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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and specific terms related to names and titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eview
    -0.09
    hled
    -0.08
    ï¼Ĭ
    -0.08
    #ad
    -0.08
     tuz
    -0.08
    .EventType
    -0.08
    quelle
    -0.07
    ctp
    -0.07
    æĪIJ人
    -0.07
     èµ·
    -0.07
    POSITIVE LOGITS
    amp
    0.06
    leet
    0.06
    âĢ¦↵
    0.06
    z
    0.06
    enade
    0.06
    820
    0.05
    âĢ¦”
    0.05
    lass
    0.05
    ijIJ
    0.05
    PARATOR
    0.05
    Act Density 0.023%

    No Known Activations