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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a significant amount or degree of something

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "much."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    senal
    -0.68
    rum
    -0.64
    cium
    -0.63
    rums
    -0.63
    mone
    -0.63
    peror
    -0.62
    marine
    -0.62
     è£ıç
    -0.60
    punk
    -0.60
    riers
    -0.60
    POSITIVE LOGITS
     aside
    0.79
     notwithstanding
    0.75
     Opinion
    0.67
     refres
    0.66
     Matter
    0.65
     meanwhile
    0.62
    ortunately
    0.61
     Brief
    0.61
     Ashe
    0.61
     Works
    0.60
    Act Density 0.435%

    No Known Activations