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

    Neuronpedia

    INDEX
    Explanations

    references to individuals and their achievements or roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     فريبيس
    -0.60
    ValueStyle
    -0.54
    :✨
    -0.50
    ✨:
    -0.50
    aap
    -0.49
    Kariera
    -0.49
    Hauptartikel
    -0.48
    theless
    -0.46
    ifndef
    -0.45
     iVar
    -0.45
    POSITIVE LOGITS
     whose
    0.62
    whose
    0.61
     whofe
    0.54
     cuyo
    0.50
     whoſe
    0.50
     cuja
    0.48
     cujo
    0.47
    Whose
    0.45
     cuya
    0.45
     cuyos
    0.43
    Act Density 0.348%

    No Known Activations