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

    Neuronpedia

    INDEX
    Explanations

    references to dates and placeholders in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ToObject
    -0.17
    tea
    -0.16
    ptest
    -0.16
    osti
    -0.16
    째
    -0.15
    AMENT
    -0.15
    cly
    -0.14
    heading
    -0.14
    osta
    -0.14
    orp
    -0.14
    POSITIVE LOGITS
    Ùİس
    0.17
    REFERRED
    0.16
    zan
    0.16
    otton
    0.15
    /../
    0.15
    _ENC
    0.14
    aes
    0.14
    ä»»
    0.14
     Mona
    0.14
    pth
    0.14
    Act Density 0.012%

    No Known Activations