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

    Neuronpedia

    INDEX
    Explanations

    phrases related to concepts of governance and operations of authority

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Utf
    -0.15
    arn
    -0.15
    cap
    -0.14
     Miscellaneous
    -0.13
    ø
    -0.13
    iska
    -0.13
    ogn
    -0.13
     baģlantılar
    -0.13
    èĢħçļĦ
    -0.13
    avers
    -0.13
    POSITIVE LOGITS
     inte
    0.29
     dock
    0.28
    dock
    0.23
    Dock
    0.22
     dess
    0.21
     Dock
    0.21
     ib
    0.21
     bara
    0.21
    iaux
    0.20
     ju
    0.19
    Act Density 0.054%

    No Known Activations