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

    Neuronpedia

    INDEX
    Explanations

    mathematical notations and expressions related to norms and inequalities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agini
    -0.17
    luž
    -0.16
    oyal
    -0.15
     Prim
    -0.14
     Nej
    -0.14
    dra
    -0.14
    iasm
    -0.14
     prim
    -0.14
    erialization
    -0.14
    ÏģιÏĥ
    -0.14
    POSITIVE LOGITS
    vit
    0.16
    ÙĴس
    0.15
    oll
    0.14
    vu
    0.14
    .reserve
    0.13
    kits
    0.13
    amage
    0.13
    line
    0.13
    صت
    0.13
    ben
    0.13
    Act Density 0.040%

    No Known Activations