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

    Neuronpedia

    INDEX
    Explanations

    the frequency of the word "Johnson" in the text

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    es
    -0.73
     Sche
    -0.69
     Cale
    -0.68
    times
    -0.66
    ü
    -0.66
     scenes
    -0.65
    клопе
    -0.65
     lou
    -0.64
     Vla
    -0.64
     Beres
    -0.64
    POSITIVE LOGITS
     Johnson
    1.92
     johnson
    1.78
     JOHNSON
    1.77
    Johnson
    1.77
    NSON
    1.70
    johnson
    1.55
    JOH
    1.21
     Jonson
    1.06
    ValueStyle
    1.04
    nson
    1.02
    Act Density 0.004%

    No Known Activations