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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "are."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /XML
    -0.15
    ãĥīãĥ«
    -0.15
    /UIKit
    -0.14
    _MISC
    -0.14
    REFERRED
    -0.14
    misc
    -0.14
    .Slf
    -0.13
    ian
    -0.13
    iston
    -0.13
    erson
    -0.13
    POSITIVE LOGITS
     times
    0.17
    antha
    0.15
    iosis
    0.15
     fewer
    0.15
     ways
    0.14
    oord
    0.14
     Fry
    0.14
    ignet
    0.13
    eny
    0.13
    entic
    0.13
    Act Density 0.062%

    No Known Activations