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

    Neuronpedia

    INDEX
    Explanations

    ordinal indicators or signals within a statement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     first
    -0.16
    rone
    -0.15
    ake
    -0.15
    enko
    -0.14
    oard
    -0.14
    ining
    -0.14
    encial
    -0.14
    ook
    -0.14
    ег
    -0.13
    nze
    -0.13
    POSITIVE LOGITS
    ly
    0.25
    arily
    0.21
     importantly
    0.18
    LY
    0.17
    /th
    0.17
     اÛĮÙĨÚ©Ùĩ
    0.15
    .Second
    0.15
    ë¡ľëĬĶ
    0.14
    .scalablytyped
    0.14
     olarak
    0.14
    Act Density 0.023%

    No Known Activations