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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating separation or distance

    oai_token-act-pair · gpt-3.5-turbo

    the concept of separation or division

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    occ
    -0.66
    activated
    -0.64
    DAY
    -0.60
    reens
    -0.58
     millenn
    -0.57
     [+
    -0.56
     Cards
    -0.56
     Gos
    -0.56
     livest
    -0.56
    car
    -0.55
    POSITIVE LOGITS
    heid
    1.03
    ĸļ
    0.86
    igious
    0.86
    inguished
    0.85
     sexes
    0.75
    ellig
    0.75
    ively
    0.75
     apart
    0.73
    urbed
    0.73
    chool
    0.70
    Act Density 0.008%

    No Known Activations