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

    Neuronpedia

    INDEX
    Explanations

    mentions of government departments, specifically the Department of Homeland Security and similar agencies

    oai_token-act-pair · gpt-3.5-turbo

    references to government departments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fit
    -0.70
    faced
    -0.67
     worsh
    -0.66
    catentry
    -0.63
    iser
    -0.62
     Pose
    -0.62
    isers
    -0.60
    telling
    -0.59
    ties
    -0.58
     fry
    -0.58
    POSITIVE LOGITS
    artment
    1.00
    artments
    0.98
    al
    0.90
    alities
    0.82
    RECT
    0.80
    IJ
    0.79
    osa
    0.78
    alse
    0.78
    ysis
    0.77
     Stores
    0.76
    Act Density 0.027%

    No Known Activations