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

    Neuronpedia

    INDEX
    Explanations

    references to bans, suspensions, and rejections in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĮĢ
    -0.14
    åĪ»
    -0.14
    .cms
    -0.14
    lash
    -0.13
     Shed
    -0.13
    berger
    -0.13
    -counter
    -0.13
    oth
    -0.13
    DED
    -0.13
     decks
    -0.13
    POSITIVE LOGITS
     due
    0.37
    due
    0.35
     because
    0.34
    because
    0.32
    åĽłä¸º
    0.31
     wegen
    0.29
     بسبب
    0.28
    _due
    0.26
     debido
    0.26
    Due
    0.26
    Act Density 0.217%

    No Known Activations