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

    Neuronpedia

    INDEX
    Explanations

    references to the term "Black" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    EndContext
    -0.98
    IsMutable
    -0.88
     оригіналу
    -0.79
    NameInMap
    -0.78
     ujednoznacz
    -0.77
    DockStyle
    -0.73
     يتيمه
    -0.72
     rospy
    -0.71
    =$?
    -0.71
     myſelf
    -0.70
    POSITIVE LOGITS
    Black
    0.79
    BLACK
    0.76
    black
    0.75
     BLACK
    0.73
     Black
    0.71
     ブラック
    0.66
    Schwar
    0.65
     black
    0.65
    ening
    0.62
     Schwar
    0.59
    Act Density 0.056%

    No Known Activations