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

    Neuronpedia

    INDEX
    Explanations

    references to social or political movements

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     Lama
    -0.71
    missions
    -0.69
    Deal
    -0.69
    ãĤ¨ãĥ«
    -0.68
    ewater
    -0.68
    bats
    -0.67
    neau
    -0.67
    oba
    -0.66
     golf
    -0.65
    nect
    -0.64
    POSITIVE LOGITS
     movements
    0.89
     spearheaded
    0.89
     movement
    0.88
     organizing
    0.87
     advocating
    0.84
     leader
    0.84
     founded
    0.83
     mobilized
    0.80
     anarchism
    0.80
     mobil
    0.80
    Act Density 0.045%

    No Known Activations