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

    Neuronpedia

    INDEX
    Explanations

    terms related to criminal convictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    being convicted

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Utara
    -0.50
     Baum
    -0.49
    Air
    -0.49
     Luar
    -0.48
    Else
    -0.48
     uș
    -0.48
     Hauses
    -0.48
     Champlain
    -0.47
     look
    -0.47
     Meadow
    -0.47
    POSITIVE LOGITS
     convicted
    1.64
     conviction
    1.10
     convict
    1.09
     convictions
    1.08
     convic
    0.99
     convicts
    0.94
     guilty
    0.75
     Conv
    0.72
    guilty
    0.66
     Guilty
    0.64
    Act Density 0.015%

    No Known Activations