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

    Neuronpedia

    INDEX
    Explanations

    words and suffixes related to concepts of knowledge, awareness, and existence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    s
    -0.19
    bers
    -0.19
    leta
    -0.18
    head
    -0.18
    ses
    -0.17
    ÏĤ
    -0.17
    ŀ
    -0.16
    heads
    -0.16
    ctor
    -0.16
    Ùĩ
    -0.16
    POSITIVE LOGITS
    emente
    0.32
    iation
    0.29
    iated
    0.28
    ials
    0.23
    itious
    0.20
    ech
    0.20
    zia
    0.19
    ennial
    0.19
    alist
    0.19
    ia
    0.19
    Act Density 0.235%

    No Known Activations