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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political and social topics

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate significant ongoing political discussions or conflicts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isode
    -0.84
    iple
    -0.73
    ibo
    -0.72
    ãĤ£
    -0.71
    iton
    -0.71
    laughs
    -0.70
    ãģł
    -0.69
    cellent
    -0.69
    thur
    -0.67
    orem
    -0.67
    POSITIVE LOGITS
     albeit
    0.96
     lest
    0.93
     including
    0.87
     policymakers
    0.87
     prompting
    0.86
     namely
    0.85
     though
    0.84
     citing
    0.84
     analysts
    0.83
     overshadow
    0.81
    Act Density 0.694%

    No Known Activations