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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and notation in equations

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Dey
    -0.52
     Che
    -0.50
     che
    -0.48
     himo
    -0.48
    kfree
    -0.47
     Att
    -0.47
    ah
    -0.46
    sema
    -0.46
     Al
    -0.45
    Deuter
    -0.45
    POSITIVE LOGITS
    SpringRunner
    0.81
    IMPORTED
    0.73
    PYX
    0.73
    picasso
    0.72
    ArgumentParser
    0.70
    onomía
    0.69
    AsStream
    0.69
     Administrativna
    0.68
     screwdriver
    0.67
     Agamemnon
    0.67
    Act Density 0.009%

    No Known Activations