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

    Neuronpedia

    INDEX
    Explanations

    words related to legal issues or controversies

    oai_token-act-pair · gpt-3.5-turbo

    nouns and phrases related to various organizations, institutions, or entities involved in contemporary societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     actionGroup
    -0.76
    Frames
    -0.75
    ernels
    -0.75
    apps
    -0.69
     Events
    -0.68
     levers
    -0.68
    Apps
    -0.68
     Tags
    -0.67
     Pieces
    -0.67
     Languages
    -0.66
    POSITIVE LOGITS
     entitled
    0.88
     named
    0.88
     whose
    0.87
     called
    0.85
    whose
    0.82
     nicknamed
    0.80
     titled
    0.78
     dubbed
    0.76
     sentenced
    0.76
     collided
    0.74
    Act Density 0.434%

    No Known Activations