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

    Neuronpedia

    INDEX
    Explanations

    names, likely Swiss names like "Franz Meindl", related to discussions or statements

    oai_token-act-pair · gpt-3.5-turbo

    the word "ind"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     deaf
    -0.70
    itton
    -0.70
    senal
    -0.69
    prus
    -0.67
     tremend
    -0.67
    ngth
    -0.66
     depreciation
    -0.65
     compr
    -0.62
    xit
    -0.62
     FIRE
    -0.60
    POSITIVE LOGITS
    irect
    1.20
    ebted
    1.16
    icative
    1.14
    icator
    1.09
    erella
    1.09
    ications
    1.04
    ividually
    1.03
    sight
    1.03
    icators
    1.01
    icates
    0.99
    Act Density 0.014%

    No Known Activations