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

    Neuronpedia

    INDEX
    Explanations

    information about ownership or control

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating ownership or control by entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    asy
    -1.00
    raq
    -0.94
    omsky
    -0.76
    gradation
    -0.75
    enery
    -0.75
    iasm
    -0.74
    bia
    -0.73
    itiveness
    -0.72
    uder
    -0.71
    ilipp
    -0.70
    POSITIVE LOGITS
     virtue
    0.90
     foreigners
    0.83
     Dame
    0.74
     Georgian
    0.73
     Dmitry
    0.70
     Dominion
    0.70
     fiat
    0.70
     parliament
    0.69
    eers
    0.68
     Venezuelan
    0.68
    Act Density 0.119%

    No Known Activations