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

    Neuronpedia

    INDEX
    Explanations

    numbers and abbreviations ending with 'amp'

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    SHIP
    -0.97
    bis
    -0.89
    BLIC
    -0.86
    ALLY
    -0.79
    ryu
    -0.75
    DOM
    -0.74
    fram
    -0.73
    OH
    -0.73
     sv
    -0.72
    âĸ¬âĸ¬
    -0.72
    POSITIVE LOGITS
    hetamine
    1.06
    shire
    1.03
    stead
    0.97
    acus
    0.95
    owered
    0.94
    aic
    0.94
    ierre
    0.94
    odcast
    0.93
    agne
    0.92
    reys
    0.90
    Act Density 0.894%

    No Known Activations