INDEX
Explanations
words related to "attention" or "attaining."
mentions of acts of attribution or association
New Auto-Interp
Negative Logits
ython
-0.88
opoly
-0.82
ophobia
-0.74
Brook
-0.72
Pirates
-0.70
crop
-0.69
hole
-0.68
Cros
-0.68
ocide
-0.66
Dairy
-0.64
POSITIVE LOGITS
att
3.87
Att
1.49
Att
1.39
ATT
1.34
att
1.33
asc
1.25
attest
1.24
ATT
1.20
attr
1.14
srfN
1.12
Activations Density 0.013%