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

    Neuronpedia

    INDEX
    Explanations

    references to literature and works of authors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    racuse
    -0.89
     Philo
    -0.78
     Rufus
    -0.78
    dtd
    -0.77
    Sami
    -0.77
    Ruf
    -0.73
     Sami
    -0.72
     Ribera
    -0.72
     Yoon
    -0.70
    varez
    -0.70
    POSITIVE LOGITS
     Dö
    0.92
     Georgie
    0.92
    axel
    0.90
     Aer
    0.88
    orses
    0.88
    waite
    0.85
     MSM
    0.83
     Vey
    0.83
     Fie
    0.81
     Berwick
    0.81
    Act Density 2.405%

    No Known Activations