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

    Neuronpedia

    INDEX
    Explanations

    the specific word "dozens"

    oai_token-act-pair · gpt-3.5-turbo

    references to large quantities or groups, specifically the word "dozens."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Dub
    -0.61
    mediate
    -0.61
     illum
    -0.60
     fixation
    -0.59
    sole
    -0.59
     Lover
    -0.58
     symmetry
    -0.57
    estamp
    -0.57
     Om
    -0.56
    ppers
    -0.56
    POSITIVE LOGITS
    uously
    0.87
     Dozens
    0.83
    dozen
    0.83
     thousand
    0.81
     dozen
    0.79
     thousands
    0.79
     dozens
    0.77
    ourcing
    0.77
    paces
    0.76
    hovah
    0.76
    Act Density 0.005%

    No Known Activations