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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating years of experience in professional roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /english
    -0.15
    redo
    -0.14
    sez
    -0.14
    оби
    -0.14
    سÙĬÙĨ
    -0.14
    agra
    -0.13
    lä
    -0.13
     bre
    -0.13
    /Home
    -0.12
    spr
    -0.12
    POSITIVE LOGITS
    ilos
    0.16
    ENA
    0.14
    .Editor
    0.14
    .gravity
    0.14
    retty
    0.14
    shan
    0.14
    edla
    0.14
    ding
    0.13
    ACES
    0.13
     بشر
    0.13
    Act Density 0.037%

    No Known Activations