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

    Neuronpedia

    INDEX
    Explanations

    phrases related to efficiency and ease of use

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Comes after "easy" or "efficient"

    np_acts-logits-general · gemini-2.0-flash

    ease and efficiency

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    OrCreate
    -0.52
    قایناق‌لار
    -0.49
    XmlType
    -0.48
    lgari
    -0.43
     embaj
    -0.42
     coti
    -0.42
    stupid
    -0.41
     chofe
    -0.40
     Eichen
    -0.40
     DARK
    -0.40
    POSITIVE LOGITS
    การ
    0.70
     nakalista
    0.63
     عمليات
    0.58
     การ
    0.56
     simultaneous
    0.56
    ในการ
    0.52
    每一次
    0.52
     Italijani
    0.51
     Simultaneous
    0.50
     correcta
    0.50
    Act Density 1.747%

    No Known Activations