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

    Neuronpedia

    INDEX
    Explanations

    occurrences of events that are expected to happen

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     emphat
    -0.75
     vainly
    -0.74
     endeavouring
    -0.73
     unwarran
    -0.70
     indescri
    -0.69
     gaily
    -0.69
     Bartholo
    -0.69
     quitted
    -0.69
     increa
    -0.68
     withal
    -0.68
    POSITIVE LOGITS
     expected
    1.12
    expected
    1.05
     Expected
    1.03
     EXPECT
    1.02
     expect
    1.00
    Expected
    0.96
     expectations
    0.88
     expectation
    0.85
    expect
    0.85
     expects
    0.84
    Act Density 0.072%

    No Known Activations