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

    Neuronpedia

    INDEX
    Explanations

    references to the subject "he" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     autorytatywna
    -1.05
    tvguidetime
    -0.98
    Autoritní
    -0.91
    المناصب
    -0.87
    GEBURTSDATUM
    -0.86
     Signalez
    -0.84
    QMetaType
    -0.84
     disambiguazione
    -0.82
    adaptiveStyles
    -0.82
    >
    -0.74
    POSITIVE LOGITS
     He
    0.99
    He
    0.97
    It
    0.72
     She
    0.67
    She
    0.62
     It
    0.61
     They
    0.60
    ोंने
    0.60
     Puis
    0.59
    The
    0.59
    Act Density 0.145%

    No Known Activations