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

    Neuronpedia

    INDEX
    Explanations

    mathematical equations and expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vincia
    -0.16
    amarin
    -0.15
    anten
    -0.14
    ults
    -0.14
    usat
    -0.14
    à¸ķร
    -0.14
    felt
    -0.14
     Tray
    -0.14
    _remain
    -0.14
    /Core
    -0.13
    POSITIVE LOGITS
    ãģĭãģª
    0.16
    ãĥ³ãĤ¸
    0.15
    è¡¡
    0.15
    isy
    0.15
    IRON
    0.14
    osy
    0.14
    ãĤ¦ãĥ³
    0.14
    kul
    0.14
    .Persistent
    0.14
     Rhodes
    0.13
    Act Density 0.035%

    No Known Activations