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

    Neuronpedia

    INDEX
    Explanations

    references to hands and hand-made objects or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     McClure
    -0.88
    redients
    -0.85
    Poem
    -0.85
     odkazy
    -0.84
    ized
    -0.83
    EDEFAULT
    -0.81
    -------
    -0.81
     poems
    -0.80
     bazaar
    -0.77
    etcode
    -0.76
    POSITIVE LOGITS
     Hands
    1.67
    HAND
    1.59
     hands
    1.58
     HAND
    1.57
    Hand
    1.55
     Hand
    1.55
    Hands
    1.51
     hand
    1.48
    hand
    1.46
     HANDS
    1.35
    Act Density 0.059%

    No Known Activations