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

    Neuronpedia

    INDEX
    Explanations

    references to formal announcements or releases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Suc
    -0.19
     Petite
    -0.17
     mas
    -0.16
    fol
    -0.16
     Kes
    -0.15
     Mas
    -0.15
    mae
    -0.15
    oidal
    -0.14
     Folk
    -0.14
    olk
    -0.14
    POSITIVE LOGITS
     ÐijоÑĢ
    0.17
     press
    0.17
    Bookmark
    0.17
    boro
    0.16
     nowhere
    0.15
    Sharper
    0.15
    ãģĸ
    0.15
    emoc
    0.15
    ENSE
    0.14
     appare
    0.14
    Act Density 0.301%

    No Known Activations