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

    Neuronpedia

    INDEX
    Explanations

    character names and their attributes in a narrative context

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

    Appears before quoted nicknames

    np_acts-logits-general · gemini-2.0-flash

    names with quotes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    HasAnnotation
    -0.57
    łgorzata
    -0.55
    iliar
    -0.54
     Mahabhar
    -0.53
    ########.
    -0.51
     wohnung
    -0.50
    льников
    -0.48
     habet
    -0.48
     Katharine
    -0.47
    unesse
    -0.47
    POSITIVE LOGITS
     Doc
    0.71
     Smit
    0.71
     Big
    0.70
     Fatty
    0.64
     fatty
    0.63
     Cookie
    0.63
     defaultstate
    0.63
    Big
    0.63
     Bubba
    0.62
    uzzy
    0.61
    Act Density 0.200%

    No Known Activations