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

    Neuronpedia

    INDEX
    Explanations

    references to data structure attributes and their related fields in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iegel
    -0.14
    ULO
    -0.14
    ÑĢаг
    -0.14
    Jak
    -0.14
    imately
    -0.13
    ctal
    -0.13
    ORIZ
    -0.13
    igure
    -0.13
    encil
    -0.13
    uly
    -0.13
    POSITIVE LOGITS
    092
    0.14
     bò
    0.14
    weit
    0.13
    ucus
    0.13
    frey
    0.13
    acement
    0.13
    icked
    0.13
    _targets
    0.12
     Stark
    0.12
    omes
    0.12
    Act Density 0.380%

    No Known Activations