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

    Neuronpedia

    INDEX
    Explanations

    elements related to health and safety warnings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     يتيمه
    -0.92
    Datuak
    -0.91
    참고
    -0.89
    Hozzáférés
    -0.85
     LoggerFactory
    -0.79
    rungsseite
    -0.77
     estekak
    -0.75
    Спољашње
    -0.74
    redited
    -0.72
    AddTagHelper
    -0.69
    POSITIVE LOGITS
    …
    0.56
    ...
    0.48
    Take
    0.48
    take
    0.46
    2
    0.46
    m
    0.46
     …
    0.46
    1
    0.45
     takes
    0.45
    takes
    0.44
    Act Density 0.115%

    No Known Activations