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

    Neuronpedia

    INDEX
    Explanations

    references to hands or hand-related actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Poem
    -0.77
    -------
    -0.75
     obé
    -0.75
    Poems
    -0.75
     poems
    -0.75
    ized
    -0.75
    siębior
    -0.74
     Poems
    -0.74
    $_['
    -0.73
    redients
    -0.72
    POSITIVE LOGITS
     Hands
    1.97
     hands
    1.94
    HAND
    1.91
    Hand
    1.91
     hand
    1.90
     Hand
    1.90
     HAND
    1.89
    Hands
    1.83
    hand
    1.82
     HANDS
    1.67
    Act Density 0.056%

    No Known Activations