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

    Neuronpedia

    INDEX
    Explanations

    authorship indicators and attributions in texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    InjectAttribute
    -0.90
    <eos>
    -0.84
     CreateTagHelper
    -0.78
    MLLoader
    -0.73
    EndGlobalSection
    -0.73
    awtextra
    -0.70
     فريبيس
    -0.70
     mergeFrom
    -0.68
    }}}{\
    -0.68
     AssemblyProduct
    -0.68
    POSITIVE LOGITS
    0.90
    kadang
    0.46
    ↵↵
    0.44
    ​
    0.43
     Réponses
    0.40
    Article
    0.40
    revet
    0.39
    rašymas
    0.39
     excerpt
    0.39
    anglès
    0.38
    Act Density 0.314%

    No Known Activations