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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and quote indicators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oria
    -0.18
    ome
    -0.18
    hn
    -0.15
    aviest
    -0.15
     cr
    -0.15
    лад
    -0.14
    ht
    -0.14
    gan
    -0.14
     fair
    -0.14
    ille
    -0.14
    POSITIVE LOGITS
    illance
    0.17
    _tF
    0.16
    ccione
    0.15
    AGMA
    0.15
    ustum
    0.15
    usters
    0.14
    .OS
    0.14
    ายà¹ĥà¸Ļ
    0.14
    ãĥ©ãĤ¤ãĥ³
    0.13
    afone
    0.13
    Act Density 0.800%

    No Known Activations