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

    Neuronpedia

    INDEX
    Explanations

    the repeated word "one" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of 'one' or unity in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ooks
    -0.76
    inders
    -0.68
    cases
    -0.67
    acements
    -0.60
    oof
    -0.60
    thumbnails
    -0.59
    enegger
    -0.58
    len
    -0.58
    ories
    -0.58
    rations
    -0.57
    POSITIVE LOGITS
     hundred
    0.97
     Hundred
    0.94
     thousand
    0.85
     Thousand
    0.82
     dimensional
    0.79
     lakh
    0.76
     particular
    0.76
     million
    0.76
     minute
    0.74
     sided
    0.72
    Act Density 0.136%

    No Known Activations