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

    Neuronpedia

    INDEX
    Explanations

    references to personal or historical experiences

    oai_token-act-pair · gpt-3.5-turbo

    narrative structures that emphasize "the story of" various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hement
    -0.87
    ktop
    -0.81
    jab
    -0.75
     ILCS
    -0.72
    hee
    -0.71
    ertodd
    -0.70
    rotein
    -0.70
    chwitz
    -0.69
    hesda
    -0.69
    pload
    -0.67
    POSITIVE LOGITS
     heroism
    0.92
     unfolding
    0.75
     Stories
    0.71
     Artemis
    0.71
     epic
    0.70
     Tales
    0.70
     stories
    0.69
     how
    0.67
     sorts
    0.67
     ted
    0.66
    Act Density 0.118%

    No Known Activations