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

    Neuronpedia

    INDEX
    Explanations

    the word "man" in various languages and contexts

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "man."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    avorite
    -0.67
    PsyNetMessage
    -0.67
    anked
    -0.66
    urus
    -0.65
    ancies
    -0.65
    ÃįÃį
    -0.63
    ĸļ
    -0.63
    ierrez
    -0.62
    efficients
    -0.62
    uesday
    -0.62
    POSITIVE LOGITS
    ifest
    1.37
    ufact
    1.13
    ning
    1.11
    iac
    1.09
    iasis
    1.05
    uscript
    1.05
    ned
    1.01
    hood
    1.00
    士
    0.99
    hattan
    0.95
    Act Density 0.053%

    No Known Activations