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

    Neuronpedia

    INDEX
    Explanations

    repeated mentions of a specific character named Don

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

    Don followed by names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    queryInterface
    -0.62
    uxxxx
    -0.59
    urtz
    -0.56
    OGND
    -0.54
     Vieira
    -0.54
    RTGC
    -0.54
    日閲覧
    -0.53
    atalos
    -0.52
     Tapia
    -0.51
    TokenNameLPAREN
    -0.51
    POSITIVE LOGITS
     Don
    1.63
    Don
    1.47
     DON
    0.89
     Дон
    0.82
    Dono
    0.71
     Dons
    0.68
     Donald
    0.68
     Doesn
    0.65
     don
    0.63
     Dont
    0.63
    Act Density 0.005%

    No Known Activations