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

    Neuronpedia

    INDEX
    Explanations

    mentions of legal convictions or charges

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "convicted" and related forms, indicating legal judgments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Uni
    -0.72
    feed
    -0.72
    osh
    -0.70
     Bubble
    -0.69
     Unle
    -0.69
    Mom
    -0.64
     Sparkle
    -0.63
    ope
    -0.62
    ost
    -0.61
    mid
    -0.60
    POSITIVE LOGITS
     convicted
    3.44
     convict
    2.05
     sentenced
    2.00
     acquitted
    1.93
     indicted
    1.91
     jailed
    1.89
     incarcerated
    1.67
     prosecuted
    1.67
     convictions
    1.66
     conviction
    1.55
    Act Density 0.016%

    No Known Activations