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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating emphasis or importance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    han
    -0.14
    ston
    -0.14
    ели
    -0.13
    FFE
    -0.13
    sp
    -0.13
    arte
    -0.13
    ukan
    -0.13
    apos
    -0.13
    CEEDED
    -0.12
    žel
    -0.12
    POSITIVE LOGITS
    ,
    0.15
    ìĿ´íĦ°
    0.14
    ,↵↵
    0.14
    .ga
    0.14
    ãĥ¼ãĥĹ
    0.13
    Ậ
    0.13
    -NLS
    0.13
    дап
    0.13
    .bunifuFlatButton
    0.13
    ï¸ı
    0.13
    Act Density 0.323%

    No Known Activations