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

    Neuronpedia

    INDEX
    Explanations

    words related to frequency or ratio

    oai_token-act-pair · gpt-3.5-turbo

    the repetition of the word "every."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    phabet
    -0.76
    olas
    -0.72
    zai
    -0.71
     Metatron
    -0.68
    dict
    -0.67
     Osw
    -0.65
     Viz
    -0.63
    hess
    -0.63
    rawdownloadcloneembedreportprint
    -0.59
    ND
    -0.58
    POSITIVE LOGITS
    THING
    1.45
     conceivable
    1.08
    where
    1.00
     imaginable
    0.97
    single
    0.95
    things
    0.95
     single
    0.90
    WHERE
    0.87
    body
    0.82
    day
    0.77
    Act Density 0.042%

    No Known Activations