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

    Neuronpedia

    INDEX
    Explanations

    terms related to unlawful and improper actions, particularly in legal contexts

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

    unlawful or improper acts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    KommentareTeilen
    -0.47
     Haupts
    -0.38
     Tienes
    -0.38
    latego
    -0.37
     Portanto
    -0.37
     provas
    -0.37
    {}",
    -0.37
    — 
    -0.36
     batalla
    -0.35
     einiges
    -0.35
    POSITIVE LOGITS
     unauthorized
    0.77
    unauthorized
    0.68
     unlawful
    0.67
     unwanted
    0.66
     unauthorised
    0.65
     Unauthorized
    0.62
     illegal
    0.60
     unlawfully
    0.60
     involuntary
    0.60
     unintended
    0.60
    Act Density 0.062%

    No Known Activations