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

    Neuronpedia

    INDEX
    Explanations

    complex phrases involving scenarios, instances, or situations

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating specific instances or scenarios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ena
    -0.73
    semble
    -0.62
    tsy
    -0.59
    ails
    -0.56
    imize
    -0.56
     sqor
    -0.55
    malink
    -0.54
     appl
    -0.54
    unit
    -0.53
    ruction
    -0.53
    POSITIVE LOGITS
     where
    2.06
     wherein
    1.87
    where
    1.84
     whereby
    1.53
    when
    1.32
     WHERE
    1.28
     when
    1.28
     Where
    1.25
     whence
    1.17
    Where
    1.17
    Act Density 0.703%

    No Known Activations