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

    Neuronpedia

    INDEX
    Explanations

    words related to the concept of integration and incorporation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iyet
    -0.16
    eler
    -0.16
    indow
    -0.15
    ër
    -0.14
    etter
    -0.14
    adium
    -0.14
    etr
    -0.14
    ete
    -0.14
    .spi
    -0.14
    erne
    -0.13
    POSITIVE LOGITS
     into
    0.25
    Into
    0.20
     Into
    0.19
    into
    0.17
    tures
    0.16
    isine
    0.15
     vÃło
    0.15
    acf
    0.15
     Burl
    0.15
    rouch
    0.15
    Act Density 0.066%

    No Known Activations