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

    Neuronpedia

    INDEX
    Explanations

    references to governmental departments, agencies, and programs

    oai_token-act-pair · gpt-3.5-turbo

    references to government agencies and their activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     stones
    -0.76
    plings
    -0.74
    stones
    -0.71
    Õ
    -0.67
     lovers
    -0.67
     amph
    -0.66
     idols
    -0.64
     bou
    -0.64
    caps
    -0.64
     worship
    -0.63
    POSITIVE LOGITS
     investigating
    0.97
    Department
    0.97
     Department
    0.96
     Bureau
    0.93
     Inspect
    0.92
     oversight
    0.91
     Accountability
    0.91
    Office
    0.89
     inspectors
    0.89
     Office
    0.89
    Act Density 0.565%

    No Known Activations