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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "one" and expressions indicating singular concepts or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    reater
    -0.17
    putc
    -0.16
    ulu
    -0.15
    uluk
    -0.15
    specialchars
    -0.15
    istrovstvÃŃ
    -0.15
    icense
    -0.15
    vik
    -0.14
     ÐŁÐ¾Ñģ
    -0.14
    iveau
    -0.14
    POSITIVE LOGITS
    assis
    0.17
    ZR
    0.15
    aza
    0.14
    ạc
    0.14
    undy
    0.14
     diplom
    0.14
    ë©´
    0.14
    ockey
    0.14
     unh
    0.14
    unny
    0.13
    Act Density 0.014%

    No Known Activations