INDEX
Explanations
references to college basketball teams and their performances
New Auto-Interp
Negative Logits
mlin
-0.16
trys
-0.15
elter
-0.14
thr
-0.14
Tie
-0.14
ئ
-0.14
Lose
-0.14
createForm
-0.14
EATURE
-0.13
ÙħÙħ
-0.13
POSITIVE LOGITS
claimed
0.26
claiming
0.24
claim
0.24
Claim
0.23
Claim
0.23
exact
0.22
CLAIM
0.21
claimed
0.21
av
0.20
capture
0.20
Activations Density 0.078%