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

    Neuronpedia

    INDEX
    Explanations

    numerical values related to large quantities or amounts

    oai_token-act-pair · gpt-3.5-turbo

    references to large quantities or groups of people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cyn
    -0.78
     Cinnamon
    -0.74
     Moder
    -0.67
     Ghosts
    -0.66
     Alone
    -0.66
    cade
    -0.65
     Carnage
    -0.65
     Mystic
    -0.64
    odox
    -0.64
     Doctor
    -0.63
    POSITIVE LOGITS
     tens
    0.84
     pounds
    0.82
    inement
    0.77
     thousands
    0.77
     bonded
    0.69
    oldown
    0.66
    lbs
    0.66
    pound
    0.66
    pees
    0.65
     flown
    0.65
    Act Density 0.153%

    No Known Activations