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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases indicating necessary conditions or exceptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    macros
    -0.17
     Angiospermae
    -0.15
    wert
    -0.15
    ucz
    -0.15
    quine
    -0.15
    oken
    -0.14
    ainless
    -0.14
     Nagar
    -0.14
    stdlib
    -0.14
    fo
    -0.14
    POSITIVE LOGITS
    onn
    0.16
    KK
    0.15
    ubit
    0.15
    acen
    0.14
    ublic
    0.14
    etas
    0.14
    UCH
    0.14
     Highlander
    0.14
    pson
    0.14
    itsu
    0.14
    Act Density 0.105%

    No Known Activations