Token seismic
Token ID37463
Feature activation-8.67e-01

Pos logit contributions
��+0.495
ット+0.364
Line+0.361
�醒+0.358
uez+0.355
Neg logit contributions
iaries-0.456
acas-0.445
OTOS-0.425
ruary-0.418
mitt-0.412
Token testing
Token ID4856
Feature activation+3.90e-01

Pos logit contributions
��+0.560
ット+0.382
Line+0.379
�醒+0.372
uez+0.370
Neg logit contributions
iaries-0.749
acas-0.733
OTOS-0.705
ruary-0.696
mitt-0.687
Token in
Token ID287
Feature activation+1.36e-02

Pos logit contributions
iaries+0.260
acas+0.253
OTOS+0.240
ruary+0.236
mitt+0.233
Neg logit contributions
��-0.330
ット-0.249
Line-0.246
�醒-0.245
uez-0.243
Token B
Token ID347
Feature activation-3.33e+00

Pos logit contributions
iaries+0.009
acas+0.009
OTOS+0.008
ruary+0.008
mitt+0.008
Neg logit contributions
��-0.012
ット-0.009
�醒-0.009
Line-0.009
���-0.009
Tokenaff
Token ID2001
Feature activation+1.37e+01

Pos logit contributions
��+2.731
Line+2.113
uez+2.105
ット+2.078
�醒+2.010
Neg logit contributions
iaries-2.208
acas-2.133
OTOS-2.049
 "$:/-2.002
ruary-1.998
Tokenin
Token ID259
Feature activation+8.73e+00

Pos logit contributions
acas+8.205
iaries+7.827
mitt+7.595
imore+7.355
dom+7.309
Neg logit contributions
��-12.615
-9.419
���-9.409
�醒-9.157
ーテ-9.071
Token Bay
Token ID4696
Feature activation-9.34e-02

Pos logit contributions
iaries+5.119
acas+5.065
OTOS+4.705
ruary+4.674
mitt+4.661
Neg logit contributions
��-7.753
���-6.089
�醒-5.960
-5.856
ット-5.827
Token and
Token ID290
Feature activation+1.32e+00

Pos logit contributions
��+0.078
ット+0.058
Line+0.058
�醒+0.057
uez+0.057
Neg logit contributions
iaries-0.064
acas-0.062
OTOS-0.059
ruary-0.058
mitt-0.057
Token Davis
Token ID7802
Feature activation+3.68e+00

Pos logit contributions
iaries+0.904
acas+0.880
OTOS+0.836
ruary+0.822
mitt+0.814
Neg logit contributions
��-1.086
ット-0.813
�醒-0.805
Line-0.799
���-0.790
Token Strait
Token ID41407
Feature activation-4.96e+00

Pos logit contributions
iaries+2.556
acas+2.496
OTOS+2.364
ruary+2.320
mitt+2.314
Neg logit contributions
��-3.013
ット-2.236
�醒-2.214
Line-2.192
���-2.190
Token with
Token ID351
Feature activation-1.58e+00

Pos logit contributions
��+1.244
Line+0.928
ット+0.921
 Younger+0.904
uez+0.899
Neg logit contributions
iaries-1.111
acas-1.081
OTOS-1.032
ruary-1.014
mitt-0.992
Token a
Token ID257
Feature activation-6.00e+00

Pos logit contributions
��+1.219
Line+0.893
ット+0.891
uez+0.870
�醒+0.867
Neg logit contributions
iaries-1.174
acas-1.137
OTOS-1.086
ruary-1.079
mitt-1.052
Token lady
Token ID10846
Feature activation+1.27e-01

Pos logit contributions
��+4.079
Line+2.940
 Younger+2.903
ット+2.831
uez+2.793
Neg logit contributions
iaries-4.821
acas-4.726
OTOS-4.559
ruary-4.464
imore-4.374
Token,
Token ID11
Feature activation+2.00e+00

Pos logit contributions
iaries+0.087
acas+0.084
OTOS+0.081
ruary+0.079
mitt+0.078
Neg logit contributions
��-0.105
ット-0.079
Line-0.078
�醒-0.078
uez-0.077
Token should
Token ID815
Feature activation-8.69e-01

Pos logit contributions
iaries+1.484
acas+1.448
OTOS+1.384
ruary+1.359
mitt+1.350
Neg logit contributions
��-1.553
ット-1.130
�醒-1.122
Line-1.108
���-1.097
Token pay
Token ID1414
Feature activation+1.36e+01

Pos logit contributions
��+0.687
Line+0.511
ット+0.510
uez+0.499
�醒+0.499
Neg logit contributions
iaries-0.618
acas-0.602
OTOS-0.579
ruary-0.566
mitt-0.558
Token almost
Token ID2048
Feature activation+4.78e+00

Pos logit contributions
iaries+7.292
acas+6.753
OTOS+6.642
mitt+6.424
flush+6.328
Neg logit contributions
��-12.393
�醒-9.981
ーテ-9.630
ット-9.548
-9.430
Token exclusive
Token ID8568
Feature activation+7.44e+00

Pos logit contributions
iaries+2.932
acas+2.836
OTOS+2.732
ruary+2.657
mitt+2.634
Neg logit contributions
��-4.273
�醒-3.280
ット-3.262
uez-3.174
ーテ-3.167
Token attention
Token ID3241
Feature activation+8.32e-01

Pos logit contributions
iaries+4.343
acas+4.133
OTOS+3.955
mitt+3.810
ruary+3.756
Neg logit contributions
��-6.884
�醒-5.278
���-5.261
-5.191
ット-5.165
Token to
Token ID284
Feature activation+2.42e-01

Pos logit contributions
iaries+0.544
acas+0.529
OTOS+0.503
ruary+0.493
mitt+0.486
Neg logit contributions
��-0.714
ット-0.542
Line-0.537
�醒-0.533
uez-0.528
Token her
Token ID607
Feature activation+4.46e+00

Pos logit contributions
iaries+0.183
acas+0.178
OTOS+0.170
ruary+0.168
mitt+0.165
Neg logit contributions
��-0.184
ット-0.134
Line-0.133
�醒-0.131
uez-0.130
Token 16
Token ID1467
Feature activation+4.11e+00

Pos logit contributions
iaries+2.830
acas+2.731
OTOS+2.621
ruary+2.495
 "$:/+2.423
Neg logit contributions
��-4.965
ット-3.898
uez-3.874
�醒-3.871
-3.859
Token 17
Token ID1596
Feature activation+4.81e+00

Pos logit contributions
iaries+2.380
acas+2.325
OTOS+2.214
ruary+2.138
imore+2.082
Neg logit contributions
��-3.825
ット-2.945
uez-2.909
Line-2.888
���-2.879
Token 18
Token ID1248
Feature activation+2.00e+00

Pos logit contributions
iaries+2.742
acas+2.661
OTOS+2.569
ruary+2.381
 "$:/+2.375
Neg logit contributions
��-4.470
�醒-3.478
Line-3.440
uez-3.436
ット-3.423
Token 19
Token ID678
Feature activation+8.98e+00

Pos logit contributions
iaries+1.316
acas+1.286
OTOS+1.227
ruary+1.191
mitt+1.172
Neg logit contributions
��-1.711
ット-1.293
Line-1.277
�醒-1.272
uez-1.270
Token 20
Token ID1160
Feature activation+8.28e+00

Pos logit contributions
iaries+4.903
acas+4.807
OTOS+4.736
obin+4.352
 "$:/+4.313
Neg logit contributions
��-8.151
uez-6.337
-6.309
Line-6.274
�醒-6.271
Token 21
Token ID2310
Feature activation+1.36e+01

Pos logit contributions
iaries+4.928
acas+4.911
OTOS+4.741
ruary+4.489
obin+4.393
Neg logit contributions
��-7.197
uez-5.404
ーテ-5.383
ット-5.360
-5.316
Token 22
Token ID2534
Feature activation+9.28e+00

Pos logit contributions
iaries+6.556
acas+6.203
OTOS+6.063
ruary+5.810
mitt+5.620
Neg logit contributions
��-12.211
uez-9.763
igham-9.748
���-9.676
ーテ-9.636
Token 23
Token ID2242
Feature activation+8.77e+00

Pos logit contributions
iaries+5.212
acas+4.997
OTOS+4.827
ruary+4.553
 "$:/+4.549
Neg logit contributions
��-8.368
uez-6.539
ット-6.533
ーテ-6.423
-6.356
Token 24
Token ID1987
Feature activation+4.49e+00

Pos logit contributions
iaries+4.950
acas+4.667
OTOS+4.622
 "$:/+4.334
ruary+4.213
Neg logit contributions
��-7.882
-6.223
ット-6.191
uez-6.166
ーテ-6.106
Token 25
Token ID1679
Feature activation+1.93e+00

Pos logit contributions
iaries+2.966
acas+2.880
OTOS+2.753
ruary+2.679
 "$:/+2.630
Neg logit contributions
��-3.774
ット-2.861
uez-2.831
Line-2.804
-2.790
Token 26
Token ID2608
Feature activation+8.61e-01

Pos logit contributions
iaries+1.280
acas+1.242
OTOS+1.192
ruary+1.161
mitt+1.136
Neg logit contributions
��-1.629
ット-1.226
Line-1.222
�醒-1.214
uez-1.207
Token R
Token ID371
Feature activation+3.52e+00

Pos logit contributions
iaries+1.383
acas+1.343
OTOS+1.278
ruary+1.261
mitt+1.241
Neg logit contributions
��-1.773
ット-1.332
Line-1.317
�醒-1.315
uez-1.307
Tokenupp
Token ID7211
Feature activation-3.84e+00

Pos logit contributions
iaries+2.622
acas+2.577
OTOS+2.449
mitt+2.445
ruary+2.402
Neg logit contributions
��-2.726
���-1.987
�醒-1.974
ット-1.968
ーテ-1.940
Tokene
Token ID68
Feature activation+2.24e+00

Pos logit contributions
��+3.095
Line+2.569
uez+2.518
ット+2.433
 Younger+2.392
Neg logit contributions
iaries-2.405
acas-2.382
OTOS-2.323
ruary-2.235
ashtra-2.196
Token Award
Token ID11289
Feature activation+6.15e+00

Pos logit contributions
iaries+1.374
acas+1.329
OTOS+1.265
ruary+1.239
mitt+1.217
Neg logit contributions
��-2.015
ット-1.544
Line-1.527
�醒-1.520
uez-1.517
Token Nom
Token ID21198
Feature activation+5.30e+00

Pos logit contributions
iaries+3.986
acas+3.801
ruary+3.640
OTOS+3.626
mitt+3.605
Neg logit contributions
��-5.252
���-3.978
uez-3.899
ット-3.896
�醒-3.859
Tokenination
Token ID1883
Feature activation+1.31e+01

Pos logit contributions
iaries+3.780
acas+3.620
mitt+3.463
imore+3.349
ruary+3.327
Neg logit contributions
��-4.410
���-3.217
ット-3.192
ーテ-3.176
-3.144
Token Pack
Token ID6400
Feature activation-3.92e+00

Pos logit contributions
iaries+7.234
mitt+6.886
acas+6.783
OTOS+6.484
imore+6.308
Neg logit contributions
��-11.311
���-8.918
uez-8.716
-8.542
ーテ-8.518
Tokenet
Token ID316
Feature activation+3.14e+00

Pos logit contributions
��+2.240
ット+1.440
Line+1.425
�醒+1.413
uez+1.349
Neg logit contributions
iaries-3.612
acas-3.561
OTOS-3.456
ruary-3.399
ashtra-3.358
Token and
Token ID290
Feature activation-2.19e+00

Pos logit contributions
iaries+2.000
acas+1.932
OTOS+1.832
ruary+1.808
mitt+1.796
Neg logit contributions
��-2.740
ット-2.073
�醒-2.058
Line-2.054
���-2.046
Token submit
Token ID9199
Feature activation+4.73e+00

Pos logit contributions
��+1.729
ット+1.287
Line+1.281
�醒+1.258
uez+1.250
Neg logit contributions
iaries-1.561
acas-1.535
OTOS-1.460
ruary-1.436
imore-1.400
Token all
Token ID477
Feature activation+4.56e+00

Pos logit contributions
iaries+2.937
acas+2.783
OTOS+2.708
mitt+2.651
ruary+2.618
Neg logit contributions
��-4.206
ット-3.184
�醒-3.146
Line-3.135
uez-3.131
Token dug
Token ID18735
Feature activation-4.33e+00

Pos logit contributions
iaries+0.137
acas+0.133
OTOS+0.127
ruary+0.125
mitt+0.123
Neg logit contributions
��-0.165
ット-0.123
Line-0.122
�醒-0.121
uez-0.120
Token in
Token ID287
Feature activation-8.80e-01

Pos logit contributions
��+3.302
Line+2.444
ット+2.441
uez+2.383
+2.368
Neg logit contributions
iaries-3.128
acas-3.077
OTOS-2.948
ruary-2.909
mitt-2.847
Token.
Token ID13
Feature activation+1.35e+00

Pos logit contributions
��+0.724
ット+0.543
Line+0.540
�醒+0.531
uez+0.529
Neg logit contributions
iaries-0.602
acas-0.588
OTOS-0.561
ruary-0.551
mitt-0.540
Token
Token ID198
Feature activation+2.11e+00

Pos logit contributions
iaries+0.871
acas+0.847
OTOS+0.807
ruary+0.789
mitt+0.778
Neg logit contributions
��-1.167
ット-0.885
Line-0.875
�醒-0.872
uez-0.863
Token
Token ID198
Feature activation+2.72e+00

Pos logit contributions
iaries+1.245
acas+1.214
OTOS+1.155
mitt+1.120
ruary+1.119
Neg logit contributions
��-1.962
���-1.518
�醒-1.504
ット-1.493
ーテ-1.462
TokenP
Token ID47
Feature activation+1.31e+01

Pos logit contributions
iaries+1.658
acas+1.627
OTOS+1.563
mitt+1.507
ruary+1.491
Neg logit contributions
��-2.459
���-1.876
ット-1.871
�醒-1.859
ーテ-1.824
Tokenes
Token ID274
Feature activation-2.74e-01

Pos logit contributions
acas+6.185
iaries+5.990
imore+5.297
OTOS+5.230
mitt+5.106
Neg logit contributions
��-13.899
���-11.242
�醒-11.043
ーテ-10.731
ット-10.692
Tokenkin
Token ID5116
Feature activation+3.89e+00

Pos logit contributions
��+0.183
Line+0.128
ット+0.127
uez+0.125
�醒+0.123
Neg logit contributions
iaries-0.229
acas-0.224
OTOS-0.216
ruary-0.212
mitt-0.209
Token calls
Token ID3848
Feature activation-1.14e+00

Pos logit contributions
iaries+2.267
acas+2.221
OTOS+2.092
ruary+2.046
mitt+2.034
Neg logit contributions
��-3.575
ット-2.746
�醒-2.732
Line-2.713
���-2.691
Token it
Token ID340
Feature activation-3.23e+00

Pos logit contributions
��+0.904
Line+0.674
ット+0.672
uez+0.664
�醒+0.655
Neg logit contributions
iaries-0.816
acas-0.791
OTOS-0.758
ruary-0.747
mitt-0.732
Token Division
Token ID7458
Feature activation-1.28e-01

Pos logit contributions
��+2.526
ット+1.880
Line+1.874
�醒+1.840
+1.824
Neg logit contributions
iaries-2.319
acas-2.229
OTOS-2.132
ruary-2.122
mitt-2.064
Token on
Token ID319
Feature activation+1.87e+00

Pos logit contributions
��+0.582
ット+0.435
Line+0.432
�醒+0.427
uez+0.422
Neg logit contributions
iaries-0.501
acas-0.486
OTOS-0.465
ruary-0.454
mitt-0.446
Token the
Token ID262
Feature activation+2.34e+00

Pos logit contributions
iaries+1.249
acas+1.221
OTOS+1.163
ruary+1.138
mitt+1.133
Neg logit contributions
��-1.567
ット-1.185
Line-1.163
�醒-1.161
uez-1.153
Token convention
Token ID9831
Feature activation-5.85e-01

Pos logit contributions
iaries+1.744
acas+1.715
OTOS+1.631
mitt+1.601
ruary+1.596
Neg logit contributions
��-1.786
ット-1.312
�醒-1.285
uez-1.268
���-1.268
Token J
Token ID449
Feature activation+2.51e+00

Pos logit contributions
��+0.422
ット+0.301
Line+0.299
�醒+0.294
uez+0.292
Neg logit contributions
iaries-0.463
acas-0.451
OTOS-0.433
ruary-0.426
mitt-0.420
Tokenumb
Token ID2178
Feature activation+3.81e+00

Pos logit contributions
iaries+1.831
acas+1.803
OTOS+1.720
ruary+1.679
mitt+1.673
Neg logit contributions
��-1.953
ット-1.441
�醒-1.422
Line-1.405
���-1.399
Tokenot
Token ID313
Feature activation+1.30e+01

Pos logit contributions
iaries+2.511
acas+2.464
OTOS+2.290
mitt+2.269
ruary+2.263
Neg logit contributions
��-3.250
���-2.453
ット-2.436
-2.391
Line-2.372
Tokenron
Token ID1313
Feature activation+6.29e+00

Pos logit contributions
acas+3.016
iaries+2.953
ón+2.508
dan+2.468
imore+2.436
Neg logit contributions
��-16.063
���-13.534
ーテ-13.349
�醒-13.236
��-13.030
Token for
Token ID329
Feature activation+4.80e-02

Pos logit contributions
iaries+3.799
acas+3.734
OTOS+3.512
ruary+3.435
mitt+3.428
Neg logit contributions
��-5.497
ット-4.224
�醒-4.217
���-4.215
uez-4.170
Token donations
Token ID10976
Feature activation+1.02e+00

Pos logit contributions
iaries+0.033
acas+0.032
OTOS+0.031
ruary+0.030
mitt+0.030
Neg logit contributions
��-0.039
ット-0.029
Line-0.029
�醒-0.029
uez-0.029
Token.
Token ID13
Feature activation-3.45e+00

Pos logit contributions
iaries+0.674
acas+0.655
OTOS+0.624
ruary+0.611
mitt+0.603
Neg logit contributions
��-0.865
ット-0.654
Line-0.647
�醒-0.644
uez-0.638
Token It
Token ID632
Feature activation-2.22e+00

Pos logit contributions
��+2.598
Line+1.949
ット+1.948
 Younger+1.925
 Lines+1.909
Neg logit contributions
iaries-2.545
acas-2.480
OTOS-2.347
ruary-2.321
imore-2.310
Token comedian
Token ID23139
Feature activation-2.98e+00

Pos logit contributions
��+3.012
ット+2.221
Line+2.221
 Younger+2.181
�醒+2.176
Neg logit contributions
iaries-2.733
acas-2.602
OTOS-2.504
ruary-2.467
 "$:/-2.407
Token/
Token ID14
Feature activation+7.18e-01

Pos logit contributions
��+2.514
Line+1.891
ット+1.880
�醒+1.847
uez+1.844
Neg logit contributions
iaries-2.004
acas-1.930
OTOS-1.827
ruary-1.800
mitt-1.763
Tokenauthor
Token ID9800
Feature activation+1.39e-01

Pos logit contributions
iaries+0.475
acas+0.464
OTOS+0.440
ruary+0.431
mitt+0.428
Neg logit contributions
��-0.609
ット-0.461
Line-0.454
�醒-0.453
uez-0.449
Token Sara
Token ID24799
Feature activation-5.17e-01

Pos logit contributions
iaries+0.090
acas+0.088
OTOS+0.083
ruary+0.082
mitt+0.081
Neg logit contributions
��-0.120
ット-0.091
Line-0.090
�醒-0.089
uez-0.089
Token Ben
Token ID3932
Feature activation+2.53e-01

