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

    Neuronpedia

    INDEX
    Explanations

    references to standards and regulations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .infinity
    -0.17
    uben
    -0.17
    chner
    -0.15
    ordan
    -0.15
    ocular
    -0.15
    eyh
    -0.15
    pee
    -0.15
    dar
    -0.15
    age
    -0.15
    à¤łà¤¨
    -0.15
    POSITIVE LOGITS
    ised
    0.28
    -issue
    0.25
    -setting
    0.21
    ize
    0.20
    izes
    0.20
    ization
    0.19
     deviation
    0.18
    ized
    0.18
    .Std
    0.18
    izing
    0.18
    Act Density 0.026%

    No Known Activations