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

    Neuronpedia

    INDEX
    Explanations

    mentions of characters in narratives

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

    character's role or attributes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    OGND
    -0.68
     nahilalakip
    -0.62
    adpleegd
    -0.57
     kiệm
    -0.54
    ConstraintMaker
    -0.54
    saraba
    -0.52
    SBATCH
    -0.51
     pinulongan
    -0.51
     uș
    -0.50
    دانشنامهٔ
    -0.48
    POSITIVE LOGITS
     Characters
    0.77
    Character
    0.70
     Character
    0.70
     character
    0.70
     characters
    0.70
    Characters
    0.69
     personagem
    0.68
    character
    0.68
     personaje
    0.67
    characters
    0.67
    Act Density 0.012%

    No Known Activations