Pos logit contributions
��+0.408
ット+0.300
Line+0.299
�醒+0.294
uez+0.291
Neg logit contributions
iaries-0.376
acas-0.364
OTOS-0.349
ruary-0.342
mitt-0.337
Tokeninc
Token ID1939
Feature activation+1.27e+01

Pos logit contributions
iaries+0.173
acas+0.168
OTOS+0.161
ruary+0.158
mitt+0.155
Neg logit contributions
��-0.208
ット-0.157
Line-0.156
�醒-0.154
uez-0.153
Tokenasa
Token ID15462
Feature activation+1.35e+00

Pos logit contributions
acas+6.612
iaries+6.587
ón+6.078
obin+5.923
OTOS+5.901
Neg logit contributions
��-11.989
�醒-9.808
���-9.785
ット-9.722
ーテ-9.576
Token),
Token ID828
Feature activation-7.37e-02

Pos logit contributions
iaries+0.795
acas+0.776
OTOS+0.732
ruary+0.716
mitt+0.706
Neg logit contributions
��-1.244
ット-0.966
Line-0.956
�醒-0.953
uez-0.943
Token was
Token ID373
Feature activation-1.42e-01

Pos logit contributions
��+0.062
ット+0.046
Line+0.046
�醒+0.045
uez+0.045
Neg logit contributions
iaries-0.050
acas-0.048
OTOS-0.046
ruary-0.045
mitt-0.045
Token strangely
Token ID29381
Feature activation+1.61e+00

Pos logit contributions
��+0.112
ット+0.082
Line+0.081
�醒+0.080
uez+0.080
Neg logit contributions
iaries-0.103
acas-0.101
OTOS-0.096
ruary-0.095
mitt-0.093
Token judged
Token ID19589
Feature activation+2.70e+00

Pos logit contributions
iaries+1.210
acas+1.176
OTOS+1.128
ruary+1.107
mitt+1.099
Neg logit contributions
��-1.217
ット-0.888
Line-0.876
�醒-0.873
uez-0.859
Token list
Token ID1351
Feature activation+2.73e+00

Pos logit contributions
iaries+3.913
acas+3.808
OTOS+3.706
mitt+3.616
ruary+3.498
Neg logit contributions
��-5.538
ット-4.225
�醒-4.185
ーテ-4.076
���-4.065
Token.
Token ID13
Feature activation-5.22e-01

Pos logit contributions
iaries+1.660
acas+1.622
OTOS+1.541
ruary+1.494
mitt+1.490
Neg logit contributions
��-2.460
ット-1.881
Line-1.863
�醒-1.858
���-1.857
Token From
Token ID3574
Feature activation-2.86e+00

Pos logit contributions
��+0.440
ット+0.333
Line+0.330
�醒+0.327
uez+0.324
Neg logit contributions
iaries-0.349
acas-0.340
OTOS-0.323
ruary-0.317
mitt-0.312
Token Edward
Token ID10443
Feature activation+7.50e-03

Pos logit contributions
��+2.171
Line+1.618
ット+1.605
uez+1.580
+1.554
Neg logit contributions
iaries-2.112
acas-2.045
OTOS-1.939
ruary-1.922
aceae-1.895
Token Has
Token ID7875
Feature activation+1.18e+00

Pos logit contributions
iaries+0.005
acas+0.005
OTOS+0.005
ruary+0.005
mitt+0.005
Neg logit contributions
��-0.006
ット-0.004
Line-0.004
�醒-0.004
uez-0.004
Tokenb
Token ID65
Feature activation+1.27e+01

Pos logit contributions
iaries+0.783
acas+0.765
OTOS+0.727
ruary+0.712
mitt+0.707
Neg logit contributions
��-1.003
ット-0.756
�醒-0.746
Line-0.745
���-0.735
Tokenrou
Token ID472
Feature activation+5.09e+00

Pos logit contributions
iaries+7.350
ruary+7.027
acas+6.859
mitt+6.577
imore+6.573
Neg logit contributions
��-11.266
���-8.819
ット-8.698
ーテ-8.606
�醒-8.533
Tokenck
Token ID694
Feature activation+2.81e+00

Pos logit contributions
iaries+2.492
acas+2.432
OTOS+2.216
ruary+2.215
mitt+2.193
Neg logit contributions
��-5.195
ット-4.063
�醒-4.055
���-4.053
ーテ-4.045
Token's
Token ID338
Feature activation+5.52e+00

Pos logit contributions
iaries+1.797
acas+1.763
OTOS+1.681
ruary+1.627
mitt+1.617
Neg logit contributions
��-2.445
ット-1.846
�醒-1.829
Line-1.810
���-1.810
Token transcript
Token ID14687
Feature activation-3.45e+00

Pos logit contributions
iaries+3.869
acas+3.802
OTOS+3.611
mitt+3.534
ruary+3.514
Neg logit contributions
��-4.479
�醒-3.244
ット-3.215
���-3.159
ーテ-3.147
Token of
Token ID286
Feature activation+2.25e-01

Pos logit contributions
��+2.841
Line+2.178
ット+2.164
�醒+2.130
uez+2.106
Neg logit contributions
iaries-2.299
acas-2.229
OTOS-2.122
ruary-2.117
aceae-2.088
Token.
Token ID13
Feature activation+7.58e-01

Pos logit contributions
iaries+0.746
acas+0.725
OTOS+0.688
ruary+0.674
mitt+0.668
Neg logit contributions
��-1.009
ット-0.765
�醒-0.756
Line-0.755
���-0.748
Token WHO
Token ID19494
Feature activation+2.76e-01

Pos logit contributions
iaries+0.529
acas+0.515
OTOS+0.492
ruary+0.482
mitt+0.476
Neg logit contributions
��-0.618
ット-0.460
Line-0.456
�醒-0.453
uez-0.448
Token spokesman
Token ID6523
Feature activation+1.78e+00

Pos logit contributions
iaries+0.185
acas+0.180
OTOS+0.171
ruary+0.168
mitt+0.166
Neg logit contributions
��-0.232
Line-0.175
ット-0.175
uez-0.172
�醒-0.171
Token Gregory
Token ID20653
Feature activation+1.52e+00

Pos logit contributions
iaries+1.162
acas+1.130
OTOS+1.074
ruary+1.053
mitt+1.038
Neg logit contributions
��-1.530
ット-1.160
Line-1.150
�醒-1.142
uez-1.132
Token Hart
Token ID11345
Feature activation-3.49e+00

Pos logit contributions
iaries+1.081
acas+1.054
OTOS+1.007
ruary+0.988
mitt+0.976
Neg logit contributions
��-1.214
ット-0.899
Line-0.889
�醒-0.883
uez-0.874
Tokenl
Token ID75
Feature activation+1.27e+01

Pos logit contributions
��+2.978
Line+2.306
ット+2.281
uez+2.272
�醒+2.240
Neg logit contributions
iaries-2.244
acas-2.153
OTOS-2.048
ruary-2.019
 "$:/-1.975
Token said
Token ID531
Feature activation+4.92e+00

Pos logit contributions
acas+6.552
iaries+6.333
mitt+6.180
obin+6.090
imore+6.058
Neg logit contributions
��-11.957
ット-9.131
�醒-9.123
���-8.965
Line-8.873
Token it
Token ID340
Feature activation-3.45e-01

Pos logit contributions
iaries+3.035
acas+2.956
OTOS+2.822
ruary+2.771
mitt+2.736
Neg logit contributions
��-4.392
ット-3.351
�醒-3.316
���-3.277
Line-3.232
Token had
Token ID550
Feature activation-6.25e-01

Pos logit contributions
��+0.264
ット+0.194
Line+0.193
uez+0.190
�醒+0.190
Neg logit contributions
iaries-0.255
acas-0.248
OTOS-0.238
ruary-0.234
mitt-0.231
Token been
Token ID587
Feature activation-9.59e-01

Pos logit contributions
��+0.516
Line+0.389
ット+0.388
uez+0.381
�醒+0.380
Neg logit contributions
iaries-0.423
acas-0.414
OTOS-0.393
ruary-0.386
mitt-0.380
Token expecting
Token ID12451
Feature activation-2.47e+00

Pos logit contributions
��+0.752
Line+0.556
ット+0.554
uez+0.543
�醒+0.539
Neg logit contributions
iaries-0.691
acas-0.676
OTOS-0.648
ruary-0.635
mitt-0.623
Tokennorm
Token ID27237
Feature activation-6.65e+00

Pos logit contributions
iaries+2.211
acas+2.160
OTOS+2.052
mitt+2.036
aceae+2.008
Neg logit contributions
��-2.739
ット-2.038
���-2.033
�醒-2.014
Line-1.987
Tokenally
Token ID453
Feature activation+1.62e+00

Pos logit contributions
��+5.198
ット+4.018
uez+3.953
Line+3.904
�醒+3.847
Neg logit contributions
iaries-4.593
acas-4.458
OTOS-4.311
ruary-4.266
mitt-4.057
Token protective
Token ID14153
Feature activation+1.95e+00

Pos logit contributions
iaries+1.132
acas+1.100
OTOS+1.053
mitt+1.028
ruary+1.025
Neg logit contributions
��-1.310
ット-0.968
Line-0.966
�醒-0.963
uez-0.949
Token lact
Token ID26222
Feature activation+4.39e+00

Pos logit contributions
iaries+1.387
acas+1.346
OTOS+1.294
mitt+1.252
ruary+1.252
Neg logit contributions
��-1.553
ット-1.141
�醒-1.134
Line-1.131
���-1.121
Tokenob
Token ID672
Feature activation+1.15e+00

Pos logit contributions
iaries+2.681
acas+2.574
OTOS+2.447
mitt+2.399
obin+2.391
Neg logit contributions
��-4.028
ット-3.086
���-3.040
�醒-3.021
Line-3.018
Tokenac
Token ID330
Feature activation+1.27e+01

Pos logit contributions
iaries+0.667
acas+0.646
OTOS+0.610
ruary+0.596
mitt+0.586
Neg logit contributions
��-1.073
ット-0.834
Line-0.827
�醒-0.822
uez-0.816
Tokenilli
Token ID50173
Feature activation+6.44e+00

Pos logit contributions
iaries+5.142
acas+4.452
aceae+4.353
obin+4.132
imore+4.005
Neg logit contributions
��-13.687
���-11.510
��-11.074
�醒-10.870
 Younger-10.822
Token
Token ID447
Feature activation-3.05e+00

Pos logit contributions
iaries+3.784
acas+3.676
aceae+3.580
OTOS+3.517
mitt+3.416
Neg logit contributions
��-5.727
�醒-4.394
���-4.367
ット-4.338
Line-4.290
Token
Token ID251
Feature activation+2.70e+00

Pos logit contributions
��+2.177
ット+1.495
�醒+1.472
Line+1.460
���+1.448
Neg logit contributions
iaries-2.522
acas-2.444
OTOS-2.349
ruary-2.324
mitt-2.271
Token (
Token ID357
Feature activation+2.33e+00

Pos logit contributions
iaries+1.653
acas+1.599
OTOS+1.516
ruary+1.474
mitt+1.473
Neg logit contributions
��-2.411
�醒-1.842
ット-1.840
���-1.826
Line-1.824
TokenS
Token ID50
Feature activation+2.24e+00

Pos logit contributions
iaries+1.721
acas+1.683
OTOS+1.619
ruary+1.577
mitt+1.576
Neg logit contributions
��-1.800
ット-1.307
�醒-1.289
���-1.279
uez-1.276
Token
Token ID198
Feature activation-1.30e+00

Pos logit contributions
��+1.454
Line+1.152
ット+1.126
uez+1.112
 Younger+1.102
Neg logit contributions
iaries-1.262
acas-1.219
OTOS-1.149
ruary-1.148
imore-1.109
Token4
Token ID19
Feature activation-6.73e-01

Pos logit contributions
��+1.086
Line+0.833
ット+0.825
�醒+0.809
uez+0.806
Neg logit contributions
iaries-0.871
acas-0.842
OTOS-0.798
ruary-0.790
 "$:/-0.770
Token Comments
Token ID19502
Feature activation-1.51e+00

Pos logit contributions
��+0.571
ット+0.432
Line+0.429
�醒+0.425
uez+0.422
Neg logit contributions
iaries-0.446
acas-0.434
OTOS-0.411
ruary-0.404
mitt-0.398
Token Print
Token ID12578
Feature activation-3.65e+00

Pos logit contributions
��+1.259
Line+0.954
ット+0.946
uez+0.937
�醒+0.932
Neg logit contributions
iaries-1.012
acas-0.991
OTOS-0.935
ruary-0.927
mitt-0.910
Token This
Token ID770
Feature activation-2.94e+00

Pos logit contributions
��+2.890
Line+2.174
�醒+2.143
ット+2.143
uez+2.130
Neg logit contributions
iaries-2.552
acas-2.481
OTOS-2.357
ruary-2.316
mitt-2.289
Token Post
Token ID2947
Feature activation-1.51e+01

Pos logit contributions
��+2.065
Line+1.512
ット+1.471
�醒+1.462
uez+1.453
Neg logit contributions
iaries-2.330
acas-2.267
OTOS-2.177
ruary-2.167
mitt-2.100
Token
Token ID198
Feature activation-4.37e+00

Pos logit contributions
��+9.568
Line+7.784
 Younger+7.768
 Lines+7.738
 Cruel+7.568
Neg logit contributions
iaries-10.180
acas-10.087
OTOS-9.532
obin-9.433
ruary-9.283
Token
Token ID198
Feature activation-2.04e+00

Pos logit contributions
��+3.161
Line+2.601
ット+2.477
uez+2.464
 Younger+2.457
Neg logit contributions
iaries-3.179
acas-3.058
ruary-2.906
OTOS-2.883
ashtra-2.827
TokenP
Token ID47
Feature activation+6.47e+00

Pos logit contributions
��+1.688
Line+1.308
ット+1.286
uez+1.258
�醒+1.258
Neg logit contributions
iaries-1.373
acas-1.326
OTOS-1.255
ruary-1.247
 "$:/-1.217
TokenCC
Token ID4093
Feature activation-2.13e+00

Pos logit contributions
iaries+4.790
acas+4.692
OTOS+4.515
ruary+4.355
imore+4.311
Neg logit contributions
��-4.961
ット-3.601
ーテ-3.561
���-3.556
�醒-3.499
Token Natural
Token ID12068
Feature activation+1.50e+00

Pos logit contributions
��+1.200
Line+0.774
ット+0.769
�醒+0.746
uez+0.741
Neg logit contributions
iaries-2.003
acas-1.961
OTOS-1.890
ruary-1.867
mitt-1.860
Token speech
Token ID4046
Feature activation-2.47e+00

Pos logit contributions
��+0.790
ット+0.592
Line+0.588
�醒+0.580
uez+0.577
Neg logit contributions
iaries-0.657
acas-0.639
OTOS-0.611
ruary-0.600
mitt-0.589
Token.
Token ID13
Feature activation-2.85e+00

Pos logit contributions
��+2.029
ット+1.521
Line+1.514
�醒+1.491
 Younger+1.484
Neg logit contributions
iaries-1.696
acas-1.637
OTOS-1.577
ruary-1.538
mitt-1.503
Token
Token ID851
Feature activation+3.88e-01

Pos logit contributions
��+2.242
Line+1.668
ット+1.664
 Younger+1.643
�醒+1.625
Neg logit contributions
iaries-2.049
acas-1.986
OTOS-1.884
ruary-1.863
mitt-1.831
Token ACLU
Token ID24381
Feature activation+9.56e-01

Pos logit contributions
iaries+0.308
acas+0.300
OTOS+0.288
ruary+0.284
mitt+0.280
Neg logit contributions
��-0.279
ット-0.199
Line-0.197
�醒-0.195
uez-0.193
Token of
Token ID286
Feature activation+1.11e+00

Pos logit contributions
iaries+0.613
acas+0.596
OTOS+0.566
ruary+0.554
mitt+0.547
Neg logit contributions
��-0.833
ット-0.634
Line-0.628
�醒-0.625
uez-0.619
Token Oregon
Token ID8819
Feature activation-1.46e+01

Pos logit contributions
iaries+0.826
acas+0.806
OTOS+0.773
ruary+0.758
mitt+0.751
Neg logit contributions
��-0.854
ット-0.618
�醒-0.613
Line-0.610
���-0.605
Token (@
Token ID4275
Feature activation-3.85e-01

Pos logit contributions
��+4.638
ット+3.699
Line+3.580
 Younger+3.470
 Lines+3.454
Neg logit contributions
iaries-14.458
acas-13.811
ashtra-13.493
ruary-13.229
obin-13.117
TokenAC
Token ID2246
Feature activation-1.70e+00

Pos logit contributions
��+0.281
ット+0.203
Line+0.202
�醒+0.197
uez+0.197
Neg logit contributions
iaries-0.301
acas-0.292
OTOS-0.280
ruary-0.278
mitt-0.272
TokenLU
Token ID41596
Feature activation-5.44e-01

Pos logit contributions
��+1.329
Line+1.003
ット+0.991
uez+0.976
+0.964
Neg logit contributions
iaries-1.234
acas-1.194
OTOS-1.136
ruary-1.122
mitt-1.097
Token_
Token ID62
Feature activation-6.39e+00

Pos logit contributions
��+0.426
Line+0.320
ット+0.319
uez+0.312
+0.308
Neg logit contributions
iaries-0.391
acas-0.381
OTOS-0.363
ruary-0.358
mitt-0.350
TokenOR
Token ID1581
Feature activation-5.07e+00

Pos logit contributions
��+2.926
Line+2.195
ット+1.944
+1.893
uez+1.790
Neg logit contributions
iaries-6.363
acas-6.287
ruary-5.976
umbn-5.789
imore-5.749
Token gather
Token ID6431
Feature activation+3.70e+00

Pos logit contributions
iaries+6.116
acas+5.915
flush+5.488
 "$:/+5.474
mitt+5.445
Neg logit contributions
��-7.371
ット-5.701
���-5.650
�醒-5.618
-5.527
Token with
Token ID351
Feature activation-7.57e-01

Pos logit contributions
iaries+2.361
acas+2.306
OTOS+2.206
ruary+2.117
mitt+2.104
Neg logit contributions
��-3.235
ット-2.465
�醒-2.444
Line-2.426
���-2.416
Token
Token ID851
Feature activation+7.23e-01

Pos logit contributions
��+0.621
ット+0.463
Line+0.461
�醒+0.456
uez+0.454
Neg logit contributions
iaries-0.523
acas-0.508
OTOS-0.483
ruary-0.477
mitt-0.468
Token ACLU
Token ID24381
Feature activation+7.82e-01

Pos logit contributions
iaries+0.562
acas+0.549
OTOS+0.527
ruary+0.518
mitt+0.512
Neg logit contributions
��-0.532
ット-0.382
Line-0.377
�醒-0.374
uez-0.370
Token of
Token ID286
Feature activation+5.85e-01

Pos logit contributions
iaries+0.503
acas+0.489
OTOS+0.465
ruary+0.455
mitt+0.448
Neg logit contributions
��-0.679
ット-0.517
Line-0.512
�醒-0.509
uez-0.505
Token Oregon
Token ID8819
Feature activation-1.42e+01

Pos logit contributions
iaries+0.444
acas+0.433
OTOS+0.415
ruary+0.408
mitt+0.403
Neg logit contributions
��-0.441
ット-0.319
Line-0.316
�醒-0.313
uez-0.310
Token (@
Token ID4275
Feature activation+5.77e-01

