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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the action of setting something up

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    unan
    -0.17
    ndo
    -0.16
    htub
    -0.15
    obus
    -0.15
    aries
    -0.15
    atas
    -0.15
    orce
    -0.15
     Ekon
    -0.14
    uben
    -0.14
    asti
    -0.14
    POSITIVE LOGITS
    comm
    0.17
    itial
    0.16
    tring
    0.16
    datable
    0.16
    ture
    0.16
    itele
    0.15
    _allocator
    0.14
    atron
    0.14
    Canceled
    0.14
    dater
    0.14
    Act Density 0.021%

    No Known Activations