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

    Neuronpedia

    INDEX
    Explanations

    references to technical specifications or settings in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nÄħ
    -0.17
    er
    -0.15
    wise
    -0.15
    569
    -0.15
    /to
    -0.15
    ular
    -0.14
    iness
    -0.14
    ines
    -0.14
    ance
    -0.14
    ода
    -0.14
    POSITIVE LOGITS
    -uppercase
    0.15
    bz
    0.14
    olib
    0.14
    á»ĵng
    0.14
    ábado
    0.14
    emale
    0.13
    svc
    0.13
     há»ĵng
    0.13
     Lever
    0.13
    nesota
    0.13
    Act Density 0.025%

    No Known Activations