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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political figures and government offices

    oai_token-act-pair · gpt-3.5-turbo

    references to the White House

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anwhile
    -0.85
    ngth
    -0.85
    raints
    -0.80
    yrinth
    -0.79
    olls
    -0.79
    odcast
    -0.78
    ITAL
    -0.78
    trak
    -0.77
    rawdownloadcloneembedreportprint
    -0.76
    Downloadha
    -0.73
    POSITIVE LOGITS
    house
    1.05
    hall
    1.02
     Sox
    0.99
    hurst
    0.96
    caps
    0.96
    berry
    0.95
     supremacist
    0.94
     House
    0.92
     supremacists
    0.87
    ewater
    0.86
    Act Density 0.021%

    No Known Activations