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

    Neuronpedia

    INDEX
    Explanations

    terms related to information leaks and their implications

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "leaks"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oran
    -0.85
    iterranean
    -0.84
    stad
    -0.80
    aple
    -0.74
    ourke
    -0.70
    bal
    -0.69
    Inv
    -0.68
    ============
    -0.67
    ======
    -0.67
    sk
    -0.67
    POSITIVE LOGITS
     leaks
    1.33
    Leaks
    1.15
     leak
    1.15
     leaking
    1.05
     leaked
    0.99
    ileaks
    0.94
     leakage
    0.92
    inventoryQuantity
    0.80
     opacity
    0.78
     Nunes
    0.78
    Act Density 0.008%

    No Known Activations