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

    Neuronpedia

    INDEX
    Explanations

    references to specific individuals and their influence or contributions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nal
    -0.15
    ERGY
    -0.15
    esModule
    -0.15
    chl
    -0.15
     Intr
    -0.14
    ittest
    -0.14
     Janet
    -0.13
    airo
    -0.13
     pair
    -0.13
     heck
    -0.13
    POSITIVE LOGITS
    edException
    0.16
     NI
    0.16
    ancer
    0.15
    \API
    0.14
    anzi
    0.14
    adam
    0.14
    _scaling
    0.14
    shiv
    0.14
    åѤ
    0.14
    -wrap
    0.14
    Act Density 0.004%

    No Known Activations