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

    Neuronpedia

    INDEX
    Explanations

    felonies and related legal terms

    oai_token-act-pair · gpt-3.5-turbo

    references to felony charges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arin
    -0.84
    andr
    -0.84
    arity
    -0.83
    efficients
    -0.82
    tz
    -0.81
    aters
    -0.78
    ogi
    -0.77
    ators
    -0.76
    aeda
    -0.76
    arist
    -0.75
    POSITIVE LOGITS
     felony
    0.91
     probation
    0.86
     criminal
    0.85
     punishable
    0.84
     homicide
    0.82
     trespass
    0.79
     offenses
    0.79
     DUI
    0.78
     convictions
    0.78
     perjury
    0.77
    Act Density 0.016%

    No Known Activations