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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal or political matters

    oai_token-act-pair · gpt-3.5-turbo

    instances of a specific symbol

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    expensive
    -0.62
     tricked
    -0.61
    clone
    -0.61
     Pegasus
    -0.59
     bombed
    -0.58
    undai
    -0.58
     seeded
    -0.57
    ioxide
    -0.57
    iage
    -0.56
     winds
    -0.55
    POSITIVE LOGITS
     âĢ
    3.43
    âĢ
    2.20
    âĢł
    1.49
     **
    1.23
     â
    1.12
     âĶ
    1.10
     âĸº
    1.09
     ðŁij
    1.08
    âģ
    1.08
    âĢIJ
    1.06
    Act Density 0.235%

    No Known Activations