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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and notations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anger
    -0.16
    urat
    -0.15
    .Library
    -0.15
    asco
    -0.14
    id
    -0.14
    lein
    -0.14
    ascar
    -0.14
    zew
    -0.14
    uren
    -0.13
    again
    -0.13
    POSITIVE LOGITS
     Berk
    0.14
    KeyType
    0.14
    康
    0.14
     ÙħاÛĮÙĦ
    0.14
    äh
    0.14
     ì§Ģë°©
    0.14
    iele
    0.13
    phy
    0.13
    vy
    0.13
    audi
    0.13
    Act Density 0.085%

    No Known Activations