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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "turns."

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

    turns out

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     noDo
    -0.63
     للاسماء
    -0.59
     незавершена
    -0.59
    ChildScrollView
    -0.58
     Chwiliwch
    -0.57
     endblock
    -0.57
    Personendaten
    -0.56
     NSCoder
    -0.54
    ⓧ
    -0.53
     ब्रेकडाउन
    -0.52
    POSITIVE LOGITS
     turns
    1.91
     Turns
    1.81
    Turns
    1.75
    turns
    1.57
     turned
    0.83
    turned
    0.81
     turning
    0.78
    Turned
    0.77
     Turned
    0.76
    turning
    0.66
    Act Density 0.004%

    No Known Activations