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

    Neuronpedia

    INDEX
    Explanations

    mentions of characters in various contexts and discussions within the text

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

    character qualities and involvement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     adequacy
    -0.38
    stop
    -0.38
     nostru
    -0.36
     Neubau
    -0.35
     stance
    -0.35
    pagna
    -0.35
     визна
    -0.34
    ConstraintMaker
    -0.34
    hey
    -0.34
     Ausblick
    -0.34
    POSITIVE LOGITS
     characters
    1.61
     Characters
    1.57
    characters
    1.52
    Characters
    1.52
     CHARACTERS
    1.35
     personnages
    1.12
     personajes
    0.98
     personagens
    0.96
     personaggi
    0.94
    Personajes
    0.87
    Act Density 0.006%

    No Known Activations