Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    the
    0.80
    thew
    0.68
    К
    0.68
    Outdoor
    0.63
    šč
    0.62
     your
    0.61
    outdoor
    0.61
    Firstly
    0.59
    ̣c
    0.59
    ﻭ
    0.59
    POSITIVE LOGITS
     philanthrop
    0.65
     причем
    0.64
     CQG
    0.64
     crews
    0.63
     Boise
    0.61
     Deputies
    0.61
     newsletters
    0.61
     disgu
    0.60
     inclui
    0.60
     snar
    0.59
    Act Density 2.055%

    No Known Activations