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

    Neuronpedia

    INDEX
    Explanations

    adjectives and nouns related to size, value, and importance

    oai_token-act-pair · gpt-3.5-turbo

    significant and impactful phrases or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rounder
    -0.69
     blank
    -0.59
    angu
    -0.59
    Ĭ±
    -0.58
    alty
    -0.58
     Suppose
    -0.56
    thren
    -0.56
    heid
    -0.56
     Generic
    -0.55
    avez
    -0.53
    POSITIVE LOGITS
     culmin
    1.10
     culminated
    1.09
     culminating
    1.00
    pecially
    0.87
    including
    0.85
     paralle
    0.85
     INCLUD
    0.84
     unsur
    0.72
    ranging
    0.72
     notwithstanding
    0.71
    Act Density 0.874%

    No Known Activations