TOP ACTIVATIONS
MAX = 3.228

and an anonymous source will suffice . Any mistake sparks talk
a 2014 article , De ves h Kap ur , professor
possession and possession of drug parap hern alia . It
akh ota Lake , Government Colony , Jam n agar ,
A gentleman , while dancing with a
41 , he has re pped the 305 since 1973 .
on all previous Mars ro vers , which have examined hundreds
and down the eastern se ab oard . They now have
sounding like cock ney Tony Sop rano .
more indirectly , said Mad hur ima Bak shi , a
hand . Det Sgt Ronnie Payne asked anyone with
. The apex court had earlier issued notices and
connecting Roh t ak to Delhi . After this , the
ar of the A am Aad mi Party , arrested this
. Sc ann ell and Lt . Emil Rick ner were
cs will go here + -------------------- --+ + -------------------- --+ <
Aaron Larson , associate editor (@ Aaron
. From the Kodi home screen , choose Add
percent ). Be hold , one of the few
affairs . O vert ime for some employees on

MIN ACTIVATIONS
MIN = -2.969

States Conference of Catholic B ishops ( US CC B )
to Go Back There Som eday ." In 1984
13 ]: 137 Patrick S ü sk ind 's novel Per
who signed a letter to CMS a few weeks ago .
- shaped ep oxy resin scaff old that measures 0 .
genome , using dozens of automated sequencing machines .
rules for the Affordable Care Act ( ACA ), or Obamacare
male patriarchal methods of teaching computation and statistics in favor of
minutes later . Players s ifted over what s
support for the Affordable Care Act reaching 54 % well
alternative to the Affordable Care Act and sell the public on
's a full breakdown from CMS ) in order to be
universally across Linux distributions , bund ling any dependencies as needed
The Ol we us B ully / Vict im Question naire
, or the Affordable Care Act , required Americans who qualified
, vegetable juice , and hot o atmeal . That
its boiling , reduce the heat and cover and let it
( 0 , ($ i * $ FontSize * 2 +
c rawler , and Jub ilee hanging out in a mall
Administration . Legislative history of . 08 per se laws .

INTERVAL 1.678 - 3.228
CONTAINS 0.355%

d suggest limiting auto - ISO to 800 or lower
past . With Kron stadt and M akh no
In L in vention de la myth olog ie
under whelming . Facebook Twitter Pinterest Mick M alth
Given the far - reaching socio - economic effects , and

INTERVAL 0.129 - 1.678
CONTAINS 36.769%

to Saudi Arabia total $ 1 . 3 billion . Business
to NASA s work on the Space Launch System
>> Take action : tell Shell to drop its
to Kinder Morgan s Trans Mountain pipeline expansion ,
forward . W ong sees sad parallels

INTERVAL -1.420 - 0.129
CONTAINS 62.097%

ins cl ament que le Command ement Cors aire ser ait
, says low prices in a company 's first year don
Player Unknown specifically referenced Destiny as a title that did a
sy ur up inski y Ag rop ost ach , a
. nice hash . com , but will be disabled eventually

INTERVAL -2.969 - -1.420
CONTAINS 0.779%

. The two countries are locked in an ongoing bilateral dispute
What we can learn from this is when you
- 10 planetary system revis ited by HAR PS - N
string and go around and around the edge . This is
is hell ," William Tec um se h Sherman once said
Token and
Token ID290
Feature activation-2.04e-01

Pos logit contributions
orio+0.987
Italy+0.862
stanbul+0.858
vo+0.853
avier+0.846
Neg logit contributions
 NW-0.647
ysical-0.644
 Nest-0.624
 Harding-0.602
 nost-0.597
Token an
Token ID281
Feature activation-3.58e-01

Pos logit contributions
orio+0.180
Italy+0.156
stanbul+0.155
vo+0.154
avier+0.152
Neg logit contributions
 NW-0.136
ysical-0.134
 Nest-0.131
 Harding-0.127
 nost-0.126
Token anonymous
Token ID11614
Feature activation-3.91e-01

Pos logit contributions
orio+0.319
Italy+0.277
stanbul+0.276
vo+0.274
avier+0.272
Neg logit contributions
 NW-0.234
ysical-0.233
 Nest-0.226
 Harding-0.219
 nost-0.217
Token source
Token ID2723
Feature activation+3.12e-01

Pos logit contributions
orio+0.344
Italy+0.298
stanbul+0.297
vo+0.294
avier+0.292
Neg logit contributions
 NW-0.261
ysical-0.259
 Nest-0.253
 Harding-0.244
 nost-0.242
Token will
Token ID481
Feature activation-8.96e-02

Pos logit contributions
 NW+0.197
ysical+0.194
 Nest+0.189
 Harding+0.184
 contended+0.183
Neg logit contributions
orio-0.288
Italy-0.251
stanbul-0.249
avier-0.246
vo-0.246
Token suffice
Token ID34302
Feature activation+3.23e+00

Pos logit contributions
orio+0.084
Italy+0.073
stanbul+0.072
vo+0.071
avier+0.071
Neg logit contributions
 NW-0.056
ysical-0.055
 Nest-0.054
 nost-0.052
 Harding-0.052
Token.
Token ID13
Feature activation-1.23e-01

Pos logit contributions
 NW+2.237
ysical+2.198
 Nest+2.157
 Harding+2.098
 nost+2.091
Neg logit contributions
orio-2.743
Italy-2.370
stanbul-2.349
avier-2.320
vo-2.310
Token Any
Token ID4377
Feature activation+7.38e-01

Pos logit contributions
orio+0.118
Italy+0.103
stanbul+0.103
vo+0.102
avier+0.102
Neg logit contributions
 NW-0.072
ysical-0.071
 Nest-0.069
 Harding-0.067
 nost-0.066
Token mistake
Token ID7457
Feature activation-9.80e-01

Pos logit contributions
 NW+0.466
ysical+0.461
 Nest+0.450
 Harding+0.434
 nost+0.432
Neg logit contributions
orio-0.675
Italy-0.590
stanbul-0.588
vo-0.578
avier-0.577
Token sparks
Token ID38306
Feature activation-3.84e-01

Pos logit contributions
orio+0.904
Italy+0.789
stanbul+0.786
vo+0.782
avier+0.775
Neg logit contributions
 NW-0.607
ysical-0.606
 Nest-0.586
 Harding-0.566
 nost-0.560
Token talk
Token ID1561
Feature activation+6.80e-02

Pos logit contributions
orio+0.343
Italy+0.298
stanbul+0.296
vo+0.294
avier+0.291
Neg logit contributions
 NW-0.251
ysical-0.249
 Nest-0.243
 Harding-0.234
 nost-0.233
Token a
Token ID257
Feature activation-7.46e-02

Pos logit contributions
 NW+0.047
ysical+0.046
 Nest+0.045
 Harding+0.043
 nost+0.043
Neg logit contributions
orio-0.078
Italy-0.069
stanbul-0.068
vo-0.068
avier-0.067
Token 2014
Token ID1946
Feature activation+5.72e-01

Pos logit contributions
orio+0.072
Italy+0.064
stanbul+0.063
vo+0.063
avier+0.062
Neg logit contributions
 NW-0.043
ysical-0.043
 Nest-0.042
 Harding-0.040
 nost-0.040
Token article
Token ID2708
Feature activation+3.92e-01

Pos logit contributions
 NW+0.354
ysical+0.348
 Nest+0.341
 Harding+0.327
 nost+0.324
Neg logit contributions
orio-0.535
Italy-0.467
stanbul-0.465
vo-0.460
avier-0.458
Token,
Token ID11
Feature activation+3.11e-01

Pos logit contributions
 NW+0.249
ysical+0.248
 Nest+0.241
 Harding+0.232
 nost+0.230
Neg logit contributions
orio-0.356
Italy-0.310
stanbul-0.309
vo-0.307
avier-0.304
Token De
Token ID1024
Feature activation-2.28e-01

Pos logit contributions
ysical+0.190
 NW+0.190
 Nest+0.183
 Harding+0.177
 nost+0.175
Neg logit contributions
orio-0.290
Italy-0.253
stanbul-0.252
vo-0.251
avier-0.248
Tokenves
Token ID1158
Feature activation+3.18e+00

Pos logit contributions
orio+0.179
Italy+0.152
stanbul+0.150
vo+0.150
avier+0.148
Neg logit contributions
 NW-0.174
ysical-0.173
 Nest-0.168
 Harding-0.164
 nost-0.163
Tokenh
Token ID71
Feature activation+1.25e+00

Pos logit contributions
 NW+2.292
ysical+2.277
 Nest+2.220
 Harding+2.154
 contended+2.149
Neg logit contributions
orio-2.609
Italy-2.246
stanbul-2.246
vo-2.191
avier-2.179
Token Kap
Token ID27344
Feature activation+9.62e-01

Pos logit contributions
 NW+0.744
ysical+0.742
 Nest+0.717
 Harding+0.691
 nost+0.685
Neg logit contributions
orio-1.184
Italy-1.036
stanbul-1.031
vo-1.026
avier-1.017
Tokenur
Token ID333
Feature activation+1.73e-01

Pos logit contributions
ysical+0.695
 NW+0.695
 Nest+0.671
 Harding+0.653
 contended+0.649
Neg logit contributions
orio-0.788
Italy-0.681
stanbul-0.676
vo-0.666
avier-0.661
Token,
Token ID11
Feature activation+3.23e-01

Pos logit contributions
 NW+0.109
ysical+0.109
 Nest+0.105
 Harding+0.101
 nost+0.101
Neg logit contributions
orio-0.158
Italy-0.138
stanbul-0.137
vo-0.137
avier-0.135
Token professor
Token ID6240
Feature activation-3.51e-01

Pos logit contributions
 NW+0.204
ysical+0.204
 Nest+0.198
 Harding+0.191
 nost+0.189
Neg logit contributions
orio-0.295
Italy-0.257
stanbul-0.256
vo-0.254
avier-0.252
Token possession
Token ID7797
Feature activation+1.23e+00

Pos logit contributions
orio+0.853
Italy+0.737
vo+0.732
stanbul+0.731
avier+0.721
Neg logit contributions
ysical-0.674
 NW-0.669
 Nest-0.651
 Harding-0.632
 nost-0.623
Token and
Token ID290
Feature activation+4.37e-01

Pos logit contributions
 NW+0.826
ysical+0.824
 Nest+0.800
 Harding+0.775
 nost+0.768
Neg logit contributions
orio-1.073
Italy-0.928
stanbul-0.924
vo-0.918
avier-0.909
Token possession
Token ID7797
Feature activation+8.84e-01

Pos logit contributions
 NW+0.274
ysical+0.272
 Nest+0.264
 Harding+0.255
 nost+0.252
Neg logit contributions
orio-0.403
Italy-0.351
stanbul-0.350
vo-0.347
avier-0.344
Token of
Token ID286
Feature activation+2.24e-01

Pos logit contributions
ysical+0.515
 NW+0.512
 Nest+0.495
 Harding+0.477
 nost+0.472
Neg logit contributions
orio-0.851
Italy-0.745
stanbul-0.743
vo-0.741
avier-0.731
Token drug
Token ID2563
Feature activation-8.58e-01

Pos logit contributions
ysical+0.133
 NW+0.132
 Nest+0.128
 Harding+0.124
 nost+0.122
Neg logit contributions
orio-0.212
Italy-0.186
stanbul-0.185
vo-0.185
avier-0.183
Token parap
Token ID41406
Feature activation+3.08e+00

Pos logit contributions
orio+0.790
Italy+0.690
vo+0.687
stanbul+0.682
avier+0.676
Neg logit contributions
ysical-0.535
 NW-0.523
 Nest-0.512
 Harding-0.497
 nost-0.487
Tokenhern
Token ID2881
Feature activation+2.68e+00

Pos logit contributions
ysical+1.557
 NW+1.538
 Nest+1.464
 Harding+1.406
 contended+1.396
Neg logit contributions
orio-3.211
Italy-2.862
stanbul-2.843
vo-2.756
oS-2.723
Tokenalia
Token ID9752
Feature activation+7.16e-01

Pos logit contributions
ysical+2.471
 NW+2.451
 Nest+2.380
 Harding+2.350
 nost+2.322
Neg logit contributions
orio-1.673
stanbul-1.376
Italy-1.370
vo-1.316
avier-1.285
Token.
Token ID13
Feature activation+3.65e-01

Pos logit contributions
ysical+0.500
 NW+0.499
 Nest+0.485
 Harding+0.470
 nost+0.466
Neg logit contributions
orio-0.606
Italy-0.521
stanbul-0.518
vo-0.516
avier-0.510
Token It
Token ID632
Feature activation+7.06e-01

Pos logit contributions
 NW+0.215
ysical+0.214
 Nest+0.207
 Harding+0.199
 nost+0.197
Neg logit contributions
orio-0.349
Italy-0.306
stanbul-0.305
vo-0.303
avier-0.301
Token
Token ID447
Feature activation+4.89e-01

Pos logit contributions
 NW+0.365
ysical+0.360
 Nest+0.348
 contended+0.335
 Harding+0.334
Neg logit contributions
orio-0.727
Italy-0.645
stanbul-0.641
vo-0.634
avier-0.630
Tokenakh
Token ID11322
Feature activation+7.28e-01

Pos logit contributions
 NW+0.337
ysical+0.336
 Nest+0.327
 Harding+0.318
 nost+0.315
Neg logit contributions
orio-0.371
Italy-0.317
stanbul-0.316
vo-0.313
avier-0.310
Tokenota
Token ID4265
Feature activation+5.31e-01

Pos logit contributions
 NW+0.587
ysical+0.583
 Nest+0.572
 Harding+0.555
 nost+0.551
Neg logit contributions
orio-0.537
Italy-0.453
stanbul-0.451
vo-0.442
avier-0.439
Token Lake
Token ID6233
Feature activation+7.65e-01

Pos logit contributions
ysical+0.347
 NW+0.342
 Nest+0.332
 Harding+0.322
 nost+0.320
Neg logit contributions
orio-0.474
Italy-0.411
vo-0.411
stanbul-0.410
avier-0.403
Token,
Token ID11
Feature activation+3.66e-01

Pos logit contributions
ysical+0.505
 NW+0.499
 Nest+0.484
 Harding+0.471
 contended+0.467
Neg logit contributions
orio-0.677
Italy-0.587
stanbul-0.585
vo-0.584
avier-0.573
Token Government
Token ID5070
Feature activation+1.25e+00

Pos logit contributions
ysical+0.226
 NW+0.223
 Nest+0.216
 Harding+0.209
 nost+0.208
Neg logit contributions
orio-0.339
Italy-0.297
stanbul-0.295
vo-0.293
avier-0.290
Token Colony
Token ID34480
Feature activation+2.98e+00

Pos logit contributions
ysical+0.733
 NW+0.731
 Nest+0.704
 Harding+0.680
 nost+0.673
Neg logit contributions
orio-1.203
Italy-1.055
stanbul-1.054
vo-1.047
avier-1.036
Token,
Token ID11
Feature activation+6.50e-01

Pos logit contributions
 NW+1.881
ysical+1.850
 Nest+1.812
 Harding+1.744
 nost+1.725
Neg logit contributions
orio-2.745
Italy-2.387
stanbul-2.378
vo-2.361
avier-2.346
Token Jam
Token ID9986
Feature activation+4.10e-01

Pos logit contributions
ysical+0.403
 NW+0.402
 Nest+0.389
 Harding+0.376
 nost+0.373
Neg logit contributions
orio-0.601
Italy-0.525
stanbul-0.522
vo-0.519
avier-0.514
Tokenn
Token ID77
Feature activation+9.96e-01

Pos logit contributions
ysical+0.280
 NW+0.279
 Nest+0.271
 Harding+0.263
 nost+0.260
Neg logit contributions
orio-0.355
Italy-0.306
stanbul-0.305
vo-0.303
avier-0.299
Tokenagar
Token ID32452
Feature activation+1.33e+00

Pos logit contributions
ysical+0.563
 NW+0.561
 Nest+0.539
 Harding+0.522
 contended+0.511
Neg logit contributions
orio-0.972
Italy-0.861
stanbul-0.856
vo-0.850
avier-0.837
Token,
Token ID11
Feature activation+5.65e-01

Pos logit contributions
ysical+0.855
 NW+0.853
 Nest+0.825
 Harding+0.799
 nost+0.792
Neg logit contributions
orio-1.200
Italy-1.047
stanbul-1.040
vo-1.036
avier-1.023
Token
Token ID198
Feature activation+1.20e-01

Pos logit contributions
 NW+0.154
ysical+0.153
 Nest+0.149
 Harding+0.143
 nost+0.141
Neg logit contributions
orio-0.264
Italy-0.231
stanbul-0.231
vo-0.229
avier-0.227
Token
Token ID198
Feature activation+2.80e-01

Pos logit contributions
 NW+0.063
ysical+0.061
 Nest+0.060
 Harding+0.057
 nost+0.056
Neg logit contributions
orio-0.125
stanbul-0.111
Italy-0.109
avier-0.108
vo-0.108
Token
Token ID447
Feature activation+7.15e-02

Pos logit contributions
 NW+0.200
ysical+0.199
 Nest+0.194
 Harding+0.189
 nost+0.186
Neg logit contributions
orio-0.232
stanbul-0.197
Italy-0.195
vo-0.194
avier-0.193
Token
Token ID250
Feature activation+1.65e-01

Pos logit contributions
 NW+0.062
ysical+0.061
 Nest+0.060
 Harding+0.058
 nost+0.058
Neg logit contributions
orio-0.049
Italy-0.041
stanbul-0.040
vo-0.040
avier-0.039
TokenA
Token ID32
Feature activation-2.05e-01

Pos logit contributions
 NW+0.104
ysical+0.103
 Nest+0.100
 Harding+0.097
 nost+0.095
Neg logit contributions
orio-0.152
Italy-0.132
stanbul-0.132
vo-0.131
avier-0.130
Token gentleman
Token ID22427
Feature activation+2.93e+00

Pos logit contributions
orio+0.199
Italy+0.175
stanbul+0.174
vo+0.173
avier+0.172
Neg logit contributions
 NW-0.118
ysical-0.117
 Nest-0.114
 Harding-0.109
 nost-0.108
Token,
Token ID11
Feature activation+3.44e-01

Pos logit contributions
 NW+1.816
ysical+1.779
 Nest+1.754
 contended+1.707
 Harding+1.693
Neg logit contributions
orio-2.701
Italy-2.364
stanbul-2.350
vo-2.322
oS-2.269
Token while
Token ID981
Feature activation+6.13e-01

Pos logit contributions
 NW+0.219
ysical+0.218
 Nest+0.212
 Harding+0.205
 contended+0.203
Neg logit contributions
orio-0.314
Italy-0.273
stanbul-0.272
vo-0.269
avier-0.267
Token dancing
Token ID15360
Feature activation+1.19e+00

Pos logit contributions
 NW+0.390
ysical+0.385
 Nest+0.377
 Harding+0.364
 contended+0.362
Neg logit contributions
orio-0.562
Italy-0.489
stanbul-0.487
vo-0.482
avier-0.477
Token with
Token ID351
Feature activation+3.20e-01

Pos logit contributions
 NW+0.725
ysical+0.710
 Nest+0.698
 contended+0.672
 Harding+0.672
Neg logit contributions
orio-1.126
stanbul-0.986
Italy-0.982
vo-0.965
avier-0.958
Token a
Token ID257
Feature activation+2.22e-01

Pos logit contributions
 NW+0.219
ysical+0.218
 Nest+0.213
 Harding+0.206
 nost+0.204
Neg logit contributions
orio-0.276
Italy-0.238
stanbul-0.237
vo-0.235
avier-0.232
Token 41
Token ID6073
Feature activation+6.18e-02

Pos logit contributions
 NW+0.342
ysical+0.338
 Nest+0.330
 Harding+0.318
 nost+0.314
Neg logit contributions
orio-0.508
Italy-0.443
stanbul-0.441
vo-0.438
avier-0.434
Token,
Token ID11
Feature activation-7.47e-02

Pos logit contributions
 NW+0.041
ysical+0.041
 Nest+0.040
 Harding+0.038
 nost+0.038
Neg logit contributions
orio-0.054
Italy-0.047
stanbul-0.047
vo-0.046
avier-0.046
Token he
Token ID339
Feature activation+2.78e-02

Pos logit contributions
orio+0.071
Italy+0.062
stanbul+0.062
vo+0.062
avier+0.061
Neg logit contributions
 NW-0.044
ysical-0.044
 Nest-0.043
 Harding-0.041
 nost-0.041
Token has
Token ID468
Feature activation-2.39e-01

Pos logit contributions
 NW+0.017
ysical+0.017
 Nest+0.016
 Harding+0.016
 contended+0.016
Neg logit contributions
orio-0.026
Italy-0.023
stanbul-0.023
vo-0.022
avier-0.022
Token re
Token ID302
Feature activation-1.23e-01

Pos logit contributions
orio+0.209
Italy+0.181
stanbul+0.180
vo+0.178
avier+0.178
Neg logit contributions
 NW-0.162
ysical-0.160
 Nest-0.157
 Harding-0.151
 nost-0.150
Tokenpped
Token ID1496
Feature activation+2.91e+00

Pos logit contributions
orio+0.093
Italy+0.078
stanbul+0.078
vo+0.077
avier+0.077
Neg logit contributions
 NW-0.098
ysical-0.097
 Nest-0.095
 Harding-0.092
 nost-0.092
Token the
Token ID262
Feature activation-9.00e-02

Pos logit contributions
 NW+1.972
ysical+1.906
 Nest+1.902
 Harding+1.838
 nost+1.812
Neg logit contributions
orio-2.549
Italy-2.211
stanbul-2.194
vo-2.165
avier-2.163
Token 305
Token ID32747
Feature activation+1.66e-02

Pos logit contributions
orio+0.081
Italy+0.070
stanbul+0.070
vo+0.069
avier+0.069
Neg logit contributions
 NW-0.059
ysical-0.058
 Nest-0.057
 Harding-0.055
 nost-0.054
Token since
Token ID1201
Feature activation-8.06e-03

Pos logit contributions
 NW+0.011
ysical+0.011
 Nest+0.011
 Harding+0.011
 nost+0.010
Neg logit contributions
orio-0.014
Italy-0.012
stanbul-0.012
vo-0.012
avier-0.012
Token 1973
Token ID15674
Feature activation+2.32e-01

Pos logit contributions
orio+0.008
Italy+0.007
stanbul+0.007
vo+0.007
avier+0.007
Neg logit contributions
 NW-0.005
ysical-0.005
 Nest-0.004
 Harding-0.004
 nost-0.004
Token.
Token ID13
Feature activation-1.75e-01

Pos logit contributions
 NW+0.161
ysical+0.159
 Nest+0.155
 Harding+0.150
 nost+0.149
Neg logit contributions
orio-0.199
Italy-0.172
stanbul-0.171
vo-0.170
avier-0.168
Token on
Token ID319
Feature activation+3.16e-01

Pos logit contributions
 NW+0.297
ysical+0.293
 Nest+0.288
 Harding+0.278
 nost+0.276
Neg logit contributions
orio-0.373
Italy-0.323
stanbul-0.321
vo-0.318
avier-0.314
Token all
Token ID477
Feature activation+1.44e-01

Pos logit contributions
 NW+0.165
ysical+0.163
 Nest+0.159
 Harding+0.152
 nost+0.149
Neg logit contributions
orio-0.325
Italy-0.288
stanbul-0.288
vo-0.285
avier-0.283
Token previous
Token ID2180
Feature activation-2.12e-01

Pos logit contributions
 NW+0.095
ysical+0.094
 Nest+0.092
 Harding+0.089
 nost+0.088
Neg logit contributions
orio-0.128
Italy-0.111
stanbul-0.111
vo-0.110
avier-0.109
Token Mars
Token ID8706
Feature activation+2.97e-01

Pos logit contributions
orio+0.184
Italy+0.159
stanbul+0.158
vo+0.157
avier+0.156
Neg logit contributions
 NW-0.143
ysical-0.143
 Nest-0.139
 Harding-0.134
 nost-0.133
Token ro
Token ID686
Feature activation+8.39e-01

Pos logit contributions
 NW+0.228
ysical+0.226
 Nest+0.221
 Harding+0.215
 nost+0.213
Neg logit contributions
orio-0.231
stanbul-0.198
Italy-0.197
avier-0.193
vo-0.193
Tokenvers
Token ID690
Feature activation+2.90e+00

Pos logit contributions
ysical+0.671
 NW+0.670
 Nest+0.653
 Harding+0.639
 nost+0.633
Neg logit contributions
orio-0.615
stanbul-0.529
Italy-0.519
avier-0.513
vo-0.500
Token,
Token ID11
Feature activation-4.13e-02

Pos logit contributions
 NW+1.972
ysical+1.933
 Nest+1.925
 Harding+1.845
 contended+1.831
Neg logit contributions
orio-2.508
Italy-2.173
stanbul-2.167
vo-2.127
avier-2.112
Token which
Token ID543
Feature activation+2.63e-01

