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

    Neuronpedia

    INDEX
    Explanations

    words related to social issues and activism

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    RAW
    -0.84
    DCS
    -0.70
    SPONSORED
    -0.70
    agonist
    -0.68
     Flavoring
    -0.67
     Lovecraft
    -0.67
    Defense
    -0.66
    puff
    -0.66
    warming
    -0.65
    clinton
    -0.64
    POSITIVE LOGITS
     alle
    0.98
     qui
    0.92
     mi
    0.91
     si
    0.88
     que
    0.87
     este
    0.86
     est
    0.85
    beit
    0.85
    cknowled
    0.85
     ja
    0.81
    Act Density 0.146%

    No Known Activations