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

    Neuronpedia

    INDEX
    Explanations

    references to cars and automotive-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ka
    -0.17
    urn
    -0.16
    URN
    -0.14
    interactive
    -0.14
    ç²Ĵ
    -0.14
    704
    -0.14
    894
    -0.14
    ettes
    -0.14
    itt
    -0.14
    clusions
    -0.14
    POSITIVE LOGITS
    ibbean
    0.27
    bohydr
    0.24
    lsen
    0.23
    olina
    0.21
    acter
    0.21
    abin
    0.20
    ousing
    0.20
    rying
    0.20
    erer
    0.19
    bons
    0.18
    Act Density 0.032%

    No Known Activations