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

    Neuronpedia

    INDEX
    Explanations

    affirmations or confirmations in conversation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     autonome
    -0.37
     cinquième
    -0.36
     Witness
    -0.35
     portefeuille
    -0.35
     isolé
    -0.34
     épais
    -0.34
     Vok
    -0.34
     operations
    -0.34
     Fußballspieler
    -0.34
    WriteLiteral
    -0.34
    POSITIVE LOGITS
    eraard
    0.97
    følgelig
    0.88
    verständlich
    0.88
     natürlich
    0.86
     Natürlich
    0.86
    Natürlich
    0.80
    当然
    0.78
     natuurlijk
    0.76
    czywiście
    0.75
     Naturally
    0.75
    Act Density 0.053%

    No Known Activations