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

    Neuronpedia

    INDEX
    Explanations

    references to statistical representation and accuracy in study data

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

    representative, accurate, important

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     noqa
    -0.42
     <=",
    -0.39
    AnchorStyles
    -0.33
    Filmo
    -0.33
    riwal
    -0.32
    XCTAssertEqual
    -0.31
    =$?
    -0.31
    postsleuth
    -0.31
    Puri
    -0.30
    Obvious
    -0.30
    POSITIVE LOGITS
    tinyos
    0.59
     المعيارى
    0.53
     betweenstory
    0.52
     ffilmiau
    0.52
    Tikang
    0.52
    éndolo
    0.51
    ACHUSET
    0.49
     saites
    0.48
     <<<<<<<<<<<<<<
    0.48
    anjutnya
    0.47
    Act Density 0.198%

    No Known Activations