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

    Neuronpedia

    INDEX
    Explanations

    references to evidence and examples used in arguments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ayout
    -0.16
    ston
    -0.15
    iek
    -0.15
    ãĥŃãĥ³
    -0.15
    211
    -0.14
    LIKELY
    -0.14
    Æ°á»Ľc
    -0.14
    uzzi
    -0.14
    æĹ
    -0.14
    oyer
    -0.14
    POSITIVE LOGITS
     example
    0.37
     examples
    0.31
     Example
    0.30
     Examples
    0.30
    example
    0.30
     ejemplo
    0.30
     exemp
    0.28
    Example
    0.27
     exemplo
    0.27
    (example
    0.26
    Act Density 0.243%

    No Known Activations