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

    Neuronpedia

    INDEX
    Explanations

    expressions of uncertainty or ambiguity

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

    depending on what

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    LookAnd
    -0.60
    帖最后由
    -0.43
    허
    -0.43
    ؤلاء
    -0.40
     recommends
    -0.40
    Referencies
    -0.40
     yoda
    -0.40
    คะ
    -0.40
    msleep
    -0.39
    agisse
    -0.39
    POSITIVE LOGITS
     noDo
    0.48
     materialize
    0.47
     CreateTagHelper
    0.47
     betweenstory
    0.46
    haustible
    0.41
    DockStyle
    0.40
    AnchorStyles
    0.39
     Konsequ
    0.39
     Martens
    0.39
    localctx
    0.39
    Act Density 0.003%

    No Known Activations