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

    Neuronpedia

    INDEX
    Explanations

    significant concepts and models in environmental or social contexts

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

    phrases describing organizational or systemic models and benchmarks.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Negative Logits
     onCancelled
    -0.36
    rippa
    -0.35
     kří
    -0.31
     menik
    -0.31
     vermo
    -0.31
     doprav
    -0.30
     osallist
    -0.30
    chaik
    -0.30
     Verkehrs
    -0.29
    agré
    -0.29
    POSITIVE LOGITS
    +#+
    0.67
     examples
    0.65
     Vorbild
    0.64
    ScopeManager
    0.62
    oredCriteria
    0.58
     example
    0.58
    EXAMPLE
    0.57
     пример
    0.57
     Beispiele
    0.57
    ंदीखरीदारी
    0.57
    Act Density 0.142%

    No Known Activations