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

    Neuronpedia

    INDEX
    Explanations

    verb-noun pairs that could describe physical activities or interactions

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     FG
    -0.82
     Cay
    -0.75
     Quarterly
    -0.72
     Associates
    -0.70
     unfocusedRange
    -0.68
    HQ
    -0.66
     Ib
    -0.66
     Gaming
    -0.64
     Chim
    -0.64
     Extensions
    -0.64
    POSITIVE LOGITS
    vered
    0.86
    ously
    0.85
    itude
    0.82
    ities
    0.81
    itud
    0.80
    ancial
    0.79
    emonic
    0.77
    ebted
    0.77
    rous
    0.77
    arted
    0.75
    Act Density 11.399%

    No Known Activations