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

    Neuronpedia

    INDEX
    Explanations

    references to numerical data and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    632
    -0.17
     Leader
    -0.15
    rium
    -0.14
    iques
    -0.14
    mentor
    -0.14
    маз
    -0.14
    osl
    -0.14
    lime
    -0.14
    ¿
    -0.14
    772
    -0.14
    POSITIVE LOGITS
     Norris
    0.16
    stoff
    0.15
    EventListener
    0.14
    ستÙĩ
    0.14
    tails
    0.14
     Hib
    0.14
     FindObjectOfType
    0.13
    lops
    0.13
    ibilidade
    0.13
     pack
    0.13
    Act Density 0.284%

    No Known Activations