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

    Neuronpedia

    INDEX
    Explanations

    references to academic writing, specifically dissertations and theses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Shelter
    -0.17
    ea
    -0.16
    ley
    -0.16
    leys
    -0.14
    lesh
    -0.14
    oo
    -0.14
    ashi
    -0.14
    UCT
    -0.14
    aho
    -0.14
     Duch
    -0.13
    POSITIVE LOGITS
    esor
    0.20
    Ø·Ùĩ
    0.18
    aire
    0.15
     padr
    0.15
    ith
    0.14
    ammer
    0.14
    /story
    0.14
    è¿°
    0.14
    ãģĴ
    0.13
    ÄĽÅ¾
    0.13
    Act Density 0.012%

    No Known Activations