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

    Neuronpedia

    INDEX
    Explanations

    indicators of resignation or departure announcements

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

    Signals the end of a turn or resignation

    np_acts-logits-general · gemini-2.0-flash

    end of resignation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GOTREF
    -0.40
     Matériau
    -0.38
    "]]
    -0.37
    nP
    -0.37
    cahontas
    -0.37
     frequenza
    -0.37
     kohdetta
    -0.36
    ]]);
    -0.36
     RAI
    -0.36
    ⏟
    -0.36
    POSITIVE LOGITS
     resignation
    0.68
     resign
    0.60
     resigning
    0.54
    resign
    0.54
     announced
    0.52
     farewell
    0.52
     renuncia
    0.50
     departure
    0.50
     quits
    0.49
     retiring
    0.48
    Act Density 0.162%

    No Known Activations