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

    Neuronpedia

    INDEX
    Explanations

    numbers indicating either specific scores or quantities

    oai_token-act-pair · gpt-3.5-turbo

    numerical values indicating ages or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     lawy
    -0.72
    ezvous
    -0.69
    achus
    -0.68
    yang
    -0.66
    ettings
    -0.65
    ellation
    -0.63
    lace
    -0.59
    gets
    -0.59
    yi
    -0.58
    rouch
    -0.58
    POSITIVE LOGITS
    00
    1.26
    %
    1.15
     ILCS
    1.06
     percent
    1.05
    %-
    1.05
    70
    0.99
    80
    0.96
    %,
    0.96
    mph
    0.96
    percent
    0.95
    Act Density 0.114%

    No Known Activations