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

    Neuronpedia

    INDEX
    Explanations

    adjectives related to quantity or intensity

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ufact
    -0.71
    ESCO
    -0.70
    heid
    -0.69
    gary
    -0.63
    orthy
    -0.61
    ental
    -0.61
    agate
    -0.60
     Telecommunications
    -0.60
    sburgh
    -0.59
    perature
    -0.59
    POSITIVE LOGITS
     of
    0.97
     nicer
    0.76
    ãĤ§
    0.70
    bos
    0.68
     smarter
    0.67
     different
    0.67
     worse
    0.67
     OF
    0.66
     Of
    0.65
     more
    0.65
    Act Density 0.058%

    No Known Activations