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

    Neuronpedia

    INDEX
    Explanations

    references to foundational principles or structures in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Hartman
    -0.87
     Smarty
    -0.86
     HttpNotFound
    -0.85
    HttpPost
    -0.80
     Miki
    -0.78
    GenerationType
    -0.77
     MainAxisSize
    -0.74
    ########.
    -0.74
    /***/
    -0.73
    !*\
    -0.73
    POSITIVE LOGITS
     Und
    1.39
     UND
    1.30
     und
    1.28
    underline
    1.25
    Und
    1.13
    und
    1.09
    UND
    1.01
    Underline
    1.00
     underline
    0.98
    Underlying
    0.97
    Act Density 0.071%

    No Known Activations