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

    Neuronpedia

    INDEX
    Explanations

    the term "abstract" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    abstract:

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pedagogical
    -0.43
    Guard
    -0.42
    <>("
    -0.41
     Census
    -0.40
     guard
    -0.40
     Kamin
    -0.39
    Fla
    -0.38
     fla
    -0.38
     pedagogy
    -0.38
     Pedagog
    -0.37
    POSITIVE LOGITS
    abstract
    2.34
    abstractmethod
    0.92
    abstra
    0.72
    Abstract
    0.67
     abstract
    0.65
    ABSTRACT
    0.64
     abstrato
    0.64
    참고
    0.62
     незавершена
    0.59
    抽象
    0.57
    Act Density 0.001%

    No Known Activations