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

    Neuronpedia

    INDEX
    Explanations

    references to authors or contributors in a publication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uge
    -0.18
    ello
    -0.17
    unt
    -0.17
    ansa
    -0.17
     subur
    -0.17
    annes
    -0.17
    orr
    -0.16
    itch
    -0.15
    ühr
    -0.15
    entai
    -0.15
    POSITIVE LOGITS
    viz
    0.20
    allet
    0.18
    aims
    0.17
    rade
    0.16
    rus
    0.16
    inkle
    0.16
    ulse
    0.15
    ruby
    0.15
    uy
    0.15
    yy
    0.15
    Act Density 0.037%

    No Known Activations