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

    Neuronpedia

    INDEX
    Explanations

    locations or specific places

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    =]
    -1.18
     Bulg
    -1.02
    enegger
    -0.97
     mascul
    -0.95
    esa
    -0.91
    bol
    -0.90
    hler
    -0.88
    %"
    -0.84
    maker
    -0.82
     Goldberg
    -0.80
    POSITIVE LOGITS
    ordinate
    1.33
    animate
    1.19
    umbn
    1.16
    offensive
    0.97
    æĹ
    0.95
    tical
    0.91
    apt
    0.90
    patient
    0.89
    igious
    0.89
    estern
    0.86
    Act Density 0.659%

    No Known Activations