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

    Neuronpedia

    INDEX
    Explanations

    descriptions of criminal events involving robbery and violence

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    apps
    -0.72
    ernels
    -0.71
     Enemies
    -0.71
    aeda
    -0.68
     virtues
    -0.67
    çļ
    -0.67
     Dates
    -0.67
    âĶĢâĶĢâĶĢâĶĢ
    -0.66
     Gods
    -0.64
    headers
    -0.64
    POSITIVE LOGITS
     named
    1.08
     testified
    0.98
     drove
    0.95
     wrote
    0.94
     threw
    0.93
     alerted
    0.92
     approached
    0.90
     informs
    0.88
     told
    0.87
     complained
    0.87
    Act Density 0.209%

    No Known Activations