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

    Neuronpedia

    INDEX
    Explanations

    phrases and words related to metaphors or stylized descriptions

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of text structure or format, specifically regarding 'aphorisms' or 'aphoristic' expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    PUT
    -0.75
    nings
    -0.75
    gewater
    -0.68
    swick
    -0.67
    berman
    -0.66
    fit
    -0.65
    ously
    -0.64
    ced
    -0.63
     Wend
    -0.62
    pend
    -0.62
    POSITIVE LOGITS
    orically
    1.20
    ysics
    1.09
    ysical
    1.06
    orical
    1.05
    obia
    1.00
    obic
    0.94
    oric
    0.88
    ract
    0.84
    ilic
    0.83
    oreAnd
    0.82
    Act Density 0.061%

    No Known Activations