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

    Neuronpedia

    INDEX
    Explanations

    references to authors, scholars, and academic affiliations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ازÙĩ
    -0.18
    ahat
    -0.16
    .ActionListener
    -0.16
    hazi
    -0.16
    ymoon
    -0.15
    cratch
    -0.15
    اباÙĨ
    -0.15
    ARSER
    -0.15
    ponent
    -0.14
    regor
    -0.14
    POSITIVE LOGITS
     Crafts
    0.19
     Autor
    0.17
    Autor
    0.17
     Econ
    0.17
     Obst
    0.16
     econ
    0.16
     styl
    0.16
    incer
    0.16
     Rebel
    0.15
    ermal
    0.15
    Act Density 0.025%

    No Known Activations