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

    Neuronpedia

    INDEX
    Explanations

    words related to societal issues and government actions

    oai_token-act-pair · gpt-3.5-turbo

    calls to action and reflections on societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    )|
    -0.63
     ®
    -0.63
    Below
    -0.59
     cous
    -0.55
    apps
    -0.53
     Below
    -0.53
    iciary
    -0.52
     Annotations
    -0.52
    usage
    -0.51
    modified
    -0.51
    POSITIVE LOGITS
     even
    0.75
     also
    0.71
     likewise
    0.66
     EVEN
    0.65
     goddamn
    0.62
    Ŀ
    0.61
    Ļ½
    0.61
     drown
    0.59
     Lindsey
    0.57
     enough
    0.55
    Act Density 0.457%

    No Known Activations