Pos logit contributions
��+4.805
ット+3.639
Line+3.618
 Lines+3.465
 Cruel+3.433
Neg logit contributions
iaries-14.104
acas-13.521
ashtra-13.170
ruary-12.983
obin-12.802
TokenAC
Token ID2246
Feature activation-1.59e+00

Pos logit contributions
iaries+0.438
acas+0.428
OTOS+0.411
ruary+0.403
mitt+0.399
Neg logit contributions
��-0.434
ット-0.314
Line-0.310
�醒-0.309
uez-0.305
TokenLU
Token ID41596
Feature activation-6.14e-01

Pos logit contributions
��+1.246
Line+0.939
ット+0.928
uez+0.914
+0.902
Neg logit contributions
iaries-1.150
acas-1.114
OTOS-1.058
ruary-1.046
mitt-1.024
Token_
Token ID62
Feature activation-6.59e+00

Pos logit contributions
��+0.478
Line+0.359
ット+0.358
uez+0.350
+0.345
Neg logit contributions
iaries-0.443
acas-0.432
OTOS-0.411
ruary-0.406
mitt-0.397
TokenOR
Token ID1581
Feature activation-5.72e+00

Pos logit contributions
��+3.020
Line+2.251
ット+1.999
+1.923
uez+1.847
Neg logit contributions
iaries-6.553
acas-6.467
ruary-6.150
umbn-5.950
imore-5.923
Token his
Token ID465
Feature activation+1.19e+00

Pos logit contributions
��+2.300
ット+1.712
Line+1.708
uez+1.667
�醒+1.655
Neg logit contributions
iaries-2.040
acas-1.979
OTOS-1.909
ruary-1.883
mitt-1.833
Token head
Token ID1182
Feature activation+1.99e+00

Pos logit contributions
iaries+0.770
acas+0.748
OTOS+0.711
ruary+0.697
mitt+0.687
Neg logit contributions
��-1.026
ット-0.780
Line-0.772
�醒-0.768
uez-0.761
Token).
Token ID737
Feature activation+6.76e-01

Pos logit contributions
iaries+1.192
acas+1.163
OTOS+1.095
ruary+1.073
mitt+1.058
Neg logit contributions
��-1.818
ット-1.405
�醒-1.387
Line-1.387
���-1.376
Token
Token ID198
Feature activation-1.50e+00

Pos logit contributions
iaries+0.452
acas+0.440
OTOS+0.419
ruary+0.410
mitt+0.405
Neg logit contributions
��-0.571
ット-0.431
Line-0.427
�醒-0.424
uez-0.420
Token
Token ID198
Feature activation-3.22e+00

Pos logit contributions
��+1.195
Line+0.944
ット+0.926
uez+0.913
 Younger+0.905
Neg logit contributions
iaries-1.029
acas-0.997
OTOS-0.942
ruary-0.937
ashtra-0.909
Token(
Token ID7
Feature activation-1.40e+01

Pos logit contributions
��+2.533
Line+1.941
ット+1.890
uez+1.829
�醒+1.820
Neg logit contributions
iaries-2.297
acas-2.228
ruary-2.144
OTOS-2.112
 "$:/-2.040
TokenExample
Token ID16281
Feature activation-1.58e+00

Pos logit contributions
��+4.121
Line+3.636
 Younger+2.216
PLA+2.174
ット+2.145
Neg logit contributions
iaries-14.267
ruary-14.253
acas-14.054
umbn-13.769
OTOS-13.689
Token:
Token ID25
Feature activation-4.82e+00

Pos logit contributions
��+1.320
Line+1.047
ット+1.029
uez+1.014
 Younger+1.005
Neg logit contributions
iaries-1.031
acas-0.998
OTOS-0.940
ruary-0.938
imore-0.905
Token Because
Token ID4362
Feature activation-3.14e+00

Pos logit contributions
��+3.522
 Younger+2.711
 Lines+2.652
Line+2.626
ット+2.613
Neg logit contributions
acas-3.530
iaries-3.522
OTOS-3.341
ruary-3.292
mitt-3.286
Token of
Token ID286
Feature activation-5.94e+00

Pos logit contributions
��+2.369
Line+1.852
ット+1.815
uez+1.798
 Younger+1.794
Neg logit contributions
iaries-2.256
acas-2.208
ruary-2.091
OTOS-2.083
ashtra-2.012
Token a
Token ID257
Feature activation-7.63e+00

Pos logit contributions
��+3.754
Line+2.857
ット+2.787
uez+2.787
 Younger+2.770
Neg logit contributions
iaries-4.856
acas-4.689
ruary-4.542
OTOS-4.476
imore-4.362
Token in
Token ID287
Feature activation+2.28e+00

Pos logit contributions
��+1.391
Line+1.053
ット+1.050
uez+1.029
�醒+1.027
Neg logit contributions
iaries-1.154
acas-1.122
OTOS-1.070
ruary-1.053
mitt-1.034
Token Allen
Token ID9659
Feature activation-2.17e+00

Pos logit contributions
iaries+1.585
acas+1.548
OTOS+1.476
ruary+1.443
mitt+1.433
Neg logit contributions
��-1.868
ット-1.387
�醒-1.371
Line-1.368
uez-1.352
Token Robinson
Token ID12652
Feature activation+2.71e-01

Pos logit contributions
��+1.818
ット+1.375
Line+1.365
�醒+1.351
uez+1.340
Neg logit contributions
iaries-1.457
acas-1.414
OTOS-1.345
ruary-1.322
mitt-1.294
Token,
Token ID11
Feature activation-1.22e+00

Pos logit contributions
iaries+0.184
acas+0.179
OTOS+0.170
ruary+0.167
mitt+0.165
Neg logit contributions
��-0.226
ット-0.170
Line-0.169
�醒-0.167
uez-0.166
Token Allen
Token ID9659
Feature activation-2.03e+00

Pos logit contributions
��+1.006
ット+0.756
Line+0.755
�醒+0.744
uez+0.740
Neg logit contributions
iaries-0.831
acas-0.809
OTOS-0.767
ruary-0.755
mitt-0.742
Token H
Token ID367
Feature activation-1.40e+01

Pos logit contributions
��+1.786
ット+1.365
Line+1.361
�醒+1.350
uez+1.341
Neg logit contributions
iaries-1.273
acas-1.235
OTOS-1.173
ruary-1.148
mitt-1.121
Tokenurn
Token ID700
Feature activation+4.99e-01

Pos logit contributions
��+4.879
uez+3.806
Line+3.747
uce+3.487
ット+3.369
Neg logit contributions
iaries-13.671
 "$:/-13.649
acas-13.434
OTOS-13.400
ashtra-12.986
Tokens
Token ID82
Feature activation+1.48e+00

Pos logit contributions
iaries+0.313
acas+0.308
OTOS+0.289
ruary+0.285
mitt+0.283
Neg logit contributions
��-0.443
ット-0.335
�醒-0.332
Line-0.331
���-0.329
Token and
Token ID290
Feature activation+2.48e-01

Pos logit contributions
iaries+0.989
acas+0.964
OTOS+0.916
ruary+0.899
mitt+0.888
Neg logit contributions
��-1.256
ット-0.947
Line-0.936
�醒-0.932
uez-0.922
Token Julius
Token ID32834
Feature activation-1.57e+00

Pos logit contributions
iaries+0.167
acas+0.162
OTOS+0.155
ruary+0.152
mitt+0.150
Neg logit contributions
��-0.207
ット-0.156
Line-0.155
�醒-0.153
uez-0.152
Token Thomas
Token ID5658
Feature activation-1.90e+00

Pos logit contributions
��+1.453
ット+1.133
Line+1.131
�醒+1.112
uez+1.111
Neg logit contributions
iaries-0.918
acas-0.882
OTOS-0.832
ruary-0.814
mitt-0.800
Token Irvine
Token ID37277
Feature activation-7.16e-01

Pos logit contributions
��+0.122
ット+0.089
Line+0.088
�醒+0.087
uez+0.087
Neg logit contributions
iaries-0.117
acas-0.114
OTOS-0.109
ruary-0.107
mitt-0.106
Token,
Token ID11
Feature activation-6.92e+00

Pos logit contributions
��+0.596
ット+0.448
Line+0.444
�醒+0.441
uez+0.437
Neg logit contributions
iaries-0.486
acas-0.471
OTOS-0.450
ruary-0.442
mitt-0.435
Token California
Token ID3442
Feature activation-2.30e-01

Pos logit contributions
��+3.717
Line+2.683
uez+2.542
 Younger+2.509
 Cruel+2.494
Neg logit contributions
acas-6.226
iaries-6.149
ruary-5.936
OTOS-5.921
obin-5.881
Token.
Token ID13
Feature activation-1.35e+00

Pos logit contributions
��+0.202
ット+0.154
Line+0.153
�醒+0.152
uez+0.150
Neg logit contributions
iaries-0.147
acas-0.142
OTOS-0.135
ruary-0.132
mitt-0.130
Token Hide
Token ID10415
Feature activation-4.84e+00

Pos logit contributions
��+1.037
ット+0.780
Line+0.778
 Younger+0.759
 Lines+0.758
Neg logit contributions
iaries-0.987
acas-0.956
OTOS-0.909
ruary-0.895
imore-0.889
Token Caption
Token ID11260
Feature activation-1.40e+01

Pos logit contributions
��+2.579
Line+1.859
ット+1.802
 Younger+1.774
 Lines+1.742
Neg logit contributions
iaries-4.476
acas-4.401
ruary-4.209
OTOS-4.199
imore-4.159
Token 9
Token ID860
Feature activation+1.17e-01

Pos logit contributions
Line+4.960
��+4.916
 Lines+4.817
 Cruel+4.449
 Younger+4.257
Neg logit contributions
iaries-12.822
ashtra-12.291
acas-12.281
ruary-12.202
imore-12.065
Token of
Token ID286
Feature activation-4.17e+00

Pos logit contributions
iaries+0.077
acas+0.075
OTOS+0.071
ruary+0.070
mitt+0.069
Neg logit contributions
��-0.098
ット-0.075
Line-0.075
uez-0.073
�醒-0.073
Token 15
Token ID1315
Feature activation-4.36e+00

Pos logit contributions
��+3.074
Line+2.465
 Younger+2.393
ット+2.364
 Lines+2.312
Neg logit contributions
iaries-3.004
acas-2.927
ruary-2.769
OTOS-2.753
ashtra-2.718
Token Photos
Token ID9434
Feature activation-1.34e+00

Pos logit contributions
��+3.381
Line+2.771
 Lines+2.741
 Younger+2.718
ット+2.706
Neg logit contributions
iaries-2.955
acas-2.811
ruary-2.704
ashtra-2.631
imore-2.589
Token:
Token ID25
Feature activation-6.86e+00

Pos logit contributions
��+1.121
Line+0.888
ット+0.874
uez+0.860
 Younger+0.855
Neg logit contributions
iaries-0.873
acas-0.847
OTOS-0.793
ruary-0.791
imore-0.768
Token ]
Token ID2361
Feature activation+1.66e+00

Pos logit contributions
iaries+0.764
acas+0.739
OTOS+0.700
ruary+0.683
mitt+0.673
Neg logit contributions
��-1.264
ット-0.975
�醒-0.972
���-0.968
Line-0.963
Token
Token ID198
Feature activation+1.97e-01

Pos logit contributions
iaries+1.002
acas+0.974
OTOS+0.925
ruary+0.903
mitt+0.894
Neg logit contributions
��-1.522
�醒-1.160
ット-1.160
���-1.159
Line-1.137
Token
Token ID198
Feature activation+2.12e-04

Pos logit contributions
iaries+0.126
acas+0.122
OTOS+0.116
ruary+0.114
mitt+0.112
Neg logit contributions
��-0.170
ット-0.131
Line-0.130
uez-0.128
�醒-0.128
TokenGeneral
Token ID12218
Feature activation-2.93e+00

Pos logit contributions
iaries+0.000
acas+0.000
OTOS+0.000
ruary+0.000
mitt+0.000
Neg logit contributions
��-0.000
ット-0.000
Line-0.000
�醒-0.000
uez-0.000
Token Ge
Token ID2269
Feature activation-1.78e+00

Pos logit contributions
��+2.275
ット+1.719
Line+1.695
uez+1.673
 Younger+1.656
Neg logit contributions
iaries-2.088
acas-2.047
OTOS-1.953
ruary-1.916
imore-1.898
Tokenor
Token ID273
Feature activation-1.39e+01

Pos logit contributions
��+1.389
uez+1.062
Line+1.049
ット+1.044
 Younger+1.014
Neg logit contributions
iaries-1.254
acas-1.202
OTOS-1.187
 "$:/-1.145
ruary-1.137
Tokengy
Token ID1360
Feature activation-6.45e-01

Pos logit contributions
��+7.809
uez+6.103
 Younger+5.718
Line+5.679
 Lines+5.579
Neg logit contributions
iaries-11.511
OTOS-10.984
acas-10.735
ruary-10.252
 "$:/-10.200
Token Zh
Token ID10511
Feature activation-1.19e+00

Pos logit contributions
��+0.510
ット+0.378
Line+0.375
uez+0.371
�醒+0.369
Neg logit contributions
iaries-0.464
acas-0.451
OTOS-0.431
ruary-0.424
mitt-0.417
Tokenuk
Token ID2724
Feature activation+4.86e-01

Pos logit contributions
��+0.762
Line+0.525
uez+0.525
ット+0.525
�醒+0.502
Neg logit contributions
iaries-1.024
acas-0.990
OTOS-0.963
ruary-0.946
 "$:/-0.929
Tokenov
Token ID709
Feature activation-9.60e-01

Pos logit contributions
iaries+0.286
acas+0.277
OTOS+0.262
ruary+0.256
mitt+0.252
Neg logit contributions
��-0.449
ット-0.349
Line-0.346
�醒-0.343
uez-0.341
Token speaking
Token ID5486
Feature activation-5.72e-01

Pos logit contributions
��+0.798
ット+0.601
Line+0.598
uez+0.589
�醒+0.585
Neg logit contributions
iaries-0.650
acas-0.633
OTOS-0.602
ruary-0.590
mitt-0.581
Token States
Token ID1829
Feature activation-2.41e-01

Pos logit contributions
iaries+0.544
acas+0.529
OTOS+0.505
ruary+0.495
mitt+0.490
Neg logit contributions
��-0.642
ット-0.477
�醒-0.471
Line-0.470
���-0.465
Token.
Token ID13
Feature activation-4.12e+00

Pos logit contributions
��+0.208
ット+0.158
Line+0.157
�醒+0.155
uez+0.154
Neg logit contributions
iaries-0.157
acas-0.152
OTOS-0.145
ruary-0.142
mitt-0.140
Token
Token ID851
Feature activation+1.17e+00

Pos logit contributions
��+3.103
Line+2.325
ット+2.307
 Younger+2.294
 Lines+2.266
Neg logit contributions
iaries-3.045
acas-2.952
OTOS-2.783
ruary-2.769
imore-2.728
Token ACLU
Token ID24381
Feature activation+9.74e-01

Pos logit contributions
iaries+0.923
acas+0.903
OTOS+0.866
ruary+0.852
mitt+0.842
Neg logit contributions
��-0.848
ット-0.604
Line-0.597
�醒-0.591
uez-0.586
Token of
Token ID286
Feature activation+3.13e-02

Pos logit contributions
iaries+0.627
acas+0.609
OTOS+0.579
ruary+0.567
mitt+0.559
Neg logit contributions
��-0.847
ット-0.645
Line-0.639
�醒-0.634
uez-0.629
Token Oregon
Token ID8819
Feature activation-1.39e+01

Pos logit contributions
iaries+0.024
acas+0.023
OTOS+0.022
ruary+0.022
mitt+0.022
Neg logit contributions
��-0.023
ット-0.017
Line-0.017
�醒-0.016
uez-0.016
Token (@
Token ID4275
Feature activation+9.21e-02

Pos logit contributions
��+4.624
ット+3.693
Line+3.576
 Younger+3.463
 Lines+3.456
Neg logit contributions
iaries-13.651
acas-13.087
ashtra-12.759
ruary-12.519
obin-12.408
TokenAC
Token ID2246
Feature activation-1.52e+00

Pos logit contributions
iaries+0.071
acas+0.069
OTOS+0.066
ruary+0.065
mitt+0.064
Neg logit contributions
��-0.068
ット-0.049
Line-0.049
�醒-0.048
uez-0.048
TokenLU
Token ID41596
Feature activation+1.22e-02

Pos logit contributions
��+1.195
Line+0.900
ット+0.891
uez+0.877
+0.866
Neg logit contributions
iaries-1.101
acas-1.066
OTOS-1.014
ruary-1.002
mitt-0.980
Token_
Token ID62
Feature activation-5.81e+00

Pos logit contributions
iaries+0.009
acas+0.008
OTOS+0.008
ruary+0.008
mitt+0.008
Neg logit contributions
��-0.010
ット-0.007
Line-0.007
uez-0.007
�醒-0.007
TokenOR
Token ID1581
Feature activation-4.92e+00

Pos logit contributions
��+2.710
Line+2.040
ット+1.819
+1.769
uez+1.681
Neg logit contributions
iaries-5.750
acas-5.687
ruary-5.397
umbn-5.229
imore-5.195
Token scientists
Token ID5519
Feature activation+1.54e+00

Pos logit contributions
iaries+1.602
acas+1.560
OTOS+1.490
ruary+1.451
mitt+1.439
Neg logit contributions
��-1.918
ット-1.435
�醒-1.412
Line-1.410
uez-1.391
Token at
Token ID379
Feature activation+9.56e-01

Pos logit contributions
iaries+1.050
acas+1.022
OTOS+0.975
ruary+0.956
mitt+0.944
Neg logit contributions
��-1.273
ット-0.953
Line-0.942
�醒-0.940
uez-0.927
Token the
Token ID262
Feature activation-3.26e-01

Pos logit contributions
iaries+0.628
acas+0.610
OTOS+0.581
ruary+0.568
mitt+0.561
Neg logit contributions
��-0.820
ット-0.620
Line-0.614
�醒-0.612
uez-0.604
Token American
Token ID1605
Feature activation-3.16e+00

Pos logit contributions
��+0.289
ット+0.221
Line+0.219
�醒+0.217
uez+0.216
Neg logit contributions
iaries-0.205
acas-0.199
OTOS-0.189
ruary-0.185
mitt-0.183
Token Museum
Token ID9594
Feature activation-4.93e+00

Pos logit contributions
��+2.702
Line+2.051
ット+2.041
uez+2.027
�醒+2.009
Neg logit contributions
iaries-2.064
acas-2.003
OTOS-1.894
ruary-1.881
imore-1.829
Token of
Token ID286
Feature activation-1.36e+01

Pos logit contributions
��+3.894
Line+2.863
ット+2.851
 Younger+2.842
 Lines+2.807
Neg logit contributions
iaries-3.466
acas-3.436
OTOS-3.218
ruary-3.198
mitt-3.166
Token Natural
Token ID12068
Feature activation-2.80e+00

Pos logit contributions
��+4.370
 Lines+2.684
 Younger+2.659
Line+2.541
 Cruel+2.457
Neg logit contributions
iaries-14.588
ruary-13.931
acas-13.887
obin-13.812
ashtra-13.693
Token History
Token ID7443
Feature activation-8.39e+00

Pos logit contributions
��+2.465
ット+1.904
Line+1.891
�醒+1.867
uez+1.862
Neg logit contributions
iaries-1.732
acas-1.699
OTOS-1.598
ruary-1.584
mitt-1.562
Token (
Token ID357
Feature activation+1.50e+00

Pos logit contributions
��+5.925
Line+4.362
 Younger+4.308
uez+4.228
 Lines+4.224
Neg logit contributions
iaries-6.313
acas-6.159
ruary-5.728
OTOS-5.717
 "$:/-5.691
Tokenwhich
Token ID4758
Feature activation-4.27e+00

