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

    Neuronpedia

    INDEX
    Explanations

    references to mock objects in testing code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aida
    -0.16
    bish
    -0.15
    lox
    -0.15
    utin
    -0.15
    onth
    -0.14
    oser
    -0.14
    ypy
    -0.14
     zim
    -0.14
    acet
    -0.14
    uing
    -0.14
    POSITIVE LOGITS
    elerik
    0.15
    yt
    0.14
     ucwords
    0.14
     Reef
    0.14
    203
    0.14
    ाब
    0.14
    ody
    0.14
    apture
    0.14
     Marshall
    0.14
     italic
    0.14
    Act Density 0.142%

    No Known Activations