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

    Neuronpedia

    INDEX
    Explanations

    references to people and pronouns in a conversational context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Allí
    -0.48
    ारे
    -0.46
     tasse
    -0.45
     globos
    -0.45
     habet
    -0.44
     provinciale
    -0.44
    '
    -0.44
    äsident
    -0.43
     Squal
    -0.43
     conceit
    -0.42
    POSITIVE LOGITS
     Signalez
    0.92
     ProtoMessage
    0.82
    transQ
    0.79
     autorytatywna
    0.72
     indisponible
    0.70
    apimachinery
    0.70
    Vidite
    0.70
    IContainer
    0.67
    Архівовано
    0.67
     hObject
    0.66
    Act Density 0.322%

    No Known Activations