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

    Neuronpedia

    INDEX
    Explanations

    words related to political processes, such as legislation, voting, ratification, and submission to different governmental bodies

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     Reincarnated
    -0.79
     scam
    -0.73
     faked
    -0.72
     befriend
    -0.70
     kidnapped
    -0.70
    Born
    -0.70
     horr
    -0.69
     wrongly
    -0.68
     stealing
    -0.67
     kidnap
    -0.67
    POSITIVE LOGITS
     final
    1.21
     recommendations
    1.16
     deliberations
    1.13
     ratification
    1.12
     hearings
    1.09
     finalized
    1.08
     submissions
    0.99
     approval
    0.99
     legislative
    0.98
     amendments
    0.98
    Act Density 0.503%

    No Known Activations