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

    Neuronpedia

    INDEX
    Explanations

    references to policies or regulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    áo
    -0.16
    ilda
    -0.14
    è§ī
    -0.13
     Îļο
    -0.13
    unda
    -0.13
    kul
    -0.13
    лек
    -0.13
    oday
    -0.13
     rog
    -0.13
    ãģ¡ãĤĥãĤĵ
    -0.13
    POSITIVE LOGITS
    ettings
    0.17
    forth
    0.16
     ########.
    0.16
    isters
    0.15
    ystore
    0.14
     endors
    0.14
    rief
    0.14
    foy
    0.14
    istrar
    0.14
    560
    0.14
    Act Density 0.005%

    No Known Activations