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

    Neuronpedia

    INDEX
    Explanations

    instances of punctuation or specific phrases that signal conversation or quotations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ìĨ
    -0.16
    ÐĴÐIJ
    -0.14
     gan
    -0.14
    ocation
    -0.14
    cent
    -0.14
    doll
    -0.14
    ÏĪη
    -0.13
    odnÃŃ
    -0.13
    anted
    -0.13
    /assert
    -0.13
    POSITIVE LOGITS
    heiten
    0.16
    prite
    0.15
    ptime
    0.14
     encodeURIComponent
    0.14
    erton
    0.14
    pt
    0.14
    .mybatis
    0.14
    éŀ
    0.14
    instein
    0.14
    tering
    0.14
    Act Density 0.141%

    No Known Activations