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

    Neuronpedia

    INDEX
    Explanations

    references to examples and hypothetical scenarios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Bernstein
    -0.16
     Vers
    -0.15
    æĮĩ
    -0.14
    ausal
    -0.14
     sund
    -0.14
     Cruise
    -0.14
     Bern
    -0.14
    OTS
    -0.14
     supply
    -0.14
    aux
    -0.13
    POSITIVE LOGITS
     example
    0.18
    ä¾ĭ
    0.18
    -example
    0.17
    Example
    0.16
    example
    0.16
     exemplo
    0.16
     Example
    0.15
    (example
    0.15
     ejemplo
    0.15
    /example
    0.15
    Act Density 0.096%

    No Known Activations