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

    Neuronpedia

    INDEX
    Explanations

    key concepts related to security and its implications for broader societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uj
    -0.15
     Bü
    -0.14
    ington
    -0.14
    acted
    -0.14
    جÙĪÛĮ
    -0.14
    plural
    -0.14
    ooter
    -0.14
     é¢
    -0.14
    okie
    -0.13
    hin
    -0.13
    POSITIVE LOGITS
    åŁºæľ¬
    0.18
     basic
    0.18
     ÑĦÑĥн
    0.17
     base
    0.17
    -basic
    0.17
     foundation
    0.17
    먼
    0.17
     fundamental
    0.17
     core
    0.16
     everything
    0.16
    Act Density 0.227%

    No Known Activations