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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "doing" in various contexts

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

    what we are doing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     olvido
    -0.35
    nestjs
    -0.34
     cubierto
    -0.33
     probado
    -0.32
    ỏa
    -0.31
    Saiba
    -0.31
     arreglar
    -0.31
    arzt
    -0.31
     jamás
    -0.31
    :+:
    -0.30
    POSITIVE LOGITS
     ſind
    0.67
     يتيمه
    0.62
     للمعارف
    0.62
    MLLoader
    0.60
    存于互联网档案馆
    0.59
     المعيارى
    0.58
     jScrollPane
    0.57
    Enemies
    0.56
    tagHelper
    0.55
     @"/
    0.52
    Act Density 0.028%

    No Known Activations