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

    Neuronpedia

    INDEX
    Explanations

    terms related to programming constructs such as functions, methods, and their properties in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     inherit
    -0.60
     subclass
    -0.56
    extends
    -0.56
    aarrggbb
    -0.54
     Widerspruch
    -0.53
    inherits
    -0.53
     inherits
    -0.52
     stratification
    -0.51
    ntz
    -0.51
     subclasses
    -0.50
    POSITIVE LOGITS
     method
    0.79
     Method
    0.73
    Method
    0.72
    method
    0.72
    FunctionFlags
    0.71
     méthodes
    0.69
     méthode
    0.69
     metodi
    0.68
     methods
    0.67
     methode
    0.66
    Act Density 0.472%

    No Known Activations