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

    Neuronpedia

    INDEX
    Explanations

    terms related to surveillance

    oai_token-act-pair · gpt-3.5-turbo

    references to surveillance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    equal
    -0.75
    versions
    -0.75
    gran
    -0.74
    interstitial
    -0.71
    ogen
    -0.69
    uca
    -0.69
    onement
    -0.68
    olen
    -0.67
    erry
    -0.67
    xual
    -0.66
    POSITIVE LOGITS
     surveillance
    0.95
     cameras
    0.94
     ank
    0.92
    illance
    0.89
     Surveillance
    0.78
    oleon
    0.77
     systems
    0.77
     spree
    0.74
     Systems
    0.74
     tactics
    0.72
    Act Density 0.015%

    No Known Activations