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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of "split" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ist
    -0.16
    ensen
    -0.15
    ulin
    -0.15
    izes
    -0.15
    cedes
    -0.14
     alike
    -0.14
    909
    -0.14
    zet
    -0.14
     witness
    -0.14
    cent
    -0.14
    POSITIVE LOGITS
    reff
    0.17
    omba
    0.16
    tiler
    0.16
    ì²ľ
    0.16
    flen
    0.16
    obl
    0.15
     Split
    0.15
    bounce
    0.15
    txn
    0.15
    apter
    0.15
    Act Density 0.014%

    No Known Activations