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

    Neuronpedia

    INDEX
    Explanations

    words related to political and economic topics

    oai_token-act-pair · gpt-3.5-turbo

    references to political or governmental issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    outs
    -0.74
    pool
    -0.70
    dale
    -0.70
     Osw
    -0.69
     TMZ
    -0.68
    RANT
    -0.68
     whence
    -0.68
    cases
    -0.67
    dra
    -0.65
    plane
    -0.64
    POSITIVE LOGITS
    ipolar
    0.68
    âĸ¬âĸ¬
    0.67
     princip
    0.67
     Proced
    0.66
     qualitative
    0.66
    urated
    0.65
    accompan
    0.64
     Principle
    0.63
    ass
    0.63
    ocative
    0.62
    Act Density 0.000%

    No Known Activations