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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "factual" and its relevance in the context

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

    already or more

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    raborty
    -0.47
     Bim
    -0.45
    こんな感じで
    -0.44
     BaseEntity
    -0.44
    綺麗な
    -0.44
     Vanden
    -0.43
     Barna
    -0.42
     Wilfred
    -0.41
     vacancy
    -0.40
     Mox
    -0.40
    POSITIVE LOGITS
    说
    1.63
    說
    1.52
     说
    1.27
     說
    1.16
     nói
    0.96
    的说
    0.95
    地说
    0.94
     say
    0.85
    她说
    0.84
    他说
    0.82
    Act Density 0.003%

    No Known Activations