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

    Neuronpedia

    INDEX
    Explanations

    words that express positive or negative emotional states and confidence levels

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

    degree of feeling or judgment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     BorderSide
    -0.47
    addGap
    -0.45
    BeginContext
    -0.42
    InputBorder
    -0.40
     entrado
    -0.39
    انجليز
    -0.39
     otomatig
    -0.39
     թվական
    -0.38
     المعيارى
    -0.38
     fotográfico
    -0.38
    POSITIVE LOGITS
    asList
    0.54
    TestFixture
    0.52
    sively
    0.50
    lessly
    0.49
    aneously
    0.49
    culously
    0.48
    ingly
    0.48
    newArrayList
    0.48
    xically
    0.47
    ously
    0.47
    Act Density 0.050%

    No Known Activations