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

    Neuronpedia

    INDEX
    Explanations

    parentheses and related formatting in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ensch
    -0.19
    Ø°
    -0.17
    359
    -0.16
    891
    -0.15
    alendar
    -0.15
     Aç
    -0.14
    gia
    -0.14
    bnb
    -0.14
    ALSE
    -0.14
    563
    -0.14
    POSITIVE LOGITS
    utas
    0.18
    åĬ¡
    0.14
    ÄĽj
    0.14
     Sta
    0.14
    iber
    0.14
    .ribbon
    0.13
    paralle
    0.13
    Äįit
    0.13
    çĭ¬
    0.13
    ovaly
    0.13
    Act Density 0.037%

    No Known Activations