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

    Neuronpedia

    INDEX
    Explanations

    references to documents and codes in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     unlike
    -0.19
     beyond
    -0.17
     Fuller
    -0.16
    Beyond
    -0.15
    lev
    -0.15
    éis
    -0.14
     Osborne
    -0.14
    ãĥ³ãĥķ
    -0.14
    icky
    -0.14
    dec
    -0.14
    POSITIVE LOGITS
     instead
    0.56
    instead
    0.50
     Instead
    0.41
    Instead
    0.38
     вмеÑģÑĤ
    0.31
    à¹ģà¸Ĺà¸Ļ
    0.25
     naopak
    0.22
     inve
    0.20
    ãģ»ãģĨ
    0.20
     代
    0.18
    Act Density 0.406%

    No Known Activations