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

    Neuronpedia

    INDEX
    Explanations

    names of individuals or specific entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Kira
    -0.78
     petal
    -0.73
     Hirst
    -0.73
    ValueMap
    -0.73
     décret
    -0.73
     Sheeran
    -0.71
    cipar
    -0.71
     Mero
    -0.70
    hift
    -0.68
     Wilma
    -0.68
    POSITIVE LOGITS
     LOU
    1.16
     DOU
    1.13
     Sou
    1.13
    hou
    1.11
     Rou
    1.08
    DOU
    1.06
     gou
    1.05
    ou
    1.05
     Cou
    1.05
     Hou
    1.04
    Act Density 0.276%

    No Known Activations