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

    Neuronpedia

    INDEX
    Explanations

    references to legal actions and financial transactions

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    é¾įå
    -0.54
    ourt
    -0.47
     Coup
    -0.46
     Hurricanes
    -0.46
    aldi
    -0.45
     Cancel
    -0.45
     Compos
    -0.44
    UFC
    -0.43
    ontent
    -0.43
    JM
    -0.43
    POSITIVE LOGITS
     staircase
    0.52
     shadowy
    0.48
     shimmer
    0.43
    aligned
    0.43
     flickering
    0.42
     twisting
    0.42
     beck
    0.42
    ¥ŀ
    0.41
    uyomi
    0.41
     goblins
    0.41
    Act Density 0.010%

    No Known Activations