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

    Neuronpedia

    INDEX
    Explanations

    words related to the concept of "deconstruction" or similar processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    YTE
    -0.16
    ium
    -0.16
    olley
    -0.15
    ège
    -0.14
     fixed
    -0.14
    æ¶
    -0.14
    shop
    -0.14
    sport
    -0.14
     Democracy
    -0.14
    è¦Ĩ
    -0.14
    POSITIVE LOGITS
     clutter
    0.17
    escal
    0.16
    icers
    0.15
     trest
    0.15
     bunk
    0.15
    hub
    0.15
     commission
    0.14
    Hub
    0.14
    BUG
    0.14
     rig
    0.14
    Act Density 0.027%

    No Known Activations