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

    Neuronpedia

    INDEX
    Explanations

    references to personal pronouns and interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     himſelf
    -0.88
     itſelf
    -0.77
     Cæsar
    -0.77
     myſelf
    -0.75
     themſelves
    -0.75
     fubject
    -0.70
     houſe
    -0.67
     perfons
    -0.66
     Monfieur
    -0.65
     becauſe
    -0.65
    POSITIVE LOGITS
     a
    1.07
     an
    0.83
    Gimme
    0.83
    DockStyle
    0.79
     the
    0.73
    цездатний
    0.69
    GEBURTSDATUM
    0.69
     some
    0.68
     plenty
    0.68
    RegistryLite
    0.68
    Act Density 0.112%

    No Known Activations