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

    Neuronpedia

    INDEX
    Explanations

    words associated with the concept of "value" or "worth."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     enclosed
    -0.14
    wert
    -0.14
    EMBER
    -0.14
    oui
    -0.14
     identical
    -0.14
    Ľå»º
    -0.13
    ноÑģÑĤ
    -0.13
    o
    -0.13
     Antar
    -0.13
     dress
    -0.13
    POSITIVE LOGITS
    udev
    0.28
    ude
    0.26
    unted
    0.24
    ULT
    0.21
     va
    0.20
    Va
    0.20
     Va
    0.19
    adin
    0.18
    leting
    0.17
    HING
    0.17
    Act Density 0.008%

    No Known Activations