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

    Neuronpedia

    INDEX
    Explanations

    phrases and terms related to the concept of innocence, particularly in legal or moral contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AnimationsModule
    -0.56
    الحياه
    -0.54
     fubject
    -0.53
    ьаж
    -0.50
     betweenstory
    -0.50
    Numerology
    -0.48
    InputBorder
    -0.48
     كورة
    -0.47
     MainAxisSize
    -0.47
    достатки
    -0.46
    POSITIVE LOGITS
    да
    0.59
    Configurable
    0.47
    后
    0.47
     bParam
    0.45
     accidentally
    0.45
    (:,:,
    0.42
     оригіналу
    0.42
    後
    0.41
     innocent
    0.40
     Người
    0.40
    Act Density 0.299%

    No Known Activations