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

    Neuronpedia

    INDEX
    Explanations

    isolated periods or punctuation marks in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    noinspection
    -0.16
    ÙIJ
    -0.14
    696
    -0.14
    osaur
    -0.14
    hythm
    -0.14
    wart
    -0.13
    ïľ
    -0.13
    \<^
    -0.13
    asper
    -0.13
    ãĥ¼ãĥijãĥ¼
    -0.13
    POSITIVE LOGITS
     Tou
    0.19
     tou
    0.14
    ets
    0.14
    лаг
    0.14
    enna
    0.14
     Torch
    0.14
    estro
    0.14
    thesis
    0.14
    vil
    0.14
     Cra
    0.13
    Act Density 0.005%

    No Known Activations