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

    Neuronpedia

    INDEX
    Explanations

    specific page numbers and citations in a written text

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     settled
    -0.67
     Clicker
    -0.67
     Chow
    -0.62
     awoke
    -0.62
     Stronghold
    -0.60
     Ronaldo
    -0.59
     Ragnarok
    -0.58
     settlement
    -0.58
     overnight
    -0.57
     wiser
    -0.57
    POSITIVE LOGITS
     seq
    0.99
    VII
    0.94
    xx
    0.91
     iii
    0.87
     139
    0.87
     409
    0.86
    xxx
    0.85
     371
    0.85
     412
    0.83
     149
    0.82
    Act Density 0.068%

    No Known Activations