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

    Neuronpedia

    INDEX
    Explanations

    references to dates, mathematical notation, and names or titles in structured contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     mor
    -0.16
    coni
    -0.15
    ksen
    -0.15
     Blow
    -0.15
    urrenc
    -0.15
     recurs
    -0.14
    fell
    -0.14
    風
    -0.14
     rel
    -0.14
     ret
    -0.14
    POSITIVE LOGITS
    emm
    0.15
    bette
    0.14
    ae
    0.14
    oldt
    0.14
     Vern
    0.14
     Vinyl
    0.14
    ’B
    0.14
    stin
    0.14
    æĻĵ
    0.14
    antanamo
    0.13
    Act Density 0.021%

    No Known Activations