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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their patterns in written text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    LEC
    -0.16
    ilent
    -0.15
    uto
    -0.15
    amo
    -0.15
     Giz
    -0.14
    uzzi
    -0.14
    uner
    -0.14
    enco
    -0.14
    569
    -0.14
    elu
    -0.14
    POSITIVE LOGITS
    EDGE
    0.16
     carts
    0.15
    çī
    0.14
    ÑĢид
    0.14
    sid
    0.14
    å¯Ĵ
    0.14
     zb
    0.13
    opsis
    0.13
    EIF
    0.13
    дап
    0.13
    Act Density 0.004%

    No Known Activations