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

    Neuronpedia

    INDEX
    Explanations

    terms related to architecture and architectural styles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    PEC
    -0.15
     __("
    -0.15
    532
    -0.14
    ection
    -0.14
    ici
    -0.14
    ysz
    -0.14
    IRROR
    -0.14
    ç¯ĩ
    -0.13
    jsc
    -0.13
    ucher
    -0.13
    POSITIVE LOGITS
    affer
    0.16
    ç´
    0.15
    βο
    0.15
    inp
    0.15
    Ïģά
    0.15
    inne
    0.14
    illes
    0.14
    onaut
    0.14
     Obr
    0.14
    nave
    0.14
    Act Density 0.014%

    No Known Activations