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

    Neuronpedia

    INDEX
    Explanations

    political and social statements made by public figures

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the rights or interests of the American public

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ortment
    -0.70
    tein
    -0.69
     Xuan
    -0.69
     Ops
    -0.68
    ourney
    -0.64
    iba
    -0.64
    hent
    -0.63
     Equip
    -0.63
    inet
    -0.63
     Staff
    -0.62
    POSITIVE LOGITS
     clam
    1.02
     overwhelmingly
    0.95
     electing
    0.93
     Vote
    0.92
     vote
    0.92
     revolt
    0.86
     ballots
    0.81
     voting
    0.78
     votes
    0.78
     elected
    0.76
    Act Density 0.484%

    No Known Activations