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

    Neuronpedia

    INDEX
    Explanations

    comparative statistics and numerical comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    undy
    -0.16
    zos
    -0.16
    ijo
    -0.15
    anner
    -0.15
    cil
    -0.14
     Formatter
    -0.14
    uyen
    -0.14
    rais
    -0.14
    *)_
    -0.14
    oppel
    -0.13
    POSITIVE LOGITS
    ätz
    0.18
    awah
    0.15
    LOB
    0.15
    rido
    0.15
    orz
    0.14
     Tep
    0.14
    oire
    0.14
     ved
    0.14
     Atlas
    0.13
    etine
    0.13
    Act Density 0.070%

    No Known Activations