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

    Neuronpedia

    INDEX
    Explanations

    technical jargon and function definitions related to programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    icle
    -0.19
     Poz
    -0.14
    erson
    -0.14
    -0.14
    aiser
    -0.14
    ÑĮ
    -0.13
    force
    -0.13
    cmc
    -0.13
     matter
    -0.13
    neath
    -0.13
    POSITIVE LOGITS
    ude
    0.16
    átka
    0.15
     DECLARE
    0.15
    hait
    0.14
    éri
    0.14
    еÑĤÑĮ
    0.14
    ruž
    0.14
    contro
    0.14
    axe
    0.13
    CRET
    0.13
    Act Density 0.016%

    No Known Activations