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

    Neuronpedia

    INDEX
    Explanations

    specific structural or relational tokens that indicate the beginning or end of segments in a technical or formal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    非常的
    -1.09
    Whilst
    -0.94
     diatas
    -0.93
     dimana
    -0.91
     içerisinde
    -0.90
     Whilst
    -0.90
     coté
    -0.86
    很多的
    -0.85
     whilst
    -0.82
     posiada
    -0.81
    POSITIVE LOGITS
     freilich
    1.20
    WebElementEntity
    0.89
     guère
    0.78
     едва
    0.78
     :
    0.77
     offenbar
    0.75
    refour
    0.74
     "'");
    0.74
     voilà
    0.73
    extAlignment
    0.72
    Act Density 1.630%

    No Known Activations