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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "upon" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    poke
    -0.17
    idge
    -0.16
    runner
    -0.15
    room
    -0.15
    uces
    -0.15
    wyn
    -0.15
    aceous
    -0.15
    vice
    -0.15
    ening
    -0.14
    ubit
    -0.14
    POSITIVE LOGITS
     Upon
    0.17
    prav
    0.17
    Upon
    0.17
     upon
    0.16
    orex
    0.15
    mw
    0.14
    ร
    0.14
    mol
    0.14
    assis
    0.14
    warts
    0.14
    Act Density 0.028%

    No Known Activations