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

    Neuronpedia

    INDEX
    Explanations

    phrases related to cyber attacks and hacking

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Towns
    -0.90
    illard
    -0.81
    coat
    -0.80
     Presbyter
    -0.72
    zl
    -0.71
    Dialogue
    -0.71
    alist
    -0.69
    uces
    -0.68
    otide
    -0.68
    letcher
    -0.67
    POSITIVE LOGITS
     hackers
    1.18
     hacker
    1.08
     hacking
    0.99
     cyber
    0.91
     attackers
    0.89
     cybersecurity
    0.87
    DoS
    0.87
     malware
    0.86
     hacked
    0.86
     penetrated
    0.86
    Act Density 0.046%

    No Known Activations