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

    Neuronpedia

    INDEX
    Explanations

    details related to income, fiscal policies, financial thresholds, and economic indicators

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    pload
    -0.80
    Tes
    -0.63
     enthusi
    -0.62
     myster
    -0.62
     ACTIONS
    -0.59
    ãĤ»
    -0.58
    THING
    -0.56
     Mex
    -0.56
    ãĤ±
    -0.55
    Tumblr
    -0.53
    POSITIVE LOGITS
     (>
    0.95
     (<
    0.94
     or
    0.82
     (~
    0.77
     ($
    0.73
     whatsoever
    0.73
     qualify
    0.72
     backgrounds
    0.71
     such
    0.68
    hips
    0.68
    Act Density 0.382%

    No Known Activations