Pos logit contributions
orio+0.037
Italy+0.032
stanbul+0.032
vo+0.032
avier+0.031
Neg logit contributions
 NW-0.027
ysical-0.027
 Nest-0.026
 Harding-0.025
 contended-0.025
Token have
Token ID423
Feature activation+2.64e-01

Pos logit contributions
 NW+0.158
ysical+0.156
 Nest+0.153
 Harding+0.148
 contended+0.146
Neg logit contributions
orio-0.249
Italy-0.218
stanbul-0.217
vo-0.215
avier-0.213
Token examined
Token ID11068
Feature activation-4.41e-01

Pos logit contributions
 NW+0.161
ysical+0.159
 Nest+0.156
 Harding+0.151
 contended+0.150
Neg logit contributions
orio-0.248
Italy-0.216
stanbul-0.215
vo-0.213
avier-0.212
Token hundreds
Token ID5179
Feature activation-2.33e-01

Pos logit contributions
orio+0.388
Italy+0.336
stanbul+0.334
vo+0.332
avier+0.329
Neg logit contributions
 NW-0.294
ysical-0.293
 Nest-0.285
 Harding-0.275
 nost-0.273
Token and
Token ID290
Feature activation+3.15e-01

Pos logit contributions
 NW+0.191
ysical+0.189
 Nest+0.184
 Harding+0.178
 nost+0.177
Neg logit contributions
orio-0.251
Italy-0.217
stanbul-0.216
vo-0.215
avier-0.213
Token down
Token ID866
Feature activation+3.67e-01

Pos logit contributions
 NW+0.191
ysical+0.190
 Nest+0.184
 Harding+0.178
 nost+0.176
Neg logit contributions
orio-0.296
Italy-0.258
stanbul-0.257
vo-0.256
avier-0.253
Token the
Token ID262
Feature activation+2.04e-01

Pos logit contributions
ysical+0.221
 NW+0.220
 Nest+0.213
 Harding+0.205
 nost+0.203
Neg logit contributions
orio-0.346
Italy-0.303
stanbul-0.302
vo-0.300
avier-0.297
Token eastern
Token ID10183
Feature activation-3.40e-01

Pos logit contributions
 NW+0.122
ysical+0.120
 Nest+0.117
 Harding+0.113
 nost+0.112
Neg logit contributions
orio-0.195
Italy-0.171
stanbul-0.170
vo-0.169
avier-0.168
Token se
Token ID384
Feature activation+8.28e-01

Pos logit contributions
orio+0.279
Italy+0.238
stanbul+0.238
vo+0.234
avier+0.233
Neg logit contributions
 NW-0.250
ysical-0.245
 Nest-0.240
 Harding-0.233
 nost-0.232
Tokenab
Token ID397
Feature activation+2.86e+00

Pos logit contributions
 NW+0.541
ysical+0.540
 Nest+0.523
 Harding+0.506
 nost+0.501
Neg logit contributions
orio-0.739
Italy-0.642
stanbul-0.639
vo-0.637
avier-0.630
Tokenoard
Token ID11953
Feature activation-1.08e+00

Pos logit contributions
 NW+2.476
ysical+2.430
 Nest+2.378
 Harding+2.310
 nost+2.295
Neg logit contributions
orio-1.995
stanbul-1.659
Italy-1.637
vo-1.615
avier-1.560
Token.
Token ID13
Feature activation+2.03e-01

Pos logit contributions
orio+0.913
stanbul+0.788
Italy+0.788
vo+0.781
avier+0.769
Neg logit contributions
ysical-0.758
 NW-0.752
 Nest-0.734
 Harding-0.711
 contended-0.705
Token They
Token ID1119
Feature activation+6.60e-01

Pos logit contributions
 NW+0.136
ysical+0.136
 Nest+0.132
 Harding+0.128
 nost+0.127
Neg logit contributions
orio-0.177
Italy-0.153
stanbul-0.153
vo-0.152
avier-0.150
Token now
Token ID783
Feature activation-2.04e-01

Pos logit contributions
 NW+0.401
ysical+0.395
 Nest+0.384
 contended+0.372
 Harding+0.370
Neg logit contributions
orio-0.622
Italy-0.545
stanbul-0.537
vo-0.534
avier-0.530
Token have
Token ID423
Feature activation-1.47e-02

Pos logit contributions
orio+0.184
Italy+0.159
stanbul+0.158
vo+0.157
avier+0.156
Neg logit contributions
 NW-0.133
ysical-0.131
 Nest-0.128
 Harding-0.123
 contended-0.123
Token sounding
Token ID22655
Feature activation+6.66e-01

Pos logit contributions
 NW+0.109
ysical+0.107
 Nest+0.106
 nost+0.101
 Harding+0.101
Neg logit contributions
orio-0.168
Italy-0.147
stanbul-0.145
vo-0.144
avier-0.143
Token like
Token ID588
Feature activation-3.29e-01

Pos logit contributions
 NW+0.451
ysical+0.443
 Nest+0.435
 Harding+0.421
 nost+0.418
Neg logit contributions
orio-0.584
Italy-0.504
stanbul-0.501
vo-0.496
avier-0.492
Token cock
Token ID7540
Feature activation-2.50e-01

Pos logit contributions
orio+0.297
Italy+0.258
stanbul+0.257
vo+0.255
avier+0.253
Neg logit contributions
 NW-0.211
ysical-0.210
 Nest-0.204
 Harding-0.197
 nost-0.195
Tokenney
Token ID1681
Feature activation-6.99e-01

Pos logit contributions
orio+0.201
Italy+0.171
stanbul+0.170
vo+0.168
avier+0.167
Neg logit contributions
 NW-0.185
ysical-0.184
 Nest-0.180
 Harding-0.174
 nost-0.174
Token Tony
Token ID8832
Feature activation+3.36e-01

Pos logit contributions
orio+0.590
Italy+0.508
stanbul+0.505
vo+0.501
avier+0.497
Neg logit contributions
 NW-0.490
ysical-0.489
 Nest-0.475
 Harding-0.461
 nost-0.457
Token Sop
Token ID35643
Feature activation+2.86e+00

Pos logit contributions
 NW+0.211
ysical+0.209
 Nest+0.204
 Harding+0.197
 nost+0.195
Neg logit contributions
orio-0.309
Italy-0.269
stanbul-0.268
vo-0.265
avier-0.264
Tokenrano
Token ID35823
Feature activation-3.90e-01

Pos logit contributions
ysical+3.002
 NW+2.996
 Nest+2.922
 Harding+2.870
 nost+2.840
Neg logit contributions
orio-1.385
Italy-1.091
stanbul-1.076
vo-1.050
avier-1.027
Token.
Token ID13
Feature activation-6.47e-02

Pos logit contributions
orio+0.335
Italy+0.290
stanbul+0.287
vo+0.285
avier+0.283
Neg logit contributions
 NW-0.268
ysical-0.266
 Nest-0.260
 Harding-0.252
 nost-0.250
Token
Token ID447
Feature activation+1.28e-01

Pos logit contributions
orio+0.057
Italy+0.050
stanbul+0.049
vo+0.049
avier+0.049
Neg logit contributions
 NW-0.043
ysical-0.043
 Nest-0.041
 Harding-0.040
 nost-0.040
Token
Token ID251
Feature activation+9.05e-02

Pos logit contributions
 NW+0.115
ysical+0.114
 Nest+0.112
 Harding+0.109
 nost+0.109
Neg logit contributions
orio-0.083
Italy-0.068
stanbul-0.068
vo-0.068
avier-0.066
Token
Token ID198
Feature activation-2.23e-01

Pos logit contributions
 NW+0.053
ysical+0.053
 Nest+0.051
 Harding+0.049
 nost+0.049
Neg logit contributions
orio-0.087
Italy-0.076
stanbul-0.076
vo-0.075
avier-0.075
Token more
Token ID517
Feature activation-2.26e-01

Pos logit contributions
 NW+0.402
ysical+0.394
 Nest+0.391
 Harding+0.371
 contended+0.370
Neg logit contributions
orio-0.565
Italy-0.489
stanbul-0.486
vo-0.483
avier-0.482
Token indirectly
Token ID20762
Feature activation-6.42e-01

Pos logit contributions
orio+0.167
Italy+0.140
stanbul+0.139
vo+0.138
avier+0.137
Neg logit contributions
 NW-0.183
ysical-0.181
 Nest-0.178
 Harding-0.173
 contended-0.172
Token,
Token ID11
Feature activation-1.35e-01

Pos logit contributions
orio+0.557
Italy+0.482
stanbul+0.480
vo+0.475
avier+0.472
Neg logit contributions
 NW-0.436
ysical-0.432
 Nest-0.422
 Harding-0.408
 nost-0.404
Token said
Token ID531
Feature activation+1.79e-01

Pos logit contributions
orio+0.124
Italy+0.108
stanbul+0.107
vo+0.107
avier+0.106
Neg logit contributions
 NW-0.085
ysical-0.084
 Nest-0.082
 Harding-0.079
 nost-0.078
Token Mad
Token ID4627
Feature activation+6.79e-01

Pos logit contributions
 NW+0.111
ysical+0.110
 Nest+0.107
 Harding+0.103
 nost+0.102
Neg logit contributions
orio-0.166
Italy-0.145
stanbul-0.145
vo-0.144
avier-0.142
Tokenhur
Token ID48349
Feature activation+2.84e+00

Pos logit contributions
 NW+0.487
ysical+0.485
 Nest+0.472
 Harding+0.458
 nost+0.454
Neg logit contributions
orio-0.564
Italy-0.484
stanbul-0.481
vo-0.478
avier-0.473
Tokenima
Token ID8083
Feature activation+4.99e-02

Pos logit contributions
 NW+1.764
ysical+1.743
 Nest+1.716
 Harding+1.655
 contended+1.629
Neg logit contributions
orio-2.627
Italy-2.300
stanbul-2.294
vo-2.253
avier-2.234
Token Bak
Token ID17466
Feature activation+5.01e-02

Pos logit contributions
ysical+0.031
 NW+0.031
 Nest+0.030
 Harding+0.029
 nost+0.028
Neg logit contributions
orio-0.046
Italy-0.040
stanbul-0.040
vo-0.040
avier-0.040
Tokenshi
Token ID44019
Feature activation-5.12e-01

Pos logit contributions
 NW+0.048
ysical+0.048
 Nest+0.047
 Harding+0.046
 nost+0.046
Neg logit contributions
orio-0.029
Italy-0.023
stanbul-0.023
vo-0.023
avier-0.022
Token,
Token ID11
Feature activation-2.30e-02

Pos logit contributions
orio+0.450
Italy+0.389
vo+0.388
stanbul+0.388
avier+0.382
Neg logit contributions
ysical-0.341
 NW-0.338
 Nest-0.327
 Harding-0.316
 nost-0.315
Token a
Token ID257
Feature activation+2.09e-03

Pos logit contributions
orio+0.021
Italy+0.018
stanbul+0.018
vo+0.018
avier+0.017
Neg logit contributions
 NW-0.015
ysical-0.015
 Nest-0.014
 Harding-0.014
 nost-0.014
Token hand
Token ID1021
Feature activation+6.64e-01

Pos logit contributions
 NW+0.102
ysical+0.101
 Nest+0.098
 Harding+0.095
 nost+0.094
Neg logit contributions
orio-0.157
Italy-0.137
stanbul-0.136
vo-0.136
avier-0.134
Token.
Token ID13
Feature activation+2.28e-01

Pos logit contributions
 NW+0.479
ysical+0.475
 Nest+0.464
 Harding+0.450
 nost+0.448
Neg logit contributions
orio-0.548
Italy-0.471
stanbul-0.468
vo-0.463
avier-0.459
Token
Token ID198
Feature activation+2.50e-01

Pos logit contributions
ysical+0.131
 NW+0.130
 Nest+0.125
 Harding+0.120
 nost+0.120
Neg logit contributions
orio-0.221
Italy-0.194
stanbul-0.193
vo-0.193
avier-0.190
Token
Token ID198
Feature activation+3.59e-01

Pos logit contributions
 NW+0.131
ysical+0.126
 Nest+0.125
 Harding+0.118
 nost+0.116
Neg logit contributions
orio-0.259
stanbul-0.229
Italy-0.227
avier-0.224
vo-0.224
TokenDet
Token ID11242
Feature activation+7.75e-01

Pos logit contributions
 NW+0.258
ysical+0.255
 Nest+0.250
 Harding+0.243
 nost+0.239
Neg logit contributions
orio-0.297
stanbul-0.252
Italy-0.248
avier-0.247
vo-0.247
Token Sgt
Token ID22925
Feature activation+2.82e+00

Pos logit contributions
 NW+0.430
ysical+0.428
 Nest+0.414
 Harding+0.397
 nost+0.393
Neg logit contributions
orio-0.768
Italy-0.678
stanbul-0.675
vo-0.670
avier-0.665
Token Ronnie
Token ID40892
Feature activation+1.13e+00

Pos logit contributions
 NW+1.909
ysical+1.870
 Nest+1.850
 Harding+1.798
 Symb+1.754
Neg logit contributions
orio-2.462
Italy-2.152
stanbul-2.145
vo-2.099
avier-2.076
Token Payne
Token ID32788
Feature activation+2.69e-01

Pos logit contributions
 NW+0.662
ysical+0.658
 Nest+0.639
 Harding+0.616
 nost+0.607
Neg logit contributions
orio-1.082
Italy-0.950
stanbul-0.947
vo-0.939
avier-0.931
Token asked
Token ID1965
Feature activation+6.08e-01

Pos logit contributions
 NW+0.156
ysical+0.156
 Nest+0.150
 Harding+0.145
 nost+0.143
Neg logit contributions
orio-0.260
Italy-0.228
stanbul-0.227
vo-0.226
avier-0.224
Token anyone
Token ID2687
Feature activation-1.58e-01

Pos logit contributions
 NW+0.394
ysical+0.385
 Nest+0.381
 Harding+0.370
 nost+0.362
Neg logit contributions
orio-0.549
Italy-0.481
stanbul-0.475
vo-0.471
avier-0.468
Token with
Token ID351
Feature activation+3.30e-01

Pos logit contributions
orio+0.149
Italy+0.131
stanbul+0.130
vo+0.129
avier+0.128
Neg logit contributions
 NW-0.094
ysical-0.094
 Nest-0.091
 Harding-0.088
 nost-0.087
Token.
Token ID13
Feature activation+2.30e-01

Pos logit contributions
orio+0.970
Italy+0.838
stanbul+0.834
vo+0.829
avier+0.821
Neg logit contributions
ysical-0.770
 NW-0.769
 Nest-0.745
 Harding-0.722
 nost-0.715
Token
Token ID198
Feature activation-9.24e-02

Pos logit contributions
ysical+0.137
 NW+0.136
 Nest+0.131
 Harding+0.127
 nost+0.126
Neg logit contributions
orio-0.218
Italy-0.191
stanbul-0.190
vo-0.189
avier-0.187
Token
Token ID198
Feature activation+1.03e-02

Pos logit contributions
orio+0.094
stanbul+0.083
Italy+0.083
vo+0.082
avier+0.082
Neg logit contributions
 NW-0.049
ysical-0.048
 Nest-0.047
 Harding-0.045
 nost-0.044
TokenThe
Token ID464
Feature activation-1.45e-01

Pos logit contributions
 NW+0.007
ysical+0.007
 Nest+0.007
 Harding+0.006
 nost+0.006
Neg logit contributions
orio-0.009
Italy-0.008
stanbul-0.008
vo-0.008
avier-0.008
Token apex
Token ID40167
Feature activation+2.39e+00

Pos logit contributions
orio+0.121
Italy+0.104
stanbul+0.104
vo+0.103
avier+0.102
Neg logit contributions
 NW-0.103
ysical-0.102
 Nest-0.100
 Harding-0.096
 nost-0.096
Token court
Token ID2184
Feature activation+2.81e+00

Pos logit contributions
 NW+1.954
ysical+1.919
 Nest+1.901
 contended+1.882
 Harding+1.845
Neg logit contributions
orio-1.733
stanbul-1.458
Italy-1.439
vo-1.421
ppo-1.395
Token had
Token ID550
Feature activation+4.76e-02

Pos logit contributions
 NW+1.614
ysical+1.569
 Nest+1.555
 contended+1.555
 nost+1.494
Neg logit contributions
orio-2.737
Italy-2.404
stanbul-2.377
vo-2.350
avier-2.325
Token earlier
Token ID2961
Feature activation-5.17e-02

Pos logit contributions
 NW+0.026
ysical+0.026
 Nest+0.025
 Harding+0.024
 contended+0.024
Neg logit contributions
orio-0.047
Italy-0.042
stanbul-0.041
vo-0.041
avier-0.041
Token issued
Token ID4884
Feature activation+1.25e+00

Pos logit contributions
orio+0.054
Italy+0.048
stanbul+0.048
vo+0.047
avier+0.047
Neg logit contributions
 NW-0.026
ysical-0.026
 Nest-0.025
 contended-0.024
 Harding-0.024
Token notices
Token ID19748
Feature activation+3.25e-01

Pos logit contributions
 NW+0.898
ysical+0.885
 Nest+0.870
 Harding+0.842
 contended+0.837
Neg logit contributions
orio-1.047
Italy-0.895
stanbul-0.884
vo-0.881
avier-0.873
Token and
Token ID290
Feature activation-6.80e-02

Pos logit contributions
 NW+0.214
ysical+0.213
 Nest+0.207
 Harding+0.200
 nost+0.198
Neg logit contributions
orio-0.288
Italy-0.250
stanbul-0.249
vo-0.247
avier-0.245
Token connecting
Token ID14320
Feature activation+1.83e+00

Pos logit contributions
 NW+0.302
ysical+0.299
 Nest+0.292
 Harding+0.283
 nost+0.280
Neg logit contributions
orio-0.404
Italy-0.349
stanbul-0.348
vo-0.345
avier-0.343
Token Roh
Token ID32694
Feature activation-8.05e-01

Pos logit contributions
 NW+1.086
ysical+1.070
 Nest+1.048
 Harding+1.004
 nost+0.994
Neg logit contributions
orio-1.752
Italy-1.535
stanbul-1.524
vo-1.518
avier-1.510
Tokent
Token ID83
Feature activation-1.11e-01

Pos logit contributions
orio+0.484
Italy+0.389
stanbul+0.388
vo+0.384
avier+0.377
Neg logit contributions
 NW-0.759
ysical-0.758
 Nest-0.741
 Harding-0.725
 nost-0.721
Tokenak
Token ID461
Feature activation+1.18e+00

Pos logit contributions
orio+0.104
Italy+0.091
stanbul+0.090
vo+0.089
avier+0.089
Neg logit contributions
 NW-0.067
ysical-0.067
 Nest-0.065
 Harding-0.063
 nost-0.062
Token to
Token ID284
Feature activation+4.55e-01

Pos logit contributions
 NW+0.785
ysical+0.778
 Nest+0.757
 Harding+0.732
 nost+0.726
Neg logit contributions
orio-1.046
Italy-0.907
stanbul-0.900
vo-0.893
avier-0.889
Token Delhi
Token ID12517
Feature activation+2.80e+00

Pos logit contributions
ysical+0.271
 NW+0.271
 Nest+0.261
 Harding+0.252
 nost+0.250
Neg logit contributions
orio-0.431
Italy-0.378
stanbul-0.377
vo-0.374
avier-0.370
Token.
Token ID13
Feature activation+5.11e-01

Pos logit contributions
 NW+1.947
ysical+1.904
 Nest+1.870
 Harding+1.813
 nost+1.794
Neg logit contributions
orio-2.405
Italy-2.075
stanbul-2.044
vo-2.037
avier-2.029
Token After
Token ID2293
Feature activation+1.52e-01

Pos logit contributions
 NW+0.310
ysical+0.308
 Nest+0.300
 Harding+0.289
 nost+0.285
Neg logit contributions
orio-0.481
Italy-0.420
stanbul-0.419
vo-0.416
avier-0.413
Token this
Token ID428
Feature activation+5.39e-01

Pos logit contributions
 NW+0.101
ysical+0.101
 Nest+0.098
 Harding+0.095
 nost+0.094
Neg logit contributions
orio-0.133
Italy-0.115
stanbul-0.115
vo-0.114
avier-0.113
Token,
Token ID11
Feature activation+6.23e-01

Pos logit contributions
 NW+0.348
ysical+0.348
 Nest+0.337
 Harding+0.326
 nost+0.322
Neg logit contributions
orio-0.484
Italy-0.421
stanbul-0.419
vo-0.417
avier-0.412
Token the
Token ID262
Feature activation-1.06e-02

Pos logit contributions
 NW+0.420
ysical+0.417
 Nest+0.407
 Harding+0.393
 nost+0.389
Neg logit contributions
orio-0.544
Italy-0.471
stanbul-0.468
vo-0.465
avier-0.461
Tokenar
Token ID283
Feature activation+1.04e+00

Pos logit contributions
 NW+0.690
ysical+0.688
 Nest+0.671
 Harding+0.657
 contended+0.649
Neg logit contributions
orio-0.602
Italy-0.514
stanbul-0.509
vo-0.497
avier-0.487
Token of
Token ID286
Feature activation+3.20e-01

Pos logit contributions
 NW+0.643
ysical+0.638
 Nest+0.621
 Harding+0.599
 contended+0.595
Neg logit contributions
orio-0.965
Italy-0.842
stanbul-0.838
vo-0.832
avier-0.825
Token the
Token ID262
Feature activation+1.22e-01

Pos logit contributions
ysical+0.190
 NW+0.189
 Nest+0.182
 Harding+0.176
 nost+0.175
Neg logit contributions
orio-0.304
Italy-0.266
stanbul-0.265
vo-0.263
avier-0.261
Token A
Token ID317
Feature activation-3.73e-01

Pos logit contributions
 NW+0.070
ysical+0.069
 Nest+0.067
 Harding+0.064
 nost+0.064
Neg logit contributions
orio-0.119
Italy-0.105
stanbul-0.105
vo-0.104
avier-0.103
Tokenam
Token ID321
Feature activation+4.94e-01

Pos logit contributions
orio+0.303
Italy+0.260
stanbul+0.258
vo+0.258
avier+0.254
Neg logit contributions
ysical-0.273
 NW-0.272
 Nest-0.264
 Harding-0.256
 nost-0.254
Token Aad
Token ID38746
Feature activation+2.78e+00

Pos logit contributions
 NW+0.302
ysical+0.301
 Nest+0.291
 Harding+0.281
 nost+0.278
Neg logit contributions
orio-0.461
Italy-0.403
stanbul-0.401
vo-0.399
avier-0.395
Tokenmi
Token ID11632
Feature activation+2.20e+00

Pos logit contributions
ysical+2.378
 NW+2.365
 Nest+2.323
 Harding+2.259
 contended+2.250
Neg logit contributions
orio-1.890
stanbul-1.578
Italy-1.577
vo-1.539
avier-1.535
Token Party
Token ID3615
Feature activation+5.39e-02

Pos logit contributions
 NW+1.268
ysical+1.259
 Nest+1.221
 Harding+1.170
 nost+1.166
Neg logit contributions
orio-2.152
Italy-1.881
stanbul-1.877
vo-1.864
avier-1.853
Token,
Token ID11
Feature activation+1.48e-01

Pos logit contributions
 NW+0.035
ysical+0.034
 Nest+0.033
 Harding+0.032
 nost+0.032
Neg logit contributions
orio-0.049
Italy-0.042
stanbul-0.042
vo-0.042
avier-0.042
Token arrested
Token ID5169
Feature activation+2.29e-01

Pos logit contributions
ysical+0.088
 NW+0.088
 Nest+0.085
 Harding+0.082
 nost+0.081
Neg logit contributions
orio-0.140
Italy-0.123
stanbul-0.122
vo-0.122
avier-0.121
Token this
Token ID428
Feature activation-5.33e-02

Pos logit contributions
 NW+0.134
ysical+0.134
 Nest+0.130
 Harding+0.125
 nost+0.123
Neg logit contributions
orio-0.219
Italy-0.192
stanbul-0.192
vo-0.190
avier-0.189
Token.
Token ID13
Feature activation-4.80e-01

Pos logit contributions
 NW+0.081
ysical+0.081
 Nest+0.078
 Harding+0.076
 nost+0.075
Neg logit contributions
orio-0.103
Italy-0.089
stanbul-0.088
vo-0.087
avier-0.087
Token Sc
Token ID1446
Feature activation-6.26e-01

Pos logit contributions
orio+0.464
Italy+0.408
stanbul+0.405
vo+0.405
avier+0.400
Neg logit contributions
ysical-0.277
 NW-0.275
 Nest-0.264
 contended-0.255
 nost-0.254
Tokenann
Token ID1236
Feature activation-6.33e-01

Pos logit contributions
orio+0.396
Italy+0.324
stanbul+0.322
vo+0.318
avier+0.313
Neg logit contributions
 NW-0.569
ysical-0.568
 Nest-0.555
 Harding-0.544
 nost-0.539
Tokenell
Token ID695
Feature activation-8.77e-02

