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

    Neuronpedia

    INDEX
    Explanations

    phrases related to formal legal contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to British culture or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    str
    -0.78
    tx
    -0.74
    pu
    -0.73
    Actor
    -0.73
    yi
    -0.69
    iri
    -0.69
    guy
    -0.66
     Qiao
    -0.65
    apor
    -0.64
    pex
    -0.64
    POSITIVE LOGITS
    Brit
    1.08
     published
    0.86
     publishes
    0.81
    published
    0.74
    ãĤ¼ãĤ¦ãĤ¹
    0.70
     births
    0.69
     possessions
    0.68
     miscar
    0.68
     RELE
    0.68
     sheds
    0.67
    Act Density 0.001%

    No Known Activations