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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns and references to individuals' actions or experiences

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

    First-person pronouns followed by auxiliary verbs

    np_acts-logits-general · gemini-2.0-flash

    she wasI hadI do

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AssemblyTitle
    -0.62
    alleros
    -0.60
    adura
    -0.59
    vair
    -0.59
    URATION
    -0.59
    ^(@)
    -0.59
    '):
    -0.59
    MLLoader
    -0.59
    outchouc
    -0.58
    äus
    -0.58
    POSITIVE LOGITS
    WireFormat
    0.55
    them
    0.54
     őket
    0.51
     HasFactory
    0.49
    BeginInit
    0.48
    HomeAsUpEnabled
    0.48
    RSpec
    0.47
    ValueStyle
    0.47
    pity
    0.47
     them
    0.47
    Act Density 0.282%

    No Known Activations