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

    Neuronpedia

    INDEX
    Explanations

    words related to cyber activities or cyber technology

    oai_token-act-pair · gpt-3.5-turbo

    terms related to cyber activities and threats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Burr
    -0.78
     Cla
    -0.71
     Norris
    -0.70
     Kenny
    -0.68
     Kis
    -0.68
     Ambrose
    -0.67
     Meadows
    -0.67
    iatus
    -0.66
     Lann
    -0.66
     Clause
    -0.65
    POSITIVE LOGITS
    based
    1.17
    driven
    1.17
    generated
    1.15
    friendly
    1.14
    operated
    1.12
    enabled
    1.10
    centric
    1.07
    indust
    1.05
    induced
    1.05
    processing
    1.05
    Act Density 0.088%

    No Known Activations