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

    Neuronpedia

    INDEX
    Explanations

    information related to public opinion polls, including views on different topics and approval ratings of political figures

    oai_token-act-pair · gpt-3.5-turbo

    statistical data and public opinion metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    -0.69
     unwitting
    -0.69
     Panzer
    -0.63
    odder
    -0.62
    ãĤº
    -0.60
     playbook
    -0.60
    batch
    -0.60
     unsuspecting
    -0.60
     batches
    -0.59
     hiber
    -0.59
    POSITIVE LOGITS
     favorably
    1.05
     negatively
    0.90
     unfavorable
    0.85
     compared
    0.82
     favorable
    0.80
     overall
    0.78
     positively
    0.77
    avorable
    0.76
    government
    0.74
     moderately
    0.70
    Act Density 0.359%

    No Known Activations