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

    Neuronpedia

    INDEX
    Explanations

    instances where hands are being mentioned

    oai_token-act-pair · gpt-3.5-turbo

    references to hands and their actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    undown
    -0.89
    Wars
    -0.78
    Trend
    -0.76
    mingham
    -0.76
    izophren
    -0.73
     RAND
    -0.71
    ãĥ´
    -0.69
    burgh
    -0.69
    COMPLE
    -0.67
     Atmosp
    -0.66
    POSITIVE LOGITS
    bag
    0.99
    maid
    0.82
    ker
    0.79
     catcher
    0.77
    tips
    0.77
     clen
    0.76
    rail
    0.75
     clasp
    0.75
     restrained
    0.74
     clutching
    0.74
    Act Density 0.031%

    No Known Activations