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

    Neuronpedia

    INDEX
    Explanations

    pronouns related to personal perspectives and identities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    NameInMap
    -0.64
    IndentedString
    -0.54
     kasarigan
    -0.53
     branca
    -0.51
     Arund
    -0.46
     Canarias
    -0.46
    jupiter
    -0.45
    Geplaatst
    -0.44
     segu
    -0.44
     Polynesia
    -0.43
    POSITIVE LOGITS
     المعيارى
    1.04
    Tikang
    0.90
    }\]
    0.84
     own
    0.83
    '}>
    0.83
    "):
    0.81
    到你
    0.80
    >--}}
    0.77
     BaseActivity
    0.76
    évaluateur
    0.76
    Act Density 0.319%

    No Known Activations