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

    Neuronpedia

    INDEX
    Explanations

    entities and phrases related to government institutions and security services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ONGL
    -0.16
     Deputy
    -0.15
    ilan
    -0.14
     Ere
    -0.14
    ãĤĿ
    -0.13
    adin
    -0.13
    elsey
    -0.13
    _nl
    -0.13
    Periph
    -0.13
     caut
    -0.13
    POSITIVE LOGITS
     security
    0.34
     intelligence
    0.32
     Intelligence
    0.28
     Security
    0.27
     Sicher
    0.25
    intelligence
    0.25
    security
    0.25
     Internal
    0.24
    Security
    0.23
    -security
    0.23
    Act Density 0.083%

    No Known Activations