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

    Neuronpedia

    INDEX
    Explanations

    references to specific scientific studies or examples in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    izza
    -0.16
    andro
    -0.16
    deaux
    -0.16
    Äįel
    -0.15
    ivec
    -0.15
     adulte
    -0.15
     ↵↵
    -0.15
    inos
    -0.15
    nict
    -0.14
    actionDate
    -0.14
    POSITIVE LOGITS
    itsu
    0.18
    ãĤ¿ãĥ¼
    0.16
    enson
    0.15
     Exiting
    0.14
    lyn
    0.14
    PERT
    0.14
    ensen
    0.14
    ias
    0.14
    lymp
    0.14
    918
    0.14
    Act Density 0.018%

    No Known Activations