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

    Neuronpedia

    INDEX
    Explanations

    references to the FBI

    oai_token-act-pair · gpt-3.5-turbo

    references to the FBI and associated investigations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    faces
    -0.75
    faced
    -0.72
    piring
    -0.72
    ktop
    -0.71
    lived
    -0.70
    lass
    -0.70
    opian
    -0.69
    flush
    -0.69
    comes
    -0.68
    pas
    -0.68
    POSITIVE LOGITS
     informant
    0.88
     Director
    0.87
     Commissioner
    0.85
     investigation
    0.82
     Oversight
    0.82
    FBI
    0.81
     Bureau
    0.81
     commissioner
    0.80
     Agency
    0.79
     counterterrorism
    0.78
    Act Density 0.019%

    No Known Activations