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

    Neuronpedia

    INDEX
    Explanations

    contractions and possessive forms in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    دارÛĮ
    -0.15
    ican
    -0.15
    ´
    -0.14
    zelf
    -0.14
     Ministry
    -0.14
    íļĮìĿĺ
    -0.14
    asco
    -0.14
    .ua
    -0.13
    Dry
    -0.13
    ippo
    -0.13
    POSITIVE LOGITS
    egrate
    0.14
    ollar
    0.14
    expects
    0.14
    ör
    0.14
    à¸ı
    0.14
    eneg
    0.13
    -at
    0.13
     enf
    0.13
    omics
    0.13
    kul
    0.13
    Act Density 0.030%

    No Known Activations