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

    Neuronpedia

    INDEX
    Explanations

    themes related to tension and suspense in narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yer
    -0.17
    ìĤ´
    -0.17
    ivant
    -0.16
    reas
    -0.15
    edException
    -0.15
    rips
    -0.15
    ajs
    -0.15
    ater
    -0.15
    avier
    -0.15
    itures
    -0.14
    POSITIVE LOGITS
    empo
    0.15
     fed
    0.14
     Fund
    0.14
     fund
    0.14
    uck
    0.14
    ucket
    0.13
    urrect
    0.13
     uncomp
    0.13
    309
    0.13
    ↵
    0.13
    Act Density 0.103%

    No Known Activations