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

    Neuronpedia

    INDEX
    Explanations

    unusual and mysterious events or creatures

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    cussion
    -0.84
    vation
    -0.83
    payers
    -0.81
    igate
    -0.79
    apers
    -0.79
    inders
    -0.78
    agles
    -0.78
    amaru
    -0.77
    rators
    -0.77
    chen
    -0.75
    POSITIVE LOGITS
     occurrences
    1.04
    ly
    0.97
    ness
    0.94
     coincidence
    0.92
    worldly
    0.88
     twists
    0.88
    ities
    0.86
     twist
    0.85
    nesses
    0.81
     assortment
    0.81
    Act Density 10.943%

    No Known Activations