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

    Neuronpedia

    INDEX
    Explanations

    expressions of personal feelings or experiences, often regarding preferences or emotions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    非常
    -0.52
     incredibly
    -0.51
     unbelievably
    -0.49
     merveille
    -0.48
    amssymb
    -0.46
    URIComponent
    -0.46
     assolu
    -0.45
     Krakowie
    -0.45
     fantastic
    -0.45
     absolument
    -0.44
    POSITIVE LOGITS
     дописавши
    0.89
     فريبيس
    0.84
     متعلقه
    0.81
     autorytatywna
    0.80
     nahilalakip
    0.80
    niająca
    0.78
    tagHelperRunner
    0.78
    GEBURTSDATUM
    0.77
    TypedDataSet
    0.75
    fjspx
    0.74
    Act Density 0.289%

    No Known Activations