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

    Neuronpedia

    INDEX
    Explanations

    phrases related to superhuman abilities or qualities

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "super."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     casualty
    -0.75
     RF
    -0.68
     Jays
    -0.67
     Dres
    -0.67
     DPR
    -0.62
     burned
    -0.62
     rounded
    -0.61
     FG
    -0.61
     drip
    -0.60
     empt
    -0.60
    POSITIVE LOGITS
    super
    3.94
    Super
    2.68
     super
    1.80
     SUPER
    1.78
     Super
    1.57
    sup
    1.54
    SUP
    1.54
    uper
    1.47
    special
    1.23
    hyper
    1.15
    Act Density 0.011%

    No Known Activations