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

    Neuronpedia

    INDEX
    Explanations

    expressions indicating clarity and understanding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pherals
    -0.54
     мәкал
    -0.43
     незавершена
    -0.43
    matchCondition
    -0.43
    ✭✭
    -0.42
     propOrder
    -0.40
    tonsoft
    -0.39
     Goldberg
    -0.38
     Martino
    -0.38
     ویکی‌پدی
    -0.37
    POSITIVE LOGITS
     clear
    2.36
    clear
    1.84
     CLEAR
    1.58
     Clear
    1.57
    Clear
    1.47
     crystal
    1.40
     klar
    1.39
     claro
    1.38
    CLEAR
    1.37
     clearer
    1.36
    Act Density 0.569%

    No Known Activations