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

    Neuronpedia

    INDEX
    Explanations

    references to artistic works or title formats, particularly those that include parentheses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anse
    -0.15
     releg
    -0.15
    ],
    -0.15
    abay
    -0.15
    ls
    -0.14
    (
    -0.14
    ież
    -0.14
    [
    -0.14
     quote
    -0.14
     tutorials
    -0.13
    POSITIVE LOGITS
    noun
    0.20
    continued
    0.18
    thing
    0.16
    ä¸ŃæĸĩåŃĹå¹ķ
    0.16
    redux
    0.16
     continued
    0.16
    주ìĭľ
    0.16
    اÙĦØ¥ÙĨجÙĦÙĬزÙĬØ©
    0.15
    ioms
    0.15
    tm
    0.15
    Act Density 0.152%

    No Known Activations