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

    Neuronpedia

    INDEX
    Explanations

    specific technical terms and concepts related to theoretical frameworks and measurements in scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OGND
    -0.51
    :✨
    -0.48
    AddHtmlAttribute
    -0.45
    OOTDTY
    -0.43
    RTLU
    -0.42
    ဲ
    -0.42
    -0.42
    Cyfeiriadau
    -0.41
    -0.41
    ftagPool
    -0.41
    POSITIVE LOGITS
     imaginable
    0.52
    任何人
    0.45
    servable
    0.43
     considérons
    0.42
     ktorý
    0.40
     tačiau
    0.40
    -------
    0.40
     ktorá
    0.40
    lámpara
    0.39
    ことなく
    0.39
    Act Density 1.544%

    No Known Activations