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

    Neuronpedia

    INDEX
    Explanations

    words related to ownership and responsibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elt
    -0.18
    ullet
    -0.16
    eli
    -0.15
    utar
    -0.14
    898
    -0.14
     Sv
    -0.14
     tol
    -0.14
    tero
    -0.14
     Sor
    -0.14
     cod
    -0.13
    POSITIVE LOGITS
    antis
    0.20
    byt
    0.19
    TRS
    0.16
    بÙĪد
    0.16
    ÃŃnh
    0.15
    PUTE
    0.15
    idot
    0.15
    uddle
    0.14
    маÑĤи
    0.14
    lemn
    0.14
    Act Density 0.004%

    No Known Activations