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

    Neuronpedia

    INDEX
    Explanations

    references to specific techniques or methods in a procedural context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cé
    -0.17
    adle
    -0.17
    #af
    -0.15
     luder
    -0.15
    iska
    -0.15
    arris
    -0.15
    _RAD
    -0.14
     âĹĦ
    -0.14
    ãĥªãĤ¹
    -0.14
    eniable
    -0.14
    POSITIVE LOGITS
    661
    0.16
    231
    0.16
    493
    0.15
    anni
    0.15
    ona
    0.15
    igroup
    0.14
    avors
    0.14
    Ãłng
    0.14
    ascript
    0.13
    unos
    0.13
    Act Density 0.005%

    No Known Activations