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

    Neuronpedia

    INDEX
    Explanations

    terms related to degrees or levels of measurement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    izop
    -0.84
    zyb
    -0.69
     Selby
    -0.68
     Şi
    -0.68
     ['./
    -0.67
     Bub
    -0.67
    Vill
    -0.66
     muzik
    -0.66
     Zand
    -0.66
    ilirsiniz
    -0.65
    POSITIVE LOGITS
     degrees
    1.61
     Degrees
    1.56
     degree
    1.49
     Degree
    1.46
     DEGREE
    1.39
    Degree
    1.38
    Degrees
    1.38
    degrees
    1.34
    degree
    1.30
    GREES
    1.24
    Act Density 0.096%

    No Known Activations