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

    Neuronpedia

    INDEX
    Explanations

    references to safety or security

    oai_token-act-pair · gpt-3.5-turbo

    references to safety and secure spaces

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    naire
    -0.81
    yss
    -0.73
    issance
    -0.73
    fred
    -0.70
    mot
    -0.67
     elig
    -0.65
     XIII
    -0.62
    kay
    -0.61
     Fiber
    -0.60
    hiba
    -0.59
    POSITIVE LOGITS
     havens
    1.14
    keeping
    1.09
    haven
    1.00
     haven
    0.95
     harbor
    0.94
    inventoryQuantity
    0.89
    house
    0.87
     harbour
    0.87
     Haven
    0.84
     deposit
    0.82
    Act Density 0.039%

    No Known Activations