Pos logit contributions
iaries+0.836
acas+0.825
OTOS+0.779
mitt+0.749
ruary+0.748
Neg logit contributions
��-1.421
ット-1.109
�醒-1.096
Line-1.089
uez-1.088
Token houses
Token ID7777
Feature activation-4.65e+00

Pos logit contributions
��+3.262
ット+2.423
Line+2.388
uez+2.367
���+2.363
Neg logit contributions
iaries-3.043
acas-3.012
OTOS-2.856
ruary-2.778
mitt-2.770
Token
Token ID851
Feature activation+3.89e+00

Pos logit contributions
��+1.684
Line+1.255
ット+1.252
 Younger+1.222
 Lines+1.220
Neg logit contributions
iaries-1.586
acas-1.544
OTOS-1.462
ruary-1.443
mitt-1.427
Token Ren
Token ID7152
Feature activation+1.56e+00

Pos logit contributions
iaries+2.494
acas+2.445
OTOS+2.330
ruary+2.263
mitt+2.239
Neg logit contributions
��-3.352
ット-2.546
�醒-2.504
Line-2.486
uez-2.474
Tokenaud
Token ID3885
Feature activation+3.28e-02

Pos logit contributions
iaries+1.289
acas+1.262
OTOS+1.213
ruary+1.194
mitt+1.181
Neg logit contributions
��-1.068
ット-0.744
Line-0.734
�醒-0.729
uez-0.719
Token Lav
Token ID21438
Feature activation+1.40e+00

Pos logit contributions
iaries+0.014
acas+0.013
OTOS+0.012
ruary+0.012
mitt+0.012
Neg logit contributions
��-0.035
ット-0.029
Line-0.029
uez-0.028
�醒-0.028
Tokeno
Token ID78
Feature activation-4.34e+00

Pos logit contributions
iaries+0.969
acas+0.944
OTOS+0.901
ruary+0.882
mitt+0.872
Neg logit contributions
��-1.147
ット-0.854
Line-0.843
�醒-0.843
���-0.833
Tokenie
Token ID494
Feature activation-1.35e+01

Pos logit contributions
��+2.296
Line+1.644
uez+1.587
ット+1.556
 Younger+1.497
Neg logit contributions
iaries-3.989
acas-3.920
ruary-3.789
OTOS-3.772
ashtra-3.686
Token (@
Token ID4275
Feature activation+3.04e+00

Pos logit contributions
��+4.339
Line+3.828
 Younger+3.411
ット+3.382
 Lines+3.376
Neg logit contributions
iaries-13.513
acas-12.839
ashtra-12.644
ruary-12.560
izoph-12.278
Tokenren
Token ID918
Feature activation+3.68e+00

Pos logit contributions
iaries+2.403
acas+2.362
OTOS+2.240
mitt+2.223
ruary+2.219
Neg logit contributions
��-2.222
���-1.597
ット-1.569
�醒-1.563
ーテ-1.530
Tokenlav
Token ID18809
Feature activation+7.20e-01

Pos logit contributions
iaries+1.676
acas+1.640
OTOS+1.494
mitt+1.458
ruary+1.457
Neg logit contributions
��-3.933
���-3.196
�醒-3.146
ット-3.117
ーテ-3.109
Tokeno
Token ID78
Feature activation-1.78e+00

Pos logit contributions
iaries+0.509
acas+0.495
OTOS+0.474
ruary+0.466
mitt+0.458
Neg logit contributions
��-0.577
ット-0.430
Line-0.427
uez-0.421
�醒-0.420
Tokeniet
Token ID1155
Feature activation-4.35e+00

Pos logit contributions
��+1.504
Line+1.155
ット+1.151
uez+1.146
�醒+1.121
Neg logit contributions
iaries-1.156
acas-1.124
OTOS-1.079
ruary-1.053
 "$:/-1.024
Token#
Token ID2
Feature activation-2.99e+00

Pos logit contributions
��+2.250
Line+1.695
ット+1.676
�醒+1.637
uez+1.633
Neg logit contributions
iaries-2.025
acas-1.939
OTOS-1.850
ruary-1.835
mitt-1.800
Token ==
Token ID6624
Feature activation-1.97e+00

Pos logit contributions
��+2.101
Line+1.516
ット+1.506
uez+1.466
�醒+1.466
Neg logit contributions
iaries-2.404
acas-2.315
OTOS-2.209
ruary-2.184
mitt-2.169
Token "
Token ID366
Feature activation-2.52e+00

Pos logit contributions
��+1.616
ット+1.213
Line+1.210
�醒+1.194
uez+1.182
Neg logit contributions
iaries-1.367
acas-1.323
OTOS-1.257
ruary-1.233
mitt-1.229
TokenE
Token ID36
Feature activation-3.38e+00

Pos logit contributions
��+1.988
Line+1.506
ット+1.480
uez+1.461
�醒+1.451
Neg logit contributions
iaries-1.809
acas-1.738
OTOS-1.658
ruary-1.645
mitt-1.606
Token"
Token ID1
Feature activation-6.13e+00

Pos logit contributions
��+2.789
Line+2.106
ット+2.082
�醒+2.059
uez+2.044
Neg logit contributions
iaries-2.323
acas-2.223
OTOS-2.117
ruary-2.072
mitt-2.048
Token ||
Token ID8614
Feature activation-1.34e+01

Pos logit contributions
��+4.358
Line+3.300
ット+3.229
�醒+3.151
 Lines+3.116
Neg logit contributions
iaries-4.791
acas-4.545
OTOS-4.326
mitt-4.248
ruary-4.216
Token #
Token ID1303
Feature activation-3.98e+00

Pos logit contributions
��+6.566
 Lines+4.529
Line+4.493
ット+4.304
�醒+4.298
Neg logit contributions
iaries-12.225
acas-11.544
mitt-11.263
ruary-11.145
imore-11.003
Token ==
Token ID6624
Feature activation-3.44e+00

Pos logit contributions
��+2.250
ット+1.572
Line+1.572
uez+1.515
 Lines+1.498
Neg logit contributions
iaries-3.655
acas-3.534
ruary-3.365
OTOS-3.363
mitt-3.304
Token "
Token ID366
Feature activation-1.79e+00

Pos logit contributions
��+2.583
Line+2.022
ット+1.984
 Younger+1.949
uez+1.942
Neg logit contributions
iaries-2.532
acas-2.446
OTOS-2.317
ruary-2.300
imore-2.252
TokenA
Token ID32
Feature activation-5.89e+00

Pos logit contributions
��+1.376
Line+1.025
ット+1.013
uez+0.993
�醒+0.992
Neg logit contributions
iaries-1.328
acas-1.285
OTOS-1.225
ruary-1.212
mitt-1.188
Token"
Token ID1
Feature activation-6.02e+00

Pos logit contributions
��+4.213
Line+3.465
ット+3.263
uez+3.215
+3.153
Neg logit contributions
iaries-4.407
acas-4.220
ruary-3.964
OTOS-3.939
ashtra-3.851
Token P
Token ID350
Feature activation-3.31e+00

Pos logit contributions
iaries+0.062
acas+0.061
OTOS+0.058
ruary+0.057
mitt+0.056
Neg logit contributions
��-0.073
ット-0.054
Line-0.054
�醒-0.053
uez-0.053
Token217
Token ID24591
Feature activation-1.72e+00

Pos logit contributions
��+2.598
Line+1.940
ット+1.940
uez+1.913
�醒+1.870
Neg logit contributions
iaries-2.345
acas-2.288
OTOS-2.189
ruary-2.143
mitt-2.114
Token Gibson
Token ID20400
Feature activation+4.66e+00

Pos logit contributions
��+1.388
ット+1.037
Line+1.036
uez+1.018
�醒+1.013
Neg logit contributions
iaries-1.220
acas-1.178
OTOS-1.129
ruary-1.105
mitt-1.086
Token of
Token ID286
Feature activation-8.40e-01

Pos logit contributions
iaries+2.908
acas+2.872
OTOS+2.714
ruary+2.667
mitt+2.639
Neg logit contributions
��-4.061
ット-3.064
�醒-3.063
���-3.014
Line-2.965
Token United
Token ID1578
Feature activation+2.09e-01

Pos logit contributions
��+0.695
ット+0.524
Line+0.521
uez+0.512
�醒+0.511
Neg logit contributions
iaries-0.573
acas-0.555
OTOS-0.531
ruary-0.518
mitt-0.512
Token Aut
Token ID5231
Feature activation-1.31e+01

Pos logit contributions
iaries+0.140
acas+0.136
OTOS+0.130
ruary+0.127
mitt+0.125
Neg logit contributions
��-0.175
ット-0.133
Line-0.132
�醒-0.130
uez-0.130
Tokenos
Token ID418
Feature activation-6.15e+00

Pos logit contributions
��+8.224
uez+7.121
 Lines+6.988
Line+6.859
uce+6.665
Neg logit contributions
OTOS-8.405
 "$:/-8.333
iaries-8.319
ruary-8.140
acas-7.939
Tokenports
Token ID3742
Feature activation-2.52e+00

Pos logit contributions
��+6.617
Line+5.485
 Lines+5.451
uez+5.450
ット+5.404
Neg logit contributions
iaries-2.420
acas-2.205
OTOS-2.116
 "$:/-2.039
ruary-2.021
Token in
Token ID287
Feature activation-2.52e+00

Pos logit contributions
��+2.050
Line+1.555
ット+1.551
uez+1.518
 Lines+1.508
Neg logit contributions
iaries-1.734
acas-1.677
OTOS-1.612
ruary-1.571
 "$:/-1.544
Token fifth
Token ID8150
Feature activation+1.09e+00

Pos logit contributions
��+1.952
Line+1.458
ット+1.453
uez+1.421
�醒+1.399
Neg logit contributions
iaries-1.835
acas-1.764
OTOS-1.701
ruary-1.670
mitt-1.643
Token.
Token ID13
Feature activation+4.25e-01

Pos logit contributions
iaries+0.747
acas+0.728
OTOS+0.695
ruary+0.681
mitt+0.671
Neg logit contributions
��-0.900
ット-0.672
�醒-0.663
Line-0.662
���-0.654
Token the
Token ID262
Feature activation+1.21e-01

Pos logit contributions
��+0.763
Line+0.574
ット+0.573
uez+0.562
�醒+0.559
Neg logit contributions
iaries-0.662
acas-0.642
OTOS-0.612
ruary-0.603
mitt-0.588
Token NFL
Token ID5134
Feature activation-3.87e+00

Pos logit contributions
iaries+0.088
acas+0.085
OTOS+0.082
ruary+0.080
mitt+0.079
Neg logit contributions
��-0.094
ット-0.070
Line-0.069
�醒-0.068
uez-0.068
Token Commissioner
Token ID13270
Feature activation-3.35e-01

Pos logit contributions
��+2.991
Line+2.316
ット+2.259
uez+2.229
 Lines+2.219
Neg logit contributions
iaries-2.734
acas-2.668
OTOS-2.533
ruary-2.483
imore-2.441
Token as
Token ID355
Feature activation-3.94e+00

Pos logit contributions
��+0.279
ット+0.210
Line+0.208
�醒+0.207
uez+0.205
Neg logit contributions
iaries-0.227
acas-0.221
OTOS-0.210
ruary-0.206
mitt-0.203
Token judge
Token ID5052
Feature activation+8.23e-01

Pos logit contributions
��+3.020
Line+2.206
ット+2.198
�醒+2.156
 Younger+2.151
Neg logit contributions
iaries-2.853
acas-2.823
OTOS-2.693
ruary-2.666
aceae-2.601
Token,
Token ID11
Feature activation-1.31e+01

Pos logit contributions
iaries+0.546
acas+0.531
OTOS+0.505
ruary+0.495
mitt+0.489
Neg logit contributions
��-0.699
ット-0.528
Line-0.523
�醒-0.519
uez-0.515
Token jury
Token ID9002
Feature activation-1.86e+00

Pos logit contributions
��+7.066
�醒+4.982
Line+4.877
 Younger+4.857
 Lines+4.845
Neg logit contributions
acas-11.156
iaries-10.978
OTOS-10.639
aceae-10.397
obin-10.285
Token,
Token ID11
Feature activation-3.20e+00

Pos logit contributions
��+1.508
ット+1.118
�醒+1.110
Line+1.108
uez+1.079
Neg logit contributions
iaries-1.311
acas-1.278
OTOS-1.230
ruary-1.204
flush-1.177
Token execution
Token ID9706
Feature activation-2.01e+00

Pos logit contributions
��+2.516
Line+1.863
ット+1.856
�醒+1.850
uez+1.819
Neg logit contributions
iaries-2.281
acas-2.240
OTOS-2.140
ruary-2.097
mitt-2.062
Tokenor
Token ID273
Feature activation-2.29e+00

Pos logit contributions
��+1.649
ット+1.232
Line+1.227
�醒+1.219
uez+1.205
Neg logit contributions
iaries-1.388
acas-1.354
OTOS-1.296
ruary-1.271
mitt-1.251
Token,
Token ID11
Feature activation-3.03e+00

Pos logit contributions
��+1.846
ット+1.369
Line+1.366
�醒+1.360
uez+1.336
Neg logit contributions
iaries-1.596
acas-1.562
OTOS-1.494
ruary-1.464
mitt-1.439
Token know
Token ID760
Feature activation+1.93e+00

Pos logit contributions
��+0.583
ット+0.427
Line+0.426
uez+0.419
�醒+0.419
Neg logit contributions
iaries-0.559
acas-0.544
OTOS-0.523
ruary-0.513
mitt-0.507
Token choose
Token ID3853
Feature activation+1.43e+00

Pos logit contributions
iaries+1.306
acas+1.277
OTOS+1.212
ruary+1.190
mitt+1.177
Neg logit contributions
��-1.610
ット-1.206
�醒-1.196
Line-1.189
���-1.173
Token )
Token ID1267
Feature activation+1.71e+00

Pos logit contributions
iaries+0.980
acas+0.955
OTOS+0.910
ruary+0.891
mitt+0.882
Neg logit contributions
��-1.188
ット-0.891
Line-0.880
�醒-0.877
uez-0.866
Token
Token ID198
Feature activation-9.62e-01

Pos logit contributions
iaries+1.142
acas+1.114
OTOS+1.061
ruary+1.039
mitt+1.026
Neg logit contributions
��-1.444
ット-1.085
�醒-1.071
Line-1.071
���-1.057
Token
Token ID198
Feature activation-3.84e+00

Pos logit contributions
��+0.806
Line+0.625
ット+0.622
uez+0.608
 Younger+0.603
Neg logit contributions
iaries-0.639
acas-0.618
OTOS-0.583
ruary-0.579
mitt-0.562
Token(
Token ID7
Feature activation-1.31e+01

Pos logit contributions
��+3.141
Line+2.437
ット+2.405
�醒+2.317
uez+2.295
Neg logit contributions
iaries-2.622
acas-2.531
ruary-2.410
OTOS-2.394
mitt-2.314
TokenExample
Token ID16281
Feature activation-3.77e+00

Pos logit contributions
��+6.263
Line+4.513
ット+3.930
 Lines+3.661
 Younger+3.657
Neg logit contributions
iaries-11.726
acas-11.460
ruary-11.452
OTOS-11.158
mitt-11.046
Token:
Token ID25
Feature activation-1.28e+01

Pos logit contributions
��+2.946
Line+2.378
ット+2.312
 Younger+2.286
uez+2.277
Neg logit contributions
iaries-2.602
acas-2.506
ruary-2.389
OTOS-2.348
ashtra-2.290
Token Your
Token ID3406
Feature activation-5.35e+00

Pos logit contributions
��+7.073
 Younger+4.892
ット+4.867
 Lines+4.821
 Cruel+4.758
Neg logit contributions
iaries-10.825
acas-10.784
ruary-10.372
mitt-10.273
obin-10.104
Token +
Token ID1343
Feature activation-4.26e+00

Pos logit contributions
��+4.071
Line+3.089
ット+3.066
 reflex+2.969
uez+2.937
Neg logit contributions
iaries-3.905
acas-3.773
ruary-3.569
OTOS-3.543
mitt-3.476
Token1
Token ID16
Feature activation-1.03e+00

Pos logit contributions
��+2.856
Line+2.230
ット+2.165
uez+2.151
 Younger+2.056
Neg logit contributions
iaries-3.381
acas-3.257
ruary-3.162
OTOS-3.122
imore-3.017
Token from
Token ID422
Feature activation-9.60e-01

Pos logit contributions
iaries+1.086
acas+1.050
OTOS+0.998
ruary+0.979
mitt+0.964
Neg logit contributions
��-1.525
ット-1.159
Line-1.152
�醒-1.151
uez-1.138
Token the
Token ID262
Feature activation+5.68e-02

Pos logit contributions
��+0.794
ット+0.598
Line+0.592
uez+0.585
�醒+0.584
Neg logit contributions
iaries-0.656
acas-0.636
OTOS-0.607
ruary-0.595
mitt-0.587
Token National
Token ID2351
Feature activation+1.94e+00

Pos logit contributions
iaries+0.040
acas+0.039
OTOS+0.037
ruary+0.036
mitt+0.036
Neg logit contributions
��-0.046
ット-0.034
Line-0.034
�醒-0.034
uez-0.034
Token Ocean
Token ID10692
Feature activation-2.25e+00

Pos logit contributions
iaries+1.195
acas+1.141
OTOS+1.100
ruary+1.062
mitt+1.060
Neg logit contributions
��-1.777
�醒-1.342
ット-1.334
���-1.326
Line-1.305
Tokenic
Token ID291
Feature activation-1.51e+00

Pos logit contributions
��+1.935
ット+1.492
Line+1.480
�醒+1.466
uez+1.434
Neg logit contributions
iaries-1.448
acas-1.416
OTOS-1.341
ruary-1.321
mitt-1.288
Token and
Token ID290
Feature activation-1.31e+01

Pos logit contributions
��+1.227
ット+0.925
Line+0.915
�醒+0.903
uez+0.894
Neg logit contributions
iaries-1.049
acas-1.021
OTOS-0.973
ruary-0.959
mitt-0.942
Token Atmospheric
Token ID41516
Feature activation-5.79e+00

Pos logit contributions
��+5.095
ット+4.194
 Lines+4.091
 Younger+3.892
 Cruel+3.771
Neg logit contributions
iaries-13.044
acas-12.370
OTOS-12.034
imore-12.003
ruary-11.977
Token Administration
Token ID8694
Feature activation-1.95e+00

Pos logit contributions
��+4.454
Line+3.562
ット+3.538
 Lines+3.490
uez+3.472
Neg logit contributions
iaries-3.962
acas-3.840
ruary-3.666
OTOS-3.612
mitt-3.543
Token
Token ID447
Feature activation-3.75e+00

Pos logit contributions
��+1.608
ット+1.212
Line+1.203
uez+1.190
�醒+1.182
Neg logit contributions
iaries-1.332
acas-1.298
OTOS-1.226
ruary-1.207
mitt-1.192
Token
Token ID247
Feature activation-3.96e+00

Pos logit contributions
��+2.523
ット+1.668
�醒+1.644
Line+1.621
uez+1.590
Neg logit contributions
iaries-3.256
acas-3.174
OTOS-3.044
ruary-2.981
mitt-2.950
Tokens
Token ID82
Feature activation-8.06e-01

Pos logit contributions
��+3.157
ット+2.409
Line+2.400
uez+2.378
�醒+2.315
Neg logit contributions
iaries-2.739
acas-2.672
OTOS-2.550
ruary-2.469
imore-2.460
Token but
Token ID475
Feature activation+6.83e-01

