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

    Neuronpedia

    INDEX
    Explanations

    references to circles or circular shapes

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    EOUT
    -0.66
    s
    -0.65
    ',[
    -0.65
    YourGuide
    -0.63
     thiết
    -0.61
     Giang
    -0.61
    fitted
    -0.61
    لاثة
    -0.60
    wendi
    -0.59
     Boucher
    -0.59
    POSITIVE LOGITS
     CIRCLE
    1.42
     Circle
    1.30
    CIRCLE
    1.20
     Circles
    1.18
    Circles
    1.17
     circles
    1.16
     circle
    1.16
    Circle
    1.16
    circles
    1.09
     Krone
    1.01
    Act Density 0.004%

    No Known Activations