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

    Neuronpedia

    INDEX
    Explanations

    details related to criminal activities and police actions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Historically
    -0.82
    uably
    -0.80
     historically
    -0.80
     Inher
    -0.78
     Nobel
    -0.74
     intrinsically
    -0.73
     globally
    -0.72
     domestically
    -0.70
     traditionally
    -0.70
     bestselling
    -0.69
    POSITIVE LOGITS
     proceeded
    1.11
     hurried
    1.08
    upon
    1.07
     panicked
    1.04
     calmed
    1.01
     promptly
    1.01
     startled
    0.99
     yelled
    0.99
     grabbed
    0.98
     escorted
    0.96
    Act Density 3.139%

    No Known Activations