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

    Neuronpedia

    INDEX
    Explanations

    references to the word "who."

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

    who is or did what

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     FES
    -0.47
     Ext
    -0.45
     Fes
    -0.42
     carefully
    -0.41
    WithFormat
    -0.40
    eway
    -0.40
     a
    -0.39
    嘉
    -0.39
     careful
    -0.39
    突
    -0.38
    POSITIVE LOGITS
     hvem
    1.01
    Who
    0.88
     siapa
    0.87
     quién
    0.85
     Siapa
    0.82
    Hvem
    0.82
     Who
    0.80
    Quién
    0.79
    Quiénes
    0.79
    誰が
    0.75
    Act Density 0.009%

    No Known Activations