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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the concept of superiority or advancement

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "super."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ruciating
    -0.79
    Fi
    -0.78
    appointed
    -0.78
    semble
    -0.74
    told
    -0.73
    isol
    -0.73
     Cind
    -0.72
    pas
    -0.71
    equal
    -0.70
    fortune
    -0.68
    POSITIVE LOGITS
     supers
    2.36
     suppl
    0.90
     annex
    0.73
     matter
    0.69
     sup
    0.68
     grape
    0.67
     Napoleon
    0.66
    hyde
    0.64
     obsolete
    0.64
     trump
    0.64
    Act Density 0.005%

    No Known Activations