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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political interference in elections

    oai_token-act-pair · gpt-3.5-turbo

    mentions of interference in elections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    \">
    -0.83
    illac
    -0.75
    uffer
    -0.73
    hani
    -0.72
    bryce
    -0.70
    OLD
    -0.66
    ItemThumbnailImage
    -0.65
    hoe
    -0.63
    heny
    -0.62
    olf
    -0.62
    POSITIVE LOGITS
     Serbia
    0.79
     Yugoslavia
    0.70
     materially
    0.67
     commerce
    0.67
     Myanmar
    0.66
     Russia
    0.66
     Rhodes
    0.65
     foreign
    0.64
    orea
    0.64
    ovo
    0.62
    Act Density 0.149%

    No Known Activations