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

    Neuronpedia

    INDEX
    Explanations

    mentions of duration or amounts of time

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "many" referring to quantity or frequency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    acus
    -0.89
    adish
    -0.79
    atum
    -0.72
    atism
    -0.69
    etry
    -0.69
    amation
    -0.68
    oulos
    -0.67
    ataka
    -0.67
    roup
    -0.67
    anut
    -0.66
    POSITIVE LOGITS
     times
    0.96
    body
    0.90
     facets
    0.87
     aspects
    0.83
     nights
    0.81
     dozen
    0.79
     iterations
    0.79
     unanswered
    0.77
     thousands
    0.76
     kinds
    0.76
    Act Density 0.076%

    No Known Activations