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

    Neuronpedia

    INDEX
    Explanations

    political and social issues or topics

    oai_token-act-pair · gpt-3.5-turbo

    key policy issues and debates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iren
    -0.68
    alan
    -0.67
    agues
    -0.65
    Laughs
    -0.65
    olo
    -0.64
    ells
    -0.63
    ideshow
    -0.63
    nova
    -0.63
    姫
    -0.63
    ëĭ
    -0.63
    POSITIVE LOGITS
     whether
    1.41
    whether
    1.15
     how
    1.12
     taxation
    1.02
     affordability
    1.01
     finances
    0.98
     issues
    0.96
     economics
    0.96
     sustainability
    0.95
     why
    0.93
    Act Density 0.414%

    No Known Activations