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

    Neuronpedia

    INDEX
    Explanations

    references to research and documentation credibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    à¸Ļà¸Ń
    -0.14
    æ±ł
    -0.14
     Wet
    -0.13
    ewith
    -0.13
    ìŀ¬
    -0.13
     Polic
    -0.13
    pak
    -0.13
     repro
    -0.13
     Oversight
    -0.13
    ebek
    -0.13
    POSITIVE LOGITS
     Pub
    0.16
    çĮľ
    0.15
    nerg
    0.14
     ìĨ
    0.14
     kir
    0.14
     Lem
    0.14
     pub
    0.14
    arat
    0.14
    ASE
    0.14
    olid
    0.14
    Act Density 0.129%

    No Known Activations