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

    Neuronpedia

    INDEX
    Explanations

    proper names, specifically those of political figures

    oai_token-act-pair · gpt-3.5-turbo

    mentions of individuals with the title "Mr." or "Mrs." in the context of political discourse

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     exting
    -0.68
    theless
    -0.68
     eleph
    -0.68
    ©¶æ
    -0.67
     pione
    -0.67
     actionGroup
    -0.62
     organis
    -0.61
     ensu
    -0.60
    20439
    -0.60
    catentry
    -0.59
    POSITIVE LOGITS
    .,
    1.39
    .;
    1.21
    .,"
    1.19
    .?
    1.15
    ./
    1.13
    .),
    1.07
    .—
    1.06
    ._
    0.96
    orporated
    0.96
    .
    0.94
    Act Density 0.036%

    No Known Activations