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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of “ultra” or variations of it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kö
    -0.17
    unami
    -0.15
    plier
    -0.15
    IPH
    -0.14
    .NewReader
    -0.14
    chars
    -0.14
    older
    -0.14
    бина
    -0.14
    maf
    -0.14
    .writer
    -0.14
    POSITIVE LOGITS
    aviolet
    0.26
     ultr
    0.24
    asonic
    0.24
     Violet
    0.22
    ason
    0.22
    fine
    0.21
     violet
    0.21
     Ultr
    0.21
     sonic
    0.20
    -ul
    0.19
    Act Density 0.005%

    No Known Activations