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

    Neuronpedia

    INDEX
    Explanations

    references to hacks and technical tricks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     morgan
    -0.41
    readystatechange
    -0.39
    -0.38
    createServer
    -0.38
     архивлан
    -0.38
    WebServlet
    -0.38
    permitAll
    -0.38
     demen
    -0.38
    DIPSETTING
    -0.37
    Rujuakan
    -0.37
    POSITIVE LOGITS
     hack
    0.71
    Rig
    0.69
     Rig
    0.68
     logical
    0.68
    hack
    0.67
     rig
    0.62
    cshtml
    0.62
     hacked
    0.61
    Hack
    0.60
    rig
    0.57
    Act Density 1.225%

    No Known Activations