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

    Neuronpedia

    INDEX
    Explanations

    affirmations or confirmations in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aldi
    -0.19
    _LSB
    -0.18
    ä¸įäºĨ
    -0.17
    ÑĨионнÑĭй
    -0.15
    оÑı
    -0.15
    doesn
    -0.14
    à¹Ħม
    -0.14
    nesc
    -0.14
     niet
    -0.14
     नह
    -0.14
    POSITIVE LOGITS
    yes
    0.36
     yes
    0.35
     indeed
    0.34
     Yes
    0.28
    Yes
    0.26
    Yep
    0.26
     Yep
    0.26
     Indeed
    0.24
    Indeed
    0.23
    =yes
    0.23
    Act Density 0.066%

    No Known Activations