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

    Neuronpedia

    INDEX
    Explanations

    code-related constructs and conditional statements in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    **.
    -0.63
    .</
    -0.61
    *</
    -0.53
    **
    -0.52
    **,
    -0.51
    *.
    -0.51
    ########.
    -0.51
     **
    -0.50
    '>";
    -0.50
    .**
    -0.49
    POSITIVE LOGITS
     defined
    1.07
    defined
    1.01
     define
    0.89
    Define
    0.87
    define
    0.86
    定義
    0.82
     Defined
    0.81
     definition
    0.80
     definido
    0.80
     definiert
    0.79
    Act Density 0.846%

    No Known Activations