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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases or questions indicating uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eel
    -0.14
    chap
    -0.14
    iye
    -0.14
    igne
    -0.14
     jet
    -0.14
    .mixin
    -0.14
    =__
    -0.14
    roman
    -0.13
    uj
    -0.13
    ãģĮãģĦ
    -0.13
    POSITIVE LOGITS
     Mun
    0.14
    /how
    0.14
    umann
    0.14
     Amateur
    0.14
     zda
    0.13
    fans
    0.13
     Bilg
    0.13
    694
    0.13
    readcr
    0.13
    oks
    0.13
    Act Density 0.047%

    No Known Activations