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

    Neuronpedia

    INDEX
    Explanations

    discussion or argumentative statements related to various topics such as politics, legislation, crime, and social issues

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    relative
    -0.91
    ogi
    -0.90
    anking
    -0.89
    ãģı
    -0.86
    cause
    -0.86
     creek
    -0.84
    NAME
    -0.83
    rig
    -0.83
    brance
    -0.82
    oxin
    -0.82
    POSITIVE LOGITS
     aptly
    0.89
     charism
    0.84
     paraph
    0.82
     Dragonbound
    0.82
     Slate
    0.82
     (),
    0.79
     Thumbnails
    0.78
     summar
    0.77
     bluntly
    0.77
     Sack
    0.76
    Act Density 0.572%

    No Known Activations