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

    Neuronpedia

    INDEX
    Explanations

    alphabetic and linguistic elements related to writing systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    holm
    -0.17
    ugins
    -0.17
    indy
    -0.16
    ocha
    -0.15
     Lens
    -0.15
    oly
    -0.15
    252
    -0.14
    ầm
    -0.14
    uhl
    -0.14
     Tor
    -0.14
    POSITIVE LOGITS
     actionTypes
    0.14
    .isSuccessful
    0.14
     дÑĸй
    0.14
    ENTIAL
    0.14
    atform
    0.14
    EMP
    0.14
    Writes
    0.14
    طار
    0.14
     ActionTypes
    0.13
     Downs
    0.13
    Act Density 0.019%

    No Known Activations