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

    Neuronpedia

    INDEX
    Explanations

    references to complaints or reports about misconduct or inappropriate behavior

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     preprint
    -0.55
    TRIES
    -0.52
    rostis
    -0.51
    ąt
    -0.50
    acce
    -0.50
     Martyr
    -0.49
    enné
    -0.49
     epistle
    -0.49
     Entrance
    -0.49
     Vessels
    -0.49
    POSITIVE LOGITS
     autorytatywna
    0.67
     فريبيس
    0.63
     ویکی‌پدی
    0.63
    Demografie
    0.62
    Lähteet
    0.61
    Населення
    0.59
    MessageTagHelper
    0.59
     segnal
    0.58
    Aiheesta
    0.58
    Enllaces
    0.57
    Act Density 0.062%

    No Known Activations