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

    Neuronpedia

    INDEX
    Explanations

    elements related to rules or criteria pertaining to processes or systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kul
    -0.17
    avic
    -0.14
    htm
    -0.14
    elper
    -0.14
    riere
    -0.13
    terior
    -0.13
    riors
    -0.13
    asks
    -0.13
    cej
    -0.13
    äter
    -0.13
    POSITIVE LOGITS
    (s
    0.96
    (es
    0.59
    [s
    0.57
    /s
    0.45
    (S
    0.45
    {s
    0.40
    (en
    0.35
    (-
    0.33
    (e
    0.32
    =s
    0.29
    Act Density 0.087%

    No Known Activations