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

    Neuronpedia

    INDEX
    Explanations

    recent events or occurrences

    oai_token-act-pair · gpt-3.5-turbo

    references to recent events or updates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tracks
    -0.94
    assies
    -0.83
     actionGroup
    -0.83
     brakes
    -0.82
    ences
    -0.82
     detectors
    -0.81
    urches
    -0.81
    ernels
    -0.80
     pedals
    -0.78
     decks
    -0.76
    POSITIVE LOGITS
     staffer
    0.88
     colleague
    0.86
     pamphlet
    0.81
     statement
    0.81
     batch
    0.80
     snippet
    0.80
     iteration
    0.80
     classmate
    0.79
     standpoint
    0.78
     member
    0.78
    Act Density 0.319%

    No Known Activations