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

    Neuronpedia

    INDEX
    Explanations

    indications of the start and end of blocks or sections within structured texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     finally
    -0.66
     TAMBÉM
    -0.57
     meanwhile
    -0.55
    ברים
    -0.54
     lastly
    -0.52
    đ
    -0.52
    hibernate
    -0.51
     Magdalene
    -0.50
    anglès
    -0.50
     whole
    -0.50
    POSITIVE LOGITS
    tagHelperRunner
    0.86
     يتيمه
    0.81
     ujednoznacz
    0.75
    GEBURTSDATUM
    0.67
     líqu
    0.65
     disambiguazione
    0.63
    }}_
    0.58
     otomatig
    0.55
     the
    0.54
    TagMode
    0.52
    Act Density 0.002%

    No Known Activations