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

    Neuronpedia

    INDEX
    Explanations

    references to angles and geometric relationships involving angles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cuth
    -0.93
    __(/*!
    -0.77
     pranzo
    -0.77
     Hilde
    -0.75
    abestanden
    -0.73
    rmtree
    -0.72
     Ciò
    -0.71
    ="/"
    -0.70
     McCulloch
    -0.70
     Farmington
    -0.69
    POSITIVE LOGITS
     angles
    1.91
     angle
    1.86
     Angle
    1.79
     Angles
    1.75
    Angle
    1.65
     ANGLE
    1.62
    Angles
    1.58
    angle
    1.38
    angles
    1.33
    ANGLE
    1.27
    Act Density 0.132%

    No Known Activations