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

    Neuronpedia

    INDEX
    Explanations

    sequences of numbers or numerical values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    681
    -0.18
    ingles
    -0.15
    irect
    -0.15
    ero
    -0.15
    iji
    -0.14
    ernes
    -0.14
    xed
    -0.14
    pent
    -0.14
    ux
    -0.14
    uling
    -0.14
    POSITIVE LOGITS
    ìĸ´ëĤĺ
    0.15
    DESC
    0.14
     IOCTL
    0.14
    éķĩ
    0.14
     Mara
    0.14
    raki
    0.13
    .Timestamp
    0.13
    pery
    0.13
    crest
    0.13
     Ell
    0.13
    Act Density 0.010%

    No Known Activations