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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "one" followed by a number (or by words representing numbers)

    oai_token-act-pair · gpt-3.5-turbo

    the repeated mention of the word "one" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    osponsors
    -0.78
    inders
    -0.74
    ooks
    -0.73
    grounds
    -0.73
    ories
    -0.71
    lations
    -0.68
    sav
    -0.66
    idences
    -0.66
    emies
    -0.64
    esta
    -0.64
    POSITIVE LOGITS
     hundred
    0.93
     thing
    0.89
     Hundred
    0.89
    Shot
    0.86
     heck
    0.79
     thousand
    0.78
     overriding
    0.75
     overarching
    0.74
     sided
    0.72
     apiece
    0.72
    Act Density 0.119%

    No Known Activations