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

    Neuronpedia

    INDEX
    Explanations

    references to undercover operations or individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to undercover operations and agents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    jri
    -0.78
    hement
    -0.77
    enburg
    -0.77
    estone
    -0.75
    wake
    -0.74
    yards
    -0.74
    conservancy
    -0.73
    usable
    -0.73
    grave
    -0.71
    hof
    -0.71
    POSITIVE LOGITS
     FBI
    0.93
     ops
    0.92
     operatives
    0.92
     CIA
    0.92
     operation
    0.87
     officer
    0.86
     sting
    0.84
     operative
    0.83
     Operation
    0.82
     cops
    0.82
    Act Density 0.092%

    No Known Activations