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

    Neuronpedia

    INDEX
    Explanations

    phrases related to politics and government

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ortium
    -0.72
     Beir
    -0.72
    thening
    -0.70
    inki
    -0.63
    fty
    -0.62
     optic
    -0.59
     Apost
    -0.56
     Shipping
    -0.56
    identally
    -0.55
    brow
    -0.55
    POSITIVE LOGITS
    wright
    1.20
    ername
    1.05
    plays
    1.04
    wr
    0.89
     played
    0.88
    GROUND
    0.88
     Piano
    0.86
     poker
    0.84
    testers
    0.84
    testing
    0.83
    Act Density 3.480%

    No Known Activations