Pos logit contributions
iaries+0.937
acas+0.912
OTOS+0.870
ruary+0.854
mitt+0.846
Neg logit contributions
��-1.065
ット-0.790
�醒-0.779
Line-0.779
uez-0.768
Token
Token ID1399
Feature activation-2.67e+00

Pos logit contributions
iaries+0.473
acas+0.462
OTOS+0.440
ruary+0.431
mitt+0.427
Neg logit contributions
��-0.559
ット-0.419
�醒-0.412
Line-0.412
uez-0.405
Token
Token ID851
Feature activation+4.25e-01

Pos logit contributions
��+2.194
Line+1.645
ット+1.635
�醒+1.613
uez+1.612
Neg logit contributions
iaries-1.833
acas-1.759
OTOS-1.682
ruary-1.658
mitt-1.613
Token ACLU
Token ID24381
Feature activation+1.19e+00

Pos logit contributions
iaries+0.310
acas+0.302
OTOS+0.289
ruary+0.284
mitt+0.280
Neg logit contributions
��-0.333
ット-0.244
Line-0.242
�醒-0.240
uez-0.238
Token of
Token ID286
Feature activation+1.66e+00

Pos logit contributions
iaries+0.770
acas+0.748
OTOS+0.712
ruary+0.697
mitt+0.687
Neg logit contributions
��-1.023
ット-0.778
Line-0.770
�醒-0.765
uez-0.759
Token Oregon
Token ID8819
Feature activation-1.30e+01

Pos logit contributions
iaries+1.230
acas+1.201
OTOS+1.149
ruary+1.128
mitt+1.117
Neg logit contributions
��-1.286
ット-0.937
Line-0.927
�醒-0.925
uez-0.909
Token (@
Token ID4275
Feature activation+5.11e-01

Pos logit contributions
��+5.163
Line+3.753
 Lines+3.647
 Cruel+3.602
ット+3.600
Neg logit contributions
iaries-12.446
acas-11.961
ruary-11.547
ashtra-11.454
obin-11.303
TokenAC
Token ID2246
Feature activation-5.34e-01

Pos logit contributions
iaries+0.390
acas+0.381
OTOS+0.365
ruary+0.359
mitt+0.355
Neg logit contributions
��-0.382
ット-0.276
Line-0.273
�醒-0.271
uez-0.268
TokenLU
Token ID41596
Feature activation+5.99e-01

Pos logit contributions
��+0.434
ット+0.324
Line+0.323
�醒+0.317
uez+0.317
Neg logit contributions
iaries-0.373
acas-0.363
OTOS-0.345
ruary-0.340
mitt-0.334
Token_
Token ID62
Feature activation-5.93e+00

Pos logit contributions
iaries+0.419
acas+0.408
OTOS+0.389
ruary+0.382
mitt+0.377
Neg logit contributions
��-0.486
ット-0.363
Line-0.360
�醒-0.356
uez-0.354
TokenOR
Token ID1581
Feature activation-6.60e+00

Pos logit contributions
��+2.857
Line+2.078
ット+1.900
+1.804
uez+1.783
Neg logit contributions
iaries-5.816
acas-5.734
ruary-5.445
imore-5.282
umbn-5.249
Token line
Token ID1627
Feature activation+1.01e+00

Pos logit contributions
iaries+2.336
acas+2.292
OTOS+2.194
ruary+2.174
mitt+2.138
Neg logit contributions
��-1.730
ット-1.200
���-1.159
�醒-1.157
uez-1.130
Token.
Token ID13
Feature activation-3.05e+00

Pos logit contributions
iaries+0.639
acas+0.622
OTOS+0.589
ruary+0.578
mitt+0.569
Neg logit contributions
��-0.883
ット-0.674
Line-0.667
�醒-0.664
uez-0.658
Token
Token ID851
Feature activation+8.42e-01

Pos logit contributions
��+2.340
ット+1.728
Line+1.726
 Younger+1.694
�醒+1.687
Neg logit contributions
iaries-2.255
acas-2.183
OTOS-2.074
ruary-2.057
mitt-2.022
Token ACLU
Token ID24381
Feature activation+4.82e-01

Pos logit contributions
iaries+0.670
acas+0.655
OTOS+0.629
ruary+0.619
mitt+0.612
Neg logit contributions
��-0.603
ット-0.428
Line-0.423
�醒-0.419
uez-0.415
Token of
Token ID286
Feature activation+7.87e-01

Pos logit contributions
iaries+0.316
acas+0.307
OTOS+0.291
ruary+0.286
mitt+0.281
Neg logit contributions
��-0.412
ット-0.314
Line-0.312
�醒-0.307
uez-0.306
Token Oregon
Token ID8819
Feature activation-1.29e+01

Pos logit contributions
iaries+0.594
acas+0.580
OTOS+0.555
ruary+0.545
mitt+0.540
Neg logit contributions
��-0.597
ット-0.432
Line-0.427
�醒-0.426
uez-0.420
Token (@
Token ID4275
Feature activation+9.19e-02

Pos logit contributions
��+4.535
ット+3.639
Line+3.512
 Younger+3.408
 Lines+3.369
Neg logit contributions
iaries-12.657
acas-12.131
ashtra-11.818
ruary-11.615
obin-11.489
TokenAC
Token ID2246
Feature activation-1.66e+00

Pos logit contributions
iaries+0.071
acas+0.069
OTOS+0.066
ruary+0.065
mitt+0.064
Neg logit contributions
��-0.068
ット-0.049
Line-0.049
�醒-0.048
uez-0.048
TokenLU
Token ID41596
Feature activation-1.62e-01

Pos logit contributions
��+1.294
Line+0.978
ット+0.966
uez+0.950
+0.939
Neg logit contributions
iaries-1.206
acas-1.166
OTOS-1.108
ruary-1.096
mitt-1.071
Token_
Token ID62
Feature activation-5.74e+00

Pos logit contributions
��+0.129
ット+0.096
Line+0.096
uez+0.094
�醒+0.093
Neg logit contributions
iaries-0.115
acas-0.112
OTOS-0.107
ruary-0.105
mitt-0.103
TokenOR
Token ID1581
Feature activation-4.97e+00

Pos logit contributions
��+2.677
Line+2.027
ット+1.805
+1.764
uez+1.668
Neg logit contributions
iaries-5.692
acas-5.612
ruary-5.335
umbn-5.169
imore-5.128
Token )
Token ID1267
Feature activation+1.71e+00

Pos logit contributions
iaries+0.980
acas+0.955
OTOS+0.910
ruary+0.891
mitt+0.882
Neg logit contributions
��-1.188
ット-0.891
Line-0.880
�醒-0.877
uez-0.866
Token
Token ID198
Feature activation-9.62e-01

Pos logit contributions
iaries+1.142
acas+1.114
OTOS+1.061
ruary+1.039
mitt+1.026
Neg logit contributions
��-1.444
ット-1.085
�醒-1.071
Line-1.071
���-1.057
Token
Token ID198
Feature activation-3.84e+00

Pos logit contributions
��+0.806
Line+0.625
ット+0.622
uez+0.608
 Younger+0.603
Neg logit contributions
iaries-0.639
acas-0.618
OTOS-0.583
ruary-0.579
mitt-0.562
Token(
Token ID7
Feature activation-1.31e+01

Pos logit contributions
��+3.141
Line+2.437
ット+2.405
�醒+2.317
uez+2.295
Neg logit contributions
iaries-2.622
acas-2.531
ruary-2.410
OTOS-2.394
mitt-2.314
TokenExample
Token ID16281
Feature activation-3.77e+00

Pos logit contributions
��+6.263
Line+4.513
ット+3.930
 Lines+3.661
 Younger+3.657
Neg logit contributions
iaries-11.726
acas-11.460
ruary-11.452
OTOS-11.158
mitt-11.046
Token:
Token ID25
Feature activation-1.28e+01

Pos logit contributions
��+2.946
Line+2.378
ット+2.312
 Younger+2.286
uez+2.277
Neg logit contributions
iaries-2.602
acas-2.506
ruary-2.389
OTOS-2.348
ashtra-2.290
Token Your
Token ID3406
Feature activation-5.35e+00

Pos logit contributions
��+7.073
 Younger+4.892
ット+4.867
 Lines+4.821
 Cruel+4.758
Neg logit contributions
iaries-10.825
acas-10.784
ruary-10.372
mitt-10.273
obin-10.104
Token +
Token ID1343
Feature activation-4.26e+00

Pos logit contributions
��+4.071
Line+3.089
ット+3.066
 reflex+2.969
uez+2.937
Neg logit contributions
iaries-3.905
acas-3.773
ruary-3.569
OTOS-3.543
mitt-3.476
Token1
Token ID16
Feature activation-1.03e+00

Pos logit contributions
��+2.856
Line+2.230
ット+2.165
uez+2.151
 Younger+2.056
Neg logit contributions
iaries-3.381
acas-3.257
ruary-3.162
OTOS-3.122
imore-3.017
Token shield
Token ID7614
Feature activation-2.46e+00

Pos logit contributions
��+0.811
ット+0.608
Line+0.602
uez+0.597
�醒+0.584
Neg logit contributions
iaries-0.734
acas-0.714
OTOS-0.681
ruary-0.673
mitt-0.656
Token keeps
Token ID7622
Feature activation-5.20e+00

Pos logit contributions
��+1.609
Line+1.153
ット+1.121
uez+1.104
 Younger+1.094
Neg logit contributions
iaries-2.049
acas-2.006
OTOS-1.928
ruary-1.913
ashtra-1.875
Token Ad
Token ID1215
Feature activation-1.75e-01

Pos logit contributions
��+2.972
ット+2.203
Line+2.174
�醒+2.172
 Younger+2.156
Neg logit contributions
iaries-2.485
acas-2.417
OTOS-2.327
ruary-2.274
mitt-2.229
Tokenept
Token ID19598
Feature activation+1.48e-01

Pos logit contributions
��+0.180
ット+0.142
Line+0.142
�醒+0.141
uez+0.140
Neg logit contributions
iaries-0.085
acas-0.082
OTOS-0.078
ruary-0.075
 "$:/-0.072
Token
Token ID198
Feature activation+7.17e-01

Pos logit contributions
iaries+0.095
acas+0.092
OTOS+0.087
ruary+0.085
mitt+0.084
Neg logit contributions
��-0.130
ット-0.099
Line-0.098
�醒-0.098
uez-0.097
Token
Token ID198
Feature activation-7.14e-01

Pos logit contributions
iaries+0.456
acas+0.442
OTOS+0.420
ruary+0.412
mitt+0.404
Neg logit contributions
��-0.626
ット-0.480
Line-0.477
�醒-0.470
uez-0.469
TokenEye
Token ID24876
Feature activation-1.52e+00

Pos logit contributions
��+0.593
Line+0.448
ット+0.447
�醒+0.437
uez+0.435
Neg logit contributions
iaries-0.486
acas-0.472
OTOS-0.448
ruary-0.442
mitt-0.432
Token of
Token ID286
Feature activation-1.28e+01

Pos logit contributions
��+1.269
Line+0.957
ット+0.955
uez+0.928
�醒+0.926
Neg logit contributions
iaries-1.033
acas-1.002
OTOS-0.955
ruary-0.945
mitt-0.914
Token Doom
Token ID18688
Feature activation-2.06e+00

Pos logit contributions
��+8.841
 Younger+7.003
 Cruel+6.979
 Lines+6.920
ット+6.788
Neg logit contributions
iaries-8.894
OTOS-8.735
ruary-8.379
acas-8.378
aceae-8.109
Token vs
Token ID3691
Feature activation-3.11e+00

Pos logit contributions
��+1.596
ット+1.184
Line+1.165
�醒+1.150
uez+1.143
Neg logit contributions
iaries-1.513
acas-1.475
OTOS-1.418
ruary-1.377
mitt-1.359
Token Moment
Token ID29278
Feature activation+2.17e+00

Pos logit contributions
��+2.495
Line+1.878
ット+1.872
 Younger+1.854
uez+1.833
Neg logit contributions
iaries-2.155
acas-2.098
OTOS-2.017
ruary-1.982
mitt-1.936
Tokenous
Token ID516
Feature activation+4.93e-01

Pos logit contributions
iaries+1.407
acas+1.368
OTOS+1.298
ruary+1.273
mitt+1.257
Neg logit contributions
��-1.871
ット-1.420
Line-1.406
�醒-1.399
uez-1.383
Token Fall
Token ID7218
Feature activation-2.36e-01

Pos logit contributions
iaries+0.349
acas+0.340
OTOS+0.325
ruary+0.319
mitt+0.315
Neg logit contributions
��-0.396
ット-0.294
Line-0.291
�醒-0.289
uez-0.286
Token on
Token ID319
Feature activation-1.24e+00

Pos logit contributions
iaries+1.734
acas+1.707
OTOS+1.613
mitt+1.585
ruary+1.574
Neg logit contributions
��-2.254
ット-1.697
�醒-1.687
���-1.666
Line-1.662
Token Ubuntu
Token ID14949
Feature activation-9.40e-01

Pos logit contributions
��+0.970
Line+0.716
ット+0.715
uez+0.707
�醒+0.699
Neg logit contributions
iaries-0.899
acas-0.870
OTOS-0.836
ruary-0.818
mitt-0.803
Token above
Token ID2029
Feature activation+3.85e-01

Pos logit contributions
��+0.800
ット+0.605
Line+0.600
�醒+0.594
uez+0.591
Neg logit contributions
iaries-0.623
acas-0.604
OTOS-0.575
ruary-0.564
mitt-0.555
Token and
Token ID290
Feature activation-1.59e+00

Pos logit contributions
iaries+0.255
acas+0.248
OTOS+0.236
ruary+0.231
mitt+0.228
Neg logit contributions
��-0.327
ット-0.248
Line-0.245
�醒-0.244
uez-0.241
Token lo
Token ID2376
Feature activation-4.80e+00

Pos logit contributions
��+1.237
Line+0.911
ット+0.910
uez+0.895
�醒+0.886
Neg logit contributions
iaries-1.172
acas-1.137
OTOS-1.086
ruary-1.067
mitt-1.049
Token and
Token ID290
Feature activation-1.27e+01

Pos logit contributions
��+3.649
Line+2.697
ット+2.675
uez+2.670
�醒+2.550
Neg logit contributions
iaries-3.493
acas-3.366
OTOS-3.263
ruary-3.235
ashtra-3.163
Token behold
Token ID23700
Feature activation-4.93e+00

Pos logit contributions
��+4.338
 haw+2.372
uez+2.238
 tack+2.153
 Lines+2.124
Neg logit contributions
iaries-13.243
acas-13.128
OTOS-12.909
ashtra-12.799
imore-12.514
Token,
Token ID11
Feature activation-1.38e+00

Pos logit contributions
��+3.720
Line+2.821
ット+2.785
uez+2.761
 Lines+2.702
Neg logit contributions
iaries-3.653
acas-3.461
OTOS-3.307
ruary-3.257
imore-3.215
Token the
Token ID262
Feature activation+5.21e-01

Pos logit contributions
��+1.080
ット+0.803
Line+0.802
uez+0.789
�醒+0.781
Neg logit contributions
iaries-1.006
acas-0.973
OTOS-0.930
ruary-0.915
mitt-0.896
Token problem
Token ID1917
Feature activation-1.62e+00

Pos logit contributions
iaries+0.385
acas+0.376
OTOS+0.360
ruary+0.353
mitt+0.350
Neg logit contributions
��-0.404
ット-0.294
Line-0.291
�醒-0.290
uez-0.286
Token isn
Token ID2125
Feature activation-9.85e-01

Pos logit contributions
��+1.295
ット+0.969
Line+0.968
�醒+0.944
uez+0.943
Neg logit contributions
iaries-1.159
acas-1.113
OTOS-1.067
ruary-1.049
mitt-1.025
Token
Token ID198
Feature activation-1.10e+00

Pos logit contributions
��+1.398
ット+1.061
Line+1.061
 Younger+1.043
 Lines+1.034
Neg logit contributions
iaries-1.239
acas-1.215
OTOS-1.147
ruary-1.133
mitt-1.126
Token
Token ID198
Feature activation-1.83e+00

Pos logit contributions
��+0.907
Line+0.707
ット+0.699
uez+0.689
 Younger+0.680
Neg logit contributions
iaries-0.741
acas-0.717
OTOS-0.679
ruary-0.673
mitt-0.653
Token"
Token ID1
Feature activation-1.36e+00

Pos logit contributions
��+1.520
Line+1.173
ット+1.154
uez+1.131
�醒+1.127
Neg logit contributions
iaries-1.232
acas-1.194
OTOS-1.125
ruary-1.123
mitt-1.090
TokenSome
Token ID4366
Feature activation+1.62e+00

Pos logit contributions
��+1.172
ット+0.895
Line+0.894
�醒+0.877
uez+0.873
Neg logit contributions
iaries-0.881
acas-0.858
OTOS-0.811
ruary-0.800
mitt-0.784
Token may
Token ID743
Feature activation+5.00e+00

Pos logit contributions
iaries+1.077
acas+1.037
OTOS+0.984
ruary+0.963
mitt+0.953
Neg logit contributions
��-1.383
ット-1.051
�醒-1.044
Line-1.032
���-1.025
Token qu
Token ID627
Feature activation+1.05e+01

Pos logit contributions
iaries+3.709
acas+3.554
ruary+3.329
flush+3.315
 "$:/+3.305
Neg logit contributions
��-3.931
�醒-2.916
ット-2.874
���-2.827
-2.793
Tokenibble
Token ID43992
Feature activation+2.47e+00

Pos logit contributions
acas+4.563
iaries+4.360
mitt+3.872
imore+3.853
flush+3.844
Neg logit contributions
��-11.501
ーテ-9.295
���-9.126
�醒-9.054
��-8.965
Token that
Token ID326
Feature activation-5.98e-01

Pos logit contributions
iaries+1.660
acas+1.619
OTOS+1.535
ruary+1.511
mitt+1.495
Neg logit contributions
��-2.069
ット-1.551
�醒-1.537
Line-1.528
���-1.514
Token this
Token ID428
Feature activation+3.18e+00

Pos logit contributions
��+0.495
ット+0.371
Line+0.368
�醒+0.365
uez+0.362
Neg logit contributions
iaries-0.409
acas-0.398
OTOS-0.380
ruary-0.373
mitt-0.367
Token doesn
Token ID1595
Feature activation+1.63e+00

Pos logit contributions
iaries+2.143
acas+2.078
OTOS+1.972
ruary+1.928
mitt+1.908
Neg logit contributions
��-2.668
ット-2.009
�醒-2.004
���-1.950
Line-1.946
Token't
Token ID470
Feature activation-5.77e-01

Pos logit contributions
iaries+1.142
acas+1.112
OTOS+1.062
ruary+1.040
mitt+1.036
Neg logit contributions
��-1.341
���-0.990
�醒-0.986
ット-0.983
Line-0.962
Token O
Token ID440
Feature activation+1.05e+00

Pos logit contributions
iaries+1.239
acas+1.205
OTOS+1.151
ruary+1.104
mitt+1.099
Neg logit contributions
��-2.185
�醒-1.701
ット-1.692
���-1.690
Line-1.668
Token&
Token ID5
Feature activation-7.28e+00

Pos logit contributions
iaries+0.700
acas+0.683
OTOS+0.653
ruary+0.636
mitt+0.633
Neg logit contributions
��-0.896
ット-0.670
�醒-0.667
���-0.662
Line-0.660
TokenA
Token ID32
Feature activation-3.72e-01

