INDEX
Explanations
words related to current events or present situations
references to the present time
New Auto-Interp
Negative Logits
similarity
-0.60
Mata
-0.58
similarities
-0.56
Ammunition
-0.55
ortment
-0.52
Trouble
-0.52
pointers
-0.52
ZIP
-0.52
Tenth
-0.51
bounty
-0.51
POSITIVE LOGITS
adays
1.57
here
1.36
abouts
1.04
heres
1.02
defunct
0.87
tics
0.84
terday
0.83
heric
0.80
orthy
0.79
lins
0.72
Activations Density 0.085%