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

    Neuronpedia

    INDEX
    Explanations

    names or terms related to legal or official positions

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Magna Carta" and its variations in historical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãģį
    -1.00
    OPLE
    -0.83
     Rockefeller
    -0.65
     kHz
    -0.65
    INGTON
    -0.63
    éĹĺ
    -0.63
     Hurricanes
    -0.63
     Vaugh
    -0.62
     wart
    -0.62
    ãģ¯
    -0.61
    POSITIVE LOGITS
    istrate
    1.49
    istrates
    1.47
    azines
    1.33
    netic
    1.24
    nesium
    1.24
    ikarp
    1.23
    ento
    1.15
    enta
    1.11
    ificent
    1.08
    pie
    1.08
    Act Density 0.020%

    No Known Activations