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

    Neuronpedia

    INDEX
    Explanations

    references to dates and events

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific film or media title

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Bulg
    -0.65
     thin
    -0.63
     Thin
    -0.62
    terday
    -0.62
     Pry
    -0.60
     slack
    -0.60
     Beau
    -0.60
     Luxem
    -0.59
     slurs
    -0.59
     Hera
    -0.59
    POSITIVE LOGITS
    iscovery
    1.39
    ynam
    1.35
    etermin
    1.31
    owntown
    1.30
    irection
    1.29
    inosaur
    1.27
    ennis
    1.25
    ynasty
    1.24
    etermination
    1.23
    erek
    1.23
    Act Density 0.038%

    No Known Activations