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

    Neuronpedia

    INDEX
    Explanations

    themes related to social interactions and relationships among characters

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

    interesting people and characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Chriftian
    -0.57
     reaſon
    -0.55
     uſed
    -0.52
    principalColumn
    -0.52
     juſ
    -0.51
     ſever
    -0.50
    raulic
    -0.50
     ſta
    -0.50
     faſt
    -0.49
     purpoſe
    -0.48
    POSITIVE LOGITS
     characters
    1.59
    characters
    1.41
     Characters
    1.34
     personajes
    1.24
     character
    1.23
    Characters
    1.22
     CHARACTERS
    1.19
     personagens
    1.14
     personaggi
    1.09
     personaje
    1.08
    Act Density 0.055%

    No Known Activations