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

    Neuronpedia

    INDEX
    Explanations

    quantifiable metrics or values related to performance and comparison

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orris
    -0.15
     обоÑĢ
    -0.15
    UPI
    -0.14
    ension
    -0.14
    utex
    -0.14
    udeau
    -0.14
    aren
    -0.14
    cret
    -0.14
     queryInterface
    -0.14
    lož
    -0.13
    POSITIVE LOGITS
     ES
    0.17
     Merr
    0.16
     hol
    0.15
     Truy
    0.14
    imers
    0.14
    ured
    0.14
    upal
    0.14
    社
    0.14
    strup
    0.14
    éĽĦ
    0.14
    Act Density 0.001%

    No Known Activations