Pos logit contributions
��+3.937
Line+3.420
ット+2.960
 Younger+2.920
 partName+2.830
Neg logit contributions
iaries-6.489
acas-6.149
ruary-6.051
imore-5.937
ashtra-5.818
Token-
Token ID12
Feature activation-1.12e+00

Pos logit contributions
��+0.299
ット+0.224
Line+0.223
�醒+0.218
uez+0.218
Neg logit contributions
iaries-0.262
acas-0.255
OTOS-0.243
ruary-0.239
mitt-0.235
TokenJ
Token ID41
Feature activation+1.67e+00

Pos logit contributions
��+0.927
Line+0.701
ット+0.700
�醒+0.683
uez+0.681
Neg logit contributions
iaries-0.765
acas-0.739
OTOS-0.701
ruary-0.693
mitt-0.678
Tokenimm
Token ID8608
Feature activation+1.11e+01

Pos logit contributions
iaries+1.059
acas+1.030
OTOS+0.976
ruary+0.955
mitt+0.943
Neg logit contributions
��-1.463
ット-1.116
Line-1.103
�醒-1.099
uez-1.086
Tokenys
Token ID893
Feature activation-3.32e+00

Pos logit contributions
iaries+7.333
acas+7.133
imore+6.812
mitt+6.787
OTOS+6.600
Neg logit contributions
��-9.052
���-6.891
ット-6.724
-6.592
�醒-6.497
Token 3
Token ID513
Feature activation+4.23e-01

Pos logit contributions
��+2.708
ット+2.040
Line+2.036
 Younger+1.995
uez+1.987
Neg logit contributions
iaries-2.275
acas-2.184
OTOS-2.106
ruary-2.059
mitt-2.018
Tokenway
Token ID1014
Feature activation+3.88e+00

Pos logit contributions
iaries+0.288
acas+0.281
OTOS+0.267
ruary+0.262
mitt+0.259
Neg logit contributions
��-0.352
ット-0.264
Line-0.262
�醒-0.259
uez-0.257
Token Dream
Token ID7610
Feature activation+1.55e+00

Pos logit contributions
iaries+2.669
acas+2.623
OTOS+2.489
ruary+2.449
mitt+2.411
Neg logit contributions
��-3.170
ット-2.350
�醒-2.336
Line-2.317
-2.299
Token-
Token ID12
Feature activation+2.12e+00

Pos logit contributions
iaries+1.075
acas+1.047
OTOS+0.997
ruary+0.980
mitt+0.967
Neg logit contributions
��-1.267
ット-0.945
Line-0.934
�醒-0.929
uez-0.920
Token
Token ID229
Feature activation-3.39e-01

Pos logit contributions
iaries+4.312
acas+4.244
OTOS+4.133
ruary+3.970
mitt+3.932
Neg logit contributions
��-5.879
ット-4.684
uez-4.652
 Younger-4.627
Line-4.625
Token
Token ID118
Feature activation+3.13e+00

Pos logit contributions
��+0.233
ット+0.161
Line+0.158
�醒+0.158
���+0.155
Neg logit contributions
iaries-0.283
acas-0.276
OTOS-0.265
ruary-0.262
mitt-0.258
Token
Token ID8582
Feature activation+6.57e+00

Pos logit contributions
iaries+2.377
acas+2.334
OTOS+2.247
ruary+2.203
mitt+2.178
Neg logit contributions
��-2.342
ット-1.690
�醒-1.660
Line-1.650
���-1.639
Token
Token ID229
Feature activation-2.51e-01

Pos logit contributions
iaries+3.962
acas+3.889
OTOS+3.732
ruary+3.573
mitt+3.569
Neg logit contributions
��-5.529
ット-4.368
uez-4.365
Line-4.328
 Younger-4.320
Token
Token ID116
Feature activation+2.50e+00

Pos logit contributions
��+0.186
ット+0.133
Line+0.131
�醒+0.131
���+0.129
Neg logit contributions
iaries-0.195
acas-0.189
OTOS-0.182
ruary-0.179
mitt-0.177
Token (@
Token ID4275
Feature activation+9.72e+00

Pos logit contributions
iaries+1.952
acas+1.915
OTOS+1.849
ruary+1.810
mitt+1.797
Neg logit contributions
��-1.818
ット-1.300
�醒-1.273
Line-1.267
���-1.255
Tokenm
Token ID76
Feature activation+6.57e+00

Pos logit contributions
acas+6.198
iaries+6.120
mitt+5.937
dan+5.853
flush+5.784
Neg logit contributions
��-8.016
���-6.236
�醒-6.096
ーテ-5.992
ット-5.986
Tokenf
Token ID69
Feature activation+5.79e+00

Pos logit contributions
iaries+3.547
acas+3.449
mitt+3.225
ruary+3.188
OTOS+3.173
Neg logit contributions
��-6.375
���-5.037
�醒-4.964
ット-4.920
ーテ-4.831
Tokenlynn
Token ID12935
Feature activation+1.27e+00

Pos logit contributions
iaries+3.879
acas+3.737
ruary+3.565
mitt+3.549
flush+3.523
Neg logit contributions
��-4.876
���-3.701
�醒-3.661
ット-3.626
ーテ-3.578
TokenJR
Token ID44817
Feature activation-1.51e+00

Pos logit contributions
iaries+0.835
acas+0.812
OTOS+0.772
ruary+0.757
mitt+0.748
Neg logit contributions
��-1.084
ット-0.820
Line-0.810
�醒-0.808
uez-0.798
Token)
Token ID8
Feature activation+1.56e+00

Pos logit contributions
��+1.343
Line+1.039
ット+1.032
uez+1.020
�醒+1.014
Neg logit contributions
iaries-0.922
acas-0.894
OTOS-0.842
ruary-0.836
mitt-0.816
Token Marshall
Token ID13606
Feature activation-4.01e+00

Pos logit contributions
��+0.881
Line+0.640
uez+0.628
 Younger+0.626
ット+0.624
Neg logit contributions
iaries-0.977
acas-0.955
OTOS-0.915
ruary-0.907
mitt-0.889
Token intercepted
Token ID29842
Feature activation+8.09e-01

Pos logit contributions
��+3.147
Line+2.375
ット+2.363
uez+2.332
+2.306
Neg logit contributions
iaries-2.849
acas-2.739
OTOS-2.638
ruary-2.598
aceae-2.522
Token a
Token ID257
Feature activation-1.10e+00

Pos logit contributions
iaries+0.556
acas+0.541
OTOS+0.516
ruary+0.506
mitt+0.500
Neg logit contributions
��-0.668
ット-0.500
Line-0.494
�醒-0.491
uez-0.487
Token pass
Token ID1208
Feature activation+1.56e+00

Pos logit contributions
��+0.836
ット+0.609
Line+0.607
�醒+0.598
uez+0.593
Neg logit contributions
iaries-0.827
acas-0.805
OTOS-0.772
ruary-0.759
mitt-0.745
Token over
Token ID625
Feature activation+5.08e+00

Pos logit contributions
iaries+1.027
acas+1.003
OTOS+0.950
ruary+0.932
mitt+0.929
Neg logit contributions
��-1.338
ット-1.005
�醒-0.993
Line-0.990
���-0.982
Token the
Token ID262
Feature activation+9.71e+00

Pos logit contributions
iaries+3.136
acas+3.095
mitt+2.911
OTOS+2.907
dan+2.814
Neg logit contributions
��-4.405
ット-3.354
�醒-3.318
uez-3.315
���-3.294
Token middle
Token ID3504
Feature activation+2.51e+00

Pos logit contributions
acas+6.116
iaries+6.085
OTOS+5.828
mitt+5.631
flush+5.629
Neg logit contributions
��-7.859
�醒-6.030
ット-5.994
ーテ-5.972
uez-5.865
Token by
Token ID416
Feature activation-5.32e-01

Pos logit contributions
iaries+1.610
acas+1.571
OTOS+1.487
mitt+1.460
ruary+1.459
Neg logit contributions
��-2.182
ット-1.646
�醒-1.626
���-1.619
Line-1.618
Token Siem
Token ID45196
Feature activation+5.33e-02

Pos logit contributions
��+0.434
ット+0.324
Line+0.323
�醒+0.319
uez+0.316
Neg logit contributions
iaries-0.370
acas-0.360
OTOS-0.343
ruary-0.338
mitt-0.332
Tokenian
Token ID666
Feature activation-1.27e+00

Pos logit contributions
iaries+0.037
acas+0.036
OTOS+0.034
ruary+0.034
mitt+0.033
Neg logit contributions
��-0.044
ット-0.033
�醒-0.032
Line-0.032
���-0.032
Token.
Token ID13
Feature activation-2.10e-01

Pos logit contributions
��+1.035
ット+0.777
Line+0.774
�醒+0.760
uez+0.757
Neg logit contributions
iaries-0.886
acas-0.858
OTOS-0.819
ruary-0.802
mitt-0.789
Token a
Token ID257
Feature activation+2.01e+00

Pos logit contributions
iaries+1.298
acas+1.261
OTOS+1.213
ruary+1.181
mitt+1.177
Neg logit contributions
��-1.313
�醒-0.957
ット-0.954
Line-0.926
���-0.919
Token bit
Token ID1643
Feature activation+1.77e+00

Pos logit contributions
iaries+1.241
acas+1.205
OTOS+1.144
ruary+1.111
mitt+1.110
Neg logit contributions
��-1.789
ット-1.362
�醒-1.356
���-1.347
Line-1.337
Token safer
Token ID14178
Feature activation+1.28e+00

Pos logit contributions
iaries+1.363
acas+1.319
OTOS+1.269
ruary+1.239
mitt+1.237
Neg logit contributions
��-1.322
ット-0.952
�醒-0.947
Line-0.927
���-0.922
Token than
Token ID621
Feature activation-4.23e-01

Pos logit contributions
iaries+0.824
acas+0.801
OTOS+0.762
ruary+0.744
mitt+0.736
Neg logit contributions
��-1.106
ット-0.841
Line-0.830
�醒-0.830
uez-0.819
Token they
Token ID484
Feature activation+7.73e+00

Pos logit contributions
��+0.346
ット+0.258
Line+0.257
uez+0.253
�醒+0.253
Neg logit contributions
iaries-0.293
acas-0.285
OTOS-0.272
ruary-0.268
mitt-0.263
Token otherwise
Token ID4306
Feature activation+9.05e+00

Pos logit contributions
iaries+4.696
acas+4.553
OTOS+4.138
obin+4.115
mitt+4.104
Neg logit contributions
��-6.924
�醒-5.502
ット-5.307
ーテ-5.264
-5.181
Token might
Token ID1244
Feature activation+8.48e+00

Pos logit contributions
iaries+5.502
acas+5.312
mitt+4.948
OTOS+4.882
obin+4.828
Neg logit contributions
��-7.891
�醒-6.267
ット-5.973
ーテ-5.904
Line-5.897
Token be
Token ID307
Feature activation+3.17e+00

Pos logit contributions
iaries+5.523
acas+5.229
OTOS+5.054
mitt+4.818
flush+4.769
Neg logit contributions
��-6.958
ット-5.349
�醒-5.288
Line-5.262
���-5.223
Token.
Token ID13
Feature activation+4.73e-01

Pos logit contributions
iaries+1.861
acas+1.805
OTOS+1.709
ruary+1.656
mitt+1.649
Neg logit contributions
��-2.900
ット-2.252
�醒-2.240
Line-2.222
���-2.216
Token So
Token ID1406
Feature activation+1.89e+00

Pos logit contributions
iaries+0.337
acas+0.328
OTOS+0.314
ruary+0.308
mitt+0.304
Neg logit contributions
��-0.379
ット-0.281
Line-0.278
�醒-0.276
uez-0.273
Token let
Token ID1309
Feature activation+2.79e+00

Pos logit contributions
iaries+1.330
acas+1.295
OTOS+1.236
ruary+1.210
mitt+1.203
Neg logit contributions
��-1.529
ット-1.138
�醒-1.128
Line-1.117
���-1.107
Tokenas
Token ID292
Feature activation-2.42e+00

Pos logit contributions
iaries+0.022
acas+0.022
OTOS+0.020
ruary+0.020
mitt+0.020
Neg logit contributions
��-0.030
ット-0.023
Line-0.023
�醒-0.022
uez-0.022
Token long
Token ID890
Feature activation+3.09e+00

Pos logit contributions
��+1.881
Line+1.379
ット+1.375
uez+1.349
�醒+1.335
Neg logit contributions
iaries-1.761
acas-1.725
OTOS-1.627
ruary-1.616
aceae-1.580
Token as
Token ID355
Feature activation+3.17e+00

Pos logit contributions
iaries+2.020
acas+1.955
OTOS+1.889
ruary+1.831
mitt+1.821
Neg logit contributions
��-2.651
ット-2.009
�醒-1.994
Line-1.954
���-1.952
Token it
Token ID340
Feature activation-3.86e-01

Pos logit contributions
iaries+2.135
acas+2.082
OTOS+1.995
mitt+1.941
ruary+1.937
Neg logit contributions
��-2.652
ット-2.000
�醒-1.988
Line-1.946
-1.926
Token wasn
Token ID2492
Feature activation+1.97e+00

Pos logit contributions
��+0.308
ット+0.229
Line+0.227
�醒+0.224
uez+0.223
Neg logit contributions
iaries-0.275
acas-0.268
OTOS-0.256
ruary-0.251
mitt-0.247
Token't
Token ID470
Feature activation+3.54e+00

Pos logit contributions
iaries+1.375
acas+1.341
OTOS+1.282
ruary+1.254
mitt+1.249
Neg logit contributions
��-1.628
���-1.203
�醒-1.198
ット-1.190
Line-1.165
Token the
Token ID262
Feature activation+5.01e+00

Pos logit contributions
iaries+2.488
acas+2.402
OTOS+2.299
ruary+2.245
mitt+2.241
Neg logit contributions
��-2.865
ット-2.124
�醒-2.121
Line-2.085
uez-2.052
Token el
Token ID1288
Feature activation-2.84e+00

Pos logit contributions
iaries+3.461
acas+3.348
OTOS+3.225
ruary+3.114
mitt+3.114
Neg logit contributions
��-4.071
ット-3.044
�醒-3.042
Line-2.974
-2.924
Tokenche
Token ID2395
Feature activation+1.15e+00

Pos logit contributions
��+2.410
Line+1.833
ット+1.818
�醒+1.797
uez+1.779
Neg logit contributions
iaries-1.836
acas-1.779
OTOS-1.715
ruary-1.675
mitt-1.624
Tokenapo
Token ID41817
Feature activation-2.12e-01

Pos logit contributions
iaries+0.779
acas+0.758
OTOS+0.722
ruary+0.708
mitt+0.700
Neg logit contributions
��-0.961
ット-0.720
Line-0.714
�醒-0.712
uez-0.703
Token method
Token ID2446
Feature activation-2.56e+00

Pos logit contributions
��+0.170
ット+0.126
Line+0.125
�醒+0.124
uez+0.123
Neg logit contributions
iaries-0.150
acas-0.146
OTOS-0.139
ruary-0.137
mitt-0.135
Token of
Token ID286
Feature activation+4.65e-01

Pos logit contributions
��+0.857
ット+0.648
Line+0.648
�醒+0.636
uez+0.631
Neg logit contributions
iaries-0.682
acas-0.666
OTOS-0.634
ruary-0.622
mitt-0.613
Token the
Token ID262
Feature activation+2.45e+00

Pos logit contributions
iaries+0.311
acas+0.302
OTOS+0.288
ruary+0.282
mitt+0.278
Neg logit contributions
��-0.393
ット-0.297
Line-0.294
�醒-0.291
uez-0.290
Token building
Token ID2615
Feature activation+2.73e-01

Pos logit contributions
iaries+1.788
acas+1.748
OTOS+1.658
ruary+1.625
mitt+1.609
Neg logit contributions
��-1.925
ット-1.417
�醒-1.407
Line-1.391
���-1.374
Token,
Token ID11
Feature activation+5.19e-01

Pos logit contributions
iaries+0.183
acas+0.178
OTOS+0.169
ruary+0.166
mitt+0.164
Neg logit contributions
��-0.230
ット-0.174
Line-0.172
�醒-0.171
uez-0.170
Token seeing
Token ID4379
Feature activation+6.28e+00

Pos logit contributions
iaries+0.374
acas+0.365
OTOS+0.349
ruary+0.342
mitt+0.338
Neg logit contributions
��-0.412
ット-0.303
Line-0.300
�醒-0.299
uez-0.295
Token the
Token ID262
Feature activation+1.01e+00

Pos logit contributions
iaries+3.885
acas+3.876
OTOS+3.671
mitt+3.522
imore+3.491
Neg logit contributions
��-5.529
�醒-4.288
ット-4.163
���-4.157
-4.061
Token handheld
Token ID33811
Feature activation-5.10e+00

Pos logit contributions
iaries+0.731
acas+0.713
OTOS+0.681
ruary+0.666
mitt+0.660
Neg logit contributions
��-0.799
ット-0.588
Line-0.581
�醒-0.580
uez-0.571
Token bomb
Token ID5194
Feature activation+3.62e+00

Pos logit contributions
��+3.740
Line+2.799
ット+2.767
 Younger+2.749
uez+2.748
Neg logit contributions
iaries-3.736
acas-3.690
ruary-3.547
OTOS-3.496
ashtra-3.440
Token go
Token ID467
Feature activation+2.63e+00

Pos logit contributions
iaries+2.448
acas+2.384
OTOS+2.268
ruary+2.212
mitt+2.206
Neg logit contributions
��-3.062
�醒-2.267
ット-2.238
���-2.238
Line-2.216
Token off
Token ID572
Feature activation-2.15e+00

Pos logit contributions
iaries+1.546
acas+1.496
OTOS+1.411
ruary+1.376
mitt+1.370
Neg logit contributions
��-2.435
ット-1.862
�醒-1.859
Line-1.856
���-1.840
Token in
Token ID287
Feature activation+1.68e+00

Pos logit contributions
��+1.745
ット+1.327
Line+1.322
uez+1.298
�醒+1.286
Neg logit contributions
iaries-1.474
acas-1.428
OTOS-1.360
ruary-1.332
mitt-1.312
Token of
Token ID286
Feature activation-2.71e+00

Pos logit contributions
iaries+0.574
acas+0.558
OTOS+0.530
ruary+0.519
mitt+0.512
Neg logit contributions
��-0.766
ット-0.582
Line-0.577
�醒-0.573
uez-0.568
Token satellite
Token ID11210
Feature activation-1.76e+00

Pos logit contributions
��+2.068
Line+1.547
ット+1.543
uez+1.520
 Younger+1.514
Neg logit contributions
iaries-1.969
acas-1.923
OTOS-1.829
ruary-1.817
mitt-1.778
Token-
Token ID12
Feature activation-7.17e+00

Pos logit contributions
��+1.375
Line+1.019
ット+1.017
uez+0.993
�醒+0.989
Neg logit contributions
iaries-1.264
acas-1.241
OTOS-1.182
ruary-1.170
mitt-1.144
Tokenbased
Token ID3106
Feature activation-4.35e+00

Pos logit contributions
��+4.947
Line+3.932
uez+3.758
 Younger+3.703
ット+3.674
Neg logit contributions
iaries-5.268
acas-5.119
OTOS-4.998
ruary-4.993
 "$:/-4.749
Token temperature
Token ID5951
Feature activation-2.59e-01

Pos logit contributions
��+3.285
Line+2.509
ット+2.455
 Younger+2.440
uez+2.435
Neg logit contributions
iaries-3.107
acas-3.086
OTOS-2.931
ruary-2.915
flush-2.841
Token estimates
Token ID7746
Feature activation+2.34e+00

