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

    Neuronpedia

    INDEX
    Explanations

    references to hands and physical positions or gestures

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to control and positioning of hands

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gradation
    -0.88
    ablishment
    -0.72
    reditary
    -0.71
    venants
    -0.68
    issions
    -0.66
    abwe
    -0.66
    iage
    -0.65
    uilt
    -0.65
    >]
    -0.65
    anguage
    -0.65
    POSITIVE LOGITS
     shoulders
    0.88
     shoulder
    0.83
     necks
    0.82
    stretched
    0.73
     hers
    0.71
     palms
    0.69
     toes
    0.68
     elbows
    0.68
     fists
    0.67
     cheek
    0.66
    Act Density 0.211%

    No Known Activations