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

    Neuronpedia

    INDEX
    Explanations

    phrases that refer to narratives or stories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    shire
    -0.16
    edList
    -0.16
    lund
    -0.16
    est
    -0.15
    lah
    -0.15
    zell
    -0.15
    emple
    -0.15
    estar
    -0.15
    lander
    -0.15
    wich
    -0.15
    POSITIVE LOGITS
     tale
    0.22
     tales
    0.21
     Tale
    0.20
     told
    0.19
    /story
    0.17
    ith
    0.17
    ãĤ¹ãĥ¬
    0.16
    -utils
    0.15
    tras
    0.15
     milano
    0.15
    Act Density 0.014%

    No Known Activations