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

    Neuronpedia

    INDEX
    Explanations

    instances of specific markers or special tokens indicating the beginning of a text or paragraph

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    terase
    -0.52
    aarrggbb
    -0.48
    AnchorTagHelper
    -0.46
    thenReturn
    -0.46
     архивлан
    -0.45
    Gov
    -0.43
    borderSide
    -0.42
    delmi
    -0.41
     feveral
    -0.41
     समीक्षाओं
    -0.40
    POSITIVE LOGITS
    ########.
    1.25
    <bos>
    1.15
     >=",
    0.90
    ViewImports
    0.74
     صوتيه
    0.68
    cplusplus
    0.68
     فريبيس
    0.68
    Parcelize
    0.68
    PreferredItem
    0.64
    DeleteBehavior
    0.64
    Act Density 0.003%

    No Known Activations