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

    Neuronpedia

    INDEX
    Explanations

    transitional phrases and connectors in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -0.97
     "..\..\
    -0.76
    ]<<"
    -0.73
    ]--;
    -0.71
     "..\..\..\
    -0.70
     *>(
    -0.68
     AssemblyCompany
    -0.68
    ,:),
    -0.67
    *>(
    -0.65
    Portail
    -0.64
    POSITIVE LOGITS
     שוליים
    0.64
    HtmlAttribute
    0.56
    ArgumentParser
    0.53
    KommentareTeilen
    0.52
    Obrázky
    0.52
    Niels
    0.52
    RuleContext
    0.51
     quads
    0.50
    הערות
    0.49
     Unders
    0.48
    Act Density 0.367%

    No Known Activations