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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate sequencing or listing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    after "following"

    np_acts-logits-general · gemini-2.0-flash

    following introduces items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    XmlAccessorType
    -0.72
     vägen
    -0.68
     barnen
    -0.67
     nuages
    -0.67
     különböz
    -0.66
     démocr
    -0.64
    AddTagHelper
    -0.63
     början
    -0.63
    flink
    -0.63
     ddelweddau
    -0.62
    POSITIVE LOGITS
     types
    0.69
     kinds
    0.69
     items
    0.67
     three
    0.64
     two
    0.64
     four
    0.58
    OrNil
    0.57
    rungsseite
    0.57
     additional
    0.56
    ⬇️
    0.55
    Act Density 0.231%

    No Known Activations