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

    Neuronpedia

    INDEX
    Explanations

    phrases related to moral or ethical judgments

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing discontent or disagreement with societal norms and politics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    utenberg
    -0.77
    arently
    -0.72
    ciation
    -0.66
    lost
    -0.66
    imilar
    -0.66
    oaded
    -0.64
    iHUD
    -0.64
    ixt
    -0.63
    missing
    -0.62
     dizz
    -0.62
    POSITIVE LOGITS
     civilized
    1.30
     democracy
    1.23
     democracies
    1.07
     democratic
    1.00
     decency
    0.99
     Democracy
    0.97
     journalism
    0.91
     taxp
    0.90
     society
    0.87
     morals
    0.87
    Act Density 0.421%

    No Known Activations