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

    Neuronpedia

    INDEX
    Explanations

    phrases related to storytelling and truth-telling

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to storytelling and truth

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bour
    -0.74
    enegger
    -0.69
    BuyableInstoreAndOnline
    -0.66
    aband
    -0.64
    ties
    -0.64
    isk
    -0.64
    hement
    -0.64
    lihood
    -0.62
    atism
    -0.61
     obscurity
    -0.61
    POSITIVE LOGITS
     story
    1.50
     tale
    1.45
     stories
    1.40
     STORY
    1.21
     Story
    1.16
     tales
    1.15
    stories
    1.06
     Stories
    1.06
    tale
    1.00
     truth
    0.97
    Act Density 0.103%

    No Known Activations