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

    Neuronpedia

    INDEX
    Explanations

    hyperlinks of news articles or stories to share

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    isphere
    -1.04
    anooga
    -1.04
    ressor
    -1.03
    Ĥİ
    -0.98
    escal
    -0.97
    inois
    -0.96
    iland
    -0.95
    rals
    -0.94
    ierrez
    -0.94
    iciency
    -0.93
    POSITIVE LOGITS
    201
    1.40
    149
    1.28
    139
    1.27
    /#
    1.25
    449
    1.24
    245
    1.24
    146
    1.24
    159
    1.23
    646
    1.23
    145
    1.22
    Act Density 1.132%

    No Known Activations