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

    Neuronpedia

    INDEX
    Explanations

    programming-related keywords and variables

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elper
    -0.16
    rait
    -0.15
    edik
    -0.14
    heits
    -0.14
     Robertson
    -0.14
    finity
    -0.13
    .builders
    -0.13
     meaningless
    -0.13
    rix
    -0.13
     "(\<
    -0.13
    POSITIVE LOGITS
     ÃĹ
    0.27
     *
    0.21
    .multiply
    0.21
    *ft
    0.20
     times
    0.20
    .mul
    0.18
    ÃĹ
    0.18
    .dot
    0.18
    *$
    0.18
    *((
    0.18
    Act Density 0.026%

    No Known Activations