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

    Neuronpedia

    INDEX
    Explanations

    mentions of a specific place or entity, particularly the "White House."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the White House

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anwhile
    -0.77
    REM
    -0.72
    rawdownloadcloneembedreportprint
    -0.69
     facult
    -0.66
    ANS
    -0.65
    itual
    -0.64
    Downloadha
    -0.63
    lessly
    -0.62
    ingu
    -0.61
    avascript
    -0.60
    POSITIVE LOGITS
     House
    1.27
    House
    1.06
    house
    1.04
     Sox
    1.04
    hall
    0.93
     HOUSE
    0.92
    ewater
    0.91
     Houses
    0.91
    caps
    0.85
     supremacist
    0.81
    Act Density 0.015%

    No Known Activations