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

    Neuronpedia

    INDEX
    Explanations

    pronouns and references to individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Paglinawan
    -1.01
    RectangleBorder
    -0.99
     Roskov
    -0.96
     Biôgrafia
    -0.96
    UnsafeEnabled
    -0.93
    StoryboardSegue
    -0.93
    MessageOf
    -0.88
    GraphicsUnit
    -0.87
    Hentet
    -0.82
     متعلقه
    -0.82
    POSITIVE LOGITS
     Her
    0.54
     his
    0.53
     She
    0.50
    her
    0.49
     her
    0.48
     he
    0.48
     they
    0.47
    he
    0.46
     herself
    0.45
     their
    0.44
    Act Density 0.123%

    No Known Activations