Pos logit contributions
orio+0.487
Italy+0.414
stanbul+0.412
vo+0.407
avier+0.402
Neg logit contributions
 NW-0.490
ysical-0.489
 Nest-0.476
 Harding-0.463
 nost-0.460
Token and
Token ID290
Feature activation-3.43e-01

Pos logit contributions
orio+0.085
Italy+0.075
stanbul+0.075
vo+0.074
avier+0.074
Neg logit contributions
 NW-0.050
ysical-0.050
 Nest-0.048
 Harding-0.047
 contended-0.046
Token Lt
Token ID19090
Feature activation+2.77e+00

Pos logit contributions
orio+0.345
Italy+0.304
stanbul+0.302
vo+0.302
avier+0.299
Neg logit contributions
ysical-0.185
 NW-0.184
 Nest-0.176
 Harding-0.168
 contended-0.168
Token.
Token ID13
Feature activation+4.65e-01

Pos logit contributions
 NW+2.003
ysical+1.982
 Nest+1.951
 Harding+1.900
 contended+1.858
Neg logit contributions
orio-2.257
stanbul-1.959
Italy-1.953
vo-1.897
avier-1.875
Token Emil
Token ID44272
Feature activation-5.91e-01

Pos logit contributions
 NW+0.269
ysical+0.266
 Nest+0.260
 Harding+0.250
 nost+0.245
Neg logit contributions
orio-0.451
Italy-0.396
stanbul-0.395
vo-0.391
avier-0.388
Token Rick
Token ID8759
Feature activation-3.40e-01

Pos logit contributions
orio+0.486
Italy+0.415
stanbul+0.412
vo+0.411
avier+0.406
Neg logit contributions
 NW-0.429
ysical-0.427
 Nest-0.415
 Harding-0.402
 nost-0.400
Tokenner
Token ID1008
Feature activation+4.61e-01

Pos logit contributions
orio+0.282
Italy+0.242
stanbul+0.241
vo+0.239
avier+0.236
Neg logit contributions
 NW-0.244
ysical-0.243
 Nest-0.237
 Harding-0.230
 contended-0.228
Token were
Token ID547
Feature activation+3.15e-01

Pos logit contributions
 NW+0.288
ysical+0.282
 Nest+0.279
 Harding+0.271
 contended+0.268
Neg logit contributions
orio-0.424
Italy-0.372
stanbul-0.369
avier-0.364
vo-0.363
Tokencs
Token ID6359
Feature activation+8.45e-01

Pos logit contributions
 NW+0.031
ysical+0.031
 Nest+0.030
 Harding+0.029
 nost+0.029
Neg logit contributions
orio-0.038
Italy-0.033
stanbul-0.033
vo-0.032
avier-0.032
Token will
Token ID481
Feature activation+3.32e-01

Pos logit contributions
 NW+0.553
ysical+0.546
 Nest+0.533
 Harding+0.513
 nost+0.512
Neg logit contributions
orio-0.757
Italy-0.658
stanbul-0.652
vo-0.647
avier-0.642
Token go
Token ID467
Feature activation-5.92e-01

Pos logit contributions
 NW+0.212
ysical+0.207
 Nest+0.203
 nost+0.196
 contended+0.195
Neg logit contributions
orio-0.305
Italy-0.265
stanbul-0.262
vo-0.260
avier-0.260
Token here
Token ID994
Feature activation+7.44e-01

Pos logit contributions
orio+0.561
Italy+0.491
stanbul+0.489
vo+0.485
avier+0.481
Neg logit contributions
 NW-0.355
ysical-0.353
 Nest-0.342
 Harding-0.329
 nost-0.327
Token +
Token ID1343
Feature activation+5.45e-01

Pos logit contributions
 NW+0.511
ysical+0.505
 Nest+0.493
 Harding+0.476
 nost+0.475
Neg logit contributions
orio-0.642
Italy-0.555
stanbul-0.549
vo-0.545
avier-0.539
Token--------------------
Token ID19351
Feature activation+2.77e+00

Pos logit contributions
 NW+0.226
ysical+0.225
 Nest+0.214
 Harding+0.203
 nost+0.200
Neg logit contributions
orio-0.616
Italy-0.551
stanbul-0.550
vo-0.547
avier-0.543
Token--+
Token ID44785
Feature activation+5.03e-01

Pos logit contributions
 NW+2.175
ysical+2.172
 Nest+2.116
 Harding+2.055
 nost+2.040
Neg logit contributions
orio-2.095
Italy-1.773
stanbul-1.761
vo-1.748
avier-1.712
Token +
Token ID1343
Feature activation+4.18e-01

Pos logit contributions
 NW+0.329
ysical+0.328
 Nest+0.318
 Harding+0.308
 nost+0.305
Neg logit contributions
orio-0.449
Italy-0.389
stanbul-0.388
vo-0.385
avier-0.381
Token--------------------
Token ID19351
Feature activation+2.30e+00

Pos logit contributions
 NW+0.171
ysical+0.170
 Nest+0.162
 Harding+0.153
 nost+0.151
Neg logit contributions
orio-0.475
Italy-0.426
stanbul-0.424
vo-0.422
avier-0.419
Token--+
Token ID44785
Feature activation+4.06e-01

Pos logit contributions
 NW+1.809
ysical+1.807
 Nest+1.761
 Harding+1.711
 contended+1.700
Neg logit contributions
orio-1.731
Italy-1.467
stanbul-1.455
vo-1.446
avier-1.416
Token <
Token ID1279
Feature activation+9.56e-01

Pos logit contributions
 NW+0.274
ysical+0.273
 Nest+0.265
 Harding+0.257
 nost+0.254
Neg logit contributions
orio-0.353
Italy-0.305
stanbul-0.304
vo-0.302
avier-0.299
Token
Token ID251
Feature activation-9.07e-02

Pos logit contributions
 NW+0.088
ysical+0.087
 Nest+0.086
 Harding+0.084
 nost+0.083
Neg logit contributions
orio-0.058
Italy-0.047
stanbul-0.047
vo-0.046
avier-0.046
Token
Token ID198
Feature activation+5.60e-02

Pos logit contributions
orio+0.086
Italy+0.075
stanbul+0.075
vo+0.075
avier+0.074
Neg logit contributions
ysical-0.054
 NW-0.054
 Nest-0.052
 Harding-0.050
 nost-0.050
Token
Token ID198
Feature activation+1.34e-01

Pos logit contributions
 NW+0.030
ysical+0.029
 Nest+0.028
 Harding+0.027
 nost+0.026
Neg logit contributions
orio-0.057
stanbul-0.051
Italy-0.050
vo-0.050
avier-0.050
Token
Token ID960
Feature activation-4.39e-02

Pos logit contributions
 NW+0.097
ysical+0.096
 Nest+0.094
 Harding+0.091
 nost+0.090
Neg logit contributions
orio-0.110
Italy-0.094
stanbul-0.094
vo-0.093
avier-0.092
TokenAaron
Token ID34451
Feature activation+5.46e-01

Pos logit contributions
orio+0.036
Italy+0.031
stanbul+0.031
vo+0.031
avier+0.030
Neg logit contributions
 NW-0.031
ysical-0.031
 Nest-0.030
 Harding-0.030
 nost-0.029
Token Larson
Token ID42630
Feature activation+2.74e+00

Pos logit contributions
 NW+0.327
ysical+0.326
 Nest+0.316
 Harding+0.304
 nost+0.301
Neg logit contributions
orio-0.517
Italy-0.453
stanbul-0.451
vo-0.448
avier-0.444
Token,
Token ID11
Feature activation+3.71e-01

Pos logit contributions
 NW+1.617
ysical+1.582
 Nest+1.561
 Harding+1.501
 contended+1.484
Neg logit contributions
orio-2.617
Italy-2.303
stanbul-2.289
vo-2.267
avier-2.256
Token associate
Token ID11602
Feature activation+1.33e+00

Pos logit contributions
 NW+0.246
ysical+0.244
 Nest+0.238
 Harding+0.230
 nost+0.227
Neg logit contributions
orio-0.328
Italy-0.285
stanbul-0.283
vo-0.281
avier-0.279
Token editor
Token ID5464
Feature activation-8.80e-01

Pos logit contributions
 NW+0.898
ysical+0.889
 Nest+0.868
 Harding+0.840
 nost+0.832
Neg logit contributions
orio-1.155
Italy-1.000
stanbul-0.996
vo-0.987
avier-0.978
Token (@
Token ID4275
Feature activation-6.52e-01

Pos logit contributions
orio+0.805
Italy+0.698
stanbul+0.695
vo+0.692
avier+0.685
Neg logit contributions
ysical-0.558
 NW-0.551
 Nest-0.533
 Harding-0.517
 nost-0.515
TokenAaron
Token ID34451
Feature activation+3.01e-01

Pos logit contributions
orio+0.505
Italy+0.428
stanbul+0.426
vo+0.423
avier+0.418
Neg logit contributions
 NW-0.503
ysical-0.501
 Nest-0.489
 Harding-0.475
 nost-0.471
Token.
Token ID13
Feature activation-4.75e-01

Pos logit contributions
orio+0.096
Italy+0.083
stanbul+0.082
vo+0.082
avier+0.081
Neg logit contributions
 NW-0.075
ysical-0.075
 Nest-0.073
 Harding-0.070
 nost-0.070
Token From
Token ID3574
Feature activation-2.71e-02

Pos logit contributions
orio+0.469
Italy+0.413
stanbul+0.412
vo+0.409
avier+0.406
Neg logit contributions
 NW-0.266
ysical-0.264
 Nest-0.256
 Harding-0.246
 nost-0.243
Token the
Token ID262
Feature activation+2.66e-01

Pos logit contributions
orio+0.026
Italy+0.023
stanbul+0.023
vo+0.023
avier+0.022
Neg logit contributions
 NW-0.016
ysical-0.016
 Nest-0.015
 Harding-0.015
 nost-0.015
Token Kodi
Token ID44129
Feature activation+1.08e+00

Pos logit contributions
 NW+0.169
ysical+0.168
 Nest+0.163
 Harding+0.157
 nost+0.156
Neg logit contributions
orio-0.243
Italy-0.212
stanbul-0.211
vo-0.209
avier-0.207
Token home
Token ID1363
Feature activation-3.32e-01

Pos logit contributions
 NW+0.887
ysical+0.876
 Nest+0.867
 Harding+0.840
 nost+0.835
Neg logit contributions
orio-0.791
Italy-0.662
stanbul-0.658
vo-0.650
avier-0.645
Token screen
Token ID3159
Feature activation+2.74e+00

Pos logit contributions
orio+0.281
Italy+0.242
vo+0.241
stanbul+0.240
avier+0.237
Neg logit contributions
ysical-0.231
 NW-0.230
 Nest-0.222
 Harding-0.217
 contended-0.215
Token,
Token ID11
Feature activation-1.00e-01

Pos logit contributions
 NW+1.733
ysical+1.713
 Nest+1.673
 Harding+1.608
 nost+1.601
Neg logit contributions
orio-2.512
Italy-2.188
stanbul-2.177
vo-2.158
avier-2.144
Token choose
Token ID3853
Feature activation+5.87e-01

Pos logit contributions
orio+0.096
Italy+0.084
stanbul+0.084
vo+0.084
avier+0.083
Neg logit contributions
 NW-0.059
ysical-0.059
 Nest-0.057
 Harding-0.055
 nost-0.054
Token
Token ID564
Feature activation-3.72e-01

Pos logit contributions
 NW+0.425
ysical+0.423
 Nest+0.414
 Harding+0.400
 nost+0.398
Neg logit contributions
orio-0.483
Italy-0.414
stanbul-0.413
vo-0.408
avier-0.405
Token
Token ID246
Feature activation-7.78e-03

Pos logit contributions
orio+0.253
Italy+0.211
stanbul+0.209
vo+0.205
avier+0.204
Neg logit contributions
 NW-0.321
ysical-0.320
 Nest-0.313
 Harding-0.304
 nost-0.303
TokenAdd
Token ID4550
Feature activation-4.02e-02

Pos logit contributions
orio+0.007
Italy+0.006
stanbul+0.006
vo+0.006
avier+0.006
Neg logit contributions
 NW-0.005
ysical-0.005
 Nest-0.005
 Harding-0.005
 nost-0.005
Token percent
Token ID1411
Feature activation-6.63e-01

Pos logit contributions
 NW+0.149
ysical+0.147
 Nest+0.144
 Harding+0.140
 nost+0.139
Neg logit contributions
orio-0.161
Italy-0.138
stanbul-0.137
vo-0.136
avier-0.135
Token).
Token ID737
Feature activation-2.34e-01

Pos logit contributions
orio+0.559
Italy+0.481
stanbul+0.479
vo+0.475
avier+0.470
Neg logit contributions
 NW-0.465
ysical-0.464
 Nest-0.451
 Harding-0.437
 nost-0.433
Token
Token ID198
Feature activation-1.37e-01

Pos logit contributions
orio+0.227
Italy+0.200
stanbul+0.199
vo+0.198
avier+0.196
Neg logit contributions
ysical-0.135
 NW-0.135
 Nest-0.129
 Harding-0.125
 nost-0.124
Token
Token ID198
Feature activation-1.39e-02

Pos logit contributions
orio+0.141
stanbul+0.125
Italy+0.124
vo+0.123
avier+0.122
Neg logit contributions
 NW-0.072
ysical-0.070
 Nest-0.069
 Harding-0.065
 nost-0.064
TokenBe
Token ID3856
Feature activation+4.53e-01

Pos logit contributions
orio+0.011
stanbul+0.010
Italy+0.010
vo+0.009
avier+0.009
Neg logit contributions
 NW-0.010
ysical-0.010
 Nest-0.010
 Harding-0.010
 nost-0.010
Tokenhold
Token ID2946
Feature activation+2.73e+00

Pos logit contributions
 NW+0.343
ysical+0.342
 Nest+0.333
 Harding+0.324
 nost+0.321
Neg logit contributions
orio-0.357
Italy-0.304
stanbul-0.302
vo-0.299
avier-0.296
Token,
Token ID11
Feature activation+2.04e-01

Pos logit contributions
 NW+1.828
ysical+1.781
 Nest+1.771
 Harding+1.701
 nost+1.688
Neg logit contributions
orio-2.400
Italy-2.079
stanbul-2.063
vo-2.038
avier-2.032
Token one
Token ID530
Feature activation+5.09e-01

Pos logit contributions
ysical+0.127
 NW+0.127
 Nest+0.122
 Harding+0.118
 nost+0.117
Neg logit contributions
orio-0.187
Italy-0.163
stanbul-0.163
vo-0.162
avier-0.160
Token of
Token ID286
Feature activation+2.43e-01

Pos logit contributions
 NW+0.294
ysical+0.293
 Nest+0.283
 Harding+0.272
 nost+0.269
Neg logit contributions
orio-0.493
Italy-0.433
stanbul-0.432
vo-0.429
avier-0.425
Token the
Token ID262
Feature activation+1.46e-01

Pos logit contributions
 NW+0.148
ysical+0.147
 Nest+0.142
 Harding+0.137
 nost+0.136
Neg logit contributions
orio-0.227
Italy-0.199
stanbul-0.198
vo-0.197
avier-0.195
Token few
Token ID1178
Feature activation+7.23e-01

Pos logit contributions
 NW+0.108
ysical+0.105
 Nest+0.104
 Harding+0.101
 nost+0.100
Neg logit contributions
orio-0.121
Italy-0.103
stanbul-0.103
vo-0.101
avier-0.101
Token affairs
Token ID9674
Feature activation+3.81e-01

Pos logit contributions
orio+0.775
Italy+0.664
stanbul+0.660
vo+0.659
avier+0.651
Neg logit contributions
ysical-0.679
 NW-0.677
 Nest-0.659
 Harding-0.639
 nost-0.633
Token.
Token ID13
Feature activation-3.44e-01

Pos logit contributions
 NW+0.281
ysical+0.281
 Nest+0.273
 Harding+0.265
 nost+0.263
Neg logit contributions
orio-0.308
Italy-0.263
stanbul-0.262
vo-0.260
avier-0.257
Token
Token ID198
Feature activation+1.38e-01

Pos logit contributions
orio+0.312
Italy+0.273
stanbul+0.270
vo+0.270
avier+0.267
Neg logit contributions
ysical-0.218
 NW-0.216
 Nest-0.209
 Harding-0.202
 nost-0.202
Token
Token ID198
Feature activation+2.66e-01

Pos logit contributions
 NW+0.073
ysical+0.071
 Nest+0.070
 Harding+0.066
 nost+0.065
Neg logit contributions
orio-0.141
stanbul-0.124
Italy-0.123
vo-0.122
avier-0.122
TokenO
Token ID46
Feature activation+9.28e-01

Pos logit contributions
 NW+0.185
ysical+0.184
 Nest+0.179
 Harding+0.174
 nost+0.172
Neg logit contributions
orio-0.226
stanbul-0.194
Italy-0.193
vo-0.191
avier-0.190
Tokenvert
Token ID1851
Feature activation+2.72e+00

Pos logit contributions
 NW+0.738
ysical+0.735
 Nest+0.716
 Harding+0.698
 nost+0.693
Neg logit contributions
orio-0.693
Italy-0.588
stanbul-0.583
vo-0.573
avier-0.571
Tokenime
Token ID524
Feature activation-1.15e-01

Pos logit contributions
 NW+2.463
ysical+2.457
 Nest+2.405
 Harding+2.340
 nost+2.316
Neg logit contributions
orio-1.731
Italy-1.434
stanbul-1.423
vo-1.370
avier-1.353
Token for
Token ID329
Feature activation+1.60e-02

Pos logit contributions
orio+0.103
Italy+0.090
stanbul+0.089
vo+0.089
avier+0.088
Neg logit contributions
 NW-0.074
ysical-0.074
 Nest-0.072
 Harding-0.069
 nost-0.069
Token some
Token ID617
Feature activation+3.58e-01

Pos logit contributions
 NW+0.010
ysical+0.010
 Nest+0.010
 Harding+0.010
 nost+0.009
Neg logit contributions
orio-0.014
Italy-0.013
stanbul-0.013
vo-0.012
avier-0.012
Token employees
Token ID4409
Feature activation-5.92e-01

Pos logit contributions
 NW+0.229
ysical+0.229
 Nest+0.221
 Harding+0.214
 nost+0.212
Neg logit contributions
orio-0.323
Italy-0.281
stanbul-0.280
vo-0.278
avier-0.276
Token on
Token ID319
Feature activation+1.12e-01

Pos logit contributions
orio+0.566
Italy+0.496
stanbul+0.494
vo+0.491
avier+0.486
Neg logit contributions
 NW-0.350
ysical-0.348
 Nest-0.337
 Harding-0.325
 nost-0.321
Token States
Token ID1829
Feature activation+7.16e-02

Pos logit contributions
orio+0.732
vo+0.649
Italy+0.649
stanbul+0.648
avier+0.633
Neg logit contributions
ysical-0.366
 NW-0.363
 Nest-0.346
 Harding-0.335
 contended-0.333
Token Conference
Token ID8785
Feature activation+3.20e-01

Pos logit contributions
 NW+0.042
ysical+0.042
 Nest+0.041
 Harding+0.039
 nost+0.039
Neg logit contributions
orio-0.069
Italy-0.060
stanbul-0.060
vo-0.059
avier-0.059
Token of
Token ID286
Feature activation+6.48e-02

Pos logit contributions
 NW+0.185
ysical+0.185
 Nest+0.178
 Harding+0.173
 nost+0.171
Neg logit contributions
orio-0.310
Italy-0.270
stanbul-0.270
vo-0.269
avier-0.265
Token Catholic
Token ID7835
Feature activation-1.19e-01

Pos logit contributions
ysical+0.043
 NW+0.043
 Nest+0.042
 Harding+0.041
 nost+0.040
Neg logit contributions
orio-0.057
Italy-0.049
stanbul-0.049
vo-0.049
avier-0.048
Token B
Token ID347
Feature activation-1.99e-01

Pos logit contributions
orio+0.114
Italy+0.101
vo+0.099
stanbul+0.099
avier+0.098
Neg logit contributions
 NW-0.070
ysical-0.069
 Nest-0.067
 Harding-0.065
 nost-0.065
Tokenishops
Token ID21863
Feature activation-2.97e+00

Pos logit contributions
orio+0.119
stanbul+0.099
Italy+0.097
vo+0.094
avier+0.091
Neg logit contributions
ysical-0.188
 NW-0.187
 Nest-0.183
 Harding-0.178
 contended-0.178
Token (
Token ID357
Feature activation-2.89e-02

Pos logit contributions
orio+2.806
stanbul+2.466
Italy+2.463
vo+2.454
avier+2.421
Neg logit contributions
ysical-1.759
 NW-1.740
 Nest-1.684
 Harding-1.623
 nost-1.600
TokenUS
Token ID2937
Feature activation-1.20e-01

Pos logit contributions
orio+0.017
stanbul+0.014
Italy+0.014
vo+0.013
avier+0.013
Neg logit contributions
 NW-0.027
ysical-0.027
 Nest-0.027
 Harding-0.026
 nost-0.026
TokenCC
Token ID4093
Feature activation+5.39e-02

Pos logit contributions
orio+0.092
Italy+0.078
stanbul+0.077
vo+0.077
avier+0.076
Neg logit contributions
 NW-0.094
ysical-0.093
 Nest-0.091
 Harding-0.089
 contended-0.088
TokenB
Token ID33
Feature activation-8.32e-03

Pos logit contributions
 NW+0.038
ysical+0.038
 Nest+0.037
 Harding+0.036
 nost+0.036
Neg logit contributions
orio-0.045
Italy-0.039
stanbul-0.039
vo-0.038
avier-0.038
Token)
Token ID8
Feature activation+1.29e-01

Pos logit contributions
orio+0.007
Italy+0.006
stanbul+0.006
vo+0.006
avier+0.006
Neg logit contributions
 NW-0.006
ysical-0.006
 Nest-0.006
 Harding-0.006
 nost-0.006
Token to
Token ID284
Feature activation+2.55e-01

Pos logit contributions
orio+0.805
Italy+0.699
stanbul+0.696
vo+0.692
avier+0.685
Neg logit contributions
 NW-0.584
ysical-0.583
 Nest-0.565
 Harding-0.547
 nost-0.542
Token Go
Token ID1514
Feature activation-2.99e-01

Pos logit contributions
 NW+0.145
ysical+0.143
 Nest+0.140
 Harding+0.134
 nost+0.132
Neg logit contributions
orio-0.251
Italy-0.220
stanbul-0.219
vo-0.218
avier-0.216
Token Back
Token ID5157
Feature activation+9.87e-01

Pos logit contributions
orio+0.275
Italy+0.240
stanbul+0.238
vo+0.237
avier+0.235
Neg logit contributions
 NW-0.188
ysical-0.187
 Nest-0.182
 Harding-0.175
 nost-0.173
Token There
Token ID1318
Feature activation+1.93e-01

Pos logit contributions
 NW+0.669
ysical+0.657
 Nest+0.650
 Harding+0.623
 Symb+0.612
Neg logit contributions
orio-0.864
Italy-0.748
stanbul-0.739
vo-0.732
avier-0.730
Token Som
Token ID9995
Feature activation-9.34e-01

Pos logit contributions
 NW+0.126
ysical+0.125
 Nest+0.122
 Harding+0.117
 nost+0.116
Neg logit contributions
orio-0.172
Italy-0.150
stanbul-0.149
vo-0.147
avier-0.146
Tokeneday
Token ID23712
Feature activation-2.96e+00

Pos logit contributions
orio+0.532
Italy+0.421
stanbul+0.418
vo+0.414
avier+0.406
Neg logit contributions
 NW-0.911
ysical-0.910
 Nest-0.890
 Harding-0.872
 contended-0.866
Token."
Token ID526
Feature activation-2.80e-01

Pos logit contributions
orio+2.527
stanbul+2.174
vo+2.162
Italy+2.162
avier+2.131
Neg logit contributions
ysical-2.028
 NW-2.005
 Nest-1.935
 nost-1.888
 contended-1.885
Token
Token ID198
Feature activation+1.81e-01

Pos logit contributions
orio+0.272
Italy+0.238
stanbul+0.238
vo+0.235
avier+0.234
Neg logit contributions
 NW-0.163
ysical-0.160
 Nest-0.157
 Harding-0.151
 contended-0.148
Token
Token ID198
Feature activation+2.58e-01

Pos logit contributions
 NW+0.094
ysical+0.091
 Nest+0.090
 Harding+0.085
 nost+0.084
Neg logit contributions
orio-0.188
stanbul-0.167
Italy-0.165
vo-0.163
avier-0.163
TokenIn
Token ID818
Feature activation-3.21e-01

Pos logit contributions
 NW+0.183
ysical+0.181
 Nest+0.178
 Harding+0.173
 nost+0.170
Neg logit contributions
orio-0.215
stanbul-0.184
Italy-0.180
vo-0.180
avier-0.179
Token 1984
Token ID12844
Feature activation-2.01e-01

