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

    Neuronpedia

    INDEX
    Explanations

    variations and forms of the word "super."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     للاسماء
    -0.83
    Vidite
    -0.81
    PreferredItem
    -0.77
     kaynağından
    -0.77
    Jog
    -0.75
    ItemBackground
    -0.74
    uParam
    -0.73
    }")]
    -0.72
    IVEREF
    -0.71
    .*")]
    -0.71
    POSITIVE LOGITS
     super
    1.22
     SUPER
    1.21
    Super
    1.19
     Super
    1.19
    Supers
    1.10
     Supers
    1.06
    uper
    1.06
     supers
    1.05
    super
    1.05
    SUPER
    1.04
    Act Density 0.109%

    No Known Activations