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

    Neuronpedia

    INDEX
    Explanations

    words related to leaks or leakage

    oai_token-act-pair · gpt-3.5-turbo

    references to leaks in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iterranean
    -0.91
    HCR
    -0.63
     Dragons
    -0.62
    =-=-=-=-
    -0.62
    ;;;;;;;;
    -0.61
    zees
    -0.61
    arching
    -0.60
    eele
    -0.60
    ieval
    -0.60
     Gentle
    -0.59
    POSITIVE LOGITS
    inventoryQuantity
    0.84
     leaks
    0.78
     leak
    0.78
     leaking
    0.78
    Leaks
    0.76
    acious
    0.75
     leakage
    0.74
    y
    0.72
    rets
    0.72
    worthiness
    0.72
    Act Density 0.015%

    No Known Activations