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

    Neuronpedia

    INDEX
    Explanations

    words related to traffic and its implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Pwr
    -0.66
     Loll
    -0.66
    amental
    -0.64
    EXP
    -0.64
     Seym
    -0.63
     warranties
    -0.61
    THING
    -0.61
    ATES
    -0.61
     WARN
    -0.59
    lists
    -0.59
    POSITIVE LOGITS
    pped
    1.24
    pping
    1.19
    verse
    1.17
    umat
    1.14
    ffic
    1.12
    itored
    1.09
    pez
    1.04
    ppings
    1.04
    aching
    1.00
    ppers
    0.99
    Act Density 0.019%

    No Known Activations