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

    Neuronpedia

    INDEX
    Explanations

    mathematical variables and symbols in equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    оÑģоб
    -0.16
    ænd
    -0.15
    urgeon
    -0.15
    cé
    -0.15
    주ìĿĺ
    -0.14
    fallback
    -0.14
     оÑģоб
    -0.14
    neas
    -0.14
    kÄĻ
    -0.14
    otre
    -0.14
    POSITIVE LOGITS
    1
    0.31
    2
    0.18
    iano
    0.17
    ÑĤоÑĢа
    0.15
    01
    0.15
    rag
    0.15
    Û±
    0.15
    unge
    0.14
     toll
    0.14
    ActionCreators
    0.14
    Act Density 0.058%

    No Known Activations