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

    Neuronpedia

    INDEX
    Explanations

    studies and research papers mentioned in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to academic studies and research findings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     goodbye
    -0.75
     toast
    -0.69
     veto
    -0.68
     ceremony
    -0.68
     Strongh
    -0.67
     symbol
    -0.66
     wishes
    -0.65
     mute
    -0.64
    alogue
    -0.64
    ulkan
    -0.64
    POSITIVE LOGITS
     conducted
    1.29
    Study
    1.14
     examined
    1.09
     analyzed
    1.09
     researchers
    1.09
    Researchers
    1.07
     published
    1.05
    uggest
    1.05
     analyzing
    1.04
     examining
    1.04
    Act Density 0.371%

    No Known Activations