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

    Neuronpedia

    INDEX
    Explanations

    legal terminology related to charges and penalties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     spir
    -0.16
    ress
    -0.16
     ne
    -0.15
    -0.15
    udas
    -0.15
    ucha
    -0.15
    isen
    -0.14
     Ki
    -0.14
    fs
    -0.14
    ongo
    -0.14
    POSITIVE LOGITS
     imprisonment
    0.23
     jail
    0.20
     maximum
    0.20
     Fine
    0.20
    Fine
    0.20
    maximum
    0.20
     fine
    0.19
    fine
    0.18
     prison
    0.18
    Maximum
    0.18
    Act Density 0.026%

    No Known Activations