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

    Neuronpedia

    INDEX
    Explanations

    instances where the word "one" is used frequently in a text

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "one."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    osponsors
    -0.74
    ories
    -0.72
    ypes
    -0.70
    avascript
    -0.70
    ocks
    -0.65
    apons
    -0.64
    ICO
    -0.64
    illon
    -0.63
    ourn
    -0.63
    æĸ
    -0.63
    POSITIVE LOGITS
     exception
    1.06
     thing
    1.03
     hundred
    0.89
     caveat
    0.82
     eyed
    0.82
     guy
    0.81
     remaining
    0.80
     person
    0.80
     closest
    0.78
     Hundred
    0.77
    Act Density 0.045%

    No Known Activations