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

    Neuronpedia

    INDEX
    Explanations

    references to human relationships and social roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ArrowToggle
    -0.74
    writeFieldEnd
    -0.72
     nahilalakip
    -0.66
    IVEREF
    -0.65
     EconPapers
    -0.58
    poons
    -0.57
     lenker
    -0.57
    uron
    -0.57
     CURIAM
    -0.55
     utafiti
    -0.55
    POSITIVE LOGITS
     who
    4.51
    who
    3.43
     whom
    3.05
     quien
    2.60
    whom
    2.54
    Who
    2.51
     Who
    2.46
     whose
    2.26
     którzy
    2.15
     quienes
    2.14
    Act Density 1.341%

    No Known Activations