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

    Neuronpedia

    INDEX
    Explanations

    phrases that suggest uncertainty or speculation

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

    seems to, seems that, seems like

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nahilalakip
    -0.52
    InputTagHelper
    -0.51
    tagHelperRunner
    -0.51
    BufferException
    -0.45
    jonal
    -0.44
    chlag
    -0.44
    Manbalar
    -0.41
    hicule
    -0.41
    RenderAtEndOf
    -0.41
     mxArray
    -0.41
    POSITIVE LOGITS
    好像
    0.68
    Parece
    0.57
     seems
    0.56
     seem
    0.55
    setVerticalGroup
    0.54
    似乎
    0.54
    のようです
    0.50
    好像是
    0.49
     кажется
    0.48
    看来
    0.48
    Act Density 0.008%

    No Known Activations