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

    Neuronpedia

    INDEX
    Explanations

    phrases or sentences indicating a narrative or story

    oai_token-act-pair · gpt-3.5-turbo

    references to narratives or stories about individuals or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hement
    -0.88
    reau
    -0.80
    ktop
    -0.79
    ascus
    -0.78
     cutoff
    -0.74
    cone
    -0.74
    apons
    -0.69
    ocate
    -0.67
    itored
    -0.67
    hesda
    -0.67
    POSITIVE LOGITS
     heroism
    0.98
     Stories
    0.80
     Oprah
    0.78
     Artemis
    0.77
     unfolding
    0.76
     Tales
    0.75
     Lazarus
    0.75
     tales
    0.75
     stories
    0.73
     how
    0.72
    Act Density 0.156%

    No Known Activations