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

    Neuronpedia

    INDEX
    Explanations

    references to government activities and involvement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ocious
    -0.77
    linger
    -0.75
    thora
    -0.74
    thur
    -0.74
    ostic
    -0.73
    jen
    -0.72
     Tome
    -0.72
    onge
    -0.71
    issan
    -0.71
    hirt
    -0.70
    POSITIVE LOGITS
     agencies
    1.25
     officials
    1.18
     coffers
    1.11
     institutions
    1.06
     departments
    1.02
     bureaucracy
    1.01
     procurement
    0.99
     subsidies
    0.98
     sanctioned
    0.98
     bureaucr
    0.97
    Act Density 0.049%

    No Known Activations