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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific political affiliations

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     eternity
    -0.65
    ategory
    -0.64
    =~
    -0.64
    ILA
    -0.63
     Deadly
    -0.62
     Okawaru
    -0.61
     Teacher
    -0.61
     Rocks
    -0.60
     Lets
    -0.59
     Chimera
    -0.59
    POSITIVE LOGITS
     specialize
    1.05
     prefer
    1.04
     have
    1.02
     opted
    1.02
     succumbed
    1.02
     swear
    1.00
     agree
    0.99
     believe
    0.99
     aspire
    0.97
     participated
    0.95
    Act Density 0.290%

    No Known Activations