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

    Neuronpedia

    INDEX
    Explanations

    the word "one" with a high activation level

    oai_token-act-pair · gpt-3.5-turbo

    the repetition of the word "one."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ooks
    -0.68
    lov
    -0.66
     actionGroup
    -0.64
    inas
    -0.60
    Available
    -0.59
    Ec
    -0.58
     cores
    -0.58
     Frames
    -0.58
    gif
    -0.58
    inders
    -0.57
    POSITIVE LOGITS
     Hundred
    0.84
     dimensional
    0.79
    rency
    0.79
     hundred
    0.79
     thing
    0.73
    oxide
    0.71
     Thousand
    0.69
     thousand
    0.68
     person
    0.67
    ones
    0.66
    Act Density 0.129%

    No Known Activations