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

    Neuronpedia

    INDEX
    Explanations

    questions starting with the word "Who"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "who."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    emin
    -0.64
    PORT
    -0.64
    GV
    -0.62
     immersion
    -0.62
     Globe
    -0.61
     saturation
    -0.61
    MER
    -0.61
     compatibility
    -0.58
    rocket
    -0.58
     Pilgrim
    -0.57
    POSITIVE LOGITS
    soever
    1.18
    ever
    1.16
     cares
    1.15
     else
    1.15
    oping
    1.09
     knows
    1.04
    ops
    0.99
    oped
    0.92
    osh
    0.89
    opsy
    0.84
    Act Density 0.039%

    No Known Activations