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

    Neuronpedia

    INDEX
    Explanations

    specific technical language related to performance metrics and configurations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    )frame
    -0.16
     -*-č↵
    -0.14
    #ab
    -0.14
    /***/
    -0.14
    )application
    -0.13
    #ad
    -0.13
    #ac
    -0.12
    ãģŀ
    -0.12
    CJK
    -0.12
    $$$$
    -0.12
    POSITIVE LOGITS
    âĢ¦↵
    0.27
    âĢ¦”
    0.24
    âĢ¦and
    0.22
     âĢ¦↵
    0.22
    âĢ¦I
    0.21
    âĢ¦
    0.21
    âĢ¦the
    0.20
    âĢ¦.
    0.20
     [âĢ¦]↵
    0.20
    âĢ¦âĢ¦
    0.20
    Act Density 0.394%

    No Known Activations