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

    Neuronpedia

    INDEX
    Explanations

    the word "many" in a sentence

    oai_token-act-pair · gpt-3.5-turbo

    references to the quantity "many."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    acus
    -0.86
    adish
    -0.81
    atum
    -0.75
    etry
    -0.71
    amation
    -0.71
    atism
    -0.68
    oulos
    -0.68
    OPE
    -0.68
    ataka
    -0.67
    roup
    -0.67
    POSITIVE LOGITS
     facets
    0.94
     times
    0.94
    body
    0.93
     aspects
    0.87
     iterations
    0.85
     kinds
    0.84
     different
    0.81
     unanswered
    0.81
     dozen
    0.81
     hundred
    0.80
    Act Density 0.063%

    No Known Activations