Pos logit contributions
��+0.196
ット+0.142
Line+0.140
�醒+0.139
uez+0.138
Neg logit contributions
iaries-0.196
acas-0.192
OTOS-0.184
ruary-0.180
mitt-0.178
Token to
Token ID284
Feature activation-4.48e-01

Pos logit contributions
iaries+1.465
acas+1.426
OTOS+1.351
ruary+1.325
mitt+1.307
Neg logit contributions
��-2.080
ット-1.583
�醒-1.574
Line-1.563
���-1.542
Token reach
Token ID3151
Feature activation+4.38e+00

Pos logit contributions
��+0.340
ット+0.249
Line+0.247
uez+0.243
�醒+0.242
Neg logit contributions
iaries-0.335
acas-0.326
OTOS-0.314
ruary-0.307
mitt-0.304
Token their
Token ID511
Feature activation-1.16e+00

Pos logit contributions
iaries+2.855
acas+2.790
OTOS+2.650
mitt+2.591
ruary+2.590
Neg logit contributions
��-3.762
�醒-2.841
ット-2.787
���-2.786
Line-2.750
Token conclusion
Token ID7664
Feature activation+6.02e-01

Pos logit contributions
��+0.900
ット+0.661
Line+0.657
uez+0.645
�醒+0.643
Neg logit contributions
iaries-0.855
acas-0.832
OTOS-0.799
ruary-0.782
mitt-0.772
Token.
Token ID13
Feature activation-1.58e+00

Pos logit contributions
iaries+0.408
acas+0.396
OTOS+0.378
ruary+0.370
mitt+0.365
Neg logit contributions
��-0.504
ット-0.379
Line-0.376
�醒-0.373
uez-0.370
TokenColor
Token ID10258
Feature activation+2.60e+00

Pos logit contributions
iaries+4.059
acas+4.025
OTOS+3.764
mitt+3.704
dan+3.691
Neg logit contributions
��-5.762
�醒-4.412
���-4.395
ット-4.335
ーテ-4.310
Tokenlines
Token ID6615
Feature activation-3.30e-01

Pos logit contributions
iaries+2.539
acas+2.490
OTOS+2.408
ruary+2.371
mitt+2.365
Neg logit contributions
��-1.401
ット-0.850
�醒-0.838
���-0.824
uez-0.803
Token)
Token ID8
Feature activation-9.92e-01

Pos logit contributions
��+0.277
Line+0.211
ット+0.210
uez+0.206
�醒+0.205
Neg logit contributions
iaries-0.219
acas-0.214
OTOS-0.203
ruary-0.200
mitt-0.196
Token September
Token ID2693
Feature activation-2.83e+00

Pos logit contributions
��+0.676
ット+0.478
Line+0.474
�醒+0.465
uez+0.463
Neg logit contributions
iaries-0.813
acas-0.796
OTOS-0.763
ruary-0.748
mitt-0.744
Token 26
Token ID2608
Feature activation-1.90e-03

Pos logit contributions
��+2.146
ット+1.612
Line+1.604
 Younger+1.583
uez+1.553
Neg logit contributions
iaries-2.104
acas-2.039
OTOS-1.942
imore-1.891
ruary-1.883
Token,
Token ID11
Feature activation+1.00e+00

Pos logit contributions
��+0.002
ット+0.001
Line+0.001
uez+0.001
�醒+0.001
Neg logit contributions
iaries-0.001
acas-0.001
OTOS-0.001
ruary-0.001
mitt-0.001
Token 2016
Token ID1584
Feature activation+7.57e-01

Pos logit contributions
iaries+0.701
acas+0.683
OTOS+0.652
ruary+0.640
mitt+0.632
Neg logit contributions
��-0.815
ット-0.605
Line-0.599
�醒-0.597
uez-0.590
Token
Token ID198
Feature activation-3.17e+00

Pos logit contributions
iaries+0.473
acas+0.459
OTOS+0.435
ruary+0.426
mitt+0.420
Neg logit contributions
��-0.673
ット-0.516
Line-0.511
�醒-0.508
uez-0.504
Token
Token ID198
Feature activation+9.10e-01

Pos logit contributions
��+2.343
Line+1.908
ット+1.838
uez+1.830
 Younger+1.821
Neg logit contributions
iaries-2.282
acas-2.194
ruary-2.084
OTOS-2.073
ashtra-2.029
TokenG
Token ID38
Feature activation-5.48e+00

Pos logit contributions
iaries+0.598
acas+0.583
OTOS+0.557
ruary+0.542
mitt+0.538
Neg logit contributions
��-0.780
ット-0.589
�醒-0.581
Line-0.579
���-0.574
Tokenotte
Token ID11404
Feature activation-3.44e+00

Pos logit contributions
��+6.340
uez+5.427
Line+5.348
ット+5.338
�醒+5.319
Neg logit contributions
iaries-1.584
acas-1.441
ruary-1.303
OTOS-1.212
 "$:/-1.185
Token him
Token ID683
Feature activation-2.07e+00

Pos logit contributions
iaries+2.012
acas+1.977
OTOS+1.865
ruary+1.836
mitt+1.810
Neg logit contributions
��-2.660
ット-2.026
�醒-1.996
Line-1.972
���-1.966
Token because
Token ID780
Feature activation-6.34e-01

Pos logit contributions
��+1.696
Line+1.276
ット+1.271
uez+1.254
�醒+1.249
Neg logit contributions
iaries-1.422
acas-1.375
OTOS-1.320
ruary-1.279
mitt-1.268
Token they
Token ID484
Feature activation-2.03e+00

Pos logit contributions
��+0.518
Line+0.387
ット+0.385
uez+0.381
�醒+0.379
Neg logit contributions
iaries-0.439
acas-0.425
OTOS-0.408
ruary-0.399
mitt-0.393
Token belonged
Token ID19611
Feature activation-9.14e-01

Pos logit contributions
��+1.610
Line+1.204
ット+1.194
uez+1.182
 Younger+1.170
Neg logit contributions
iaries-1.427
acas-1.385
OTOS-1.353
ruary-1.302
mitt-1.291
Token to
Token ID284
Feature activation+2.49e+00

Pos logit contributions
��+0.762
ット+0.574
Line+0.571
�醒+0.564
uez+0.558
Neg logit contributions
iaries-0.619
acas-0.603
OTOS-0.572
ruary-0.560
mitt-0.556
Token the
Token ID262
Feature activation+1.05e+00

Pos logit contributions
iaries+1.618
acas+1.588
OTOS+1.499
ruary+1.475
mitt+1.454
Neg logit contributions
��-2.147
ット-1.635
�醒-1.608
Line-1.597
���-1.585
Token Atlanta
Token ID9371
Feature activation+8.65e-01

Pos logit contributions
iaries+0.740
acas+0.721
OTOS+0.687
ruary+0.675
mitt+0.666
Neg logit contributions
��-0.853
ット-0.634
Line-0.624
�醒-0.623
uez-0.614
Token Hawks
Token ID23445
Feature activation-2.99e+00

Pos logit contributions
iaries+0.649
acas+0.634
OTOS+0.606
ruary+0.596
mitt+0.589
Neg logit contributions
��-0.659
ット-0.480
Line-0.473
�醒-0.470
uez-0.465
Token.
Token ID13
Feature activation+9.50e-01

Pos logit contributions
��+2.415
Line+1.815
ット+1.798
�醒+1.770
 Younger+1.756
Neg logit contributions
iaries-2.084
acas-2.013
OTOS-1.936
ruary-1.882
mitt-1.845
Token
Token ID198
Feature activation+1.30e+00

Pos logit contributions
iaries+0.634
acas+0.617
OTOS+0.587
ruary+0.576
mitt+0.568
Neg logit contributions
��-0.803
ット-0.606
Line-0.600
�醒-0.596
uez-0.591
Token
Token ID198
Feature activation+2.34e+00

Pos logit contributions
iaries+0.792
acas+0.771
OTOS+0.732
ruary+0.712
mitt+0.708
Neg logit contributions
��-1.186
ット-0.905
�醒-0.904
���-0.902
Line-0.888
Token Collection
Token ID12251
Feature activation-1.86e+00

Pos logit contributions
��+1.187
ット+0.899
Line+0.894
�醒+0.879
uez+0.874
Neg logit contributions
iaries-0.922
acas-0.898
OTOS-0.854
ruary-0.840
mitt-0.825
Token,
Token ID11
Feature activation-1.42e+00

Pos logit contributions
��+1.573
ット+1.195
Line+1.191
uez+1.167
�醒+1.165
Neg logit contributions
iaries-1.226
acas-1.194
OTOS-1.133
ruary-1.113
mitt-1.098
Token replacing
Token ID13586
Feature activation-3.21e+00

Pos logit contributions
��+1.143
ット+0.853
Line+0.850
uez+0.832
�醒+0.829
Neg logit contributions
iaries-1.005
acas-0.980
OTOS-0.933
ruary-0.913
mitt-0.904
Token Confederate
Token ID21900
Feature activation-1.62e+00

Pos logit contributions
��+2.494
Line+1.865
ット+1.853
 Younger+1.831
uez+1.820
Neg logit contributions
iaries-2.305
acas-2.237
OTOS-2.118
ruary-2.106
mitt-2.047
Token General
Token ID3611
Feature activation-3.11e+00

Pos logit contributions
��+1.249
ット+0.913
Line+0.910
uez+0.891
�醒+0.887
Neg logit contributions
iaries-1.194
acas-1.166
OTOS-1.114
ruary-1.100
mitt-1.080
Token Edmund
Token ID35646
Feature activation-1.11e+00

Pos logit contributions
��+2.436
Line+1.805
ット+1.803
 Younger+1.785
uez+1.772
Neg logit contributions
iaries-2.222
acas-2.153
OTOS-2.063
ruary-2.029
mitt-1.996
Token Kirby
Token ID23965
Feature activation+3.09e+00

Pos logit contributions
��+0.872
 Younger+0.667
Line+0.647
uez+0.647
ット+0.635
Neg logit contributions
iaries-0.810
acas-0.780
OTOS-0.741
ruary-0.722
mitt-0.712
Token Smith
Token ID4176
Feature activation+5.89e-01

Pos logit contributions
iaries+1.977
acas+1.941
OTOS+1.860
ruary+1.813
mitt+1.804
Neg logit contributions
��-2.668
ット-2.023
�醒-2.004
Line-1.984
���-1.967
Token.[
Token ID3693
Feature activation+4.13e+00

Pos logit contributions
iaries+0.384
acas+0.373
OTOS+0.355
ruary+0.348
mitt+0.343
Neg logit contributions
��-0.507
ット-0.385
Line-0.381
�醒-0.379
uez-0.375
Token7
Token ID22
Feature activation-3.93e-01

Pos logit contributions
iaries+3.191
acas+3.103
OTOS+3.000
mitt+2.931
ruary+2.925
Neg logit contributions
��-3.035
�醒-2.172
���-2.162
ット-2.146
Line-2.088
Token]
Token ID60
Feature activation-1.66e+00

Pos logit contributions
��+0.290
ット+0.209
Line+0.207
�醒+0.205
uez+0.202
Neg logit contributions
iaries-0.304
acas-0.297
OTOS-0.284
ruary-0.279
mitt-0.276
Token that
Token ID326
Feature activation+4.55e-01

Pos logit contributions
��+1.285
ット+0.953
Line+0.952
uez+0.933
�醒+0.932
Neg logit contributions
iaries-1.150
acas-1.118
OTOS-1.071
ruary-1.047
mitt-1.033
Token culminated
Token ID45200
Feature activation-2.70e-01

Pos logit contributions
iaries+0.310
acas+0.302
OTOS+0.288
ruary+0.283
mitt+0.279
Neg logit contributions
��-0.378
ット-0.283
�醒-0.279
Line-0.279
uez-0.275
Token in
Token ID287
Feature activation+1.62e+00

Pos logit contributions
��+0.224
ット+0.168
Line+0.167
�醒+0.165
uez+0.164
Neg logit contributions
iaries-0.184
acas-0.179
OTOS-0.171
ruary-0.167
mitt-0.165
Token this
Token ID428
Feature activation-1.36e+00

Pos logit contributions
iaries+1.086
acas+1.064
OTOS+1.012
ruary+0.998
mitt+0.986
Neg logit contributions
��-1.354
ット-1.014
�醒-1.010
Line-1.000
���-0.990
Token month
Token ID1227
Feature activation+3.34e-01

Pos logit contributions
��+1.058
ット+0.777
Line+0.776
uez+0.762
�醒+0.757
Neg logit contributions
iaries-0.997
acas-0.964
OTOS-0.929
ruary-0.910
mitt-0.896
Token's
Token ID338
Feature activation-2.84e+00

Pos logit contributions
iaries+0.227
acas+0.222
OTOS+0.211
ruary+0.207
mitt+0.205
Neg logit contributions
��-0.277
ット-0.208
Line-0.206
�醒-0.204
uez-0.203
Token release
Token ID2650
Feature activation-1.10e+00

Pos logit contributions
��+2.191
ット+1.622
Line+1.618
uez+1.585
 Younger+1.569
Neg logit contributions
iaries-2.081
acas-1.997
OTOS-1.928
ruary-1.891
imore-1.862
Token of
Token ID286
Feature activation-3.53e+00

Pos logit contributions
��+0.938
ット+0.709
Line+0.703
�醒+0.699
uez+0.687
Neg logit contributions
iaries-0.731
acas-0.709
OTOS-0.673
ruary-0.662
mitt-0.651
Token version
Token ID2196
Feature activation-3.99e+00

Pos logit contributions
��+2.742
ット+2.040
Line+2.023
 Younger+1.986
uez+1.978
Neg logit contributions
iaries-2.543
acas-2.469
OTOS-2.351
ruary-2.299
aceae-2.287
Token 57
Token ID7632
Feature activation-4.88e+00

Pos logit contributions
��+3.135
ット+2.348
Line+2.347
uez+2.302
 Younger+2.286
Neg logit contributions
iaries-2.794
acas-2.750
OTOS-2.625
imore-2.540
ruary-2.537
Token,
Token ID11
Feature activation-9.94e-01

Pos logit contributions
��+3.885
ット+2.904
Line+2.855
uez+2.815
+2.811
Neg logit contributions
iaries-3.412
acas-3.330
OTOS-3.166
ruary-3.108
imore-3.091
Token apolog
Token ID8453
Feature activation-5.45e-01

Pos logit contributions
iaries+3.528
acas+3.403
OTOS+3.270
ruary+3.208
mitt+3.174
Neg logit contributions
��-3.843
�醒-2.829
ット-2.782
-2.732
Line-2.730
Tokenetic
Token ID5139
Feature activation+3.35e+00

Pos logit contributions
��+0.397
ット+0.285
Line+0.282
uez+0.279
�醒+0.278
Neg logit contributions
iaries-0.422
acas-0.415
OTOS-0.400
ruary-0.393
mitt-0.386
Token intent
Token ID6824
Feature activation+2.75e+00

Pos logit contributions
iaries+2.494
acas+2.407
OTOS+2.301
ruary+2.255
mitt+2.252
Neg logit contributions
��-2.595
�醒-1.886
ット-1.880
Line-1.839
-1.836
Token,
Token ID11
Feature activation+7.37e-01

Pos logit contributions
iaries+1.778
acas+1.736
OTOS+1.641
ruary+1.624
mitt+1.607
Neg logit contributions
��-2.367
ット-1.792
�醒-1.783
Line-1.750
���-1.742
Token the
Token ID262
Feature activation-5.15e-01

Pos logit contributions
iaries+0.502
acas+0.489
OTOS+0.465
ruary+0.458
mitt+0.452
Neg logit contributions
��-0.613
ット-0.459
�醒-0.453
Line-0.453
uez-0.446
Token late
Token ID2739
Feature activation-1.49e+00

Pos logit contributions
��+0.400
ット+0.294
Line+0.292
�醒+0.287
uez+0.286
Neg logit contributions
iaries-0.378
acas-0.369
OTOS-0.354
ruary-0.347
mitt-0.342
Token English
Token ID3594
Feature activation+2.45e+00

Pos logit contributions
��+1.208
ット+0.904
Line+0.902
uez+0.887
�醒+0.881
Neg logit contributions
iaries-1.043
acas-1.013
OTOS-0.977
ruary-0.952
mitt-0.935
Token scholar
Token ID15606
Feature activation+1.46e+00

Pos logit contributions
iaries+1.645
acas+1.601
OTOS+1.518
ruary+1.485
mitt+1.479
Neg logit contributions
��-2.057
ット-1.550
�醒-1.533
Line-1.524
���-1.505
Token Martin
Token ID5780
Feature activation-9.70e-01

Pos logit contributions
iaries+0.971
acas+0.945
OTOS+0.899
ruary+0.881
mitt+0.872
Neg logit contributions
��-1.240
ット-0.936
Line-0.925
�醒-0.924
uez-0.910
Token L
Token ID406
Feature activation+1.03e-01

Pos logit contributions
��+0.758
ット+0.562
Line+0.557
�醒+0.549
uez+0.543
Neg logit contributions
iaries-0.708
acas-0.688
OTOS-0.661
ruary-0.648
mitt-0.638
Tokenings
Token ID654
Feature activation+1.47e+00

Pos logit contributions
iaries+0.066
acas+0.064
OTOS+0.062
ruary+0.060
mitt+0.059
Neg logit contributions
��-0.089
Line-0.068
ット-0.068
uez-0.067
�醒-0.067
Token,
Token ID11
Feature activation-1.32e-01

Pos logit contributions
iaries+2.715
acas+2.678
OTOS+2.540
mitt+2.467
ruary+2.457
Neg logit contributions
��-3.394
ット-2.524
�醒-2.511
���-2.479
uez-2.461
Token a
Token ID257
Feature activation-2.05e-01

Pos logit contributions
��+0.107
ット+0.079
Line+0.079
�醒+0.078
uez+0.077
Neg logit contributions
iaries-0.093
acas-0.091
OTOS-0.086
ruary-0.085
mitt-0.084
Token 1982
Token ID14489
Feature activation+9.10e-01

Pos logit contributions
��+0.163
ット+0.121
Line+0.120
�醒+0.119
uez+0.118
Neg logit contributions
iaries-0.146
acas-0.142
OTOS-0.136
ruary-0.133
mitt-0.132
Token V
Token ID569
Feature activation+3.81e-01

Pos logit contributions
iaries+0.670
acas+0.654
OTOS+0.624
ruary+0.613
mitt+0.607
Neg logit contributions
��-0.708
ット-0.517
Line-0.512
�醒-0.510
uez-0.503
Tokenitus
Token ID17506
Feature activation+9.91e-01

Pos logit contributions
iaries+0.262
acas+0.255
OTOS+0.244
ruary+0.239
mitt+0.236
Neg logit contributions
��-0.314
ット-0.235
Line-0.233
�醒-0.231
uez-0.229
Token 9
Token ID860
Feature activation-3.20e-01

Pos logit contributions
iaries+0.696
acas+0.680
OTOS+0.648
ruary+0.636
mitt+0.629
Neg logit contributions
��-0.802
ット-0.595
Line-0.588
�醒-0.586
uez-0.580
Token79
Token ID3720
Feature activation+1.59e+00

Pos logit contributions
��+0.258
ット+0.192
Line+0.190
�醒+0.188
uez+0.186
Neg logit contributions
iaries-0.226
acas-0.220
OTOS-0.210
ruary-0.206
mitt-0.203
Token road
Token ID2975
Feature activation+2.99e+00

Pos logit contributions
iaries+1.084
acas+1.063
OTOS+1.010
ruary+0.991
mitt+0.981
Neg logit contributions
��-1.323
ット-0.988
�醒-0.976
Line-0.975
uez-0.962
Token bike
Token ID7161
Feature activation+4.06e+00

