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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "are" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    igers
    -0.15
    /UIKit
    -0.15
    /XML
    -0.14
    ami
    -0.14
    ilen
    -0.14
    ãĥīãĥ«
    -0.14
    _MISC
    -0.14
    asket
    -0.13
    .Slf
    -0.13
    ANGO
    -0.13
    POSITIVE LOGITS
     Fry
    0.15
     fewer
    0.15
     times
    0.15
    iosis
    0.15
    antha
    0.14
    SSI
    0.14
    oord
    0.14
     two
    0.14
     ways
    0.13
     column
    0.13
    Act Density 0.067%

    No Known Activations