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

    Neuronpedia

    INDEX
    Explanations

    the repetition of the word "thing" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     homeland
    -0.15
    ates
    -0.15
     ìĿĺíķ´
    -0.14
    ience
    -0.14
    .toHexString
    -0.14
    ynth
    -0.14
    lemn
    -0.14
    atak
    -0.14
    aub
    -0.14
    uhan
    -0.13
    POSITIVE LOGITS
    emic
    0.17
    ValuePair
    0.17
    665
    0.17
    λεκ
    0.15
    sembly
    0.15
    OfClass
    0.15
    779
    0.15
     дÑĢÑĥго
    0.15
    leri
    0.15
    osloven
    0.15
    Act Density 0.028%

    No Known Activations