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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "one" in a sentence

    oai_token-act-pair · gpt-3.5-turbo

    repeated instances of the word "one."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ooks
    -0.73
     actionGroup
    -0.64
    inders
    -0.63
    lov
    -0.61
    osponsors
    -0.60
    ãĤµ
    -0.59
    Available
    -0.59
    ãĥĥ
    -0.58
     cliffs
    -0.58
    æĸ¹
    -0.58
    POSITIVE LOGITS
     hundred
    0.94
     Hundred
    0.94
     dimensional
    0.83
     thousand
    0.82
     Thousand
    0.78
    rency
    0.75
     thing
    0.74
     sided
    0.73
    handedly
    0.71
     person
    0.71
    Act Density 0.187%

    No Known Activations