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

    Neuronpedia

    INDEX
    Explanations

    numerical patterns in a particular format

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ezvous
    -0.76
    achus
    -0.73
    yang
    -0.69
    eering
    -0.68
    uler
    -0.67
    lings
    -0.67
    hold
    -0.66
    ifice
    -0.66
    lying
    -0.63
    BOOK
    -0.63
    POSITIVE LOGITS
     ILCS
    1.30
    00
    0.99
    «ĺ
    0.95
    mph
    0.88
     mph
    0.83
    CTV
    0.81
    317
    0.81
    %);
    0.80
    70
    0.80
    75
    0.80
    Act Density 0.119%

    No Known Activations