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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "When" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     saiba
    -0.59
    ParallelGroup
    -0.57
     gärna
    -0.56
     serem
    -0.54
     bagaimana
    -0.54
     enquanto
    -0.53
    parsedMessage
    -0.53
    IntoConstraints
    -0.53
     sebagai
    -0.52
    AddHtmlAttribute
    -0.52
    POSITIVE LOGITS
     asked
    1.25
     confronted
    1.11
     faced
    1.08
     questioned
    0.94
     compared
    0.94
     approached
    0.91
     viewed
    0.88
     they
    0.86
     discussing
    0.85
     interviewed
    0.84
    Act Density 0.118%

    No Known Activations