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

    Neuronpedia

    INDEX
    Explanations

    numbers or numerical data within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    frau
    -0.18
     edit
    -0.14
    aku
    -0.14
    inia
    -0.14
     yay
    -0.14
    bre
    -0.14
    erif
    -0.13
     Mesh
    -0.13
    RICT
    -0.13
    adem
    -0.13
    POSITIVE LOGITS
    _curve
    0.16
     ########.
    0.15
    sparse
    0.14
    ç©¿
    0.13
    oha
    0.13
    ITO
    0.13
    itous
    0.13
    obb
    0.13
    SOR
    0.13
    vie
    0.13
    Act Density 0.006%

    No Known Activations