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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "So" and its variations, indicating a conversational or transitional aspect in the text

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

    conversation starter "so"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    WebElementEntity
    -0.66
    LookAnd
    -0.59
    HasForeignKey
    -0.58
     Lightboxes
    -0.52
     AssemblyCulture
    -0.52
     kasarigan
    -0.52
    queryInterface
    -0.51
    aarrggbb
    -0.50
    Ӕ
    -0.49
     presentarse
    -0.48
    POSITIVE LOGITS
     viewDidLoad
    0.46
    omor
    0.38
     teddy
    0.37
    endcsname
    0.37
    laughs
    0.37
    flug
    0.37
     Argument
    0.36
    fal
    0.36
    Literal
    0.36
     Fallout
    0.36
    Act Density 0.006%

    No Known Activations