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

    Neuronpedia

    INDEX
    Explanations

    references to "paper" in various contexts

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

    "Paper"

    np_acts-logits-general · gemini-2.0-flash

    PaperThin and paper cutting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ]--;
    -0.60
     المعيارى
    -0.59
     BoxFit
    -0.59
    DataAnnotations
    -0.58
    schild
    -0.57
    unhofer
    -0.56
    URLConnection
    -0.55
    createClass
    -0.54
    первых
    -0.54
    insen
    -0.53
    POSITIVE LOGITS
    clip
    0.80
     mache
    0.76
     mâ
    0.70
    clips
    0.68
     mills
    0.65
     towel
    0.62
     towels
    0.62
    weight
    0.61
     mill
    0.61
    mache
    0.59
    Act Density 0.061%

    No Known Activations