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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "pass" in a variety of contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "passing" or approval in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ¼ãĤ¦ãĤ¹
    -0.75
     Archangel
    -0.67
     ASP
    -0.67
     Knot
    -0.65
     Kut
    -0.61
    selage
    -0.60
     Stevens
    -0.60
     narrator
    -0.60
    grave
    -0.59
     pudding
    -0.58
    POSITIVE LOGITS
    wd
    1.12
    engers
    0.89
     muster
    0.88
    aic
    0.87
    ives
    0.87
    phrase
    0.86
    words
    0.85
    ibility
    0.84
    ivity
    0.83
    es
    0.80
    Act Density 0.016%

    No Known Activations