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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "highlight" and its variations in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ehler
    -0.18
     Erk
    -0.15
    jac
    -0.15
    ugh
    -0.15
    aggi
    -0.14
    osti
    -0.14
    خاÙĨÙĩ
    -0.14
    uve
    -0.14
    åĿĬ
    -0.14
    astr
    -0.13
    POSITIVE LOGITS
    άÏĤ
    0.15
    bread
    0.15
    ened
    0.15
    íĮħ
    0.14
    799
    0.14
     Division
    0.14
    ãĥ¥
    0.14
    NewLabel
    0.14
    elsea
    0.13
    fait
    0.13
    Act Density 0.019%

    No Known Activations