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

    Neuronpedia

    INDEX
    Explanations

    phrases or sentences that tell a narrative or story

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate storytelling or narrative delivery

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adesh
    -0.71
    intend
    -0.69
    pac
    -0.65
    ican
    -0.63
    icut
    -0.61
    zinski
    -0.61
     Nadu
    -0.59
    aband
    -0.59
    ternity
    -0.59
    igslist
    -0.59
    POSITIVE LOGITS
    tale
    1.23
     us
    1.20
     tales
    1.10
     stories
    1.06
    ingly
    0.99
     tale
    0.91
     Stories
    0.90
     anecdotes
    0.85
     me
    0.85
     lies
    0.85
    Act Density 0.059%

    No Known Activations