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

    Neuronpedia

    INDEX
    Explanations

    specific punctuation and formatting elements in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .tc
    -0.14
    utra
    -0.14
    pyx
    -0.14
    æĺ¨
    -0.14
    unks
    -0.14
    estination
    -0.14
    \Id
    -0.14
    ycler
    -0.13
    ubo
    -0.13
    idente
    -0.13
    POSITIVE LOGITS
     don
    0.21
     Plus
    0.19
    don
    0.18
     Alternatively
    0.18
     Afterwards
    0.18
    Alternatively
    0.17
    Plus
    0.17
    Don
    0.17
     Tip
    0.17
    oh
    0.16
    Act Density 0.125%

    No Known Activations