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

    Neuronpedia

    INDEX
    Explanations

    horizontal lines or dashes in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    locker
    -0.17
    lement
    -0.15
    egl
    -0.15
    unic
    -0.15
    asn
    -0.14
    ÙĬÙĩ
    -0.14
    -même
    -0.14
    nad
    -0.14
    AEA
    -0.14
     رÙĪستا
    -0.13
    POSITIVE LOGITS
    adera
    0.14
    ponce
    0.14
    sdk
    0.14
     Hob
    0.14
    QR
    0.13
    âĩ
    0.13
    _executor
    0.13
    noch
    0.13
    IZER
    0.13
    oenix
    0.13
    Act Density 0.018%

    No Known Activations