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

    Neuronpedia

    INDEX
    Explanations

    the word "who" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    らう
    -0.73
     Eis
    -0.71
     Steck
    -0.70
    alis
    -0.64
     Merk
    -0.64
     Wellen
    -0.62
     έκ
    -0.62
    ます
    -0.61
     Augustin
    -0.61
     Veer
    -0.59
    POSITIVE LOGITS
     who
    2.00
    who
    1.66
     WHO
    1.55
     Who
    1.53
    Who
    1.47
    WHO
    1.40
     którzy
    1.35
     whom
    1.34
    whom
    1.25
     quien
    1.24
    Act Density 0.101%

    No Known Activations