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

    Neuronpedia

    INDEX
    Explanations

    numerical values related to quantity or degree

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating quantities that exceed a specified threshold

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    illary
    -0.82
    Ô
    -0.81
    antine
    -0.71
    herty
    -0.68
    hess
    -0.67
    olis
    -0.66
    alogy
    -0.66
    Creat
    -0.65
    Flo
    -0.64
    olini
    -0.64
    POSITIVE LOGITS
    whelming
    0.75
     half
    0.73
    eenth
    0.71
     acre
    0.71
    kill
    0.68
     dozen
    0.68
     750
    0.68
     hect
    0.67
     800
    0.66
    deck
    0.66
    Act Density 0.034%

    No Known Activations