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

    Neuronpedia

    INDEX
    Explanations

    references to political topics and controversies, particularly mentioning individuals and policies

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ..................
    -0.73
    BT
    -0.69
    Bomb
    -0.68
    ÙIJ
    -0.67
    Spr
    -0.66
    EEE
    -0.64
    ð
    -0.63
    Õ
    -0.63
     Lauder
    -0.63
    SHA
    -0.62
    POSITIVE LOGITS
     own
    1.01
     biggest
    1.00
     youngest
    0.99
     inability
    0.98
     oldest
    0.98
     successor
    0.98
     eldest
    0.95
     newest
    0.94
     motto
    0.93
     reputation
    0.91
    Act Density 0.134%

    No Known Activations