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

    Neuronpedia

    INDEX
    Explanations

    file paths and directory structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IsContent
    -0.94
     varandra
    -0.87
     <>",
    -0.85
    numerusform
    -0.80
    ItemBackground
    -0.80
     Baillargeon
    -0.76
     оригіналу
    -0.74
     Italijanski
    -0.74
     auffi
    -0.74
    клопе
    -0.73
    POSITIVE LOGITS
     sen
    0.57
     mal
    0.54
     th
    0.54
     equ
    0.53
    udan
    0.52
     Equ
    0.51
    uries
    0.51
     li
    0.50
     tre
    0.50
     co
    0.49
    Act Density 0.479%

    No Known Activations