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

    Neuronpedia

    INDEX
    Explanations

    definite articles and other similar grammatical markers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ipes
    -0.15
    fore
    -0.15
    imet
    -0.14
    earer
    -0.14
    tle
    -0.14
    aret
    -0.14
    oooooooo
    -0.14
    ccount
    -0.14
    ful
    -0.14
     CHARSET
    -0.14
    POSITIVE LOGITS
    acia
    0.16
    ála
    0.15
    aldi
    0.15
    ODB
    0.15
    ulis
    0.14
    ãģıãģł
    0.14
    ÑĢеÑħ
    0.14
    ortal
    0.13
    ocracy
    0.13
    kowski
    0.13
    Act Density 0.381%

    No Known Activations