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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and delimiters indicating functions or equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iterr
    -0.15
    smith
    -0.15
    uchar
    -0.15
    ç´ļ
    -0.14
    obot
    -0.14
     Suk
    -0.14
     obstruction
    -0.14
    ech
    -0.14
     buck
    -0.14
    forge
    -0.14
    POSITIVE LOGITS
    amines
    0.15
    ulled
    0.14
    owa
    0.14
     Alfred
    0.13
    avail
    0.13
    ell
    0.13
    owed
    0.13
    iffin
    0.13
    åĤĻ
    0.13
    apt
    0.13
    Act Density 0.049%

    No Known Activations