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

    Neuronpedia

    INDEX
    Explanations

    instances of authority and accountability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Äįek
    -0.17
     salopes
    -0.16
    orf
    -0.15
    .Generated
    -0.14
    icot
    -0.14
     wich
    -0.13
    yper
    -0.13
    âĪ¨
    -0.13
     reluct
    -0.13
     ThemeData
    -0.13
    POSITIVE LOGITS
     patents
    0.17
     patent
    0.16
     various
    0.16
    gh
    0.15
    itage
    0.15
     basically
    0.14
    eus
    0.14
     wast
    0.14
    652
    0.13
     copyright
    0.13
    Act Density 0.001%

    No Known Activations