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

    Neuronpedia

    INDEX
    Explanations

    words related to superpowers or exceptional abilities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to "super" as a prefix or descriptor

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Frie
    -0.76
     Rasm
    -0.72
    FFER
    -0.71
    nered
    -0.71
    Days
    -0.71
    gaard
    -0.70
    Dialogue
    -0.69
    oven
    -0.69
     Erd
    -0.69
    nell
    -0.68
    POSITIVE LOGITS
     super
    3.39
    super
    2.45
     Super
    2.04
     SUPER
    2.04
    Super
    2.02
     supers
    1.54
     mega
    1.49
     ultra
    1.40
     superpower
    1.34
     uber
    1.33
    Act Density 0.018%

    No Known Activations