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

    Neuronpedia

    INDEX
    Explanations

    updates and commentary in a news or blog article context

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     behav
    -0.53
    uve
    -0.52
    ube
    -0.52
     behavi
    -0.49
    emale
    -0.49
    ozo
    -0.46
    aband
    -0.46
    beh
    -0.45
     arrang
    -0.43
    ommel
    -0.42
    POSITIVE LOGITS
     Column
    0.53
     Simon
    0.47
     The
    0.47
     Signed
    0.47
     Pressure
    0.46
     Prelude
    0.46
     Scores
    0.45
    Statement
    0.44
     Released
    0.43
     Converted
    0.43
    Act Density 11.122%

    No Known Activations