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

    Neuronpedia

    INDEX
    Explanations

    references to historical political figures, particularly Joseph Stalin

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Joseph Stalin

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lihood
    -1.12
    es
    -0.84
    manship
    -0.79
    LEY
    -0.78
    wich
    -0.75
    git
    -0.73
    wall
    -0.70
     Indies
    -0.70
    chool
    -0.70
    verning
    -0.68
    POSITIVE LOGITS
    itri
    0.85
    éĹĺ
    0.85
    arily
    0.81
    ategory
    0.75
    apse
    0.74
    umenthal
    0.73
    istically
    0.70
    ascus
    0.69
    ossibility
    0.69
    emetery
    0.69
    Act Density 0.027%

    No Known Activations