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

    Neuronpedia

    INDEX
    Explanations

    possessive pronouns and their variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itſelf
    -0.96
    DockStyle
    -0.87
     Monfieur
    -0.85
     Cæsar
    -0.76
     Efq
    -0.75
     Houſe
    -0.73
     Shakspeare
    -0.71
     wikipagina
    -0.70
     zelve
    -0.66
    Personensuche
    -0.66
    POSITIVE LOGITS
     own
    1.02
     His
    0.91
     my
    0.85
     main
    0.84
     ur
    0.81
     her
    0.79
     entire
    0.79
     parents
    0.79
     his
    0.78
     HIS
    0.74
    Act Density 0.114%

    No Known Activations