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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal agreements and government actions

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ados
    -0.78
     (#
    -0.73
    buster
    -0.71
    itars
    -0.71
    more
    -0.71
     without
    -0.70
    split
    -0.70
     followed
    -0.70
     according
    -0.69
    ="#
    -0.69
    POSITIVE LOGITS
     latter
    1.45
     slightest
    1.42
     aforementioned
    1.42
     same
    1.34
     likes
    1.32
     highest
    1.28
     dreaded
    1.21
     wearer
    1.21
     widest
    1.20
    ses
    1.19
    Act Density 3.959%

    No Known Activations