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

    Neuronpedia

    INDEX
    Explanations

    concepts related to security and protection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ä¿
    -0.16
    avia
    -0.15
     UNUSED
    -0.15
    agh
    -0.15
    xAC
    -0.15
    ONGO
    -0.14
    elsen
    -0.14
    ITT
    -0.14
    ibu
    -0.14
    ÑĨÑĥ
    -0.14
    POSITIVE LOGITS
     Blank
    0.16
    rap
    0.16
    aber
    0.16
    nas
    0.16
    enberg
    0.15
     sour
    0.14
    ishi
    0.14
    aper
    0.14
    FN
    0.14
    anted
    0.14
    Act Density 0.067%

    No Known Activations