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

    Neuronpedia

    INDEX
    Explanations

    the word "glory"

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of glory

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    BOOK
    -0.90
    heter
    -0.76
    sense
    -0.71
    JUST
    -0.69
    chi
    -0.68
    VICE
    -0.67
     Sense
    -0.67
    smart
    -0.67
    Person
    -0.64
    ANY
    -0.63
    POSITIVE LOGITS
     glory
    1.33
     Glory
    1.02
    sburg
    0.86
    halla
    0.80
    ifully
    0.79
    oried
    0.78
    iership
    0.76
     Frieza
    0.76
     Trophy
    0.75
    atile
    0.75
    Act Density 0.010%

    No Known Activations