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

    Neuronpedia

    INDEX
    Explanations

    the word "who" in various grammatical forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     świą
    -0.69
    ArrowToggle
    -0.67
     Eis
    -0.66
     Merk
    -0.66
    らう
    -0.66
     fré
    -0.64
     paff
    -0.64
     Berech
    -0.63
    Peek
    -0.62
     رہ
    -0.62
    POSITIVE LOGITS
     who
    1.58
     WHO
    1.32
     Who
    1.29
    who
    1.18
    Who
    1.14
    osoever
    1.11
    WHO
    1.10
    Whoosh
    1.09
     którzy
    1.09
     quienes
    1.01
    Act Density 0.074%

    No Known Activations