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

    Neuronpedia

    INDEX
    Explanations

    phrases starting with the word "upon"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    room
    -0.17
    chen
    -0.15
    t
    -0.15
    rying
    -0.15
    /w
    -0.15
    idge
    -0.14
    isel
    -0.14
    xing
    -0.14
    runner
    -0.14
     tomu
    -0.14
    POSITIVE LOGITS
    soever
    0.18
    pector
    0.17
    warts
    0.17
    isphere
    0.16
    orex
    0.15
    prav
    0.15
     Upon
    0.15
    eness
    0.15
     occasion
    0.15
    Æł
    0.15
    Act Density 0.027%

    No Known Activations