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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and separators within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     total
    -0.54
     break
    -0.52
    Ã
    -0.51
    ′
    -0.51
     cà
    -0.50
    ActionCreators
    -0.49
     invol
    -0.49
     Jazeera
    -0.49
     start
    -0.48
    alach
    -0.48
    POSITIVE LOGITS
    Personensuche
    1.13
     مرئيه
    1.11
    tagHelperRunner
    0.90
    🏻‍♀️
    0.77
     utafitiHapana
    0.75
    InitVars
    0.75
    (!__
    0.73
    Autoritní
    0.73
     RIPRODUZIONE
    0.73
     فريبيس
    0.72
    Act Density 0.310%

    No Known Activations