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

    Neuronpedia

    INDEX
    Explanations

    references to political figures named "Pascal"

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "asc" in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    STER
    -0.74
     Keynes
    -0.70
     Kers
    -0.65
    kj
    -0.65
    gets
    -0.65
     stale
    -0.63
    flix
    -0.63
    tons
    -0.63
    chard
    -0.62
    frame
    -0.62
    POSITIVE LOGITS
    adia
    1.19
    ribed
    1.12
    adian
    1.07
    henko
    1.00
    ription
    0.96
    ension
    0.95
    endant
    0.95
    urred
    0.92
    ript
    0.91
    ades
    0.90
    Act Density 0.007%

    No Known Activations