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

    Neuronpedia

    INDEX
    Explanations

    words related to physical or metaphorical shrinking

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    POL
    -0.77
    PLIC
    -0.61
    Ale
    -0.59
     QC
    -0.58
    ":[{"
    -0.58
    rera
    -0.58
     HI
    -0.58
     Drama
    -0.57
    spot
    -0.56
     Viol
    -0.56
    POSITIVE LOGITS
    ular
    0.90
    eness
    0.86
     violet
    0.86
    downs
    0.85
    lasses
    0.85
    umber
    0.84
    owship
    0.83
    shr
    0.82
    aciously
    0.81
     budgets
    0.79
    Act Density 0.052%

    No Known Activations