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

    Neuronpedia

    INDEX
    Explanations

    phrases related to a continuous action or state happening over a period of time

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating ongoing actions or states of being

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Places
    -0.67
     Measures
    -0.66
     Pair
    -0.65
     Warning
    -0.64
     Manifest
    -0.64
     Approach
    -0.62
     Init
    -0.62
     Expect
    -0.59
     opener
    -0.59
     Meet
    -0.57
    POSITIVE LOGITS
     since
    1.41
     remained
    1.23
     continued
    1.11
    since
    1.09
     now
    1.04
     been
    1.03
     persisted
    1.01
     regained
    1.01
     stayed
    1.00
     resur
    0.97
    Act Density 0.192%

    No Known Activations