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

    Neuronpedia

    INDEX
    Explanations

    geometric terms related to circles and radius measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     junctions
    -0.38
    warp
    -0.35
     wasted
    -0.35
    was
    -0.35
     begrü
    -0.35
    집
    -0.34
     genders
    -0.34
     Karl
    -0.34
     squander
    -0.34
    la
    -0.33
    POSITIVE LOGITS
     radius
    1.23
    Radius
    1.05
     radii
    1.03
    radius
    1.02
     Radius
    1.01
     RADIUS
    0.85
    RADIUS
    0.81
     diameter
    0.71
     radial
    0.66
    Radial
    0.65
    Act Density 0.623%

    No Known Activations