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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or names

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     bout
    -0.98
    ============
    -0.95
    xual
    -0.94
    ISO
    -0.93
    was
    -0.92
     EVs
    -0.92
     Gamble
    -0.91
    charg
    -0.89
    xon
    -0.89
    escal
    -0.89
    POSITIVE LOGITS
    atural
    1.57
    acle
    1.51
    acles
    1.48
    acular
    1.47
    opol
    1.42
    sburg
    1.39
    igans
    1.38
    icter
    1.37
    auts
    1.31
    esis
    1.27
    Act Density 1.220%

    No Known Activations