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

    Neuronpedia

    INDEX
    Explanations

    phrases related to official statements and administrative communications

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

    Resignations, terminations, accusations, and disputes

    np_acts-logits-general · gemini-2.0-flash

    disciplinary proceedings, allegations, resignations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -0.69
     autorytatywna
    -0.63
    joyed
    -0.60
    expandindo
    -0.59
    новништво
    -0.57
     typelib
    -0.57
    perature
    -0.57
    JAKARTA
    -0.56
    Serviço
    -0.56
     ingenuity
    -0.55
    POSITIVE LOGITS
     disciplinary
    0.79
     allegations
    0.76
     accusations
    0.76
     disgruntled
    0.71
     severance
    0.70
     allegation
    0.69
     resignation
    0.67
     grievances
    0.64
    setVerticalGroup
    0.63
     dismissal
    0.62
    Act Density 0.560%

    No Known Activations