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

    Neuronpedia

    INDEX
    Explanations

    words related to domestic affairs or issues

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    uyomi
    -0.89
    uden
    -0.84
    umper
    -0.79
    */(
    -0.79
    SOURCE
    -0.75
    UMP
    -0.73
     GOODMAN
    -0.73
    displayText
    -0.71
    veyard
    -0.69
    ombs
    -0.68
    POSITIVE LOGITS
     Violence
    0.99
     violence
    0.97
     affairs
    0.94
     tranqu
    0.90
     appliances
    0.85
    violence
    0.81
     spying
    0.76
    estic
    0.76
     terrorism
    0.76
     abusers
    0.76
    Act Density 0.020%

    No Known Activations