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

    Neuronpedia

    INDEX
    Explanations

    references to political entities and governmental organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ometimes
    -0.86
    nob
    -0.75
    hops
    -0.72
    hots
    -0.71
     [];
    -0.64
    esters
    -0.64
     horr
    -0.63
    bnb
    -0.62
    urus
    -0.61
    rupulous
    -0.61
    POSITIVE LOGITS
    wide
    0.94
    's
    0.88
     residency
    0.79
     presidency
    0.76
     involvement
    0.72
     anthem
    0.72
     Handbook
    0.72
     salute
    0.69
     seal
    0.66
     authorization
    0.66
    Act Density 0.288%

    No Known Activations