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

    Neuronpedia

    INDEX
    Explanations

    instances of punctuation or commas in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    öst
    -0.17
    nova
    -0.16
    ourd
    -0.14
    dk
    -0.14
    ावन
    -0.14
    伸
    -0.14
    mw
    -0.14
    igin
    -0.14
    yne
    -0.14
     Malone
    -0.13
    POSITIVE LOGITS
     Sez
    0.15
    KEN
    0.15
     Seah
    0.15
    ongan
    0.15
     thoroughly
    0.14
    oire
    0.14
    ackbar
    0.14
    idd
    0.13
    tern
    0.13
    uai
    0.13
    Act Density 0.068%

    No Known Activations