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

    who questions and references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     FES
    -0.46
     Sanford
    -0.44
    ある
    -0.43
     an
    -0.43
     a
    -0.41
    edonian
    -0.41
     for
    -0.40
    ,
    -0.40
    weetened
    -0.38
     Stedman
    -0.38
    POSITIVE LOGITS
     who
    1.05
    Who
    1.02
     Who
    0.96
    who
    0.92
    Quién
    0.90
    Quiénes
    0.88
     whom
    0.88
     quién
    0.88
     Whom
    0.84
    whom
    0.84
    Act Density 0.013%

    No Known Activations