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

    Neuronpedia

    INDEX
    Explanations

    the word "while" and its variations in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    contrasting phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     transfieras
    -0.69
     चीज़ों
    -0.55
     rospy
    -0.55
     corne
    -0.54
     transférez
    -0.52
     Majefty
    -0.51
     indiana
    -0.51
    ſelf
    -0.48
     Houſe
    -0.48
    thansa
    -0.48
    POSITIVE LOGITS
     while
    0.70
     Sementara
    0.62
    while
    0.62
     whereas
    0.60
     sementara
    0.59
     mentre
    0.57
    whereas
    0.57
     Mentre
    0.57
    omiast
    0.57
    While
    0.56
    Act Density 0.034%

    No Known Activations