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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, particularly names of people and organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tagHelperRunner
    -1.10
     disambiguazione
    -0.83
    帖最后由
    -0.82
     متعلقه
    -0.78
     nahilalakip
    -0.73
    URLException
    -0.72
    :✨
    -0.70
    Tikang
    -0.69
    InstrumentedTest
    -0.68
    новништво
    -0.68
    POSITIVE LOGITS
    ’
    0.77
     recently
    0.66
    '
    0.66
     originally
    0.60
     spent
    0.56
     certainly
    0.55
     has
    0.52
     meanwhile
    0.52
     also
    0.52
    ?
    0.51
    Act Density 0.425%

    No Known Activations