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

    Neuronpedia

    INDEX
    Explanations

    terms related to politics, legal systems, and governance

    oai_token-act-pair · gpt-3.5-turbo

    references to common concepts or ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enda
    -0.82
    asus
    -0.80
    agate
    -0.77
    gur
    -0.74
    eki
    -0.74
    otos
    -0.73
    endas
    -0.73
    apo
    -0.73
    ega
    -0.72
    usalem
    -0.70
    POSITIVE LOGITS
    wealth
    1.41
    alities
    1.06
     ancestor
    0.99
     denomin
    0.98
    ensical
    0.96
    places
    0.96
    ality
    0.91
     decency
    0.81
    place
    0.81
     occurrence
    0.78
    Act Density 0.022%

    No Known Activations