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

    Neuronpedia

    INDEX
    Explanations

    instances of network-related incidents and security threats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sko
    -0.17
     Airways
    -0.15
     duplic
    -0.15
    lectron
    -0.15
    @mail
    -0.14
     desert
    -0.14
    _bridge
    -0.14
     LIC
    -0.14
    agus
    -0.14
     export
    -0.14
    POSITIVE LOGITS
     bot
    0.32
     denial
    0.29
     Bot
    0.28
    bot
    0.26
     Den
    0.25
     DD
    0.25
    _bot
    0.25
     Distributed
    0.25
    (bot
    0.24
    Bot
    0.24
    Act Density 0.038%

    No Known Activations