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

    Neuronpedia

    INDEX
    Explanations

    examples illustrating key concepts or principles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _iff
    -0.16
    rieve
    -0.14
    istrovstvÃŃ
    -0.13
    ãģ¯ãģļ
    -0.13
    erialize
    -0.13
    riminator
    -0.12
    Crud
    -0.12
    ạch
    -0.12
    heim
    -0.12
    isser
    -0.12
    POSITIVE LOGITS
     example
    0.86
     examples
    0.82
    example
    0.68
    ä¾ĭ
    0.67
     Examples
    0.66
    examples
    0.66
     Example
    0.65
     exemple
    0.63
     exemp
    0.62
     EXAMPLE
    0.60
    Act Density 0.608%

    No Known Activations