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

    Neuronpedia

    INDEX
    Explanations

    references to degrees or levels of measurement

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

    degree of something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Timberlake
    -0.50
     Eisenberg
    -0.48
     Harrisburg
    -0.47
    lántico
    -0.45
     sindic
    -0.43
     retrovisor
    -0.43
     Winona
    -0.43
    Mandy
    -0.43
    Neben
    -0.42
    żyw
    -0.42
    POSITIVE LOGITS
     degree
    1.23
     Degree
    1.16
    degree
    1.14
    Degree
    1.12
     degrees
    1.11
     DEGREE
    1.09
     Degrees
    1.09
    degrees
    1.05
    Degrees
    1.00
     degré
    0.90
    Act Density 0.023%

    No Known Activations