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

    Neuronpedia

    INDEX
    Explanations

    mentions or discussions related to civil liberties and rights

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    alin
    -0.51
    chrom
    -0.48
    wolf
    -0.47
    pull
    -0.47
    balls
    -0.46
    BALL
    -0.46
    ahon
    -0.45
     Reincarn
    -0.45
     fermentation
    -0.45
    jin
    -0.44
    POSITIVE LOGITS
     Liberties
    1.07
    parency
    0.61
     Union
    0.60
     Oversight
    0.58
     freedoms
    0.57
    atures
    0.55
    umbered
    0.55
     Accountability
    0.55
     ACLU
    0.54
    terness
    0.54
    Act Density 8.311%

    No Known Activations