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

    Neuronpedia

    INDEX
    Explanations

    references to specific studies or citations

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     BnF
    -0.51
    ereich
    -0.41
    marche
    -0.39
    郎
    -0.38
    áp
    -0.38
     poj
    -0.38
     sel
    -0.37
    rews
    -0.37
    שי
    -0.36
     sec
    -0.36
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.86
     дописавши
    0.80
    ++]=
    0.80
    ArrowToggle
    0.79
     مشين
    0.77
     itſelf
    0.77
     ویکی‌پدیای
    0.72
    ValueStyle
    0.71
     mourut
    0.70
    Pratique
    0.69
    Act Density 0.065%

    No Known Activations