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

    Neuronpedia

    INDEX
    Explanations

    phrases related to actions taken by individuals or groups in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itself
    -0.25
     its
    -0.23
     Its
    -0.19
    Its
    -0.19
    å®ĥ们
    -0.16
     à¤īसà¤ķ
    -0.16
    coma
    -0.15
     Sly
    -0.14
     rag
    -0.14
    olia
    -0.14
    POSITIVE LOGITS
     themselves
    0.35
    ebb
    0.16
     lượt
    0.15
    UPS
    0.15
     thems
    0.15
    oled
    0.14
    YNAM
    0.14
    äºĭ
    0.14
    umber
    0.14
    isman
    0.14
    Act Density 1.313%

    No Known Activations