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

    Neuronpedia

    INDEX
    Explanations

    words associated with choices and advantages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cia
    -0.16
     вов
    -0.16
    ãĥĥãĤ°
    -0.15
    ilig
    -0.15
    ouve
    -0.15
    ropy
    -0.14
    æ¤į
    -0.14
    Å¡k
    -0.14
     extent
    -0.14
    uba
    -0.14
    POSITIVE LOGITS
    niest
    0.16
    ClientRect
    0.15
    lux
    0.15
    serial
    0.15
    itzer
    0.14
    824
    0.14
    iken
    0.14
    astes
    0.14
    uckle
    0.14
    ******/
    0.14
    Act Density 0.085%

    No Known Activations