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

    Neuronpedia

    INDEX
    Explanations

    technical terms and function names related to programming and software configurations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    theless
    -0.18
    VILLE
    -0.17
    iras
    -0.16
    anus
    -0.16
    rtle
    -0.15
    WARDED
    -0.15
    gamber
    -0.15
    locs
    -0.14
    HING
    -0.14
    innen
    -0.14
    POSITIVE LOGITS
    ention
    0.20
    istance
    0.20
    uation
    0.18
    ениÑı
    0.17
    ifications
    0.17
    iment
    0.17
    象
    0.17
    putation
    0.16
    ivation
    0.16
    ection
    0.16
    Act Density 0.116%

    No Known Activations