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

    Neuronpedia

    INDEX
    Explanations

    topics related to national security

    oai_token-act-pair · gpt-3.5-turbo

    references to national security

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amaz
    -0.89
    unt
    -0.74
    Unity
    -0.70
    forth
    -0.68
    oven
    -0.67
    ikan
    -0.66
    bare
    -0.66
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    -0.66
    YC
    -0.66
    abouts
    -0.65
    POSITIVE LOGITS
     adviser
    1.10
     Adviser
    1.07
     advisor
    1.05
     Advisor
    1.04
     Agency
    0.97
     Advis
    0.89
     agencies
    0.88
     apparatus
    0.87
     briefings
    0.84
     secrets
    0.82
    Act Density 0.026%

    No Known Activations