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

    Neuronpedia

    INDEX
    Explanations

    segments of code related to class definitions and methods in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ucwords
    -0.14
    ctp
    -0.14
    ieux
    -0.13
    _BREAK
    -0.13
    inson
    -0.13
    uchar
    -0.13
    sem
    -0.13
    IEW
    -0.13
    inh
    -0.13
    iew
    -0.13
    POSITIVE LOGITS
     def
    0.65
    def
    0.43
    	def
    0.42
    -def
    0.31
     déf
    0.29
     Def
    0.28
    .def
    0.25
    _def
    0.24
     defy
    0.23
    :def
    0.23
    Act Density 0.008%

    No Known Activations