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

    Neuronpedia

    INDEX
    Explanations

    references to concepts of governance and accountability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    followed by prepositions/punctuation

    np_acts-logits-general · gemini-2.0-flash

    actions and their consequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AndEndTag
    -0.60
     Autorisations
    -0.52
     CreateTagHelper
    -0.51
    enetrable
    -0.43
     שוליים
    -0.42
     تضيفلها
    -0.42
    Communication
    -0.41
     Komunikasi
    -0.41
     dobles
    -0.41
    DeleteCommand
    -0.41
    POSITIVE LOGITS
    ViewImports
    0.46
     ſte
    0.41
     itſelf
    0.41
    せっかく
    0.39
    +#+
    0.39
     leſs
    0.38
     Anſ
    0.38
     Inſ
    0.37
     inſ
    0.37
    いくら
    0.37
    Act Density 0.357%

    No Known Activations