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

    Neuronpedia

    INDEX
    Explanations

    document structure and format indicators

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    bootstrapcdn
    -1.10
     étoient
    -0.91
     avoient
    -0.90
     fédé
    -0.86
    منابع
    -0.82
     setuptools
    -0.82
     Cæsar
    -0.81
     strictest
    -0.80
    styleType
    -0.78
     ainfi
    -0.78
    POSITIVE LOGITS
     imp
    0.56
     бе
    0.55
     Beck
    0.54
     now
    0.51
     م
    0.50
     fact
    0.49
     Miss
    0.49
     Im
    0.49
    asu
    0.47
     The
    0.47
    Act Density 0.012%

    No Known Activations