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

    Neuronpedia

    INDEX
    Explanations

    references to moral principles and ethical considerations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ?;↵
    -0.17
     Morm
    -0.15
    avin
    -0.14
    евеÑĢ
    -0.14
     Roths
    -0.14
    èµı
    -0.14
    ãģ¨ãĤĤ
    -0.14
    isset
    -0.14
    ?");↵
    -0.13
    ãĥĪãĥª
    -0.13
    POSITIVE LOGITS
     internet
    0.35
    Internet
    0.31
     Internet
    0.30
    internet
    0.29
    Í
    0.24
    ;
    0.24
    äºĴèģĶç½ij
    0.23
     INTERN
    0.21
     semi
    0.20
    semi
    0.19
    Act Density 0.047%

    No Known Activations