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

    Neuronpedia

    INDEX
    Explanations

    ways and methods of doing things

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     kuku
    -0.72
     obligator
    -0.72
     akut
    -0.67
     mits
    -0.67
     „,
    -0.67
     Minang
    -0.66
     ert
    -0.66
     Sén
    -0.66
     domina
    -0.65
    Lma
    -0.65
    POSITIVE LOGITS
     way
    0.99
    way
    0.93
     Way
    0.92
     ways
    0.90
    Way
    0.89
     WAY
    0.89
     Ways
    0.83
    ways
    0.83
     WAYS
    0.80
    WAY
    0.78
    Act Density 0.091%

    No Known Activations