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

    Neuronpedia

    INDEX
    Explanations

    references to political administrations and policies

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     ILCS
    -0.76
    Ô
    -0.72
     Plate
    -0.71
    #$#$
    -0.68
     Mata
    -0.67
    ificial
    -0.62
    ostic
    -0.62
    actionDate
    -0.62
    vill
    -0.62
     Kor
    -0.61
    POSITIVE LOGITS
     officials
    0.89
     playbook
    0.83
     secretaries
    0.81
     appoint
    0.80
     helicop
    0.75
     policies
    0.75
     meddling
    0.75
     tasked
    0.75
    iets
    0.74
     administrations
    0.74
    Act Density 0.096%

    No Known Activations