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

    Neuronpedia

    INDEX
    Explanations

    opinions and beliefs related to political figures and societal issues

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     laundering
    -0.80
     renovations
    -0.73
     scal
    -0.71
     Kafka
    -0.70
     wre
    -0.70
     graft
    -0.70
    RIP
    -0.69
     TTL
    -0.69
     Artemis
    -0.68
     Trilogy
    -0.68
    POSITIVE LOGITS
     respondents
    1.35
     polled
    1.31
     surveyed
    1.16
     Gallup
    1.14
     majorities
    1.12
     undecided
    1.11
     voters
    1.05
     Favor
    1.01
     respondent
    1.00
     Voters
    0.97
    Act Density 0.429%

    No Known Activations