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

    Neuronpedia

    INDEX
    Explanations

    phrases related to policy and social issues

    oai_token-act-pair · gpt-3.5-turbo

    references to economic and social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    interstitial
    -0.87
    çĶ°
    -0.86
    ''.
    -0.83
    Legend
    -0.74
    ĸļ
    -0.72
    ]."
    -0.70
    yssey
    -0.69
    SourceFile
    -0.68
     unfocusedRange
    -0.66
    Adult
    -0.66
    POSITIVE LOGITS
     democratically
    0.97
     coerc
    0.94
     harms
    0.92
     democracies
    0.86
     unpopular
    0.83
     impover
    0.81
     evils
    0.79
     oppress
    0.78
     inconven
    0.78
     trillions
    0.77
    Act Density 1.295%

    No Known Activations