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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "one" and related numerical articles and singularities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ebra
    -0.16
     меж
    -0.15
    gang
    -0.15
     Levine
    -0.15
    inium
    -0.15
    kova
    -0.15
    /rs
    -0.15
     Labrador
    -0.14
    istik
    -0.14
    stones
    -0.14
    POSITIVE LOGITS
    /single
    0.23
    tons
    0.23
    (single
    0.22
    ahn
    0.18
    istrovstvÃŃ
    0.17
    -single
    0.17
     Ù¾ÙĦ
    0.16
    ãģĹãĤĩ
    0.16
    acter
    0.15
     SINGLE
    0.15
    Act Density 0.293%

    No Known Activations