Pos logit contributions
orio+0.315
Italy+0.277
stanbul+0.277
vo+0.274
avier+0.272
Neg logit contributions
 NW-0.183
ysical-0.180
 Nest-0.176
 Harding-0.169
 nost-0.166
Token13
Token ID1485
Feature activation+1.26e-01

Pos logit contributions
 NW+0.903
ysical+0.898
 Nest+0.882
 Harding+0.863
 nost+0.854
Neg logit contributions
orio-0.715
stanbul-0.587
Italy-0.587
vo-0.577
avier-0.573
Token]:
Token ID5974
Feature activation-3.66e-01

Pos logit contributions
 NW+0.084
ysical+0.083
 Nest+0.081
 Harding+0.079
 nost+0.077
Neg logit contributions
orio-0.112
Italy-0.096
stanbul-0.096
vo-0.095
avier-0.094
Token137
Token ID19708
Feature activation+1.26e-01

Pos logit contributions
orio+0.228
stanbul+0.184
Italy+0.184
vo+0.180
avier+0.179
Neg logit contributions
 NW-0.337
ysical-0.335
 Nest-0.329
 Harding-0.322
 nost-0.318
Token Patrick
Token ID9925
Feature activation+1.85e-01

Pos logit contributions
 NW+0.074
ysical+0.073
 Nest+0.072
 Harding+0.069
 contended+0.068
Neg logit contributions
orio-0.120
Italy-0.106
stanbul-0.105
vo-0.104
avier-0.103
Token S
Token ID311
Feature activation-1.02e+00

Pos logit contributions
 NW+0.109
ysical+0.109
 Nest+0.105
 Harding+0.101
 nost+0.101
Neg logit contributions
orio-0.177
Italy-0.155
stanbul-0.154
vo-0.154
avier-0.152
Tokenü
Token ID9116
Feature activation-2.94e+00

Pos logit contributions
orio+0.828
Italy+0.701
stanbul+0.698
vo+0.698
avier+0.691
Neg logit contributions
 NW-0.757
ysical-0.753
 Nest-0.737
 Harding-0.712
 nost-0.711
Tokensk
Token ID8135
Feature activation-5.16e-01

Pos logit contributions
orio+2.108
vo+1.772
stanbul+1.744
avier+1.736
Italy+1.734
Neg logit contributions
 NW-2.420
ysical-2.415
 Nest-2.358
 Harding-2.300
 nost-2.287
Tokenind
Token ID521
Feature activation+3.73e-01

Pos logit contributions
orio+0.381
Italy+0.320
stanbul+0.319
vo+0.316
avier+0.313
Neg logit contributions
 NW-0.416
ysical-0.415
 Nest-0.405
 Harding-0.395
 nost-0.392
Token's
Token ID338
Feature activation+1.67e-01

Pos logit contributions
 NW+0.213
ysical+0.210
 Nest+0.204
 Harding+0.197
 contended+0.197
Neg logit contributions
orio-0.363
Italy-0.322
stanbul-0.319
vo-0.316
avier-0.314
Token novel
Token ID5337
Feature activation+3.81e-01

Pos logit contributions
 NW+0.120
ysical+0.118
 Nest+0.116
 Harding+0.112
 nost+0.111
Neg logit contributions
orio-0.139
Italy-0.120
stanbul-0.119
vo-0.118
avier-0.117
Token Per
Token ID2448
Feature activation-2.73e-01

Pos logit contributions
 NW+0.255
ysical+0.254
 Nest+0.246
 Harding+0.239
 nost+0.236
Neg logit contributions
orio-0.333
Italy-0.288
stanbul-0.287
vo-0.285
avier-0.282
Token who
Token ID508
Feature activation-3.68e-01

Pos logit contributions
 NW+0.079
ysical+0.078
 Nest+0.076
 Harding+0.073
 nost+0.073
Neg logit contributions
orio-0.103
Italy-0.090
stanbul-0.089
vo-0.088
avier-0.088
Token signed
Token ID4488
Feature activation-6.66e-01

Pos logit contributions
orio+0.380
Italy+0.337
stanbul+0.335
vo+0.332
avier+0.331
Neg logit contributions
 NW-0.190
ysical-0.188
 Nest-0.181
 Harding-0.174
 contended-0.173
Token a
Token ID257
Feature activation+1.53e-01

Pos logit contributions
orio+0.605
Italy+0.526
stanbul+0.524
vo+0.521
avier+0.516
Neg logit contributions
 NW-0.425
ysical-0.423
 Nest-0.410
 Harding-0.396
 nost-0.393
Token letter
Token ID3850
Feature activation-1.17e-01

Pos logit contributions
 NW+0.102
ysical+0.100
 Nest+0.098
 Harding+0.095
 nost+0.094
Neg logit contributions
orio-0.135
Italy-0.117
stanbul-0.117
vo-0.115
avier-0.115
Token to
Token ID284
Feature activation+1.53e-01

Pos logit contributions
orio+0.107
Italy+0.093
stanbul+0.093
vo+0.092
avier+0.091
Neg logit contributions
 NW-0.074
ysical-0.074
 Nest-0.072
 Harding-0.069
 nost-0.069
Token CMS
Token ID40773
Feature activation-2.93e+00

Pos logit contributions
 NW+0.090
ysical+0.088
 Nest+0.086
 Harding+0.083
 nost+0.082
Neg logit contributions
orio-0.147
Italy-0.129
stanbul-0.129
vo-0.128
avier-0.127
Token a
Token ID257
Feature activation+2.87e-01

Pos logit contributions
orio+2.632
Italy+2.289
stanbul+2.286
vo+2.278
avier+2.244
Neg logit contributions
ysical-1.866
 NW-1.853
 Nest-1.788
 Harding-1.733
 nost-1.724
Token few
Token ID1178
Feature activation+4.54e-01

Pos logit contributions
 NW+0.221
ysical+0.218
 Nest+0.215
 nost+0.207
 Harding+0.207
Neg logit contributions
orio-0.223
Italy-0.190
stanbul-0.189
vo-0.186
avier-0.185
Token weeks
Token ID2745
Feature activation+1.38e-01

Pos logit contributions
 NW+0.349
ysical+0.345
 Nest+0.339
 Harding+0.329
 nost+0.327
Neg logit contributions
orio-0.355
Italy-0.301
stanbul-0.299
vo-0.296
avier-0.294
Token ago
Token ID2084
Feature activation-9.28e-03

Pos logit contributions
 NW+0.089
ysical+0.088
 Nest+0.086
 Harding+0.083
 nost+0.082
Neg logit contributions
orio-0.124
Italy-0.108
stanbul-0.108
vo-0.106
avier-0.106
Token.
Token ID13
Feature activation+1.11e-01

Pos logit contributions
orio+0.008
Italy+0.007
stanbul+0.007
vo+0.007
avier+0.007
Neg logit contributions
 NW-0.006
ysical-0.006
 Nest-0.006
 Harding-0.006
 nost-0.006
Token-
Token ID12
Feature activation-6.37e-01

Pos logit contributions
orio+0.857
Italy+0.739
stanbul+0.736
vo+0.730
avier+0.722
Neg logit contributions
 NW-0.689
ysical-0.686
 Nest-0.667
 Harding-0.645
 nost-0.641
Tokenshaped
Token ID16760
Feature activation-7.88e-01

Pos logit contributions
orio+0.499
Italy+0.423
stanbul+0.422
vo+0.416
avier+0.413
Neg logit contributions
 NW-0.487
ysical-0.484
 Nest-0.473
 Harding-0.459
 nost-0.455
Token ep
Token ID2462
Feature activation-6.19e-01

Pos logit contributions
orio+0.697
Italy+0.604
stanbul+0.601
vo+0.597
avier+0.591
Neg logit contributions
 NW-0.523
ysical-0.519
 Nest-0.506
 Harding-0.489
 nost-0.485
Tokenoxy
Token ID23536
Feature activation-5.25e-01

Pos logit contributions
orio+0.549
Italy+0.473
vo+0.471
stanbul+0.470
avier+0.467
Neg logit contributions
 NW-0.409
ysical-0.404
 Nest-0.398
 Harding-0.385
 nost-0.381
Token resin
Token ID36536
Feature activation+1.49e-01

Pos logit contributions
orio+0.470
Italy+0.408
stanbul+0.407
vo+0.402
avier+0.398
Neg logit contributions
 NW-0.344
ysical-0.341
 Nest-0.332
 Harding-0.320
 nost-0.319
Token scaff
Token ID41498
Feature activation-2.88e+00

Pos logit contributions
 NW+0.101
ysical+0.100
 Nest+0.097
 Harding+0.094
 nost+0.093
Neg logit contributions
orio-0.131
Italy-0.113
stanbul-0.113
vo-0.111
avier-0.110
Tokenold
Token ID727
Feature activation+1.94e-01

Pos logit contributions
orio+2.354
Italy+1.990
stanbul+1.987
vo+1.983
avier+1.980
Neg logit contributions
 NW-2.105
ysical-2.051
 Nest-2.020
 nost-1.964
 Harding-1.933
Token that
Token ID326
Feature activation-3.51e-01

Pos logit contributions
 NW+0.131
ysical+0.129
 Nest+0.126
 Harding+0.121
 nost+0.121
Neg logit contributions
orio-0.171
Italy-0.148
stanbul-0.148
vo-0.146
avier-0.145
Token measures
Token ID5260
Feature activation-2.60e-01

Pos logit contributions
orio+0.334
Italy+0.291
stanbul+0.291
vo+0.288
avier+0.284
Neg logit contributions
 NW-0.211
ysical-0.207
 Nest-0.204
 Harding-0.196
 contended-0.194
Token 0
Token ID657
Feature activation-2.32e-01

Pos logit contributions
orio+0.241
Italy+0.210
stanbul+0.209
vo+0.207
avier+0.206
Neg logit contributions
 NW-0.163
ysical-0.161
 Nest-0.157
 Harding-0.151
 nost-0.150
Token.
Token ID13
Feature activation-4.48e-01

Pos logit contributions
orio+0.181
Italy+0.154
stanbul+0.153
vo+0.152
avier+0.150
Neg logit contributions
 NW-0.177
ysical-0.177
 Nest-0.172
 Harding-0.168
 contended-0.166
Token genome
Token ID19270
Feature activation-7.46e-01

Pos logit contributions
 NW+0.295
 Nest+0.288
ysical+0.288
 Harding+0.278
 nost+0.278
Neg logit contributions
orio-0.276
Italy-0.234
stanbul-0.232
vo-0.228
avier-0.228
Token,
Token ID11
Feature activation-1.88e-01

Pos logit contributions
orio+0.640
Italy+0.552
stanbul+0.549
vo+0.544
avier+0.540
Neg logit contributions
 NW-0.516
ysical-0.512
 Nest-0.500
 Harding-0.484
 contended-0.479
Token using
Token ID1262
Feature activation-9.25e-02

Pos logit contributions
orio+0.168
Italy+0.146
stanbul+0.145
vo+0.144
avier+0.143
Neg logit contributions
 NW-0.122
ysical-0.121
 Nest-0.119
 Harding-0.114
 nost-0.113
Token dozens
Token ID9264
Feature activation-6.44e-01

Pos logit contributions
orio+0.080
Italy+0.069
stanbul+0.069
vo+0.068
avier+0.067
Neg logit contributions
 NW-0.063
ysical-0.063
 Nest-0.061
 Harding-0.059
 nost-0.059
Token of
Token ID286
Feature activation-5.86e-01

Pos logit contributions
orio+0.618
Italy+0.543
stanbul+0.540
vo+0.539
avier+0.534
Neg logit contributions
 NW-0.373
ysical-0.372
 Nest-0.357
 Harding-0.348
 nost-0.342
Token automated
Token ID16359
Feature activation-2.85e+00

Pos logit contributions
orio+0.494
Italy+0.425
stanbul+0.423
vo+0.420
avier+0.415
Neg logit contributions
 NW-0.412
ysical-0.411
 Nest-0.399
 Harding-0.387
 nost-0.384
Token sequencing
Token ID32841
Feature activation-7.75e-01

Pos logit contributions
orio+2.342
Italy+2.008
stanbul+1.993
vo+1.989
avier+1.964
Neg logit contributions
ysical-2.050
 NW-2.024
 Nest-1.949
 Harding-1.914
 contended-1.891
Token machines
Token ID8217
Feature activation-5.88e-01

Pos logit contributions
orio+0.702
Italy+0.612
stanbul+0.609
vo+0.605
avier+0.599
Neg logit contributions
 NW-0.493
ysical-0.493
 Nest-0.476
 Harding-0.461
 nost-0.456
Token.
Token ID13
Feature activation-1.31e-01

Pos logit contributions
orio+0.494
Italy+0.424
stanbul+0.422
vo+0.419
avier+0.414
Neg logit contributions
 NW-0.416
ysical-0.413
 Nest-0.404
 Harding-0.391
 nost-0.388
Token
Token ID198
Feature activation-2.55e-01

Pos logit contributions
orio+0.125
Italy+0.110
stanbul+0.110
vo+0.109
avier+0.108
Neg logit contributions
 NW-0.077
ysical-0.076
 Nest-0.075
 Harding-0.072
 nost-0.071
Token
Token ID198
Feature activation-1.66e-01

Pos logit contributions
orio+0.260
stanbul+0.230
Italy+0.228
vo+0.226
avier+0.225
Neg logit contributions
 NW-0.137
ysical-0.133
 Nest-0.130
 Harding-0.124
 nost-0.122
Token rules
Token ID3173
Feature activation-5.93e-01

Pos logit contributions
orio+0.677
Italy+0.576
stanbul+0.572
vo+0.569
avier+0.562
Neg logit contributions
 NW-0.648
ysical-0.644
 Nest-0.629
 Harding-0.611
 nost-0.607
Token for
Token ID329
Feature activation-5.96e-01

Pos logit contributions
orio+0.538
Italy+0.468
stanbul+0.466
vo+0.463
avier+0.458
Neg logit contributions
 NW-0.380
ysical-0.378
 Nest-0.367
 Harding-0.354
 nost-0.351
Token the
Token ID262
Feature activation-3.06e-01

Pos logit contributions
orio+0.541
Italy+0.471
stanbul+0.468
vo+0.465
avier+0.461
Neg logit contributions
 NW-0.381
ysical-0.379
 Nest-0.368
 Harding-0.355
 nost-0.352
Token Affordable
Token ID19258
Feature activation-1.18e+00

Pos logit contributions
orio+0.282
Italy+0.246
stanbul+0.244
vo+0.243
avier+0.240
Neg logit contributions
 NW-0.194
ysical-0.191
 Nest-0.187
 Harding-0.180
 nost-0.178
Token Care
Token ID7276
Feature activation-1.31e+00

Pos logit contributions
orio+1.006
Italy+0.868
stanbul+0.867
vo+0.855
avier+0.848
Neg logit contributions
 NW-0.825
ysical-0.814
 Nest-0.799
 Harding-0.772
 nost-0.762
Token Act
Token ID2191
Feature activation-2.83e+00

Pos logit contributions
orio+1.333
Italy+1.178
stanbul+1.173
vo+1.162
avier+1.155
Neg logit contributions
 NW-0.705
ysical-0.698
 Nest-0.674
 Harding-0.646
 nost-0.637
Token (
Token ID357
Feature activation-2.86e-01

Pos logit contributions
orio+2.465
Italy+2.133
stanbul+2.126
vo+2.116
avier+2.095
Neg logit contributions
ysical-1.887
 NW-1.880
 Nest-1.824
 Harding-1.769
 nost-1.750
TokenACA
Token ID26576
Feature activation-5.37e-01

Pos logit contributions
orio+0.307
stanbul+0.273
Italy+0.272
vo+0.269
avier+0.268
Neg logit contributions
 NW-0.137
ysical-0.135
 Nest-0.129
 Harding-0.124
 nost-0.122
Token),
Token ID828
Feature activation-4.63e-01

Pos logit contributions
orio+0.414
Italy+0.350
stanbul+0.349
vo+0.346
avier+0.343
Neg logit contributions
 NW-0.415
ysical-0.415
 Nest-0.405
 Harding-0.393
 nost-0.390
Token or
Token ID393
Feature activation-3.45e-01

Pos logit contributions
orio+0.418
Italy+0.363
stanbul+0.361
vo+0.359
avier+0.355
Neg logit contributions
 NW-0.300
ysical-0.297
 Nest-0.289
 Harding-0.280
 nost-0.277
Token Obamacare
Token ID12439
Feature activation-1.37e+00

Pos logit contributions
orio+0.314
Italy+0.273
stanbul+0.272
vo+0.270
avier+0.268
Neg logit contributions
 NW-0.221
ysical-0.219
 Nest-0.212
 Harding-0.205
 nost-0.203
Token male
Token ID4257
Feature activation-7.89e-01

Pos logit contributions
ysical+0.097
 NW+0.096
 Nest+0.094
 Harding+0.091
 contended+0.090
Neg logit contributions
orio-0.117
Italy-0.101
vo-0.100
stanbul-0.100
avier-0.099
Token patriarchal
Token ID42301
Feature activation-6.82e-01

Pos logit contributions
orio+0.708
Italy+0.615
stanbul+0.611
vo+0.610
avier+0.605
Neg logit contributions
ysical-0.508
 NW-0.505
 Nest-0.491
 Harding-0.472
 contended-0.468
Token methods
Token ID5050
Feature activation-6.37e-01

Pos logit contributions
orio+0.619
Italy+0.539
stanbul+0.536
vo+0.534
avier+0.529
Neg logit contributions
ysical-0.432
 NW-0.430
 Nest-0.417
 Harding-0.402
 contended-0.398
Token of
Token ID286
Feature activation-2.14e-01

Pos logit contributions
orio+0.584
Italy+0.510
stanbul+0.507
vo+0.504
avier+0.499
Neg logit contributions
 NW-0.400
ysical-0.399
 Nest-0.386
 Harding-0.373
 nost-0.369
Token teaching
Token ID7743
Feature activation-1.04e+00

Pos logit contributions
orio+0.194
Italy+0.169
stanbul+0.168
vo+0.167
avier+0.166
Neg logit contributions
 NW-0.135
ysical-0.135
 Nest-0.131
 Harding-0.126
 nost-0.125
Token computation
Token ID29964
Feature activation-2.81e+00

Pos logit contributions
orio+0.959
Italy+0.838
stanbul+0.832
vo+0.831
avier+0.823
Neg logit contributions
ysical-0.637
 NW-0.632
 Nest-0.613
 Harding-0.589
 nost-0.585
Token and
Token ID290
Feature activation-1.68e-01

Pos logit contributions
orio+2.284
Italy+1.950
vo+1.941
stanbul+1.938
avier+1.922
Neg logit contributions
ysical-2.028
 NW-2.017
 Nest-1.972
 Harding-1.909
 nost-1.882
Token statistics
Token ID7869
Feature activation-1.04e+00

Pos logit contributions
orio+0.157
Italy+0.137
stanbul+0.137
vo+0.136
avier+0.135
Neg logit contributions
ysical-0.103
 NW-0.103
 Nest-0.099
 Harding-0.096
 nost-0.095
Token in
Token ID287
Feature activation-5.30e-02

Pos logit contributions
orio+0.851
Italy+0.730
stanbul+0.726
vo+0.722
avier+0.714
Neg logit contributions
 NW-0.745
ysical-0.745
 Nest-0.725
 Harding-0.702
 nost-0.696
Token favor
Token ID2661
Feature activation+3.52e-01

Pos logit contributions
orio+0.038
Italy+0.031
stanbul+0.031
vo+0.031
avier+0.030
Neg logit contributions
 NW-0.044
ysical-0.044
 Nest-0.043
 Harding-0.042
 nost-0.042
Token of
Token ID286
Feature activation-3.77e-02

Pos logit contributions
 NW+0.189
ysical+0.185
 Nest+0.181
 nost+0.172
 Harding+0.172
Neg logit contributions
orio-0.357
Italy-0.316
stanbul-0.314
vo-0.311
avier-0.309
Token minutes
Token ID2431
Feature activation+6.78e-01

Pos logit contributions
 NW+0.454
ysical+0.447
 Nest+0.438
 Harding+0.426
 contended+0.420
Neg logit contributions
orio-0.545
Italy-0.474
stanbul-0.470
avier-0.463
vo-0.461
Token later
Token ID1568
Feature activation-2.29e-01

Pos logit contributions
 NW+0.482
ysical+0.467
 Nest+0.464
 Harding+0.449
 contended+0.446
Neg logit contributions
orio-0.575
Italy-0.495
stanbul-0.492
vo-0.485
avier-0.484
Token.
Token ID13
Feature activation-2.01e-01

Pos logit contributions
orio+0.187
Italy+0.161
stanbul+0.159
vo+0.158
avier+0.157
Neg logit contributions
 NW-0.167
ysical-0.166
 Nest-0.162
 Harding-0.157
 nost-0.156
Token Players
Token ID13094
Feature activation+3.74e-01

Pos logit contributions
orio+0.193
Italy+0.170
stanbul+0.169
vo+0.168
avier+0.166
Neg logit contributions
 NW-0.117
ysical-0.117
 Nest-0.112
 Harding-0.108
 nost-0.107
Token s
Token ID264
Feature activation-1.24e+00

Pos logit contributions
 NW+0.228
ysical+0.225
 Nest+0.220
 Harding+0.213
 contended+0.213
Neg logit contributions
orio-0.351
Italy-0.308
stanbul-0.305
vo-0.302
avier-0.301
Tokenifted
Token ID21715
Feature activation-2.78e+00

Pos logit contributions
orio+1.144
Italy+0.997
stanbul+0.991
vo+0.990
avier+0.976
Neg logit contributions
 NW-0.774
ysical-0.772
 Nest-0.748
 Harding-0.723
 nost-0.714
Token over
Token ID625
Feature activation+1.07e-01

Pos logit contributions
orio+2.652
Italy+2.335
stanbul+2.321
vo+2.312
avier+2.290
Neg logit contributions
ysical-1.620
 NW-1.602
 Nest-1.538
 Harding-1.484
 contended-1.469
Token what
Token ID644
Feature activation-3.24e-01

Pos logit contributions
 NW+0.069
ysical+0.069
 Nest+0.067
 Harding+0.065
 nost+0.064
Neg logit contributions
orio-0.096
Italy-0.083
stanbul-0.083
vo-0.082
avier-0.082
Token
Token ID447
Feature activation-2.79e-01

Pos logit contributions
orio+0.312
Italy+0.274
stanbul+0.273
vo+0.271
avier+0.269
Neg logit contributions
 NW-0.189
ysical-0.188
 Nest-0.182
 Harding-0.175
 nost-0.174
Token
Token ID247
Feature activation+5.89e-04

Pos logit contributions
orio+0.185
Italy+0.151
stanbul+0.150
vo+0.148
avier+0.147
Neg logit contributions
 NW-0.246
ysical-0.246
 Nest-0.241
 Harding-0.236
 contended-0.234
Tokens
Token ID82
Feature activation-2.76e-01

Pos logit contributions
 NW+0.000
ysical+0.000
 Nest+0.000
 Harding+0.000
 nost+0.000
Neg logit contributions
orio-0.000
Italy-0.000
stanbul-0.000
vo-0.000
avier-0.000
Token support
Token ID1104
Feature activation-6.89e-01

Pos logit contributions
orio+0.512
Italy+0.441
stanbul+0.439
vo+0.436
avier+0.432
Neg logit contributions
 NW-0.419
ysical-0.418
 Nest-0.405
 Harding-0.393
 contended-0.389
Token for
Token ID329
Feature activation-1.50e-01

Pos logit contributions
orio+0.599
Italy+0.518
stanbul+0.516
vo+0.512
avier+0.507
Neg logit contributions
 NW-0.466
ysical-0.464
 Nest-0.451
 Harding-0.436
 nost-0.433
Token the
Token ID262
Feature activation-4.55e-02

Pos logit contributions
orio+0.131
Italy+0.114
stanbul+0.114
vo+0.112
avier+0.111
Neg logit contributions
 NW-0.100
ysical-0.099
 Nest-0.097
 Harding-0.094
 nost-0.093
Token Affordable
Token ID19258
Feature activation-1.58e+00

Pos logit contributions
orio+0.038
Italy+0.032
stanbul+0.032
vo+0.032
avier+0.032
Neg logit contributions
 NW-0.033
ysical-0.032
 Nest-0.032
 Harding-0.031
 nost-0.031
Token Care
Token ID7276
Feature activation-1.21e+00

Pos logit contributions
orio+1.334
Italy+1.148
stanbul+1.144
vo+1.132
avier+1.122
Neg logit contributions
 NW-1.118
ysical-1.110
 Nest-1.083
 Harding-1.050
 nost-1.039
Token Act
Token ID2191
Feature activation-2.75e+00

