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

    Neuronpedia

    INDEX
    Explanations

    references to authority figures or leaders in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    наÑĩе
    -0.16
    andum
    -0.15
    ì¦Ŀ
    -0.15
    ists
    -0.14
    ta
    -0.14
    nde
    -0.14
    oma
    -0.14
    ussen
    -0.14
    ogue
    -0.14
    .Gson
    -0.14
    POSITIVE LOGITS
    ships
    0.18
    erral
    0.15
    less
    0.15
    urdy
    0.15
    elerik
    0.15
    anova
    0.15
    ington
    0.15
    lich
    0.14
    Name
    0.14
    fires
    0.14
    Act Density 0.010%

    No Known Activations