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

    Neuronpedia

    INDEX
    Explanations

    links or references to additional information or content

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "can."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    burgh
    -0.66
    pires
    -0.66
     Moz
    -0.66
     Yards
    -0.61
    phas
    -0.61
     Mant
    -0.61
    Bridge
    -0.59
     Appears
    -0.59
     Passage
    -0.59
     revisions
    -0.59
    POSITIVE LOGITS
    't
    1.49
    NOT
    1.14
     optionally
    0.96
    berra
    0.92
     easily
    0.91
     choose
    0.90
    isters
    0.90
    ister
    0.88
     customize
    0.87
     activate
    0.87
    Act Density 0.093%

    No Known Activations