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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to computer programming and configuration

    oai_token-act-pair · gpt-3.5-turbo

    references to video games and gaming terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    quartered
    -0.88
     ÂŃ
    -0.85
    ×ŀ
    -0.75
    ÙĴ
    -0.72
    èĥ
    -0.71
    ij士
    -0.70
     Hew
    -0.69
     José
    -0.69
     Ronald
    -0.68
     Adolf
    -0.67
    POSITIVE LOGITS
     etc
    1.16
     tho
    1.13
     doesnt
    1.12
     stuff
    1.09
     :(
    1.01
     fiasco
    0.99
     devs
    0.98
     anyways
    0.96
     kinda
    0.94
     ->
    0.91
    Act Density 0.634%

    No Known Activations