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

    Neuronpedia

    INDEX
    Explanations

    information related to criminal activities such as theft, shoplifting, home invasion, and firearms offenses

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    intent
    -0.59
    ictional
    -0.58
     Subtle
    -0.57
    eday
    -0.57
    ========
    -0.56
    otomy
    -0.56
     Measure
    -0.55
     torch
    -0.55
     satire
    -0.54
     Proposition
    -0.53
    POSITIVE LOGITS
     said
    1.19
    said
    1.05
     says
    1.03
     Says
    0.94
     wrote
    0.89
     SAY
    0.87
     explained
    0.84
     argues
    0.84
     told
    0.83
     argued
    0.83
    Act Density 0.421%

    No Known Activations