Pos logit contributions
iaries+1.759
acas+1.738
OTOS+1.650
mitt+1.606
ruary+1.603
Neg logit contributions
��-2.712
�醒-2.078
ット-2.066
Line-2.061
uez-2.045
Token,
Token ID11
Feature activation+3.34e+00

Pos logit contributions
iaries+2.597
acas+2.569
OTOS+2.412
mitt+2.375
ruary+2.369
Neg logit contributions
��-3.502
ット-2.631
�醒-2.614
���-2.583
uez-2.568
Token made
Token ID925
Feature activation+4.82e+00

Pos logit contributions
iaries+2.286
acas+2.221
OTOS+2.127
ruary+2.069
mitt+2.060
Neg logit contributions
��-2.783
ット-2.057
�醒-2.046
Line-2.022
���-2.017
Token Damian
Token ID42574
Feature activation+4.12e+00

Pos logit contributions
��+1.963
Line+1.497
ット+1.475
�醒+1.463
uez+1.456
Neg logit contributions
iaries-1.645
acas-1.597
OTOS-1.516
ruary-1.504
mitt-1.453
Token Allow
Token ID22507
Feature activation-1.41e+00

Pos logit contributions
iaries+2.886
acas+2.847
OTOS+2.682
ruary+2.636
mitt+2.634
Neg logit contributions
��-3.358
ット-2.452
�醒-2.442
���-2.394
Line-2.388
Tokenay
Token ID323
Feature activation-1.22e+00

Pos logit contributions
��+1.055
ット+0.765
Line+0.758
�醒+0.749
uez+0.743
Neg logit contributions
iaries-1.069
acas-1.043
OTOS-1.001
ruary-0.982
mitt-0.971
Token committed
Token ID5364
Feature activation+2.06e+00

Pos logit contributions
��+0.986
Line+0.737
ット+0.737
�醒+0.722
uez+0.721
Neg logit contributions
iaries-0.856
acas-0.830
OTOS-0.793
ruary-0.779
mitt-0.764
Token to
Token ID284
Feature activation+5.00e-01

Pos logit contributions
iaries+1.329
acas+1.290
OTOS+1.227
ruary+1.204
mitt+1.188
Neg logit contributions
��-1.792
ット-1.360
Line-1.338
�醒-1.337
uez-1.325
Token UCLA
Token ID21750
Feature activation-3.04e+00

Pos logit contributions
iaries+0.336
acas+0.326
OTOS+0.311
ruary+0.305
mitt+0.300
Neg logit contributions
��-0.420
ット-0.316
Line-0.314
�醒-0.311
uez-0.309
Token on
Token ID319
Feature activation-3.59e-01

Pos logit contributions
��+2.357
Line+1.770
ット+1.728
�醒+1.708
uez+1.707
Neg logit contributions
iaries-2.202
acas-2.141
OTOS-2.033
ruary-1.989
mitt-1.963
Token Friday
Token ID3217
Feature activation+7.52e-01

Pos logit contributions
��+0.266
Line+0.193
ット+0.192
�醒+0.188
uez+0.188
Neg logit contributions
iaries-0.276
acas-0.268
OTOS-0.257
ruary-0.252
mitt-0.249
Token via
Token ID2884
Feature activation+1.89e+00

Pos logit contributions
iaries+0.520
acas+0.506
OTOS+0.482
ruary+0.473
mitt+0.467
Neg logit contributions
��-0.618
ット-0.462
Line-0.458
�醒-0.454
uez-0.450
Token Ble
Token ID17175
Feature activation-2.11e+00

Pos logit contributions
iaries+1.295
acas+1.266
OTOS+1.214
ruary+1.185
mitt+1.178
Neg logit contributions
��-1.561
ット-1.166
Line-1.145
�醒-1.142
uez-1.131
Tokenacher
Token ID3493
Feature activation+2.65e+00

Pos logit contributions
��+1.564
ット+1.149
Line+1.144
uez+1.122
�醒+1.116
Neg logit contributions
iaries-1.596
acas-1.554
OTOS-1.496
ruary-1.470
 "$:/-1.435
Token press
Token ID1803
Feature activation-5.96e-01

Pos logit contributions
iaries+3.098
acas+3.098
OTOS+2.863
ruary+2.819
mitt+2.813
Neg logit contributions
��-3.848
�醒-2.890
ット-2.886
���-2.828
-2.798
Token conference
Token ID4495
Feature activation-9.53e-01

Pos logit contributions
��+0.404
ット+0.282
Line+0.279
�醒+0.276
uez+0.272
Neg logit contributions
iaries-0.495
acas-0.484
OTOS-0.465
ruary-0.459
mitt-0.451
Token,
Token ID11
Feature activation+1.94e+00

Pos logit contributions
��+0.769
ット+0.577
Line+0.576
uez+0.561
�醒+0.560
Neg logit contributions
iaries-0.667
acas-0.641
OTOS-0.618
ruary-0.606
mitt-0.597
Token EV
Token ID8696
Feature activation+7.64e-01

Pos logit contributions
iaries+1.337
acas+1.304
OTOS+1.241
ruary+1.217
mitt+1.203
Neg logit contributions
��-1.599
ット-1.191
�醒-1.183
Line-1.175
uez-1.160
TokenO
Token ID46
Feature activation-1.96e+00

Pos logit contributions
iaries+0.567
acas+0.553
OTOS+0.531
ruary+0.519
mitt+0.514
Neg logit contributions
��-0.590
ット-0.431
�醒-0.425
Line-0.423
���-0.419
Token Japan
Token ID2869
Feature activation-7.81e+00

Pos logit contributions
��+1.699
Line+1.309
ット+1.298
uez+1.266
 Lines+1.261
Neg logit contributions
iaries-1.246
acas-1.212
OTOS-1.163
ruary-1.124
 "$:/-1.119
Token's
Token ID338
Feature activation-1.12e+00

Pos logit contributions
��+6.111
Line+4.753
 Lines+4.627
 Younger+4.514
uez+4.507
Neg logit contributions
iaries-5.227
acas-5.047
OTOS-4.881
 "$:/-4.796
mitt-4.773
Token organizers
Token ID19043
Feature activation-5.23e-01

Pos logit contributions
��+0.918
ット+0.692
Line+0.691
uez+0.674
 Younger+0.669
Neg logit contributions
iaries-0.763
acas-0.740
OTOS-0.713
ruary-0.694
mitt-0.684
Token stated
Token ID5081
Feature activation+3.28e+00

Pos logit contributions
��+0.454
ット+0.345
Line+0.344
uez+0.339
�醒+0.338
Neg logit contributions
iaries-0.336
acas-0.326
OTOS-0.312
ruary-0.303
mitt-0.299
Token that
Token ID326
Feature activation+2.34e+00

Pos logit contributions
iaries+2.213
acas+2.164
OTOS+2.057
ruary+2.021
mitt+1.997
Neg logit contributions
��-2.739
ット-2.054
�醒-2.039
Line-2.018
���-1.998
Token the
Token ID262
Feature activation+9.10e-01

Pos logit contributions
iaries+1.528
acas+1.490
OTOS+1.410
ruary+1.387
mitt+1.370
Neg logit contributions
��-2.019
ット-1.525
�醒-1.516
Line-1.499
���-1.485
Token by
Token ID416
Feature activation-2.40e+00

Pos logit contributions
��+2.345
ット+1.798
Line+1.783
uez+1.742
�醒+1.733
Neg logit contributions
iaries-1.855
acas-1.785
OTOS-1.693
ruary-1.683
imore-1.656
Token:
Token ID25
Feature activation-3.41e+00

Pos logit contributions
��+1.954
Line+1.488
ット+1.477
uez+1.451
 Lines+1.437
Neg logit contributions
iaries-1.631
acas-1.572
OTOS-1.497
ruary-1.486
mitt-1.458
Token NO
Token ID8005
Feature activation-1.46e+00

Pos logit contributions
��+2.723
Line+2.081
ット+2.061
uez+2.017
 Lines+2.006
Neg logit contributions
iaries-2.349
acas-2.265
OTOS-2.150
ruary-2.132
mitt-2.101
TokenVA
Token ID11731
Feature activation-1.54e+00

Pos logit contributions
��+1.173
ット+0.882
Line+0.877
�醒+0.863
uez+0.858
Neg logit contributions
iaries-1.033
acas-0.997
OTOS-0.939
ruary-0.936
mitt-0.921
Token.
Token ID13
Feature activation-5.95e+00

Pos logit contributions
��+1.287
ット+0.981
Line+0.976
�醒+0.954
uez+0.953
Neg logit contributions
iaries-1.027
acas-0.992
OTOS-0.934
ruary-0.927
mitt-0.916
TokenTV
Token ID6849
Feature activation-7.51e+00

Pos logit contributions
��+4.782
Line+3.710
ット+3.709
 Lines+3.571
+3.550
Neg logit contributions
iaries-3.974
acas-3.839
imore-3.615
ruary-3.607
mitt-3.565
Token
Token ID198
Feature activation-2.87e+00

Pos logit contributions
��+5.852
Line+4.540
ット+4.447
 Lines+4.421
 Younger+4.268
Neg logit contributions
iaries-5.032
acas-4.850
ruary-4.625
imore-4.612
 "$:/-4.600
Token
Token ID198
Feature activation-3.13e+00

Pos logit contributions
��+2.342
Line+1.848
ット+1.829
+1.758
uez+1.755
Neg logit contributions
iaries-1.949
acas-1.868
OTOS-1.755
ruary-1.752
imore-1.715
TokenOn
Token ID2202
Feature activation-4.48e+00

Pos logit contributions
��+2.545
Line+2.001
ット+1.959
+1.892
uez+1.892
Neg logit contributions
iaries-2.133
acas-2.055
ruary-1.933
OTOS-1.932
 "$:/-1.901
Token a
Token ID257
Feature activation-1.23e+00

Pos logit contributions
��+3.263
Line+2.471
ット+2.400
 Lines+2.359
uez+2.352
Neg logit contributions
iaries-3.379
acas-3.245
OTOS-3.150
imore-3.041
ruary-3.020
Token dramatic
Token ID10092
Feature activation+2.22e+00

Pos logit contributions
��+0.911
Line+0.660
ット+0.659
�醒+0.644
uez+0.642
Neg logit contributions
iaries-0.942
acas-0.915
OTOS-0.883
ruary-0.862
mitt-0.850
Token):
Token ID2599
Feature activation-2.92e+00

Pos logit contributions
iaries+0.275
acas+0.267
OTOS+0.253
ruary+0.248
mitt+0.244
Neg logit contributions
��-0.391
ット-0.299
Line-0.297
�醒-0.295
uez-0.292
Token
Token ID564
Feature activation-1.05e+00

Pos logit contributions
��+2.460
Line+1.851
�醒+1.848
ット+1.844
uez+1.806
Neg logit contributions
iaries-1.957
acas-1.876
OTOS-1.775
ruary-1.757
mitt-1.724
Token
Token ID250
Feature activation+2.48e-01

Pos logit contributions
��+0.683
ット+0.460
Line+0.454
�醒+0.453
uez+0.441
Neg logit contributions
iaries-0.911
acas-0.892
OTOS-0.857
ruary-0.845
mitt-0.834
Token[
Token ID58
Feature activation-4.30e-01

Pos logit contributions
iaries+0.166
acas+0.161
OTOS+0.154
ruary+0.151
mitt+0.148
Neg logit contributions
��-0.209
ット-0.157
Line-0.156
�醒-0.155
uez-0.154
Tokenemail
Token ID12888
Feature activation-4.38e+00

Pos logit contributions
��+0.361
ット+0.272
Line+0.270
�醒+0.268
uez+0.266
Neg logit contributions
iaries-0.288
acas-0.280
OTOS-0.267
ruary-0.262
mitt-0.258
Token protected
Token ID6861
Feature activation-8.21e+00

Pos logit contributions
��+3.289
ット+2.455
Line+2.424
�醒+2.349
���+2.331
Neg logit contributions
iaries-3.292
acas-3.137
OTOS-3.035
ruary-3.023
 "$:/-2.983
Token]
Token ID60
Feature activation-1.40e+00

Pos logit contributions
��+5.015
Line+3.536
ット+3.475
�醒+3.327
 Younger+3.320
Neg logit contributions
iaries-7.005
acas-6.756
OTOS-6.518
ruary-6.403
mitt-6.365
Token Luke
Token ID11336
Feature activation+3.67e+00

Pos logit contributions
��+1.317
ット+1.027
Line+1.024
�醒+1.015
uez+1.008
Neg logit contributions
iaries-0.802
acas-0.775
OTOS-0.728
ruary-0.712
mitt-0.699
Token,
Token ID11
Feature activation+3.43e+00

Pos logit contributions
iaries+2.462
acas+2.433
OTOS+2.317
ruary+2.270
mitt+2.245
Neg logit contributions
��-3.023
ット-2.287
�醒-2.244
Line-2.231
uez-2.209
Token I
Token ID314
Feature activation-1.69e+00

Pos logit contributions
iaries+2.327
acas+2.298
OTOS+2.191
ruary+2.149
mitt+2.135
Neg logit contributions
��-2.818
ット-2.113
�醒-2.080
Line-2.052
���-2.048
Token know
Token ID760
Feature activation-6.65e-01

Pos logit contributions
��+1.364
ット+1.020
Line+1.018
uez+1.000
�醒+0.992
Neg logit contributions
iaries-1.181
acas-1.146
OTOS-1.101
ruary-1.075
mitt-1.056
Token of
Token ID286
Feature activation-7.74e-01

Pos logit contributions
iaries+0.470
acas+0.457
OTOS+0.435
ruary+0.427
mitt+0.421
Neg logit contributions
��-0.575
ット-0.432
Line-0.428
�醒-0.425
uez-0.421
Token Virginia
Token ID6025
Feature activation-3.71e+00

Pos logit contributions
��+0.648
ット+0.490
Line+0.484
�醒+0.479
uez+0.477
Neg logit contributions
iaries-0.522
acas-0.506
OTOS-0.484
ruary-0.473
mitt-0.466
Token.
Token ID13
Feature activation-2.96e-01

Pos logit contributions
��+2.991
Line+2.247
ット+2.234
�醒+2.186
uez+2.169
Neg logit contributions
iaries-2.613
acas-2.507
OTOS-2.404
 "$:/-2.338
ruary-2.334
Token
Token ID198
Feature activation-5.60e-01

Pos logit contributions
��+0.249
ット+0.189
Line+0.188
�醒+0.185
uez+0.184
Neg logit contributions
iaries-0.198
acas-0.192
OTOS-0.182
ruary-0.179
mitt-0.177
Token
Token ID198
Feature activation-1.30e+00

Pos logit contributions
��+0.481
ット+0.369
Line+0.369
uez+0.361
�醒+0.359
Neg logit contributions
iaries-0.363
acas-0.352
OTOS-0.333
ruary-0.328
mitt-0.321
TokenDel
Token ID13856
Feature activation-7.40e+00

Pos logit contributions
��+1.113
Line+0.858
ット+0.851
uez+0.832
�醒+0.831
Neg logit contributions
iaries-0.856
acas-0.827
OTOS-0.779
ruary-0.774
mitt-0.754
Token.
Token ID13
Feature activation-1.71e+00

Pos logit contributions
��+5.922
Line+4.457
uez+4.356
ット+4.302
�醒+4.268
Neg logit contributions
iaries-5.049
acas-4.822
 "$:/-4.625
OTOS-4.623
mitt-4.459
Token Todd
Token ID14377
Feature activation+2.21e+00

Pos logit contributions
��+1.638
ット+1.284
Line+1.278
uez+1.263
�醒+1.260
Neg logit contributions
iaries-0.959
acas-0.919
OTOS-0.856
ruary-0.836
mitt-0.825
Token Gilbert
Token ID24023
Feature activation-9.68e-01

Pos logit contributions
iaries+1.225
acas+1.187
OTOS+1.120
ruary+1.095
mitt+1.074
Neg logit contributions
��-2.112
ット-1.659
Line-1.638
�醒-1.634
���-1.617
Token (
Token ID357
Feature activation-2.10e+00

Pos logit contributions
��+0.800
ット+0.603
Line+0.600
uez+0.591
�醒+0.589
Neg logit contributions
iaries-0.662
acas-0.641
OTOS-0.611
ruary-0.602
mitt-0.591
TokenR
Token ID49
Feature activation+2.55e+00

Pos logit contributions
��+1.926
Line+1.507
ット+1.496
�醒+1.466
uez+1.464
Neg logit contributions
iaries-1.244
acas-1.202
OTOS-1.120
ruary-1.113
 "$:/-1.079
Token,
Token ID11
Feature activation-3.82e+00

Pos logit contributions
��+2.281
ット+1.694
Line+1.682
uez+1.650
�醒+1.641
Neg logit contributions
iaries-2.032
acas-1.968
OTOS-1.900
ruary-1.861
mitt-1.820
Token and
Token ID290
Feature activation-3.07e+00

Pos logit contributions
��+3.001
Line+2.225
ット+2.213
uez+2.172
 Younger+2.151
Neg logit contributions
iaries-2.720
acas-2.659
OTOS-2.562
ruary-2.509
mitt-2.446
Token the
Token ID262
Feature activation-1.49e+00

Pos logit contributions
��+2.370
Line+1.733
ット+1.726
uez+1.698
 Younger+1.677
Neg logit contributions
iaries-2.254
acas-2.204
OTOS-2.121
ruary-2.073
mitt-2.040
Token application
Token ID3586
Feature activation-3.55e+00

Pos logit contributions
��+1.176
ット+0.867
Line+0.860
�醒+0.849
uez+0.846
Neg logit contributions
iaries-1.079
acas-1.052
OTOS-1.006
ruary-0.986
mitt-0.972
Token of
Token ID286
Feature activation-4.14e+00

Pos logit contributions
��+2.959
ット+2.202
Line+2.184
�醒+2.164
���+2.142
Neg logit contributions
iaries-2.409
acas-2.365
OTOS-2.245
ruary-2.227
mitt-2.158
Token established
Token ID4920
Feature activation-7.40e+00

Pos logit contributions
��+3.097
Line+2.282
ット+2.274
 Younger+2.230
uez+2.215
Neg logit contributions
iaries-3.090
acas-3.006
OTOS-2.882
ruary-2.862
mitt-2.777
Token theory
Token ID4583
Feature activation-5.26e+00

Pos logit contributions
��+5.108
Line+3.781
ット+3.713
 Younger+3.683
 reflex+3.645
Neg logit contributions
iaries-5.701
acas-5.630
OTOS-5.457
ruary-5.409
ashtra-5.194
Token to
Token ID284
Feature activation-1.36e+00

Pos logit contributions
��+4.216
Line+3.147
ット+3.129
uez+3.058
 Younger+3.040
Neg logit contributions
iaries-3.638
acas-3.534
OTOS-3.420
ruary-3.349
mitt-3.257
Token the
Token ID262
Feature activation-2.34e+00

Pos logit contributions
��+1.100
ット+0.823
Line+0.816
uez+0.801
�醒+0.798
Neg logit contributions
iaries-0.956
acas-0.928
OTOS-0.890
ruary-0.874
mitt-0.858
Token results
Token ID2482
Feature activation-3.03e+00

Pos logit contributions
��+1.796
ット+1.320
Line+1.311
uez+1.288
�醒+1.281
Neg logit contributions
iaries-1.729
acas-1.689
OTOS-1.625
ruary-1.593
mitt-1.567
Token.
Token ID13
Feature activation+9.04e-01

Pos logit contributions
��+2.526
ット+1.907
Line+1.904
uez+1.864
�醒+1.856
Neg logit contributions
iaries-2.026
acas-1.971
OTOS-1.900
ruary-1.859
mitt-1.807