INDEX
Explanations
mentions of the name "Rob" followed by a person's last or full name
mentions of the name "Rob."
New Auto-Interp
Negative Logits
WAYS
-0.99
SEE
-0.75
Corpus
-0.73
ãĥ¼ãĥĨãĤ£
-0.71
CVE
-0.69
Reloaded
-0.68
halls
-0.67
ç¥ŀ
-0.67
ëĭ
-0.66
uated
-0.66
POSITIVE LOGITS
bie
1.13
bery
1.09
bing
1.04
shaw
1.04
bers
0.99
roach
0.99
otics
0.98
ooth
0.97
otic
0.96
ber
0.91
Activations Density 0.009%