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

    Neuronpedia

    INDEX
    Explanations

    geographical locations, specifically related to universities

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    anwhile
    -0.87
    pless
    -0.74
     respectively
    -0.73
     Sora
    -0.68
    ãĥĸ
    -0.65
    abilities
    -0.65
    byss
    -0.64
    usercontent
    -0.64
    bernatorial
    -0.64
    lust
    -0.60
    POSITIVE LOGITS
    ħĭ
    0.71
     IPM
    0.69
    conservancy
    0.68
    wagen
    0.68
    ocene
    0.67
    Redd
    0.63
    escape
    0.62
    ?).
    0.62
    uchin
    0.60
    AMY
    0.60
    Act Density 0.000%

    No Known Activations