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

    Neuronpedia

    INDEX
    Explanations

    affirmations or confirmations, often using the word "sure."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     toch
    -0.16
    aurus
    -0.15
    wort
    -0.15
    esson
    -0.14
    Ñĥз
    -0.14
    ÐIJТ
    -0.14
    isco
    -0.14
    onte
    -0.14
    ostringstream
    -0.14
    ille
    -0.13
    POSITIVE LOGITS
    esen
    0.15
    åķ¦
    0.15
    ARING
    0.15
    jte
    0.15
    igh
    0.15
     SOME
    0.14
    inel
    0.14
    Cad
    0.14
     techn
    0.14
    TURE
    0.14
    Act Density 0.046%

    No Known Activations