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

    Neuronpedia

    INDEX
    Explanations

    sequences of characters resembling mathematical or programming syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    u
    -0.36
    l
    -0.35
    t
    -0.29
    p
    -0.23
    lint
    -0.22
    uw
    -0.22
    lil
    -0.21
    la
    -0.21
    uC
    -0.20
    lac
    -0.20
    POSITIVE LOGITS
    ubits
    0.32
    ubit
    0.32
    eu
    0.27
    eer
    0.26
    uries
    0.25
    oq
    0.25
    rcode
    0.24
    e
    0.23
    eel
    0.22
    o
    0.21
    Act Density 0.034%

    No Known Activations