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

    Neuronpedia

    INDEX
    Explanations

    references to research studies and findings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     AspNetCore
    -0.49
     ok
    -0.47
    ()?.
    -0.44
     okay
    -0.44
    Didn
    -0.43
    ]--;
    -0.42
    Does
    -0.42
    Przypisy
    -0.42
    ειτουργ
    -0.41
    吗
    -0.41
    POSITIVE LOGITS
     merupakan
    1.19
     is
    1.19
     adalah
    1.18
     là
    1.17
     является
    1.09
    是她
    1.02
    是最
    1.01
    のが
    1.01
     menjadi
    0.99
    是我
    0.99
    Act Density 0.585%

    No Known Activations