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

    Neuronpedia

    INDEX
    Explanations

    citations and references related to academic papers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    æĤł
    -0.17
     Barrier
    -0.15
    201
    -0.14
    (disposing
    -0.14
    γο
    -0.14
    zzo
    -0.14
    imler
    -0.13
    목
    -0.13
     Coupons
    -0.13
    enaire
    -0.13
    POSITIVE LOGITS
     Messiah
    0.20
    198
    0.20
    197
    0.19
     Mez
    0.17
     USSR
    0.16
    196
    0.16
     Soviet
    0.15
     Dash
    0.15
     Press
    0.15
    ÌĨ
    0.15
    Act Density 0.096%

    No Known Activations