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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating requests for information or confirmation

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

    let me know if

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     فريبيس
    -0.64
     ExecuteAsync
    -0.52
     miniaturka
    -0.51
    ❋
    -0.50
     snippetHide
    -0.49
     mikina
    -0.49
     woven
    -0.48
    AccessorTable
    -0.47
     ddelwed
    -0.46
    UseVisualStyle
    -0.46
    POSITIVE LOGITS
     notify
    0.64
     notified
    0.54
    notify
    0.52
     inform
    0.50
    Notify
    0.49
     Notify
    0.49
     informs
    0.46
     know
    0.45
    know
    0.45
    Know
    0.42
    Act Density 0.023%

    No Known Activations