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

    Neuronpedia

    INDEX
    Explanations

    spatial orientation terms related to direction

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    databind
    -0.69
    acam
    -0.62
     far
    -0.59
    ahren
    -0.59
     al
    -0.57
     ante
    -0.57
     des
    -0.57
     Sea
    -0.57
     Dars
    -0.57
    hama
    -0.56
    POSITIVE LOGITS
     corners
    1.05
     corner
    1.01
     Ecke
    0.96
     Corner
    0.94
    Corner
    0.94
     Corners
    0.91
    BufferException
    0.91
    URLException
    0.90
     CORNER
    0.85
     quadrant
    0.85
    Act Density 0.011%

    No Known Activations