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

    Neuronpedia

    INDEX
    Explanations

    terms related to social issues and political concepts

    oai_token-act-pair · gpt-3.5-turbo

    references to familial and social structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     theirs
    -0.68
     colleagues
    -0.64
     compat
    -0.61
     tha
    -0.60
     commits
    -0.60
     another
    -0.60
     lia
    -0.58
     Germany
    -0.57
     yesterday
    -0.57
     accompl
    -0.56
    POSITIVE LOGITS
     afterlife
    1.11
    urgy
    1.11
    atre
    1.07
    ocracy
    1.03
     sexes
    0.97
    ocratic
    0.97
    oret
    0.95
     Quran
    0.88
    ater
    0.88
     arts
    0.88
    Act Density 0.607%

    No Known Activations