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

    Neuronpedia

    INDEX
    Explanations

    references to sacred or religious themes

    oai_token-act-pair · gpt-3.5-turbo

    references to sacrilege or sacrificial concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Roosevelt
    -0.67
     onward
    -0.64
     Wonderland
    -0.63
     Clarkson
    -0.63
     Sutherland
    -0.62
    DonaldTrump
    -0.62
     Sawyer
    -0.62
    ocating
    -0.62
    ously
    -0.62
     onwards
    -0.62
    POSITIVE LOGITS
    char
    1.26
    rifice
    1.18
    rament
    1.15
    het
    1.09
    ros
    1.07
    rast
    1.06
    hem
    1.03
    entric
    1.03
    hemy
    1.02
    onduct
    1.01
    Act Density 0.053%

    No Known Activations