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

    Neuronpedia

    INDEX
    Explanations

    phrases with coordinated elements or items in a list

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oyer
    -0.17
    abela
    -0.15
    ::__
    -0.14
    FACT
    -0.14
    ï½į
    -0.14
    kiem
    -0.14
    aint
    -0.14
    ima
    -0.13
    ffd
    -0.13
    pons
    -0.13
    POSITIVE LOGITS
    agate
    0.16
    enticated
    0.15
    uddy
    0.14
     Jackson
    0.14
    etest
    0.14
    ãĥ¥
    0.13
    eted
    0.13
    taj
    0.13
    uw
    0.13
     Liv
    0.13
    Act Density 0.239%

    No Known Activations