Pos logit contributions
orio+1.223
Italy+1.080
stanbul+1.076
vo+1.067
avier+1.059
Neg logit contributions
 NW-0.651
ysical-0.645
 Nest-0.622
 Harding-0.597
 nost-0.590
Token reaching
Token ID8978
Feature activation-8.23e-01

Pos logit contributions
orio+2.488
Italy+2.166
stanbul+2.159
vo+2.145
avier+2.128
Neg logit contributions
 NW-1.758
ysical-1.753
 Nest-1.700
 Harding-1.640
 nost-1.623
Token 54
Token ID7175
Feature activation-1.85e-01

Pos logit contributions
orio+0.737
Italy+0.640
stanbul+0.637
vo+0.632
avier+0.627
Neg logit contributions
 NW-0.537
ysical-0.534
 Nest-0.519
 Harding-0.502
 nost-0.497
Token%
Token ID4
Feature activation-1.02e-01

Pos logit contributions
orio+0.155
Italy+0.133
stanbul+0.132
vo+0.131
avier+0.130
Neg logit contributions
 NW-0.132
ysical-0.131
 Nest-0.128
 Harding-0.124
 nost-0.123
Token
Token ID784
Feature activation-3.77e-01

Pos logit contributions
orio+0.094
Italy+0.082
stanbul+0.082
vo+0.081
avier+0.080
Neg logit contributions
 NW-0.064
ysical-0.064
 Nest-0.062
 Harding-0.060
 nost-0.059
Token well
Token ID880
Feature activation-5.57e-01

Pos logit contributions
orio+0.337
Italy+0.293
stanbul+0.291
vo+0.289
avier+0.286
Neg logit contributions
 NW-0.246
ysical-0.245
 Nest-0.238
 Harding-0.231
 nost-0.228
Token alternative
Token ID5559
Feature activation-6.12e-02

Pos logit contributions
 NW+0.020
ysical+0.020
 Nest+0.020
 Harding+0.019
 nost+0.019
Neg logit contributions
orio-0.022
Italy-0.019
stanbul-0.019
vo-0.019
avier-0.018
Token to
Token ID284
Feature activation+1.23e-01

Pos logit contributions
orio+0.050
Italy+0.043
stanbul+0.043
vo+0.042
avier+0.042
Neg logit contributions
 NW-0.045
ysical-0.044
 Nest-0.043
 Harding-0.042
 nost-0.042
Token the
Token ID262
Feature activation+2.25e-02

Pos logit contributions
 NW+0.080
ysical+0.079
 Nest+0.077
 Harding+0.075
 nost+0.074
Neg logit contributions
orio-0.110
Italy-0.096
stanbul-0.096
vo-0.095
avier-0.094
Token Affordable
Token ID19258
Feature activation-1.59e+00

Pos logit contributions
 NW+0.014
ysical+0.013
 Nest+0.013
 Harding+0.013
 nost+0.013
Neg logit contributions
orio-0.021
Italy-0.019
stanbul-0.019
vo-0.018
avier-0.018
Token Care
Token ID7276
Feature activation-1.49e+00

Pos logit contributions
orio+1.330
Italy+1.143
stanbul+1.138
vo+1.129
avier+1.118
Neg logit contributions
 NW-1.127
ysical-1.121
 Nest-1.092
 Harding-1.059
 nost-1.049
Token Act
Token ID2191
Feature activation-2.73e+00

Pos logit contributions
orio+1.511
Italy+1.335
stanbul+1.329
vo+1.319
avier+1.309
Neg logit contributions
 NW-0.803
ysical-0.796
 Nest-0.769
 Harding-0.739
 nost-0.728
Token and
Token ID290
Feature activation-3.08e-02

Pos logit contributions
orio+2.326
Italy+2.004
stanbul+1.998
vo+1.990
avier+1.965
Neg logit contributions
ysical-1.878
 NW-1.877
 Nest-1.822
 Harding-1.762
 nost-1.745
Token sell
Token ID3677
Feature activation-1.60e+00

Pos logit contributions
orio+0.028
Italy+0.024
stanbul+0.024
vo+0.024
avier+0.024
Neg logit contributions
 NW-0.020
ysical-0.020
 Nest-0.019
 Harding-0.019
 contended-0.019
Token the
Token ID262
Feature activation-2.49e-01

Pos logit contributions
orio+1.414
Italy+1.225
stanbul+1.219
vo+1.213
avier+1.202
Neg logit contributions
ysical-1.055
 NW-1.054
 Nest-1.019
 Harding-0.986
 nost-0.976
Token public
Token ID1171
Feature activation-1.10e+00

Pos logit contributions
orio+0.213
Italy+0.184
stanbul+0.183
vo+0.181
avier+0.180
Neg logit contributions
 NW-0.172
ysical-0.171
 Nest-0.167
 Harding-0.162
 nost-0.161
Token on
Token ID319
Feature activation-1.17e-01

Pos logit contributions
orio+1.059
Italy+0.929
stanbul+0.926
vo+0.919
avier+0.912
Neg logit contributions
 NW-0.640
ysical-0.636
 Nest-0.616
 Harding-0.593
 nost-0.587
Token's
Token ID338
Feature activation-7.11e-02

Pos logit contributions
 NW+0.093
ysical+0.092
 Nest+0.090
 Harding+0.087
 nost+0.087
Neg logit contributions
orio-0.100
Italy-0.085
stanbul-0.084
vo-0.084
avier-0.083
Token a
Token ID257
Feature activation+3.47e-02

Pos logit contributions
orio+0.066
Italy+0.058
stanbul+0.057
vo+0.057
avier+0.057
Neg logit contributions
ysical-0.044
 NW-0.044
 Nest-0.042
 Harding-0.041
 nost-0.040
Token full
Token ID1336
Feature activation+7.73e-01

Pos logit contributions
 NW+0.022
ysical+0.022
 Nest+0.021
 Harding+0.020
 nost+0.020
Neg logit contributions
orio-0.032
Italy-0.028
stanbul-0.028
vo-0.027
avier-0.027
Token breakdown
Token ID14608
Feature activation-2.01e-01

Pos logit contributions
 NW+0.482
ysical+0.472
 Nest+0.464
 Harding+0.447
 nost+0.443
Neg logit contributions
orio-0.717
Italy-0.626
stanbul-0.626
vo-0.620
avier-0.613
Token from
Token ID422
Feature activation+1.55e-01

Pos logit contributions
orio+0.175
Italy+0.151
stanbul+0.151
vo+0.150
avier+0.148
Neg logit contributions
 NW-0.135
ysical-0.135
 Nest-0.131
 Harding-0.127
 nost-0.126
Token CMS
Token ID40773
Feature activation-2.70e+00

Pos logit contributions
ysical+0.094
 NW+0.094
 Nest+0.091
 Harding+0.088
 nost+0.087
Neg logit contributions
orio-0.145
Italy-0.126
stanbul-0.126
vo-0.125
avier-0.124
Token)
Token ID8
Feature activation+7.64e-01

Pos logit contributions
orio+2.061
Italy+1.749
stanbul+1.743
vo+1.737
avier+1.705
Neg logit contributions
ysical-2.100
 NW-2.086
 Nest-2.031
 Harding-1.988
 nost-1.966
Token in
Token ID287
Feature activation+3.02e-01

Pos logit contributions
 NW+0.497
ysical+0.492
 Nest+0.480
 Harding+0.464
 contended+0.461
Neg logit contributions
orio-0.688
Italy-0.597
stanbul-0.596
vo-0.589
avier-0.585
Token order
Token ID1502
Feature activation-1.82e-01

Pos logit contributions
 NW+0.198
ysical+0.197
 Nest+0.192
 Harding+0.185
 nost+0.184
Neg logit contributions
orio-0.269
Italy-0.234
stanbul-0.233
vo-0.231
avier-0.229
Token to
Token ID284
Feature activation+2.34e-01

Pos logit contributions
orio+0.150
Italy+0.128
stanbul+0.127
vo+0.127
avier+0.126
Neg logit contributions
 NW-0.130
ysical-0.130
 Nest-0.126
 Harding-0.123
 nost-0.122
Token be
Token ID307
Feature activation+6.61e-01

Pos logit contributions
 NW+0.155
ysical+0.153
 Nest+0.150
 nost+0.143
 Harding+0.143
Neg logit contributions
orio-0.210
Italy-0.181
stanbul-0.180
vo-0.179
avier-0.177
Token universally
Token ID26208
Feature activation-2.40e-01

Pos logit contributions
orio+0.694
Italy+0.606
stanbul+0.602
vo+0.597
avier+0.594
Neg logit contributions
 NW-0.442
ysical-0.434
 Nest-0.427
 Harding-0.409
 nost-0.406
Token across
Token ID1973
Feature activation-3.03e-01

Pos logit contributions
orio+0.226
Italy+0.198
stanbul+0.197
vo+0.195
avier+0.194
Neg logit contributions
 NW-0.147
ysical-0.145
 Nest-0.141
 Harding-0.136
 nost-0.135
Token Linux
Token ID7020
Feature activation+1.90e-01

Pos logit contributions
orio+0.238
Italy+0.201
stanbul+0.201
vo+0.197
avier+0.197
Neg logit contributions
 NW-0.234
ysical-0.230
 Nest-0.227
 Harding-0.220
 nost-0.219
Token distributions
Token ID24570
Feature activation+7.50e-01

Pos logit contributions
 NW+0.152
ysical+0.150
 Nest+0.148
 nost+0.143
 Harding+0.143
Neg logit contributions
orio-0.143
Italy-0.120
stanbul-0.120
vo-0.117
avier-0.117
Token,
Token ID11
Feature activation-1.53e-01

Pos logit contributions
 NW+0.527
ysical+0.516
 Nest+0.510
 Harding+0.492
 nost+0.488
Neg logit contributions
orio-0.639
Italy-0.549
stanbul-0.547
avier-0.537
vo-0.537
Token bund
Token ID12207
Feature activation-2.70e+00

Pos logit contributions
orio+0.132
Italy+0.113
stanbul+0.113
vo+0.112
avier+0.111
Neg logit contributions
 NW-0.107
ysical-0.105
 Nest-0.103
 Harding-0.100
 nost-0.099
Tokenling
Token ID1359
Feature activation-6.24e-01

Pos logit contributions
orio+2.150
Italy+1.839
stanbul+1.834
vo+1.826
avier+1.802
Neg logit contributions
ysical-2.006
 NW-2.006
 Nest-1.940
 Harding-1.896
 nost-1.882
Token any
Token ID597
Feature activation+5.80e-01

Pos logit contributions
orio+0.542
Italy+0.466
stanbul+0.462
avier+0.457
vo+0.457
Neg logit contributions
 NW-0.432
ysical-0.423
 Nest-0.420
 Harding-0.403
 Symb-0.401
Token dependencies
Token ID20086
Feature activation-1.80e-01

Pos logit contributions
 NW+0.400
ysical+0.391
 Nest+0.388
 Harding+0.372
 Symb+0.371
Neg logit contributions
orio-0.505
Italy-0.435
stanbul-0.432
vo-0.425
avier-0.424
Token as
Token ID355
Feature activation-2.53e-01

Pos logit contributions
orio+0.164
Italy+0.142
stanbul+0.141
vo+0.140
avier+0.139
Neg logit contributions
 NW-0.117
ysical-0.115
 Nest-0.113
 Harding-0.109
 contended-0.108
Token needed
Token ID2622
Feature activation+2.80e-01

Pos logit contributions
orio+0.230
Italy+0.199
stanbul+0.198
vo+0.196
avier+0.195
Neg logit contributions
 NW-0.164
ysical-0.161
 Nest-0.159
 Harding-0.152
 contended-0.152
Token The
Token ID383
Feature activation+2.66e-01

Pos logit contributions
orio+0.362
Italy+0.318
stanbul+0.317
vo+0.315
avier+0.312
Neg logit contributions
 NW-0.212
ysical-0.211
 Nest-0.205
 Harding-0.197
 nost-0.194
Token Ol
Token ID6544
Feature activation+1.38e-01

Pos logit contributions
 NW+0.175
ysical+0.173
 Nest+0.169
 Harding+0.164
 nost+0.162
Neg logit contributions
orio-0.236
Italy-0.206
stanbul-0.205
vo-0.203
avier-0.201
Tokenwe
Token ID732
Feature activation-8.62e-01

Pos logit contributions
 NW+0.099
ysical+0.099
 Nest+0.096
 Harding+0.093
 nost+0.092
Neg logit contributions
orio-0.114
Italy-0.098
stanbul-0.097
vo-0.097
avier-0.096
Tokenus
Token ID385
Feature activation-1.29e+00

Pos logit contributions
orio+0.661
Italy+0.559
stanbul+0.557
vo+0.551
avier+0.546
Neg logit contributions
 NW-0.672
ysical-0.669
 Nest-0.654
 Harding-0.635
 nost-0.630
Token B
Token ID347
Feature activation+1.82e-01

Pos logit contributions
orio+1.137
Italy+0.984
stanbul+0.979
vo+0.974
avier+0.964
Neg logit contributions
 NW-0.857
ysical-0.856
 Nest-0.828
 Harding-0.801
 nost-0.795
Tokenully
Token ID2132
Feature activation-2.67e+00

Pos logit contributions
 NW+0.136
ysical+0.135
 Nest+0.132
 Harding+0.128
 contended+0.127
Neg logit contributions
orio-0.145
Italy-0.124
stanbul-0.123
vo-0.122
avier-0.120
Token/
Token ID14
Feature activation-5.88e-02

Pos logit contributions
orio+2.424
Italy+2.108
stanbul+2.097
vo+2.090
avier+2.065
Neg logit contributions
 NW-1.703
ysical-1.702
 Nest-1.643
 Harding-1.588
 nost-1.577
TokenVict
Token ID21944
Feature activation-7.44e-01

Pos logit contributions
orio+0.046
Italy+0.039
stanbul+0.039
vo+0.039
avier+0.038
Neg logit contributions
 NW-0.045
ysical-0.044
 Nest-0.043
 Harding-0.042
 nost-0.042
Tokenim
Token ID320
Feature activation+3.40e-01

Pos logit contributions
orio+0.466
Italy+0.376
stanbul+0.374
vo+0.371
avier+0.366
Neg logit contributions
 NW-0.685
ysical-0.683
 Nest-0.669
 Harding-0.654
 nost-0.650
Token Question
Token ID18233
Feature activation-3.30e-01

Pos logit contributions
 NW+0.229
ysical+0.225
 Nest+0.222
 Harding+0.213
 Symb+0.212
Neg logit contributions
orio-0.299
Italy-0.260
stanbul-0.259
vo-0.254
avier-0.254
Tokennaire
Token ID24042
Feature activation+6.64e-02

Pos logit contributions
orio+0.242
Italy+0.203
stanbul+0.203
vo+0.200
avier+0.198
Neg logit contributions
 NW-0.268
ysical-0.267
 Nest-0.262
 Harding-0.254
 nost-0.252
Token,
Token ID11
Feature activation-1.01e-01

Pos logit contributions
orio+1.912
Italy+1.685
stanbul+1.676
vo+1.673
avier+1.659
Neg logit contributions
ysical-1.120
 NW-1.111
 Nest-1.070
 Harding-1.030
 nost-1.017
Token or
Token ID393
Feature activation-1.63e-01

Pos logit contributions
orio+0.093
Italy+0.081
stanbul+0.080
vo+0.080
avier+0.079
Neg logit contributions
 NW-0.064
ysical-0.064
 Nest-0.062
 Harding-0.060
 nost-0.059
Token the
Token ID262
Feature activation-2.06e-01

Pos logit contributions
orio+0.147
Italy+0.128
stanbul+0.128
vo+0.127
avier+0.126
Neg logit contributions
 NW-0.105
ysical-0.104
 Nest-0.101
 Harding-0.098
 nost-0.097
Token Affordable
Token ID19258
Feature activation-1.56e+00

Pos logit contributions
orio+0.188
Italy+0.164
stanbul+0.163
vo+0.162
avier+0.160
Neg logit contributions
 NW-0.132
ysical-0.130
 Nest-0.127
 Harding-0.123
 nost-0.122
Token Care
Token ID7276
Feature activation-1.41e+00

Pos logit contributions
orio+1.312
Italy+1.129
stanbul+1.126
vo+1.114
avier+1.103
Neg logit contributions
 NW-1.098
ysical-1.092
 Nest-1.064
 Harding-1.031
 nost-1.020
Token Act
Token ID2191
Feature activation-2.66e+00

Pos logit contributions
orio+1.418
Italy+1.252
stanbul+1.247
vo+1.238
avier+1.229
Neg logit contributions
 NW-0.762
ysical-0.758
 Nest-0.730
 Harding-0.701
 nost-0.693
Token,
Token ID11
Feature activation-4.92e-02

Pos logit contributions
orio+2.327
Italy+2.012
stanbul+2.004
vo+1.996
avier+1.981
Neg logit contributions
ysical-1.762
 NW-1.753
 Nest-1.706
 Harding-1.648
 nost-1.634
Token required
Token ID2672
Feature activation+2.85e-01

Pos logit contributions
orio+0.050
Italy+0.044
stanbul+0.044
vo+0.044
avier+0.043
Neg logit contributions
 NW-0.026
ysical-0.026
 Nest-0.025
 Harding-0.024
 nost-0.024
Token Americans
Token ID3399
Feature activation-8.14e-01

Pos logit contributions
 NW+0.187
ysical+0.183
 Nest+0.180
 Harding+0.174
 nost+0.173
Neg logit contributions
orio-0.258
Italy-0.224
stanbul-0.223
vo-0.220
avier-0.218
Token who
Token ID508
Feature activation-5.17e-01

Pos logit contributions
orio+0.706
Italy+0.610
stanbul+0.607
vo+0.603
avier+0.597
Neg logit contributions
 NW-0.553
ysical-0.551
 Nest-0.535
 Harding-0.518
 nost-0.514
Token qualified
Token ID10617
Feature activation+2.72e-01

Pos logit contributions
orio+0.477
Italy+0.417
stanbul+0.414
vo+0.409
avier+0.407
Neg logit contributions
 NW-0.324
ysical-0.321
 Nest-0.311
 contended-0.301
 Harding-0.300
Token,
Token ID11
Feature activation-2.48e-01

Pos logit contributions
orio+0.886
Italy+0.767
stanbul+0.763
vo+0.758
avier+0.751
Neg logit contributions
 NW-0.679
ysical-0.677
 Nest-0.657
 Harding-0.636
 nost-0.630
Token vegetable
Token ID20236
Feature activation-1.33e+00

Pos logit contributions
orio+0.209
Italy+0.180
stanbul+0.179
vo+0.177
avier+0.176
Neg logit contributions
 NW-0.175
ysical-0.173
 Nest-0.170
 Harding-0.164
 nost-0.163
Token juice
Token ID13135
Feature activation-1.52e+00

Pos logit contributions
orio+1.118
Italy+0.960
stanbul+0.956
vo+0.948
avier+0.939
Neg logit contributions
 NW-0.945
ysical-0.940
 Nest-0.917
 Harding-0.889
 nost-0.882
Token,
Token ID11
Feature activation-4.17e-02

Pos logit contributions
orio+1.328
Italy+1.151
stanbul+1.144
vo+1.139
avier+1.125
Neg logit contributions
ysical-1.021
 NW-1.019
 Nest-0.987
 Harding-0.955
 contended-0.946
Token and
Token ID290
Feature activation-4.18e-01

Pos logit contributions
orio+0.036
Italy+0.031
stanbul+0.031
vo+0.030
avier+0.030
Neg logit contributions
 NW-0.029
ysical-0.029
 Nest-0.028
 Harding-0.027
 nost-0.027
Token hot
Token ID3024
Feature activation-2.65e+00

Pos logit contributions
orio+0.360
Italy+0.310
stanbul+0.309
vo+0.306
avier+0.304
Neg logit contributions
 NW-0.289
ysical-0.285
 Nest-0.280
 Harding-0.270
 nost-0.269
Token o
Token ID267
Feature activation-3.53e-02

Pos logit contributions
orio+2.201
Italy+1.894
stanbul+1.877
vo+1.875
avier+1.846
Neg logit contributions
ysical-1.892
 NW-1.885
 Nest-1.827
 Harding-1.780
 contended-1.761
Tokenatmeal
Token ID45280
Feature activation-1.90e-01

Pos logit contributions
orio+0.022
Italy+0.018
stanbul+0.018
avier+0.018
vo+0.018
Neg logit contributions
 NW-0.032
ysical-0.032
 Nest-0.031
 Harding-0.031
 nost-0.030
Token.
Token ID13
Feature activation-6.54e-01

Pos logit contributions
orio+0.159
Italy+0.136
stanbul+0.136
vo+0.135
avier+0.134
Neg logit contributions
 NW-0.135
ysical-0.134
 Nest-0.131
 Harding-0.127
 nost-0.126
Token That
Token ID1320
Feature activation-6.64e-01

Pos logit contributions
orio+0.634
Italy+0.556
stanbul+0.554
vo+0.550
avier+0.546
Neg logit contributions
 NW-0.379
ysical-0.376
 Nest-0.366
 Harding-0.352
 nost-0.347
Token
Token ID447
Feature activation-3.45e-01

Pos logit contributions
orio+0.623
Italy+0.545
stanbul+0.543
vo+0.539
avier+0.534
Neg logit contributions
 NW-0.402
ysical-0.402
 Nest-0.387
 Harding-0.374
 nost-0.370
Token its
Token ID663
Feature activation-7.99e-01

Pos logit contributions
orio+1.350
Italy+1.166
stanbul+1.154
vo+1.152
avier+1.142
Neg logit contributions
 NW-1.114
ysical-1.114
 Nest-1.075
 Harding-1.043
 contended-1.032
Token boiling
Token ID24372
Feature activation-1.13e+00

Pos logit contributions
orio+0.518
Italy+0.424
stanbul+0.421
vo+0.418
avier+0.411
Neg logit contributions
 NW-0.717
ysical-0.716
 Nest-0.699
 Harding-0.683
 nost-0.678
Token,
Token ID11
Feature activation-2.17e-01

Pos logit contributions
orio+1.010
Italy+0.877
stanbul+0.873
vo+0.868
avier+0.859
Neg logit contributions
 NW-0.742
ysical-0.741
 Nest-0.717
 Harding-0.694
 nost-0.687
Token reduce
Token ID4646
Feature activation-4.22e-01

Pos logit contributions
orio+0.201
Italy+0.175
stanbul+0.175
vo+0.173
avier+0.171
Neg logit contributions
 NW-0.136
ysical-0.135
 Nest-0.132
 Harding-0.127
 nost-0.126
Token the
Token ID262
Feature activation-1.36e+00

Pos logit contributions
orio+0.374
Italy+0.324
stanbul+0.323
vo+0.320
avier+0.318
Neg logit contributions
 NW-0.280
ysical-0.278
 Nest-0.271
 Harding-0.262
 nost-0.260
Token heat
Token ID4894
Feature activation-2.65e+00

Pos logit contributions
orio+1.038
Italy+0.881
stanbul+0.872
vo+0.871
avier+0.855
Neg logit contributions
ysical-1.056
 NW-1.053
 Nest-1.022
 Harding-0.997
 contended-0.988
Token and
Token ID290
Feature activation-9.44e-01

Pos logit contributions
orio+2.197
Italy+1.892
stanbul+1.883
vo+1.876
avier+1.853
Neg logit contributions
ysical-1.879
 NW-1.871
 Nest-1.814
 Harding-1.764
 contended-1.745
Token cover
Token ID3002
Feature activation-1.29e+00

Pos logit contributions
orio+0.812
Italy+0.700
stanbul+0.699
vo+0.691
avier+0.686
Neg logit contributions
 NW-0.652
ysical-0.646
 Nest-0.633
 Harding-0.612
 nost-0.610
Token and
Token ID290
Feature activation-7.75e-01

Pos logit contributions
orio+1.181
Italy+1.028
stanbul+1.025
vo+1.017
avier+1.008
Neg logit contributions
 NW-0.815
ysical-0.810
 Nest-0.789
 Harding-0.761
 nost-0.756
Token let
Token ID1309
Feature activation-4.47e-01

Pos logit contributions
orio+0.674
Italy+0.581
stanbul+0.580
vo+0.574
avier+0.570
Neg logit contributions
 NW-0.531
ysical-0.524
 Nest-0.514
 Harding-0.497
 nost-0.496
Token it
Token ID340
Feature activation-8.77e-01

Pos logit contributions
orio+0.402
stanbul+0.349
Italy+0.348
vo+0.345
avier+0.342
Neg logit contributions
 NW-0.291
ysical-0.289
 Nest-0.283
 Harding-0.273
 nost-0.270
Token (
Token ID357
Feature activation-6.14e-01

Pos logit contributions
orio+0.293
Italy+0.248
stanbul+0.248
vo+0.245
avier+0.243
Neg logit contributions
 NW-0.272
ysical-0.266
 Nest-0.264
 Harding-0.253
 nost-0.251
Token0
Token ID15
Feature activation-3.67e-01

