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

    Neuronpedia

    INDEX
    Explanations

    mentions of the abbreviation "Int" which could potentially stand for "intelligence."

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "Int 2"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hyde
    -0.71
     palms
    -0.70
     trailers
    -0.68
     whales
    -0.64
     flair
    -0.63
     transitional
    -0.63
     lodge
    -0.62
    culosis
    -0.61
     slopes
    -0.60
     wagon
    -0.60
    POSITIVE LOGITS
    ellect
    1.45
    ensive
    1.43
    ention
    1.43
    ellig
    1.40
    ensity
    1.38
    elligent
    1.34
    ended
    1.31
    angible
    1.31
    imate
    1.29
    uitive
    1.26
    Act Density 0.028%

    No Known Activations