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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and specialized terminology related to governance, regulation, or scientific topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oks
    -0.15
    ëłĪìĿ´
    -0.14
    /english
    -0.14
    ês
    -0.14
     Erl
    -0.13
    aus
    -0.13
    CEE
    -0.13
    riage
    -0.13
    throp
    -0.13
    æª
    -0.13
    POSITIVE LOGITS
    ing
    0.19
    izza
    0.16
    ed
    0.16
    lesh
    0.14
    nin
    0.14
    ens
    0.14
    odon
    0.14
    äºľ
    0.14
    ¯
    0.14
    ging
    0.13
    Act Density 0.367%

    No Known Activations