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

    Neuronpedia

    INDEX
    Explanations

    specific spellings and long vowel sounds in words

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    #
    -0.15
    ноз
    -0.15
    inand
    -0.15
    PERT
    -0.15
    ereum
    -0.14
     mastur
    -0.14
    LARI
    -0.14
    NER
    -0.14
    ÙĨز
    -0.14
    ýš
    -0.14
    POSITIVE LOGITS
     Aires
    0.17
    issance
    0.17
    esse
    0.16
    rients
    0.16
     rel
    0.15
     Sext
    0.15
     t
    0.15
    quist
    0.15
     perfect
    0.14
     x
    0.14
    Act Density 0.162%

    No Known Activations