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

    Neuronpedia

    INDEX
    Explanations

    instances of punctuation or sentence endings in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ¼
    -0.16
    ---</
    -0.14
    {}".
    -0.14
    éli
    -0.13
    oria
    -0.13
     Witness
    -0.13
    .Listen
    -0.13
    Ñĵ
    -0.13
    daemon
    -0.12
    orrent
    -0.12
    POSITIVE LOGITS
    æĿ¡
    0.21
    *
    0.21
    ###
    0.20
    |
    0.18
    ##
    0.17
     ''
    0.16
     Stephan
    0.16
    .|
    0.15
    ####
    0.15
    #####
    0.15
    Act Density 0.024%

    No Known Activations