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

    Neuronpedia

    INDEX
    Explanations

    terms related to modifications and improvements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DSL
    -0.14
     cle
    -0.14
    ær
    -0.13
    kek
    -0.13
    ë§Ŀ
    -0.13
    åª
    -0.13
    kas
    -0.13
    VML
    -0.13
    552
    -0.13
    éĸĢ
    -0.13
    POSITIVE LOGITS
    acco
    0.18
     Storm
    0.14
     slight
    0.14
    amenti
    0.14
    zt
    0.14
    ello
    0.14
     subur
    0.14
    628
    0.14
    reesome
    0.13
     Wer
    0.13
    Act Density 0.299%

    No Known Activations