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

    Neuronpedia

    INDEX
    Explanations

    confirmations or affirmations, particularly the word "Indeed."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iske
    -0.16
    ustral
    -0.15
     Mana
    -0.14
    aña
    -0.14
    pty
    -0.14
    esson
    -0.14
     Burl
    -0.14
    pped
    -0.13
     meanwhile
    -0.13
    isma
    -0.13
    POSITIVE LOGITS
    ement
    0.17
    rana
    0.17
    forth
    0.17
    å¤ķ
    0.15
    marvin
    0.15
    mÄĽ
    0.15
    608
    0.15
    ixa
    0.14
    inges
    0.14
    arcer
    0.14
    Act Density 0.018%

    No Known Activations