Pos logit contributions
orio+0.454
Italy+0.384
stanbul+0.379
vo+0.377
avier+0.373
Neg logit contributions
ysical-0.493
 NW-0.493
 Nest-0.481
 Harding-0.470
 contended-0.465
Token,
Token ID11
Feature activation-1.26e+00

Pos logit contributions
orio+0.342
stanbul+0.297
Italy+0.297
vo+0.293
avier+0.291
Neg logit contributions
 NW-0.228
ysical-0.223
 Nest-0.219
 Harding-0.210
 nost-0.208
Token($
Token ID16763
Feature activation-5.39e-01

Pos logit contributions
orio+0.973
Italy+0.826
stanbul+0.820
vo+0.813
avier+0.803
Neg logit contributions
 NW-0.969
ysical-0.965
 Nest-0.945
 Harding-0.922
 contended-0.912
Tokeni
Token ID72
Feature activation-1.30e+00

Pos logit contributions
orio+0.381
Italy+0.316
stanbul+0.314
vo+0.313
avier+0.307
Neg logit contributions
 NW-0.453
ysical-0.453
 Nest-0.443
 Harding-0.431
 contended-0.428
Token*
Token ID9
Feature activation-2.63e+00

Pos logit contributions
orio+0.914
Italy+0.763
stanbul+0.753
vo+0.747
avier+0.742
Neg logit contributions
ysical-1.097
 NW-1.097
 Nest-1.070
 Harding-1.040
 nost-1.033
Token$
Token ID3
Feature activation-5.25e-01

Pos logit contributions
orio+2.148
Italy+1.846
stanbul+1.832
vo+1.823
avier+1.793
Neg logit contributions
ysical-1.911
 NW-1.904
 Nest-1.862
 Harding-1.799
 contended-1.781
TokenFontSize
Token ID38160
Feature activation-1.57e-01

Pos logit contributions
orio+0.377
Italy+0.315
stanbul+0.313
vo+0.310
avier+0.306
Neg logit contributions
 NW-0.435
ysical-0.434
 Nest-0.424
 Harding-0.413
 nost-0.410
Token*
Token ID9
Feature activation-2.27e+00

Pos logit contributions
orio+0.126
Italy+0.107
stanbul+0.107
vo+0.106
avier+0.105
Neg logit contributions
 NW-0.117
ysical-0.116
 Nest-0.113
 Harding-0.110
 contended-0.109
Token2
Token ID17
Feature activation-4.86e-01

Pos logit contributions
orio+2.082
Italy+1.815
stanbul+1.807
vo+1.795
avier+1.778
Neg logit contributions
 NW-1.424
ysical-1.420
 Nest-1.376
 Harding-1.328
 nost-1.315
Token +
Token ID1343
Feature activation-8.67e-01

Pos logit contributions
orio+0.384
Italy+0.326
stanbul+0.325
vo+0.322
avier+0.319
Neg logit contributions
 NW-0.368
ysical-0.365
 Nest-0.356
 Harding-0.347
 nost-0.344
Tokenc
Token ID66
Feature activation+7.40e-01

Pos logit contributions
orio+0.074
Italy+0.063
stanbul+0.063
vo+0.062
avier+0.062
Neg logit contributions
 NW-0.065
ysical-0.064
 Nest-0.063
 Harding-0.061
 nost-0.060
Tokenrawler
Token ID39464
Feature activation-6.88e-01

Pos logit contributions
 NW+0.367
ysical+0.365
 Nest+0.354
 Harding+0.329
 nost+0.325
Neg logit contributions
orio-0.781
stanbul-0.699
Italy-0.693
vo-0.681
avier-0.678
Token,
Token ID11
Feature activation+5.15e-01

Pos logit contributions
orio+0.604
Italy+0.523
stanbul+0.520
vo+0.517
avier+0.512
Neg logit contributions
 NW-0.458
ysical-0.458
 Nest-0.443
 Harding-0.429
 nost-0.426
Token and
Token ID290
Feature activation+2.85e-01

Pos logit contributions
 NW+0.351
ysical+0.347
 Nest+0.339
 Harding+0.328
 nost+0.324
Neg logit contributions
orio-0.447
Italy-0.387
stanbul-0.385
vo-0.380
avier-0.377
Token Jub
Token ID38075
Feature activation-6.71e-02

Pos logit contributions
 NW+0.187
ysical+0.183
 Nest+0.180
 Harding+0.174
 Symb+0.171
Neg logit contributions
orio-0.257
Italy-0.223
stanbul-0.222
vo-0.219
avier-0.217
Tokenilee
Token ID40626
Feature activation-2.61e+00

Pos logit contributions
orio+0.045
Italy+0.037
stanbul+0.037
vo+0.036
avier+0.036
Neg logit contributions
 NW-0.059
ysical-0.059
 Nest-0.058
 Harding-0.056
 contended-0.056
Token hanging
Token ID10938
Feature activation+1.01e+00

Pos logit contributions
orio+2.390
Italy+2.087
stanbul+2.084
vo+2.074
avier+2.043
Neg logit contributions
ysical-1.630
 NW-1.622
 Nest-1.567
 Harding-1.510
 nost-1.503
Token out
Token ID503
Feature activation+7.72e-01

Pos logit contributions
 NW+0.653
ysical+0.631
 Nest+0.627
 Harding+0.606
 nost+0.604
Neg logit contributions
orio-0.925
Italy-0.804
stanbul-0.799
vo-0.792
avier-0.787
Token in
Token ID287
Feature activation+1.34e-01

Pos logit contributions
 NW+0.468
ysical+0.459
 Nest+0.449
 Harding+0.431
 nost+0.428
Neg logit contributions
orio-0.734
Italy-0.641
stanbul-0.636
vo-0.630
avier-0.629
Token a
Token ID257
Feature activation+2.25e-01

Pos logit contributions
 NW+0.087
ysical+0.087
 Nest+0.084
 Harding+0.081
 nost+0.080
Neg logit contributions
orio-0.120
Italy-0.104
stanbul-0.103
vo-0.103
avier-0.102
Token mall
Token ID17374
Feature activation-9.52e-01

Pos logit contributions
 NW+0.148
ysical+0.146
 Nest+0.143
 Harding+0.138
 nost+0.137
Neg logit contributions
orio-0.200
Italy-0.174
stanbul-0.173
vo-0.172
avier-0.170
Token Administration
Token ID8694
Feature activation-2.23e-01

Pos logit contributions
orio+0.007
Italy+0.006
stanbul+0.006
vo+0.006
avier+0.006
Neg logit contributions
 NW-0.006
ysical-0.006
 Nest-0.006
 Harding-0.006
 contended-0.006
Token.
Token ID13
Feature activation-6.31e-01

Pos logit contributions
orio+0.172
Italy+0.146
stanbul+0.145
vo+0.145
avier+0.143
Neg logit contributions
ysical-0.172
 NW-0.171
 Nest-0.167
 Harding-0.162
 contended-0.162
Token Legislative
Token ID30356
Feature activation+3.49e-01

Pos logit contributions
orio+0.588
Italy+0.513
stanbul+0.511
vo+0.508
avier+0.503
Neg logit contributions
 NW-0.387
ysical-0.385
 Nest-0.373
 Harding-0.360
 nost-0.357
Token history
Token ID2106
Feature activation+4.50e-01

Pos logit contributions
 NW+0.230
ysical+0.227
 Nest+0.222
 Harding+0.214
 nost+0.212
Neg logit contributions
orio-0.311
Italy-0.271
stanbul-0.269
vo-0.266
avier-0.265
Token of
Token ID286
Feature activation+2.61e-01

Pos logit contributions
 NW+0.279
ysical+0.278
 Nest+0.269
 Harding+0.260
 nost+0.257
Neg logit contributions
orio-0.416
Italy-0.363
stanbul-0.361
vo-0.359
avier-0.356
Token.
Token ID764
Feature activation-2.61e+00

Pos logit contributions
 NW+0.161
ysical+0.160
 Nest+0.155
 Harding+0.150
 nost+0.148
Neg logit contributions
orio-0.243
Italy-0.212
stanbul-0.211
vo-0.209
avier-0.207
Token08
Token ID2919
Feature activation-2.02e-01

Pos logit contributions
orio+2.140
Italy+1.855
vo+1.840
stanbul+1.833
avier+1.812
Neg logit contributions
ysical-1.864
 NW-1.855
 Nest-1.808
 Harding-1.752
 nost-1.743
Token per
Token ID583
Feature activation-1.48e-01

Pos logit contributions
orio+0.167
Italy+0.143
stanbul+0.142
vo+0.141
avier+0.139
Neg logit contributions
 NW-0.146
ysical-0.145
 Nest-0.142
 Harding-0.137
 nost-0.136
Token se
Token ID384
Feature activation-1.94e-01

Pos logit contributions
orio+0.137
Italy+0.120
vo+0.119
stanbul+0.118
avier+0.117
Neg logit contributions
ysical-0.092
 NW-0.091
 Nest-0.088
 Harding-0.085
 contended-0.084
Token laws
Token ID3657
Feature activation-6.61e-01

Pos logit contributions
orio+0.165
Italy+0.142
stanbul+0.141
vo+0.141
avier+0.139
Neg logit contributions
 NW-0.135
ysical-0.135
 Nest-0.131
 Harding-0.127
 nost-0.126
Token.
Token ID13
Feature activation-6.13e-01

Pos logit contributions
orio+0.580
Italy+0.503
stanbul+0.500
vo+0.498
avier+0.492
Neg logit contributions
ysical-0.440
 NW-0.438
 Nest-0.425
 Harding-0.411
 nost-0.407
Tokend
Token ID67
Feature activation+2.86e-01

Pos logit contributions
orio+0.110
Italy+0.094
stanbul+0.092
avier+0.091
vo+0.091
Neg logit contributions
 NW-0.111
ysical-0.111
 Nest-0.108
 Harding-0.106
 contended-0.105
Token suggest
Token ID1950
Feature activation-3.70e-01

Pos logit contributions
 NW+0.182
ysical+0.179
 Nest+0.176
 contended+0.171
 nost+0.170
Neg logit contributions
orio-0.261
Italy-0.228
stanbul-0.224
avier-0.222
vo-0.222
Token limiting
Token ID15637
Feature activation+7.58e-02

Pos logit contributions
orio+0.340
Italy+0.297
stanbul+0.295
vo+0.293
avier+0.290
Neg logit contributions
 NW-0.233
ysical-0.231
 Nest-0.225
 Harding-0.217
 nost-0.215
Token auto
Token ID8295
Feature activation+4.51e-03

Pos logit contributions
 NW+0.047
ysical+0.047
 Nest+0.045
 Harding+0.044
 nost+0.043
Neg logit contributions
orio-0.070
Italy-0.061
stanbul-0.061
vo-0.061
avier-0.060
Token-
Token ID12
Feature activation-4.07e-04

Pos logit contributions
 NW+0.003
ysical+0.003
 Nest+0.003
 Harding+0.003
 nost+0.003
Neg logit contributions
orio-0.004
Italy-0.003
stanbul-0.003
vo-0.003
avier-0.003
TokenISO
Token ID40734
Feature activation+2.08e+00

Pos logit contributions
orio+0.000
Italy+0.000
stanbul+0.000
vo+0.000
avier+0.000
Neg logit contributions
 NW-0.000
ysical-0.000
 Nest-0.000
 Harding-0.000
 nost-0.000
Token to
Token ID284
Feature activation-2.26e-01

Pos logit contributions
 NW+1.353
ysical+1.307
 Nest+1.290
 nost+1.250
 Harding+1.246
Neg logit contributions
orio-1.897
Italy-1.636
stanbul-1.627
avier-1.599
vo-1.598
Token 800
Token ID10460
Feature activation+4.67e-01

Pos logit contributions
orio+0.207
Italy+0.180
stanbul+0.179
vo+0.178
avier+0.177
Neg logit contributions
 NW-0.143
ysical-0.142
 Nest-0.138
 Harding-0.133
 nost-0.132
Token or
Token ID393
Feature activation-4.57e-01

Pos logit contributions
 NW+0.327
ysical+0.323
 Nest+0.315
 Harding+0.305
 nost+0.302
Neg logit contributions
orio-0.400
Italy-0.344
stanbul-0.342
vo-0.336
avier-0.336
Token lower
Token ID2793
Feature activation-2.74e-01

Pos logit contributions
orio+0.391
Italy+0.337
stanbul+0.335
vo+0.332
avier+0.329
Neg logit contributions
 NW-0.321
ysical-0.315
 Nest-0.309
 Harding-0.299
 contended-0.296
Token
Token ID784
Feature activation-6.61e-01

Pos logit contributions
orio+0.242
Italy+0.209
stanbul+0.207
vo+0.205
avier+0.204
Neg logit contributions
 NW-0.184
ysical-0.181
 Nest-0.177
 Harding-0.171
 nost-0.171
Token past
Token ID1613
Feature activation-9.98e-01

Pos logit contributions
orio+0.044
Italy+0.039
stanbul+0.038
vo+0.038
avier+0.038
Neg logit contributions
 NW-0.032
ysical-0.031
 Nest-0.030
 Harding-0.029
 nost-0.029
Token.
Token ID13
Feature activation-1.32e-01

Pos logit contributions
orio+0.828
Italy+0.710
stanbul+0.707
vo+0.702
avier+0.695
Neg logit contributions
 NW-0.717
ysical-0.713
 Nest-0.695
 Harding-0.674
 nost-0.669
Token
Token ID198
Feature activation+3.34e-01

Pos logit contributions
orio+0.130
Italy+0.114
stanbul+0.114
vo+0.113
avier+0.112
Neg logit contributions
 NW-0.074
ysical-0.074
 Nest-0.071
 Harding-0.068
 nost-0.068
Token
Token ID198
Feature activation+4.06e-01

Pos logit contributions
 NW+0.176
ysical+0.172
 Nest+0.168
 Harding+0.160
 nost+0.158
Neg logit contributions
orio-0.343
stanbul-0.303
Italy-0.301
vo-0.298
avier-0.297
TokenWith
Token ID3152
Feature activation+3.61e-02

Pos logit contributions
 NW+0.288
ysical+0.287
 Nest+0.280
 Harding+0.272
 nost+0.268
Neg logit contributions
orio-0.339
stanbul-0.289
Italy-0.287
vo-0.285
avier-0.283
Token Kron
Token ID44732
Feature activation+1.90e+00

Pos logit contributions
 NW+0.023
ysical+0.023
 Nest+0.022
 Harding+0.022
 nost+0.021
Neg logit contributions
orio-0.033
Italy-0.028
stanbul-0.028
vo-0.028
avier-0.028
Tokenstadt
Token ID38863
Feature activation-2.11e-01

Pos logit contributions
 NW+1.948
ysical+1.943
 Nest+1.907
 Harding+1.867
 nost+1.856
Neg logit contributions
orio-0.994
Italy-0.770
stanbul-0.763
vo-0.751
avier-0.738
Token and
Token ID290
Feature activation-8.32e-02

Pos logit contributions
orio+0.190
Italy+0.165
stanbul+0.165
vo+0.164
avier+0.162
Neg logit contributions
 NW-0.135
ysical-0.135
 Nest-0.131
 Harding-0.126
 nost-0.125
Token M
Token ID337
Feature activation+1.35e-01

Pos logit contributions
orio+0.077
Italy+0.067
stanbul+0.067
vo+0.066
avier+0.066
Neg logit contributions
ysical-0.052
 NW-0.052
 Nest-0.050
 Harding-0.048
 nost-0.048
Tokenakh
Token ID11322
Feature activation-7.10e-01

Pos logit contributions
 NW+0.082
ysical+0.082
 Nest+0.079
 Harding+0.076
 nost+0.075
Neg logit contributions
orio-0.127
Italy-0.111
stanbul-0.111
vo-0.110
avier-0.109
Tokenno
Token ID3919
Feature activation-5.95e-01

Pos logit contributions
orio+0.620
Italy+0.537
stanbul+0.535
vo+0.530
avier+0.526
Neg logit contributions
 NW-0.477
ysical-0.475
 Nest-0.461
 Harding-0.446
 nost-0.442
Token In
Token ID554
Feature activation+7.06e-02

Pos logit contributions
 NW+0.009
ysical+0.009
 Nest+0.008
 Harding+0.008
 nost+0.008
Neg logit contributions
orio-0.013
Italy-0.012
stanbul-0.012
vo-0.011
avier-0.011
Token L
Token ID406
Feature activation+1.42e-01

Pos logit contributions
 NW+0.044
ysical+0.044
 Nest+0.043
 Harding+0.041
 nost+0.041
Neg logit contributions
orio-0.065
Italy-0.057
stanbul-0.057
vo-0.056
avier-0.056
Token
Token ID447
Feature activation-4.14e-01

Pos logit contributions
 NW+0.114
ysical+0.113
 Nest+0.111
 Harding+0.108
 nost+0.107
Neg logit contributions
orio-0.105
Italy-0.089
stanbul-0.088
vo-0.087
avier-0.086
Token
Token ID247
Feature activation-2.13e-01

Pos logit contributions
orio+0.263
Italy+0.215
stanbul+0.213
vo+0.210
avier+0.207
Neg logit contributions
 NW-0.376
ysical-0.375
 Nest-0.367
 Harding-0.359
 nost-0.356
Tokenin
Token ID259
Feature activation-1.32e-01

Pos logit contributions
orio+0.167
Italy+0.142
stanbul+0.141
vo+0.140
avier+0.138
Neg logit contributions
 NW-0.162
ysical-0.162
 Nest-0.158
 Harding-0.153
 nost-0.152
Tokenvention
Token ID4018
Feature activation+1.83e+00

Pos logit contributions
orio+0.114
Italy+0.098
stanbul+0.098
vo+0.097
avier+0.096
Neg logit contributions
 NW-0.090
ysical-0.090
 Nest-0.087
 Harding-0.084
 nost-0.083
Token de
Token ID390
Feature activation+5.35e-01

Pos logit contributions
 NW+1.163
ysical+1.150
 Nest+1.130
 Harding+1.086
 nost+1.083
Neg logit contributions
orio-1.652
Italy-1.445
stanbul-1.436
vo-1.424
avier-1.415
Token la
Token ID8591
Feature activation+7.31e-01

Pos logit contributions
 NW+0.354
ysical+0.350
 Nest+0.344
 nost+0.331
 Harding+0.330
Neg logit contributions
orio-0.473
Italy-0.411
stanbul-0.410
vo-0.403
avier-0.402
Token myth
Token ID7918
Feature activation+7.89e-02

Pos logit contributions
 NW+0.439
ysical+0.435
 Nest+0.423
 Harding+0.406
 nost+0.405
Neg logit contributions
orio-0.693
Italy-0.607
stanbul-0.605
vo-0.599
avier-0.595
Tokenolog
Token ID928
Feature activation+6.70e-01

Pos logit contributions
 NW+0.059
ysical+0.058
 Nest+0.057
 Harding+0.055
 nost+0.055
Neg logit contributions
orio-0.063
Italy-0.054
stanbul-0.054
vo-0.053
avier-0.053
Tokenie
Token ID494
Feature activation-8.97e-01

Pos logit contributions
 NW+0.518
ysical+0.516
 Nest+0.501
 nost+0.488
 Harding+0.487
Neg logit contributions
orio-0.513
stanbul-0.441
Italy-0.439
vo-0.428
avier-0.423
Token under
Token ID739
Feature activation-5.12e-01

Pos logit contributions
 NW+0.065
ysical+0.065
 Nest+0.063
 Harding+0.061
 nost+0.060
Neg logit contributions
orio-0.096
Italy-0.083
stanbul-0.083
vo-0.082
avier-0.082
Tokenwhelming
Token ID36433
Feature activation+1.19e+00

Pos logit contributions
orio+0.453
Italy+0.392
stanbul+0.390
vo+0.389
avier+0.384
Neg logit contributions
 NW-0.338
ysical-0.338
 Nest-0.328
 Harding-0.317
 nost-0.314
Token.
Token ID13
Feature activation-1.32e-01

Pos logit contributions
 NW+0.869
ysical+0.864
 Nest+0.843
 Harding+0.818
 nost+0.814
Neg logit contributions
orio-0.979
Italy-0.841
stanbul-0.835
vo-0.824
avier-0.818
Token
Token ID198
Feature activation-1.94e-02

Pos logit contributions
orio+0.129
Italy+0.113
stanbul+0.113
vo+0.112
avier+0.111
Neg logit contributions
 NW-0.075
ysical-0.075
 Nest-0.072
 Harding-0.069
 nost-0.069
Token
Token ID198
Feature activation+2.96e-02

Pos logit contributions
orio+0.020
stanbul+0.018
Italy+0.018
vo+0.017
avier+0.017
Neg logit contributions
 NW-0.010
ysical-0.010
 Nest-0.010
 Harding-0.009
 nost-0.009
TokenFacebook
Token ID12025
Feature activation+1.93e+00

Pos logit contributions
 NW+0.021
ysical+0.021
 Nest+0.020
 Harding+0.020
 nost+0.019
Neg logit contributions
orio-0.025
stanbul-0.021
Italy-0.021
vo-0.021
avier-0.021
Token Twitter
Token ID3009
Feature activation+7.50e-01

Pos logit contributions
 NW+1.228
 Nest+1.195
ysical+1.190
 Harding+1.136
 nost+1.126
Neg logit contributions
orio-1.766
Italy-1.535
stanbul-1.527
vo-1.503
avier-1.497
Token Pinterest
Token ID17334
Feature activation+3.12e-01

Pos logit contributions
 NW+0.644
ysical+0.636
 Nest+0.634
 Harding+0.612
 Symb+0.605
Neg logit contributions
orio-0.519
stanbul-0.430
Italy-0.429
vo-0.424
avier-0.418
Token Mick
Token ID32722
Feature activation+5.54e-01

Pos logit contributions
ysical+0.186
 NW+0.185
 Nest+0.178
 Harding+0.172
 nost+0.171
Neg logit contributions
orio-0.296
Italy-0.260
stanbul-0.258
vo-0.257
avier-0.255
Token M
Token ID337
Feature activation+3.50e-01

Pos logit contributions
 NW+0.319
ysical+0.317
 Nest+0.307
 Harding+0.296
 nost+0.291
Neg logit contributions
orio-0.538
Italy-0.473
stanbul-0.472
vo-0.468
avier-0.464
Tokenalth
Token ID1094
Feature activation-2.59e-01

Pos logit contributions
 NW+0.232
ysical+0.231
 Nest+0.225
 Harding+0.217
 nost+0.215
Neg logit contributions
orio-0.309
Italy-0.267
stanbul-0.266
vo-0.265
avier-0.262
TokenGiven
Token ID15056
Feature activation-3.79e-01

Pos logit contributions
orio+0.026
stanbul+0.022
Italy+0.022
vo+0.022
avier+0.022
Neg logit contributions
 NW-0.022
ysical-0.022
 Nest-0.021
 Harding-0.021
 nost-0.021
Token the
Token ID262
Feature activation+8.47e-02

Pos logit contributions
orio+0.353
Italy+0.308
stanbul+0.307
vo+0.305
avier+0.302
Neg logit contributions
 NW-0.232
ysical-0.232
 Nest-0.224
 Harding-0.216
 nost-0.214
Token far
Token ID1290
Feature activation+7.35e-01

Pos logit contributions
 NW+0.054
ysical+0.054
 Nest+0.052
 Harding+0.050
 nost+0.050
Neg logit contributions
orio-0.077
Italy-0.067
stanbul-0.067
vo-0.066
avier-0.066
Token-
Token ID12
Feature activation+6.44e-02

Pos logit contributions
 NW+0.555
ysical+0.552
 Nest+0.539
 Harding+0.526
 nost+0.518
Neg logit contributions
orio-0.581
Italy-0.496
stanbul-0.495
vo-0.486
avier-0.479
Tokenreaching
Token ID30771
Feature activation+4.68e-01

Pos logit contributions
 NW+0.047
ysical+0.047
 Nest+0.046
 Harding+0.044
 nost+0.044
Neg logit contributions
orio-0.052
stanbul-0.045
Italy-0.045
vo-0.044
avier-0.044
Token socio
Token ID21790
Feature activation+1.68e+00

Pos logit contributions
 NW+0.297
ysical+0.294
 Nest+0.288
 Harding+0.276
 nost+0.274
Neg logit contributions
orio-0.429
Italy-0.375
stanbul-0.373
vo-0.369
avier-0.367
Token-
Token ID12
Feature activation-3.58e-02

Pos logit contributions
 NW+1.426
ysical+1.423
 Nest+1.389
 Harding+1.354
 nost+1.346
Neg logit contributions
orio-1.174
Italy-0.977
stanbul-0.975
vo-0.959
avier-0.950
Tokeneconomic
Token ID17079
Feature activation-1.54e-01

Pos logit contributions
orio+0.037
Italy+0.033
stanbul+0.033
vo+0.032
avier+0.032
Neg logit contributions
 NW-0.018
ysical-0.018
 Nest-0.018
 Harding-0.017
 nost-0.017
Token effects
Token ID3048
Feature activation+3.17e-01

