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

    Neuronpedia

    INDEX
    Explanations

    words related to achievements and accomplishments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     noted
    -0.55
     counter
    -0.54
     here
    -0.54
    ors
    -0.53
    C
    -0.51
     through
    -0.50
     theme
    -0.50
     as
    -0.49
    is
    -0.49
     r
    -0.49
    POSITIVE LOGITS
     Numerade
    1.10
    LookAnd
    1.07
    хьтан
    1.03
    verwijspagina
    1.02
     autorytatywna
    0.99
    AddTagHelper
    0.99
    Хьажоргаш
    0.98
    SharedDtor
    0.98
     виправивши
    0.98
     Biôgrafia
    0.97
    Act Density 0.054%

    No Known Activations