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

    Neuronpedia

    INDEX
    Explanations

    terms related to stealth and concealment

    oai_token-act-pair · gpt-3.5-turbo

    terms related to stealth and secretive characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Pwr
    -0.71
    artney
    -0.66
    ONT
    -0.62
    ICAN
    -0.62
    ENTS
    -0.61
    frey
    -0.60
     CARD
    -0.60
    ocese
    -0.59
     Atkinson
    -0.57
    Ire
    -0.56
    POSITIVE LOGITS
    ily
    1.03
    ively
    0.98
    ibility
    0.92
     bomber
    0.91
    iest
    0.89
    iness
    0.88
    loo
    0.87
     stealth
    0.85
    iveness
    0.84
    y
    0.83
    Act Density 0.027%

    No Known Activations