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

    Neuronpedia

    INDEX
    Explanations

    mentions of hackers

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     Spur
    -0.82
     Medina
    -0.76
     Relative
    -0.74
     Towns
    -0.74
    addle
    -0.73
    Ref
    -0.72
     Sadd
    -0.71
    Duration
    -0.71
     Bris
    -0.68
     NH
    -0.68
    POSITIVE LOGITS
     hackers
    3.66
     hacker
    3.30
     hacking
    2.81
     hack
    2.25
     hacked
    2.07
     hacks
    2.04
     cyber
    1.98
     Hacker
    1.96
     cybersecurity
    1.89
     Hack
    1.84
    Act Density 0.019%

    No Known Activations