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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the introduction of different objects or methods within a discussion or description of an invention

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

    is an object of the invention

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     виправивши
    -0.41
     parting
    -0.36
     Vali
    -0.36
     المعيارى
    -0.35
     समीक्षक
    -0.35
     prisms
    -0.35
     magg
    -0.35
     antim
    -0.34
     hervor
    -0.34
     chalk
    -0.34
    POSITIVE LOGITS
    WHEREAS
    0.81
    Whereas
    0.77
     Whereas
    0.75
    reamble
    0.73
    whereas
    0.72
     WHEREAS
    0.68
    Preamble
    0.68
     whereas
    0.62
     preamble
    0.60
     Background
    0.56
    Act Density 0.100%

    No Known Activations