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

    Neuronpedia

    INDEX
    Explanations

    mentions of individuals or entities being part of a specific larger group

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "among" indicating a grouping or categorization of people or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ibe
    -0.70
    dayName
    -0.68
     anytime
    -0.67
     translates
    -0.67
    zeb
    -0.65
    gran
    -0.58
     destro
    -0.58
    bane
    -0.57
    ysc
    -0.57
     Combine
    -0.57
    POSITIVE LOGITS
     those
    1.05
     dozens
    0.98
     hundreds
    0.90
     several
    0.89
    those
    0.88
    Ĥ¬
    0.87
     thousands
    0.84
     tens
    0.81
     numerous
    0.80
     countless
    0.79
    Act Density 0.055%

    No Known Activations