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

    Neuronpedia

    INDEX
    Explanations

    references to disciplinary actions and procedures within a correctional context

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

    disciplinary actions and consequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     oamen
    -0.49
     ReactDOM
    -0.49
    DrawerToggle
    -0.48
    ########.
    -0.48
    accéder
    -0.47
     Geben
    -0.47
     Übergang
    -0.46
     glisser
    -0.46
    Demografía
    -0.46
     rique
    -0.46
    POSITIVE LOGITS
     disciplinary
    1.73
     Discipl
    1.34
    Discipl
    1.23
     discipl
    1.17
    disciplinary
    1.05
     DISCIP
    0.82
    discipl
    0.81
    cipl
    0.71
     Discipline
    0.71
     misconduct
    0.69
    Act Density 0.007%

    No Known Activations