Pos logit contributions
orio+0.137
Italy+0.119
stanbul+0.118
vo+0.117
avier+0.116
Neg logit contributions
 NW-0.102
ysical-0.101
 Nest-0.098
 Harding-0.095
 nost-0.095
Token,
Token ID11
Feature activation-1.67e-01

Pos logit contributions
 NW+0.181
ysical+0.180
 Nest+0.174
 Harding+0.168
 nost+0.166
Neg logit contributions
orio-0.309
Italy-0.272
stanbul-0.271
vo-0.269
avier-0.267
Token and
Token ID290
Feature activation-3.40e-01

Pos logit contributions
orio+0.151
Italy+0.132
stanbul+0.131
vo+0.130
avier+0.129
Neg logit contributions
 NW-0.107
ysical-0.106
 Nest-0.103
 Harding-0.100
 nost-0.099
Token to
Token ID284
Feature activation+1.11e-01

Pos logit contributions
orio+0.704
Italy+0.611
stanbul+0.608
vo+0.603
avier+0.599
Neg logit contributions
 NW-0.499
ysical-0.496
 Nest-0.481
 Harding-0.464
 nost-0.462
Token Saudi
Token ID7420
Feature activation-2.85e-01

Pos logit contributions
 NW+0.072
ysical+0.072
 Nest+0.070
 Harding+0.068
 nost+0.067
Neg logit contributions
orio-0.100
Italy-0.087
stanbul-0.086
vo-0.086
avier-0.085
Token Arabia
Token ID9671
Feature activation+2.05e-03

Pos logit contributions
orio+0.296
Italy+0.263
stanbul+0.261
vo+0.261
avier+0.258
Neg logit contributions
 NW-0.144
ysical-0.144
 Nest-0.138
 Harding-0.132
 nost-0.130
Token total
Token ID2472
Feature activation-1.74e-01

Pos logit contributions
 NW+0.001
ysical+0.001
 Nest+0.001
 Harding+0.001
 nost+0.001
Neg logit contributions
orio-0.002
Italy-0.002
stanbul-0.002
vo-0.002
avier-0.002
Token $
Token ID720
Feature activation+4.66e-01

Pos logit contributions
orio+0.155
Italy+0.134
stanbul+0.134
vo+0.133
avier+0.131
Neg logit contributions
ysical-0.113
 NW-0.113
 Nest-0.110
 Harding-0.106
 nost-0.105
Token1
Token ID16
Feature activation+5.52e-01

Pos logit contributions
 NW+0.398
ysical+0.392
 Nest+0.386
 Harding+0.378
 nost+0.372
Neg logit contributions
orio-0.324
stanbul-0.266
Italy-0.264
avier-0.261
vo-0.260
Token.
Token ID13
Feature activation-4.63e-01

Pos logit contributions
 NW+0.407
ysical+0.405
 Nest+0.395
 Harding+0.384
 nost+0.381
Neg logit contributions
orio-0.446
Italy-0.381
stanbul-0.379
vo-0.376
avier-0.372
Token3
Token ID18
Feature activation+3.62e-01

Pos logit contributions
orio+0.322
stanbul+0.264
Italy+0.264
vo+0.259
avier+0.259
Neg logit contributions
 NW-0.396
ysical-0.392
 Nest-0.384
 Harding-0.376
 nost-0.371
Token billion
Token ID2997
Feature activation-1.07e+00

Pos logit contributions
 NW+0.230
ysical+0.229
 Nest+0.222
 Harding+0.214
 nost+0.213
Neg logit contributions
orio-0.330
Italy-0.288
stanbul-0.286
vo-0.284
avier-0.281
Token.
Token ID13
Feature activation-3.59e-01

Pos logit contributions
orio+0.916
Italy+0.789
stanbul+0.785
vo+0.779
avier+0.772
Neg logit contributions
 NW-0.738
ysical-0.734
 Nest-0.715
 Harding-0.692
 nost-0.686
Token Business
Token ID7320
Feature activation-1.25e-02

Pos logit contributions
orio+0.332
Italy+0.289
stanbul+0.288
vo+0.286
avier+0.284
Neg logit contributions
 NW-0.223
ysical-0.222
 Nest-0.216
 Harding-0.208
 nost-0.206
Token to
Token ID284
Feature activation-6.03e-01

Pos logit contributions
ysical+0.078
 NW+0.077
 Nest+0.075
 Harding+0.073
 nost+0.072
Neg logit contributions
orio-0.092
Italy-0.079
stanbul-0.079
vo-0.078
avier-0.077
Token NASA
Token ID8884
Feature activation+1.43e-02

Pos logit contributions
orio+0.563
Italy+0.492
stanbul+0.489
vo+0.486
avier+0.482
Neg logit contributions
 NW-0.368
ysical-0.368
 Nest-0.355
 Harding-0.342
 nost-0.341
Token
Token ID447
Feature activation-1.69e-02

Pos logit contributions
 NW+0.010
ysical+0.010
 Nest+0.010
 Harding+0.010
 nost+0.009
Neg logit contributions
orio-0.012
Italy-0.010
stanbul-0.010
vo-0.010
avier-0.010
Token
Token ID247
Feature activation-4.66e-02

Pos logit contributions
orio+0.010
Italy+0.008
stanbul+0.008
vo+0.008
avier+0.008
Neg logit contributions
 NW-0.016
ysical-0.016
 Nest-0.016
 Harding-0.016
 contended-0.016
Tokens
Token ID82
Feature activation+6.00e-02

Pos logit contributions
orio+0.034
Italy+0.029
stanbul+0.028
vo+0.028
avier+0.028
Neg logit contributions
 NW-0.038
ysical-0.038
 Nest-0.037
 Harding-0.036
 contended-0.036
Token work
Token ID670
Feature activation+2.64e-01

Pos logit contributions
 NW+0.039
ysical+0.039
 Nest+0.038
 Harding+0.036
 nost+0.036
Neg logit contributions
orio-0.054
Italy-0.047
stanbul-0.047
vo-0.046
avier-0.046
Token on
Token ID319
Feature activation+2.75e-01

Pos logit contributions
 NW+0.160
ysical+0.160
 Nest+0.155
 Harding+0.149
 nost+0.148
Neg logit contributions
orio-0.248
Italy-0.217
stanbul-0.215
vo-0.214
avier-0.212
Token the
Token ID262
Feature activation+2.92e-01

Pos logit contributions
 NW+0.170
ysical+0.169
 Nest+0.164
 Harding+0.158
 nost+0.156
Neg logit contributions
orio-0.256
Italy-0.223
stanbul-0.222
vo-0.221
avier-0.219
Token Space
Token ID4687
Feature activation+9.23e-01

Pos logit contributions
 NW+0.165
ysical+0.163
 Nest+0.158
 Harding+0.152
 nost+0.150
Neg logit contributions
orio-0.288
Italy-0.254
stanbul-0.253
vo-0.251
avier-0.249
Token Launch
Token ID21225
Feature activation+3.17e-01

Pos logit contributions
 NW+0.574
ysical+0.567
 Nest+0.554
 Harding+0.530
 Symb+0.521
Neg logit contributions
orio-0.855
Italy-0.753
stanbul-0.750
vo-0.743
avier-0.739
Token System
Token ID4482
Feature activation+1.11e+00

Pos logit contributions
 NW+0.207
ysical+0.203
 Nest+0.201
 Harding+0.195
 contended+0.191
Neg logit contributions
orio-0.283
Italy-0.249
stanbul-0.248
vo-0.247
avier-0.243
Token
Token ID198
Feature activation+4.89e-01

Pos logit contributions
 NW+0.167
ysical+0.167
 Nest+0.161
 Harding+0.155
 nost+0.153
Neg logit contributions
orio-0.288
Italy-0.254
stanbul-0.253
vo-0.251
avier-0.249
Token
Token ID198
Feature activation+5.33e-01

Pos logit contributions
 NW+0.256
ysical+0.248
 Nest+0.243
 Harding+0.231
 nost+0.228
Neg logit contributions
orio-0.504
stanbul-0.447
Italy-0.443
vo-0.438
avier-0.437
Token>>
Token ID4211
Feature activation+9.83e-04

Pos logit contributions
 NW+0.439
ysical+0.438
 Nest+0.427
 Harding+0.417
 nost+0.414
Neg logit contributions
orio-0.384
stanbul-0.319
Italy-0.318
vo-0.314
avier-0.312
Token Take
Token ID7214
Feature activation+7.12e-01

Pos logit contributions
 NW+0.001
ysical+0.001
 Nest+0.001
 Harding+0.001
 nost+0.001
Neg logit contributions
orio-0.001
Italy-0.001
stanbul-0.001
vo-0.001
avier-0.001
Token action
Token ID2223
Feature activation+3.92e-01

Pos logit contributions
 NW+0.419
ysical+0.415
 Nest+0.405
 Harding+0.389
 nost+0.384
Neg logit contributions
orio-0.683
Italy-0.598
stanbul-0.595
vo-0.591
avier-0.587
Token:
Token ID25
Feature activation+3.27e-01

Pos logit contributions
 NW+0.254
ysical+0.254
 Nest+0.246
 Harding+0.238
 nost+0.236
Neg logit contributions
orio-0.352
Italy-0.306
stanbul-0.304
vo-0.302
avier-0.299
Token tell
Token ID1560
Feature activation+4.30e-01

Pos logit contributions
ysical+0.190
 NW+0.188
 Nest+0.181
 Harding+0.176
 contended+0.173
Neg logit contributions
orio-0.315
Italy-0.277
stanbul-0.276
vo-0.275
avier-0.271
Token Shell
Token ID17537
Feature activation+1.09e+00

Pos logit contributions
 NW+0.266
ysical+0.264
 Nest+0.256
 Harding+0.247
 nost+0.245
Neg logit contributions
orio-0.399
Italy-0.349
stanbul-0.348
vo-0.345
avier-0.342
Token to
Token ID284
Feature activation+1.75e-01

Pos logit contributions
 NW+0.703
ysical+0.700
 Nest+0.680
 Harding+0.657
 nost+0.651
Neg logit contributions
orio-0.984
Italy-0.855
stanbul-0.852
vo-0.845
avier-0.839
Token drop
Token ID4268
Feature activation+1.08e+00

Pos logit contributions
 NW+0.094
ysical+0.093
 Nest+0.090
 Harding+0.086
 nost+0.085
Neg logit contributions
orio-0.177
Italy-0.156
stanbul-0.155
vo-0.154
avier-0.153
Token its
Token ID663
Feature activation+8.66e-02

Pos logit contributions
 NW+0.676
ysical+0.663
 Nest+0.654
 Harding+0.625
 nost+0.623
Neg logit contributions
orio-1.006
Italy-0.876
stanbul-0.873
vo-0.864
avier-0.860
Token to
Token ID284
Feature activation+1.42e-01

Pos logit contributions
orio+0.473
Italy+0.411
stanbul+0.410
vo+0.406
avier+0.403
Neg logit contributions
 NW-0.338
ysical-0.336
 Nest-0.327
 Harding-0.316
 nost-0.313
Token Kinder
Token ID46832
Feature activation+3.81e-01

Pos logit contributions
 NW+0.095
ysical+0.094
 Nest+0.092
 Harding+0.088
 nost+0.088
Neg logit contributions
orio-0.125
Italy-0.108
stanbul-0.108
vo-0.107
avier-0.106
Token Morgan
Token ID10805
Feature activation-1.61e-01

Pos logit contributions
ysical+0.170
 NW+0.170
 Nest+0.161
 Harding+0.154
 nost+0.152
Neg logit contributions
orio-0.418
Italy-0.374
stanbul-0.372
vo-0.371
avier-0.368
Token
Token ID447
Feature activation-1.03e-01

Pos logit contributions
orio+0.143
Italy+0.124
stanbul+0.123
vo+0.122
avier+0.121
Neg logit contributions
 NW-0.105
ysical-0.105
 Nest-0.102
 Harding-0.099
 nost-0.098
Token
Token ID247
Feature activation-7.02e-03

Pos logit contributions
orio+0.062
Italy+0.050
stanbul+0.049
vo+0.048
avier+0.048
Neg logit contributions
 NW-0.097
ysical-0.096
 Nest-0.095
 Harding-0.093
 contended-0.092
Tokens
Token ID82
Feature activation+2.18e-01

Pos logit contributions
orio+0.005
Italy+0.004
stanbul+0.004
avier+0.004
vo+0.004
Neg logit contributions
 NW-0.006
ysical-0.006
 Nest-0.005
 Harding-0.005
 contended-0.005
Token Trans
Token ID3602
Feature activation+2.59e-01

Pos logit contributions
 NW+0.144
ysical+0.142
 Nest+0.139
 Harding+0.134
 nost+0.133
Neg logit contributions
orio-0.195
Italy-0.169
stanbul-0.168
vo-0.167
avier-0.165
Token Mountain
Token ID9638
Feature activation-1.31e+00

Pos logit contributions
ysical+0.140
 NW+0.139
 Nest+0.133
 Harding+0.129
 nost+0.129
Neg logit contributions
orio-0.260
Italy-0.230
vo-0.230
stanbul-0.229
avier-0.226
Token pipeline
Token ID11523
Feature activation-2.33e-01

Pos logit contributions
orio+1.052
Italy+0.896
vo+0.892
stanbul+0.892
avier+0.878
Neg logit contributions
ysical-0.970
 NW-0.965
 Nest-0.940
 Harding-0.917
 nost-0.908
Token expansion
Token ID7118
Feature activation-1.82e-01

Pos logit contributions
orio+0.196
Italy+0.169
stanbul+0.168
vo+0.166
avier+0.165
Neg logit contributions
 NW-0.166
ysical-0.164
 Nest-0.160
 Harding-0.155
 contended-0.154
Token,
Token ID11
Feature activation+1.14e-02

Pos logit contributions
orio+0.160
Italy+0.139
stanbul+0.138
vo+0.137
avier+0.136
Neg logit contributions
 NW-0.121
ysical-0.120
 Nest-0.117
 Harding-0.113
 contended-0.112
Token forward
Token ID2651
Feature activation-1.63e-01

Pos logit contributions
orio+0.234
Italy+0.202
stanbul+0.201
vo+0.199
avier+0.198
Neg logit contributions
 NW-0.182
ysical-0.181
 Nest-0.176
 Harding-0.170
 nost-0.168
Token.
Token ID13
Feature activation+1.76e-01

Pos logit contributions
orio+0.140
Italy+0.121
stanbul+0.120
vo+0.119
avier+0.118
Neg logit contributions
 NW-0.111
ysical-0.111
 Nest-0.108
 Harding-0.105
 nost-0.104
Token
Token ID447
Feature activation+2.31e-01

Pos logit contributions
 NW+0.102
ysical+0.102
 Nest+0.099
 Harding+0.095
 nost+0.094
Neg logit contributions
orio-0.169
Italy-0.149
stanbul-0.148
vo-0.147
avier-0.146
Token
Token ID251
Feature activation-3.10e-02

Pos logit contributions
 NW+0.211
ysical+0.211
 Nest+0.206
 Harding+0.201
 nost+0.200
Neg logit contributions
orio-0.145
Italy-0.118
stanbul-0.117
vo-0.116
avier-0.114
Token
Token ID198
Feature activation+2.42e-01

Pos logit contributions
orio+0.030
Italy+0.027
stanbul+0.026
vo+0.026
avier+0.026
Neg logit contributions
 NW-0.018
ysical-0.018
 Nest-0.017
 Harding-0.017
 nost-0.016
Token
Token ID198
Feature activation+3.13e-01

Pos logit contributions
 NW+0.127
ysical+0.124
 Nest+0.121
 Harding+0.115
 nost+0.114
Neg logit contributions
orio-0.249
stanbul-0.220
Italy-0.219
vo-0.216
avier-0.216
TokenW
Token ID54
Feature activation-2.85e-01

Pos logit contributions
 NW+0.225
ysical+0.222
 Nest+0.218
 Harding+0.211
 nost+0.209
Neg logit contributions
orio-0.260
stanbul-0.222
Italy-0.220
vo-0.218
avier-0.217
Tokenong
Token ID506
Feature activation+1.17e+00

Pos logit contributions
orio+0.144
Italy+0.112
stanbul+0.111
vo+0.109
avier+0.106
Neg logit contributions
 NW-0.296
ysical-0.296
 Nest-0.289
 Harding-0.283
 nost-0.282
Token sees
Token ID7224
Feature activation+1.81e-01

Pos logit contributions
 NW+0.588
ysical+0.580
 Nest+0.563
 Harding+0.538
 contended+0.537
Neg logit contributions
orio-1.223
Italy-1.090
stanbul-1.082
vo-1.074
avier-1.063
Token sad
Token ID6507
Feature activation-1.35e-01

Pos logit contributions
 NW+0.117
ysical+0.115
 Nest+0.113
 Harding+0.109
 nost+0.108
Neg logit contributions
orio-0.163
Italy-0.142
stanbul-0.141
vo-0.140
avier-0.139
Token parallels
Token ID30614
Feature activation-4.91e-01

Pos logit contributions
orio+0.127
Italy+0.112
stanbul+0.111
vo+0.110
avier+0.109
Neg logit contributions
 NW-0.082
ysical-0.081
 Nest-0.079
 Harding-0.076
 nost-0.075
Tokenins
Token ID1040
Feature activation-2.87e-02

Pos logit contributions
orio+0.277
Italy+0.236
stanbul+0.235
vo+0.231
avier+0.229
Neg logit contributions
 NW-0.277
ysical-0.276
 Nest-0.270
 Harding-0.262
 nost-0.260
Token cl
Token ID537
Feature activation-4.64e-01

Pos logit contributions
orio+0.025
Italy+0.021
stanbul+0.021
vo+0.021
avier+0.021
Neg logit contributions
 NW-0.020
ysical-0.020
 Nest-0.019
 nost-0.019
 Harding-0.018
Tokenament
Token ID3263
Feature activation+1.86e-02

Pos logit contributions
orio+0.351
Italy+0.300
stanbul+0.299
vo+0.294
avier+0.285
Neg logit contributions
ysical-0.364
 NW-0.362
 Nest-0.352
 Harding-0.342
 nost-0.341
Token que
Token ID8358
Feature activation-1.06e-01

Pos logit contributions
 NW+0.014
ysical+0.014
 Nest+0.014
 nost+0.013
 Harding+0.013
Neg logit contributions
orio-0.015
Italy-0.013
stanbul-0.012
vo-0.012
avier-0.012
Token le
Token ID443
Feature activation+3.69e-01

Pos logit contributions
orio+0.090
Italy+0.078
stanbul+0.077
vo+0.076
avier+0.076
Neg logit contributions
 NW-0.074
ysical-0.073
 Nest-0.072
 Harding-0.069
 nost-0.069
Token Command
Token ID9455
Feature activation-7.78e-01

Pos logit contributions
 NW+0.264
ysical+0.261
 Nest+0.257
 nost+0.249
 Harding+0.247
Neg logit contributions
orio-0.305
Italy-0.264
stanbul-0.263
vo-0.256
avier-0.256
Tokenement
Token ID972
Feature activation+1.05e+00

Pos logit contributions
orio+0.628
Italy+0.537
stanbul+0.534
vo+0.530
avier+0.524
Neg logit contributions
 NW-0.575
ysical-0.572
 Nest-0.558
 Harding-0.541
 nost-0.538
Token Cors
Token ID26978
Feature activation-8.55e-01

Pos logit contributions
 NW+0.730
ysical+0.718
 Nest+0.709
 nost+0.685
 Harding+0.683
Neg logit contributions
orio-0.898
Italy-0.776
stanbul-0.772
vo-0.762
avier-0.755
Tokenaire
Token ID7626
Feature activation+1.07e+00

Pos logit contributions
orio+0.700
Italy+0.599
stanbul+0.596
vo+0.592
avier+0.586
Neg logit contributions
 NW-0.622
ysical-0.620
 Nest-0.603
 Harding-0.585
 nost-0.580
Token ser
Token ID1055
Feature activation+9.73e-01

Pos logit contributions
 NW+0.746
ysical+0.731
 Nest+0.724
 nost+0.702
 Harding+0.696
Neg logit contributions
orio-0.913
Italy-0.786
stanbul-0.783
vo-0.771
avier-0.768
Tokenait
Token ID4548
Feature activation+1.97e-02

Pos logit contributions
 NW+0.767
ysical+0.755
 Nest+0.740
 nost+0.727
 Harding+0.721
Neg logit contributions
orio-0.730
stanbul-0.620
Italy-0.620
avier-0.601
vo-0.598
Token,
Token ID11
Feature activation+2.83e-01

Pos logit contributions
 NW+0.255
ysical+0.253
 Nest+0.246
 Harding+0.238
 nost+0.235
Neg logit contributions
orio-0.360
Italy-0.313
stanbul-0.312
vo-0.310
avier-0.307
Token says
Token ID1139
Feature activation-3.62e-01

Pos logit contributions
ysical+0.126
 NW+0.125
 Nest+0.119
 Harding+0.114
 nost+0.112
Neg logit contributions
orio-0.310
Italy-0.277
stanbul-0.276
vo-0.276
avier-0.274
Token low
Token ID1877
Feature activation+4.10e-01

Pos logit contributions
orio+0.333
Italy+0.290
stanbul+0.289
vo+0.287
avier+0.284
Neg logit contributions
 NW-0.228
ysical-0.226
 Nest-0.220
 Harding-0.213
 nost-0.210
Token prices
Token ID4536
Feature activation+6.88e-01

Pos logit contributions
 NW+0.321
ysical+0.317
 Nest+0.311
 Harding+0.302
 nost+0.301
Neg logit contributions
orio-0.315
Italy-0.266
stanbul-0.266
vo-0.262
avier-0.260
Token in
Token ID287
Feature activation-3.44e-01

Pos logit contributions
 NW+0.439
ysical+0.430
 Nest+0.421
 Harding+0.407
 nost+0.406
Neg logit contributions
orio-0.631
Italy-0.549
stanbul-0.548
vo-0.539
avier-0.537
Token a
Token ID257
Feature activation-1.21e-01

Pos logit contributions
orio+0.312
Italy+0.272
stanbul+0.271
vo+0.269
avier+0.266
Neg logit contributions
 NW-0.220
ysical-0.219
 Nest-0.212
 Harding-0.205
 nost-0.203
Token company
Token ID1664
Feature activation-6.18e-01

Pos logit contributions
orio+0.096
Italy+0.082
stanbul+0.081
vo+0.081
avier+0.080
Neg logit contributions
 NW-0.091
ysical-0.090
 Nest-0.089
 Harding-0.086
 nost-0.085
Token's
Token ID338
Feature activation+2.42e-01

Pos logit contributions
orio+0.536
Italy+0.463
stanbul+0.461
vo+0.458
avier+0.453
Neg logit contributions
 NW-0.421
ysical-0.418
 Nest-0.407
 Harding-0.394
 nost-0.391
Token first
Token ID717
Feature activation-9.85e-01

Pos logit contributions
 NW+0.162
ysical+0.157
 Nest+0.156
 Harding+0.150
 nost+0.150
Neg logit contributions
orio-0.214
Italy-0.186
stanbul-0.185
vo-0.183
avier-0.182
Token year
Token ID614
Feature activation+1.66e-01

Pos logit contributions
orio+0.810
Italy+0.694
stanbul+0.692
vo+0.685
avier+0.679
Neg logit contributions
 NW-0.718
ysical-0.710
 Nest-0.696
 Harding-0.673
 nost-0.670
Token don
Token ID836
Feature activation+9.22e-01

Pos logit contributions
 NW+0.106
ysical+0.104
 Nest+0.102
 nost+0.098
 Harding+0.098
Neg logit contributions
orio-0.152
Italy-0.133
stanbul-0.132
vo-0.130
avier-0.129
Token Player
Token ID7853
Feature activation-4.31e-01

Pos logit contributions
orio+0.305
Italy+0.267
stanbul+0.266
vo+0.265
avier+0.263
Neg logit contributions
 NW-0.189
ysical-0.189
 Nest-0.182
 Harding-0.175
 nost-0.174
TokenUnknown
Token ID20035
Feature activation-1.65e+00

Pos logit contributions
orio+0.342
Italy+0.291
stanbul+0.290
vo+0.287
avier+0.284
Neg logit contributions
 NW-0.325
ysical-0.323
 Nest-0.316
 Harding-0.307
 nost-0.304
Token specifically
Token ID5734
Feature activation-8.04e-01

Pos logit contributions
orio+1.643
Italy+1.447
stanbul+1.442
vo+1.440
avier+1.427
Neg logit contributions
ysical-0.898
 NW-0.889
 Nest-0.852
 nost-0.814
 Harding-0.814
Token referenced
Token ID20717
Feature activation-4.39e-01

Pos logit contributions
orio+0.839
Italy+0.744
stanbul+0.742
vo+0.740
avier+0.734
Neg logit contributions
ysical-0.401
 NW-0.401
 Nest-0.384
 Harding-0.367
 nost-0.362
Token Destiny
Token ID17886
Feature activation-1.31e+00

