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

    Neuronpedia

    INDEX
    Explanations

    mentions of political parties

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Grizz
    -0.78
    alam
    -0.74
     Kard
    -0.73
     Wheat
    -0.69
    angelo
    -0.68
     Drake
    -0.67
     Hoo
    -0.67
     Maw
    -0.67
     Stafford
    -0.67
     Dull
    -0.67
    POSITIVE LOGITS
     affiliation
    1.16
     affili
    1.03
     leaders
    0.92
     leadership
    0.90
    Leader
    0.90
    leader
    0.89
     leader
    0.87
    arians
    0.86
     faithful
    0.84
    goers
    0.84
    Act Density 0.039%

    No Known Activations