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

    Neuronpedia

    INDEX
    Explanations

    proper names of individuals, particularly in a narrative context

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    £ı
    -0.73
    committee
    -0.71
     antim
    -0.69
    inline
    -0.67
     industrial
    -0.67
     scorp
    -0.66
     acron
    -0.65
    progress
    -0.64
    advertisement
    -0.64
    rador
    -0.64
    POSITIVE LOGITS
     Doe
    0.97
    's
    0.92
     herself
    0.91
     Jenner
    0.91
     Kir
    0.87
     Lup
    0.85
     Rivera
    0.83
     Weasley
    0.83
     Frey
    0.82
     Stark
    0.80
    Act Density 0.158%

    No Known Activations