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

    Neuronpedia

    INDEX
    Explanations

    proper nouns like names of people, places, and organizations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ");
    -0.70
    tsy
    -0.62
    ").
    -0.61
    scl
    -0.58
    "/>
    -0.57
    vale
    -0.56
    ');
    -0.56
    ocalypse
    -0.56
    nih
    -0.55
    atile
    -0.55
    POSITIVE LOGITS
     meanwhile
    1.43
     however
    1.28
     moreover
    1.15
     alas
    0.98
     unsurprisingly
    0.93
     huh
    0.91
     incidentally
    0.89
     albeit
    0.86
     along
    0.86
     therefore
    0.86
    Act Density 1.764%

    No Known Activations