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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and formatting elements within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Efq
    -1.22
     Paglinawan
    -1.16
     Majefty
    -1.13
     itſelf
    -1.10
     faſt
    -1.10
    complexContent
    -1.08
     myſelf
    -1.08
     MainAxisSize
    -1.06
     pleaſure
    -1.06
     ་་
    -1.06
    POSITIVE LOGITS
    ```
    1.20
     in
    0.64
     as
    0.62
     
    0.58
     no
    0.57
     o
    0.56
     I
    0.54
    /
    0.53
     of
    0.52
    o
    0.52
    Act Density 0.022%

    No Known Activations