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

    Neuronpedia

    INDEX
    Explanations

    references to surveillance and espionage activities

    oai_token-act-pair · gpt-3.5-turbo

    references to surveillance and spying activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gran
    -0.75
    creation
    -0.67
    usable
    -0.67
    shr
    -0.66
    joy
    -0.66
    Jer
    -0.65
    à¤
    -0.65
    Course
    -0.65
    nos
    -0.65
    ergy
    -0.65
    POSITIVE LOGITS
     spying
    1.11
     ank
    0.92
     eaves
    0.86
    sonian
    0.85
     wiret
    0.83
     spoof
    0.76
    afia
    0.75
    ãĥ¼ãĥĨãĤ£
    0.74
     spies
    0.73
    ionage
    0.72
    Act Density 0.010%

    No Known Activations