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

    Neuronpedia

    INDEX
    Explanations

    words related to societal issues and actions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to community, governance, and social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    REM
    -0.64
    DonaldTrump
    -0.61
    cture
    -0.60
    Eva
    -0.59
    ï¸
    -0.58
    Slot
    -0.57
    ibrary
    -0.57
    REE
    -0.57
    Greek
    -0.57
     Franch
    -0.55
    POSITIVE LOGITS
     thereof
    1.28
     alike
    1.05
     thereto
    0.97
     accompanying
    0.93
     therein
    0.93
     accordingly
    0.87
     respectively
    0.86
     consequ
    0.78
     thereafter
    0.77
     resultant
    0.76
    Act Density 0.481%

    No Known Activations