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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating purpose or justification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    quila
    -0.16
    afka
    -0.15
    podob
    -0.15
    jah
    -0.15
    kal
    -0.14
    LÄ°
    -0.14
    ÅĻev
    -0.14
    ãĥ³ãĥIJãĥ¼
    -0.14
     hết
    -0.14
    iale
    -0.14
    POSITIVE LOGITS
    eldo
    0.15
     trừ
    0.14
     cap
    0.14
     Pavilion
    0.13
    umed
    0.13
     Carpenter
    0.13
    ined
    0.13
    ocommerce
    0.13
    arov
    0.13
    hood
    0.13
    Act Density 0.153%

    No Known Activations