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

    Neuronpedia

    INDEX
    Explanations

    expressions of pride or pride-related sentiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Secrétaire
    -0.35
    getIntent
    -0.33
     Weiß
    -0.33
     跳转至
    -0.33
     جم
    -0.32
     classmates
    -0.31
    Okay
    -0.31
    wier
    -0.31
    琴
    -0.31
     Judge
    -0.30
    POSITIVE LOGITS
     proud
    1.45
    proud
    1.33
     proudly
    1.24
     pride
    1.12
    Proud
    1.09
     orgull
    1.09
     orgullo
    1.05
     Proud
    1.00
    pride
    0.96
     stolz
    0.94
    Act Density 0.002%

    No Known Activations