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

    Neuronpedia

    INDEX
    Explanations

    references to Dirac or concepts related to Dirac's principles

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     jPanel
    -0.84
     Gos
    -0.66
    hus
    -0.66
    hen
    -0.65
     Ess
    -0.62
     ajust
    -0.62
    dessous
    -0.59
    Gos
    -0.59
     Kartoffeln
    -0.59
    
    -0.59
    POSITIVE LOGITS
     Dirac
    2.08
    irac
    1.48
     hivat
    0.85
     itſelf
    0.85
     Reichstag
    0.84
     himſelf
    0.83
     Efq
    0.82
     myſelf
    0.81
     Mohawk
    0.80
     Marac
    0.77
    Act Density 0.000%

    No Known Activations