INDEX
Explanations
phrases related to breaks or time off in a sporting context
New Auto-Interp
Negative Logits
Craig
-0.17
essler
-0.15
okies
-0.14
Craig
-0.14
etten
-0.14
ettes
-0.14
Jong
-0.13
нки
-0.13
uite
-0.13
FAIL
-0.13
POSITIVE LOGITS
زر
0.16
illery
0.15
nst
0.15
'gc
0.15
rett
0.14
Robbins
0.14
astery
0.14
tn
0.14
etty
0.14
athing
0.14
Activations Density 0.048%