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

    Neuronpedia

    INDEX
    Explanations

    information related to contracts and legal agreements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     postmodern
    -0.69
    IQR
    -0.67
     Behaviors
    -0.64
     behaviours
    -0.63
     Accessed
    -0.63
    ictus
    -0.62
     nonetheless
    -0.62
     Dummies
    -0.61
    rivit
    -0.60
     Heidegger
    -0.60
    POSITIVE LOGITS
     autorytatywna
    0.58
     giebt
    0.54
    parsedMessage
    0.52
    qai
    0.51
    InstrumentedTest
    0.51
     mengadakan
    0.51
     her
    0.50
    definite
    0.49
    leqq
    0.49
     mußten
    0.49
    Act Density 1.505%

    No Known Activations