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

    Neuronpedia

    INDEX
    Explanations

    instances of punctuation marks, specifically commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    è¬Ŀ
    -0.15
    âķĹ
    -0.15
    模
    -0.14
    ä»ĺãģij
    -0.14
    ossa
    -0.13
     muh
    -0.13
     thé
    -0.13
    _COMBO
    -0.13
    ÄĽÅĻ
    -0.12
    nameof
    -0.12
    POSITIVE LOGITS
    eken
    0.21
     Brands
    0.21
     brands
    0.21
    brand
    0.20
     brand
    0.20
     branding
    0.20
     BRAND
    0.19
    åĵģçīĮ
    0.18
    _brand
    0.17
     Brand
    0.17
    Act Density 0.000%

    No Known Activations