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

    Neuronpedia

    INDEX
    Explanations

    the word "who" with varying contexts and forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     asti
    -0.55
    ranslated
    -0.54
     snowing
    -0.54
     avanti
    -0.53
    ArrowToggle
    -0.53
     sebe
    -0.52
     رہ
    -0.51
     diverting
    -0.51
    )]);
    -0.49
    bay
    -0.49
    POSITIVE LOGITS
    oping
    0.92
     who
    0.83
    Who
    0.80
     Who
    0.79
    SequentialGroup
    0.79
     WHO
    0.78
    Whoosh
    0.76
    who
    0.72
    Whoo
    0.68
     helst
    0.66
    Act Density 0.073%

    No Known Activations