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

    Neuronpedia

    INDEX
    Explanations

    numerical quantities or words related to quantification

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    abs
    -0.77
    tops
    -0.75
    rovers
    -0.73
    haven
    -0.72
    dn
    -0.69
    duc
    -0.65
    stones
    -0.65
    bows
    -0.65
    models
    -0.64
    children
    -0.64
    POSITIVE LOGITS
     successive
    1.17
     iteration
    0.96
     participant
    0.92
     individual
    0.88
     person
    0.86
    where
    0.84
     month
    0.84
     piece
    0.81
     element
    0.80
     member
    0.80
    Act Density 0.034%

    No Known Activations