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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating concern or critique

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicative of ethical concerns and debates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Flo
    -0.62
     unlucky
    -0.62
    \<
    -0.62
    ById
    -0.59
    devices
    -0.59
    nin
    -0.58
     ILCS
    -0.57
    nown
    -0.57
    holes
    -0.57
    hops
    -0.57
    POSITIVE LOGITS
     overturn
    0.67
     regulating
    0.64
     democracy
    0.62
    osate
    0.58
     governance
    0.58
     determining
    0.58
     preserving
    0.57
     protecting
    0.57
     upholding
    0.56
     procedural
    0.56
    Act Density 1.598%

    No Known Activations