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

    Neuronpedia

    INDEX
    Explanations

    punctuations and list formatting in textual data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.97
     '\\;'
    -0.87
    fromnode
    -0.71
     الرياضيه
    -0.70
     endregion
    -0.70
     tfsi
    -0.68
    webElementXpaths
    -0.66
    ModelAdmin
    -0.65
     Jérusalem
    -0.65
     Chwiliwch
    -0.65
    POSITIVE LOGITS
     Inc
    0.59
    kun
    0.55
     né
    0.54
    _,
    0.54
     Duf
    0.52
    inc
    0.51
    dot
    0.50
    *,
    0.50
     huh
    0.50
    cida
    0.50
    Act Density 0.458%

    No Known Activations