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

    Neuronpedia

    INDEX
    Explanations

    references to a specific personal name

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Negative Logits
     Jo
    -1.32
     JO
    -1.00
     jo
    -0.97
    Jo
    -0.93
    PerformLayout
    -0.81
     Joi
    -0.75
     Joaquin
    -0.68
     JoJo
    -0.65
     Joel
    -0.63
    ijo
    -0.62
    POSITIVE LOGITS
    jo
    1.91
    joit
    0.70
    disposing
    0.68
     चीज़ों
    0.64
    licability
    0.57
    ubility
    0.56
    endrait
    0.56
     GreatSchools
    0.55
     createState
    0.54
     écoulé
    0.52
    Act Density 0.001%

    No Known Activations