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

    Neuronpedia

    INDEX
    Explanations

    references to language learning opportunities and related contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    omer
    -0.16
    ez
    -0.15
    standen
    -0.15
    aky
    -0.15
    ynos
    -0.15
     Lady
    -0.14
     Sink
    -0.14
    éry
    -0.14
    ickers
    -0.14
    agt
    -0.14
    POSITIVE LOGITS
    åIJĦ
    0.22
     whichever
    0.20
     åIJĦ
    0.19
     Various
    0.17
    AdapterManager
    0.17
     various
    0.17
     ê°ģ
    0.17
    æŁIJ
    0.16
     respective
    0.16
     ÑĢазнÑĭÑħ
    0.15
    Act Density 0.207%

    No Known Activations