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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating official actions or orders

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Rough
    -0.17
    éģ
    -0.14
    rough
    -0.14
    istan
    -0.14
    hill
    -0.14
    legg
    -0.13
    ederation
    -0.13
    mts
    -0.13
    legates
    -0.13
    agy
    -0.13
    POSITIVE LOGITS
    SSIP
    0.14
    lej
    0.14
     Sakura
    0.14
    idor
    0.14
     breakthrough
    0.14
    anean
    0.13
    ongyang
    0.13
    ÙĬت
    0.13
    ån
    0.13
    ider
    0.13
    Act Density 0.111%

    No Known Activations