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

    Neuronpedia

    INDEX
    Explanations

    occurrences of syllables and phonetic patterns resembling "swo," "lo," and "bo."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Tham
    -0.18
    rots
    -0.17
    mates
    -0.16
    rian
    -0.15
    ness
    -0.15
    ru
    -0.15
    াà¦
    -0.15
    bib
    -0.15
    erd
    -0.15
     introductory
    -0.15
    POSITIVE LOGITS
    oking
    0.19
    ogle
    0.19
    cket
    0.18
    oling
    0.18
    xford
    0.18
    oop
    0.18
    yers
    0.18
    opers
    0.18
    oper
    0.18
    iler
    0.17
    Act Density 0.089%

    No Known Activations