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

    Neuronpedia

    INDEX
    Explanations

    references to fairy tales and related terms

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    essee
    -0.82
    arians
    -0.76
    eller
    -0.76
    ger
    -0.75
    ļéĨĴ
    -0.74
    ory
    -0.74
    ers
    -0.73
    er
    -0.72
    æĸ¹
    -0.72
    aeda
    -0.69
    POSITIVE LOGITS
    tale
    0.85
    astical
    0.84
    astically
    0.75
    BALL
    0.74
    DIV
    0.72
    ignt
    0.71
     Tail
    0.67
    afort
    0.67
    HEAD
    0.67
    grass
    0.67
    Act Density 0.153%

    No Known Activations