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

    Neuronpedia

    INDEX
    Explanations

    descriptions of language learning applications and their features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    âĢ¦↵
    -0.30
    âĢ¦”
    -0.25
    âĢ¦and
    -0.24
    âĢ¦
    -0.23
     âĢ¦↵
    -0.23
     [âĢ¦]↵
    -0.23
    âĢ¦.
    -0.22
    âĢ¦"
    -0.21
    âĢ¦the
    -0.21
     “âĢ¦
    -0.20
    POSITIVE LOGITS
    #af
    0.17
    #ab
    0.17
    #ad
    0.16
     -*-č↵
    0.15
    #ac
    0.15
    )frame
    0.15
    )application
    0.14
    /***/
    0.14
    #aa
    0.14
    /******/
    0.14
    Act Density 94.625%

    No Known Activations