Pos logit contributions
orio+0.406
Italy+0.355
stanbul+0.353
vo+0.351
avier+0.347
Neg logit contributions
 NW-0.273
ysical-0.272
 Nest-0.264
 Harding-0.255
 nost-0.252
Token as
Token ID355
Feature activation-2.57e-01

Pos logit contributions
orio+1.132
Italy+0.980
stanbul+0.975
vo+0.970
avier+0.959
Neg logit contributions
ysical-0.891
 NW-0.889
 Nest-0.860
 Harding-0.834
 nost-0.828
Token a
Token ID257
Feature activation+2.66e-01

Pos logit contributions
orio+0.229
Italy+0.199
stanbul+0.198
vo+0.196
avier+0.195
Neg logit contributions
 NW-0.168
ysical-0.168
 Nest-0.163
 Harding-0.157
 nost-0.156
Token title
Token ID3670
Feature activation-6.37e-01

Pos logit contributions
 NW+0.176
ysical+0.174
 Nest+0.170
 Harding+0.163
 nost+0.163
Neg logit contributions
orio-0.237
Italy-0.206
stanbul-0.205
vo-0.203
avier-0.201
Token that
Token ID326
Feature activation+5.82e-03

Pos logit contributions
orio+0.609
Italy+0.534
stanbul+0.532
vo+0.527
avier+0.523
Neg logit contributions
 NW-0.379
ysical-0.374
 Nest-0.364
 Harding-0.351
 contended-0.347
Token did
Token ID750
Feature activation-8.78e-02

Pos logit contributions
 NW+0.004
ysical+0.004
 Nest+0.004
 Harding+0.003
 contended+0.003
Neg logit contributions
orio-0.005
Italy-0.005
stanbul-0.005
vo-0.005
avier-0.005
Token a
Token ID257
Feature activation+9.41e-02

Pos logit contributions
orio+0.082
Italy+0.071
stanbul+0.071
vo+0.070
avier+0.070
Neg logit contributions
 NW-0.054
ysical-0.054
 Nest-0.053
 Harding-0.050
 nost-0.050
Tokensy
Token ID1837
Feature activation-1.56e-01

Pos logit contributions
orio+0.456
Italy+0.398
stanbul+0.396
vo+0.395
avier+0.389
Neg logit contributions
 NW-0.322
ysical-0.320
 Nest-0.311
 Harding-0.301
 contended-0.298
Tokenur
Token ID333
Feature activation-1.38e+00

Pos logit contributions
orio+0.104
Italy+0.085
stanbul+0.085
vo+0.084
avier+0.083
Neg logit contributions
 NW-0.138
ysical-0.137
 Nest-0.135
 Harding-0.131
 nost-0.131
Tokenup
Token ID929
Feature activation-5.49e-01

Pos logit contributions
orio+0.745
vo+0.584
Italy+0.583
stanbul+0.578
avier+0.563
Neg logit contributions
 NW-1.388
ysical-1.381
 Nest-1.352
 Harding-1.340
 contended-1.323
Tokeninski
Token ID21141
Feature activation+2.89e-01

Pos logit contributions
orio+0.442
Italy+0.377
stanbul+0.375
vo+0.372
avier+0.369
Neg logit contributions
 NW-0.407
ysical-0.406
 Nest-0.395
 Harding-0.383
 nost-0.380
Tokeny
Token ID88
Feature activation-6.56e-01

Pos logit contributions
 NW+0.167
ysical+0.167
 Nest+0.161
 Harding+0.155
 nost+0.153
Neg logit contributions
orio-0.279
Italy-0.245
stanbul-0.244
vo-0.243
avier-0.241
Token Ag
Token ID2449
Feature activation-6.98e-01

Pos logit contributions
orio+0.640
Italy+0.564
stanbul+0.562
vo+0.560
avier+0.553
Neg logit contributions
ysical-0.372
 NW-0.371
 Nest-0.355
 Harding-0.344
 contended-0.340
Tokenrop
Token ID1773
Feature activation+9.72e-01

Pos logit contributions
orio+0.598
Italy+0.515
stanbul+0.512
vo+0.511
avier+0.505
Neg logit contributions
 NW-0.479
ysical-0.477
 Nest-0.464
 Harding-0.454
 contended-0.449
Tokenost
Token ID455
Feature activation-1.25e+00

Pos logit contributions
 NW+0.754
ysical+0.752
 Nest+0.732
 Harding+0.714
 contended+0.709
Neg logit contributions
orio-0.748
Italy-0.632
stanbul-0.630
vo-0.626
avier-0.619
Tokenach
Token ID620
Feature activation+6.06e-01

Pos logit contributions
orio+1.250
Italy+1.103
stanbul+1.099
vo+1.092
avier+1.083
Neg logit contributions
 NW-0.677
ysical-0.674
 Nest-0.650
 Harding-0.624
 nost-0.617
Token,
Token ID11
Feature activation-2.27e-01

Pos logit contributions
 NW+0.419
ysical+0.419
 Nest+0.406
 Harding+0.394
 nost+0.391
Neg logit contributions
orio-0.516
Italy-0.445
stanbul-0.443
vo-0.440
avier-0.435
Token a
Token ID257
Feature activation+1.44e-01

Pos logit contributions
orio+0.200
Italy+0.174
stanbul+0.173
vo+0.172
avier+0.170
Neg logit contributions
 NW-0.150
ysical-0.150
 Nest-0.145
 Harding-0.140
 nost-0.139
Token.
Token ID13
Feature activation+3.30e-02

Pos logit contributions
orio+0.209
stanbul+0.178
Italy+0.178
vo+0.174
avier+0.174
Neg logit contributions
 NW-0.180
ysical-0.174
 Nest-0.174
 Harding-0.167
 nost-0.165
Tokennice
Token ID44460
Feature activation-1.78e-01

Pos logit contributions
 NW+0.016
ysical+0.016
 Nest+0.015
 Harding+0.015
 nost+0.015
Neg logit contributions
orio-0.034
stanbul-0.031
Italy-0.031
vo-0.030
avier-0.030
Tokenhash
Token ID17831
Feature activation-3.29e-02

Pos logit contributions
orio+0.201
Italy+0.180
stanbul+0.179
vo+0.178
avier+0.177
Neg logit contributions
 NW-0.074
ysical-0.074
 Nest-0.070
 Harding-0.067
 nost-0.066
Token.
Token ID13
Feature activation-6.45e-02

Pos logit contributions
orio+0.028
stanbul+0.024
Italy+0.024
avier+0.023
vo+0.023
Neg logit contributions
 NW-0.024
ysical-0.023
 Nest-0.023
 Harding-0.022
 nost-0.022
Tokencom
Token ID785
Feature activation+5.38e-01

Pos logit contributions
orio+0.060
stanbul+0.052
Italy+0.052
avier+0.051
vo+0.051
Neg logit contributions
 NW-0.040
ysical-0.039
 Nest-0.038
 Harding-0.037
 contended-0.036
Token,
Token ID11
Feature activation-4.69e-01

Pos logit contributions
 NW+0.327
ysical+0.313
 Nest+0.312
 Harding+0.295
 nost+0.293
Neg logit contributions
orio-0.516
Italy-0.449
stanbul-0.446
avier-0.440
vo-0.439
Token but
Token ID475
Feature activation+1.34e-01

Pos logit contributions
orio+0.414
Italy+0.356
stanbul+0.353
vo+0.351
avier+0.349
Neg logit contributions
 NW-0.318
ysical-0.312
 Nest-0.308
 nost-0.295
 Harding-0.295
Token will
Token ID481
Feature activation-2.65e-01

Pos logit contributions
 NW+0.094
ysical+0.092
 Nest+0.092
 nost+0.087
 contended+0.087
Neg logit contributions
orio-0.114
stanbul-0.098
Italy-0.098
vo-0.096
avier-0.096
Token be
Token ID307
Feature activation+3.49e-02

Pos logit contributions
orio+0.252
Italy+0.220
stanbul+0.219
vo+0.216
avier+0.215
Neg logit contributions
 NW-0.162
ysical-0.159
 Nest-0.157
 nost-0.148
 contended-0.146
Token disabled
Token ID10058
Feature activation-4.82e-01

Pos logit contributions
 NW+0.027
ysical+0.026
 Nest+0.026
 contended+0.025
 nost+0.025
Neg logit contributions
orio-0.028
stanbul-0.024
Italy-0.023
avier-0.023
vo-0.023
Token eventually
Token ID4191
Feature activation-1.17e+00

Pos logit contributions
orio+0.436
Italy+0.370
avier+0.369
stanbul+0.368
vo+0.358
Neg logit contributions
 NW-0.317
 Nest-0.305
ysical-0.304
 contended-0.301
 nost-0.296
Token.
Token ID13
Feature activation-2.24e-02

Pos logit contributions
 NW+0.318
ysical+0.314
 Nest+0.310
 Harding+0.299
 nost+0.297
Neg logit contributions
orio-0.367
Italy-0.312
stanbul-0.312
vo-0.308
avier-0.307
Token The
Token ID383
Feature activation-3.08e-01

Pos logit contributions
orio+0.021
Italy+0.018
stanbul+0.018
vo+0.018
avier+0.018
Neg logit contributions
 NW-0.014
ysical-0.014
 Nest-0.014
 Harding-0.013
 nost-0.013
Token two
Token ID734
Feature activation+2.15e-01

Pos logit contributions
orio+0.266
Italy+0.230
stanbul+0.229
vo+0.227
avier+0.225
Neg logit contributions
 NW-0.210
ysical-0.209
 Nest-0.204
 Harding-0.197
 nost-0.195
Token countries
Token ID2678
Feature activation+3.22e-01

Pos logit contributions
 NW+0.155
ysical+0.152
 Nest+0.150
 Harding+0.145
 nost+0.145
Neg logit contributions
orio-0.180
stanbul-0.153
Italy-0.153
vo-0.151
avier-0.150
Token are
Token ID389
Feature activation-3.14e-01

Pos logit contributions
 NW+0.204
ysical+0.201
 Nest+0.197
 contended+0.192
 Harding+0.190
Neg logit contributions
orio-0.294
Italy-0.256
stanbul-0.254
vo-0.251
avier-0.251
Token locked
Token ID8970
Feature activation-1.43e+00

Pos logit contributions
orio+0.282
Italy+0.245
stanbul+0.244
vo+0.243
avier+0.240
Neg logit contributions
 NW-0.203
ysical-0.202
 Nest-0.196
 Harding-0.189
 nost-0.188
Token in
Token ID287
Feature activation-2.77e-01

Pos logit contributions
orio+1.322
Italy+1.158
stanbul+1.150
vo+1.148
avier+1.134
Neg logit contributions
ysical-0.890
 NW-0.887
 Nest-0.857
 Harding-0.830
 contended-0.816
Token an
Token ID281
Feature activation-1.36e-01

Pos logit contributions
orio+0.238
Italy+0.206
stanbul+0.205
vo+0.204
avier+0.202
Neg logit contributions
ysical-0.189
 NW-0.189
 Nest-0.183
 Harding-0.177
 nost-0.175
Token ongoing
Token ID7044
Feature activation-1.11e+00

Pos logit contributions
orio+0.121
Italy+0.105
stanbul+0.105
vo+0.104
avier+0.103
Neg logit contributions
ysical-0.089
 NW-0.089
 Nest-0.086
 Harding-0.083
 nost-0.082
Token bilateral
Token ID24537
Feature activation-8.10e-01

Pos logit contributions
orio+1.018
Italy+0.891
stanbul+0.887
vo+0.885
avier+0.872
Neg logit contributions
ysical-0.689
 NW-0.680
 Nest-0.658
 Harding-0.638
 contended-0.630
Token dispute
Token ID11047
Feature activation-1.31e+00

Pos logit contributions
orio+0.754
Italy+0.662
stanbul+0.659
vo+0.658
avier+0.649
Neg logit contributions
ysical-0.491
 NW-0.486
 Nest-0.469
 Harding-0.455
 contended-0.449
Token
Token ID198
Feature activation+3.49e-02

Pos logit contributions
 NW+0.098
ysical+0.096
 Nest+0.095
 Harding+0.091
 nost+0.089
Neg logit contributions
orio-0.163
Italy-0.143
stanbul-0.142
vo-0.141
avier-0.140
Token
Token ID198
Feature activation+2.03e-02

Pos logit contributions
 NW+0.018
ysical+0.018
 Nest+0.017
 Harding+0.017
 nost+0.016
Neg logit contributions
orio-0.036
stanbul-0.032
Italy-0.032
vo-0.031
avier-0.031
TokenWhat
Token ID2061
Feature activation-2.42e-02

Pos logit contributions
 NW+0.016
ysical+0.016
 Nest+0.015
 Harding+0.015
 nost+0.015
Neg logit contributions
orio-0.016
stanbul-0.013
Italy-0.013
vo-0.013
avier-0.013
Token we
Token ID356
Feature activation-3.67e-01

Pos logit contributions
orio+0.023
Italy+0.020
stanbul+0.020
vo+0.020
avier+0.020
Neg logit contributions
 NW-0.014
ysical-0.014
 Nest-0.014
 Harding-0.013
 nost-0.013
Token can
Token ID460
Feature activation-1.88e-01

Pos logit contributions
orio+0.350
Italy+0.307
stanbul+0.304
vo+0.302
avier+0.302
Neg logit contributions
 NW-0.220
ysical-0.214
 Nest-0.209
 contended-0.202
 Harding-0.201
Token learn
Token ID2193
Feature activation-1.55e+00

Pos logit contributions
orio+0.181
Italy+0.159
stanbul+0.158
vo+0.157
avier+0.157
Neg logit contributions
 NW-0.111
ysical-0.109
 Nest-0.106
 Harding-0.102
 nost-0.102
Token from
Token ID422
Feature activation-2.17e-01

Pos logit contributions
orio+1.443
Italy+1.261
stanbul+1.255
vo+1.248
avier+1.236
Neg logit contributions
 NW-0.943
ysical-0.941
 Nest-0.910
 Harding-0.879
 nost-0.870
Token this
Token ID428
Feature activation-1.58e-01

Pos logit contributions
orio+0.192
Italy+0.166
stanbul+0.166
vo+0.164
avier+0.163
Neg logit contributions
 NW-0.145
ysical-0.143
 Nest-0.140
 Harding-0.135
 nost-0.134
Token is
Token ID318
Feature activation+1.08e-01

Pos logit contributions
orio+0.156
Italy+0.137
stanbul+0.137
vo+0.136
avier+0.135
Neg logit contributions
 NW-0.089
ysical-0.088
 Nest-0.085
 Harding-0.082
 nost-0.081
Token when
Token ID618
Feature activation-4.87e-01

Pos logit contributions
 NW+0.064
ysical+0.063
 Nest+0.061
 Harding+0.059
 nost+0.058
Neg logit contributions
orio-0.104
Italy-0.091
stanbul-0.090
vo-0.090
avier-0.089
Token you
Token ID345
Feature activation+2.97e-01

Pos logit contributions
orio+0.451
Italy+0.394
stanbul+0.393
vo+0.389
avier+0.387
Neg logit contributions
 NW-0.304
ysical-0.301
 Nest-0.293
 Harding-0.281
 nost-0.280
Token-
Token ID12
Feature activation-6.14e-01

Pos logit contributions
 NW+0.330
ysical+0.329
 Nest+0.322
 Harding+0.313
 nost+0.311
Neg logit contributions
orio-0.293
Italy-0.246
stanbul-0.245
vo-0.242
avier-0.239
Token10
Token ID940
Feature activation-3.91e-01

Pos logit contributions
orio+0.414
stanbul+0.345
Italy+0.341
vo+0.335
avier+0.334
Neg logit contributions
 NW-0.533
ysical-0.527
 Nest-0.517
 Harding-0.508
 nost-0.499
Token planetary
Token ID27047
Feature activation+8.86e-01

Pos logit contributions
orio+0.313
Italy+0.267
stanbul+0.265
vo+0.264
avier+0.261
Neg logit contributions
 NW-0.292
ysical-0.291
 Nest-0.283
 Harding-0.275
 nost-0.273
Token system
Token ID1080
Feature activation+3.21e-01

Pos logit contributions
 NW+0.692
ysical+0.689
 Nest+0.673
 Harding+0.651
 nost+0.645
Neg logit contributions
orio-0.681
Italy-0.581
stanbul-0.581
vo-0.567
avier-0.564
Token revis
Token ID22124
Feature activation-7.38e-01

Pos logit contributions
 NW+0.209
ysical+0.207
 Nest+0.203
 Harding+0.196
 contended+0.193
Neg logit contributions
orio-0.288
Italy-0.250
stanbul-0.249
vo-0.247
avier-0.245
Tokenited
Token ID863
Feature activation-1.76e+00

Pos logit contributions
orio+0.698
Italy+0.613
stanbul+0.608
vo+0.608
avier+0.601
Neg logit contributions
 NW-0.443
ysical-0.439
 Nest-0.426
 Harding-0.410
 nost-0.406
Token by
Token ID416
Feature activation-3.00e-02

Pos logit contributions
orio+1.468
Italy+1.263
stanbul+1.259
vo+1.254
avier+1.237
Neg logit contributions
 NW-1.238
ysical-1.237
 Nest-1.199
 Harding-1.166
 nost-1.157
Token HAR
Token ID43638
Feature activation-1.16e+00

Pos logit contributions
orio+0.027
Italy+0.024
stanbul+0.024
vo+0.024
avier+0.023
Neg logit contributions
 NW-0.019
ysical-0.019
 Nest-0.018
 Harding-0.018
 nost-0.018
TokenPS
Token ID3705
Feature activation+9.11e-01

Pos logit contributions
orio+0.825
Italy+0.687
stanbul+0.685
vo+0.677
avier+0.671
Neg logit contributions
 NW-0.965
ysical-0.962
 Nest-0.939
 Harding-0.916
 nost-0.908
Token-
Token ID12
Feature activation-1.46e-01

Pos logit contributions
 NW+0.639
ysical+0.638
 Nest+0.619
 Harding+0.600
 nost+0.593
Neg logit contributions
orio-0.769
Italy-0.663
stanbul-0.661
vo-0.653
avier-0.648
TokenN
Token ID45
Feature activation+1.09e+00

Pos logit contributions
orio+0.112
Italy+0.095
stanbul+0.094
vo+0.094
avier+0.093
Neg logit contributions
 NW-0.113
ysical-0.112
 Nest-0.110
 Harding-0.106
 nost-0.106
Token string
Token ID4731
Feature activation-3.69e-02

Pos logit contributions
orio+0.289
Italy+0.250
stanbul+0.248
vo+0.246
avier+0.244
Neg logit contributions
 NW-0.235
ysical-0.233
 Nest-0.228
 Harding-0.220
 nost-0.219
Token and
Token ID290
Feature activation-3.61e-01

Pos logit contributions
orio+0.033
Italy+0.029
stanbul+0.029
vo+0.028
avier+0.028
Neg logit contributions
 NW-0.024
ysical-0.024
 Nest-0.024
 Harding-0.023
 nost-0.023
Token go
Token ID467
Feature activation-1.05e+00

Pos logit contributions
orio+0.328
Italy+0.284
stanbul+0.283
vo+0.280
avier+0.278
Neg logit contributions
 NW-0.234
ysical-0.230
 Nest-0.225
 Harding-0.217
 nost-0.217
Token around
Token ID1088
Feature activation-1.32e+00

Pos logit contributions
orio+0.934
Italy+0.810
stanbul+0.806
vo+0.799
avier+0.793
Neg logit contributions
 NW-0.690
ysical-0.687
 Nest-0.667
 Harding-0.644
 nost-0.640
Token and
Token ID290
Feature activation-2.23e-01

Pos logit contributions
orio+1.148
Italy+0.993
stanbul+0.988
vo+0.983
avier+0.972
Neg logit contributions
ysical-0.889
 NW-0.888
 Nest-0.859
 Harding-0.833
 contended-0.824
Token around
Token ID1088
Feature activation-1.57e+00

Pos logit contributions
orio+0.197
Italy+0.170
stanbul+0.169
vo+0.168
avier+0.166
Neg logit contributions
 NW-0.149
ysical-0.147
 Nest-0.144
 Harding-0.139
 nost-0.139
Token the
Token ID262
Feature activation-4.21e-01

Pos logit contributions
orio+1.364
Italy+1.181
stanbul+1.175
vo+1.169
avier+1.157
Neg logit contributions
ysical-1.056
 NW-1.055
 Nest-1.021
 Harding-0.990
 contended-0.978
Token edge
Token ID5743
Feature activation-3.64e-01

Pos logit contributions
orio+0.361
Italy+0.312
stanbul+0.310
vo+0.308
avier+0.305
Neg logit contributions
 NW-0.289
ysical-0.288
 Nest-0.280
 Harding-0.271
 nost-0.269
Token.
Token ID13
Feature activation-4.77e-02

Pos logit contributions
orio+0.346
Italy+0.303
stanbul+0.301
vo+0.299
avier+0.297
Neg logit contributions
 NW-0.218
ysical-0.217
 Nest-0.210
 Harding-0.202
 nost-0.200
Token This
Token ID770
Feature activation+2.47e-01

Pos logit contributions
orio+0.046
Italy+0.041
stanbul+0.040
vo+0.040
avier+0.040
Neg logit contributions
 NW-0.028
ysical-0.027
 Nest-0.027
 Harding-0.026
 nost-0.025
Token is
Token ID318
Feature activation-1.23e-01

Pos logit contributions
 NW+0.153
ysical+0.151
 Nest+0.147
 Harding+0.142
 nost+0.141
Neg logit contributions
orio-0.230
Italy-0.201
stanbul-0.200
vo-0.199
avier-0.197
Token is
Token ID318
Feature activation-3.67e-02

Pos logit contributions
orio+0.799
Italy+0.702
stanbul+0.699
vo+0.696
avier+0.688
Neg logit contributions
ysical-0.482
 NW-0.482
 Nest-0.463
 Harding-0.448
 nost-0.442
Token hell
Token ID5968
Feature activation+9.18e-02

Pos logit contributions
orio+0.033
Italy+0.029
stanbul+0.029
vo+0.029
avier+0.029
Neg logit contributions
 NW-0.023
ysical-0.023
 Nest-0.022
 Harding-0.022
 nost-0.021
Token,"
Token ID553
Feature activation-1.20e-01

Pos logit contributions
 NW+0.062
ysical+0.061
 Nest+0.060
 Harding+0.058
 nost+0.057
Neg logit contributions
orio-0.080
Italy-0.070
stanbul-0.069
vo-0.068
avier-0.068
Token William
Token ID3977
Feature activation-2.29e-01

Pos logit contributions
orio+0.117
Italy+0.103
stanbul+0.102
vo+0.102
avier+0.101
Neg logit contributions
ysical-0.069
 NW-0.069
 Nest-0.066
 Harding-0.064
 nost-0.063
Token Tec
Token ID48257
Feature activation+1.99e+00

Pos logit contributions
orio+0.220
Italy+0.192
stanbul+0.191
vo+0.191
avier+0.189
Neg logit contributions
ysical-0.134
 NW-0.132
 Nest-0.127
 nost-0.122
 Harding-0.121
Tokenum
Token ID388
Feature activation-1.57e+00

Pos logit contributions
 NW+1.584
ysical+1.561
 Nest+1.520
 Harding+1.498
 nost+1.477
Neg logit contributions
orio-1.499
stanbul-1.304
Italy-1.293
vo-1.235
avier-1.227
Tokense
Token ID325
Feature activation+1.99e-01

Pos logit contributions
orio+0.964
vo+0.786
Italy+0.772
stanbul+0.765
avier+0.751
Neg logit contributions
ysical-1.461
 NW-1.451
 Nest-1.419
 Harding-1.392
 contended-1.378
Tokenh
Token ID71
Feature activation+7.22e-01

Pos logit contributions
ysical+0.138
 NW+0.137
 Nest+0.133
 nost+0.129
 Harding+0.129
Neg logit contributions
orio-0.169
vo-0.146
Italy-0.145
stanbul-0.145
avier-0.143
Token Sherman
Token ID23198
Feature activation-4.67e-01

Pos logit contributions
 NW+0.317
ysical+0.316
 Nest+0.301
 Harding+0.285
 nost+0.283
Neg logit contributions
orio-0.799
Italy-0.713
stanbul-0.709
vo-0.708
avier-0.702
Token once
Token ID1752
Feature activation-6.57e-01

Pos logit contributions
orio+0.462
Italy+0.406
stanbul+0.405
vo+0.403
avier+0.399
Neg logit contributions
 NW-0.260
ysical-0.260
 Nest-0.250
 Harding-0.240
 nost-0.238
Token said
Token ID531
Feature activation+4.87e-01

Pos logit contributions
orio+0.715
Italy+0.637
stanbul+0.634
vo+0.633
avier+0.628
Neg logit contributions
ysical-0.299
 NW-0.298
 Nest-0.285
 Harding-0.271
 nost-0.266