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

    Neuronpedia

    INDEX
    Explanations

    words that denote emphasis or highlight the importance of a concept

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    PT
    -0.16
    ãĤīãģı
    -0.15
    اگ
    -0.15
     Rosenstein
    -0.14
    pte
    -0.14
    ắp
    -0.14
    encent
    -0.14
    èĬ
    -0.14
    ery
    -0.14
    isd
    -0.13
    POSITIVE LOGITS
    ãĥªãĥ³ãĤ°
    0.16
    iju
    0.15
    faction
    0.14
    447
    0.14
     Miles
    0.14
    fait
    0.14
    arsi
    0.14
    lassen
    0.14
    644
    0.13
     Mars
    0.13
    Act Density 0.011%

    No Known Activations