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

    Neuronpedia

    INDEX
    Explanations

    names of specific individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Jessica" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bably
    -0.76
    ngth
    -0.76
     cele
    -0.75
    vor
    -0.73
    atre
    -0.71
    conserv
    -0.70
    ritic
    -0.69
    paste
    -0.68
    respons
    -0.67
    char
    -0.67
    POSITIVE LOGITS
     Rabbit
    0.92
    ellen
    0.89
    udeau
    0.87
     Lange
    0.84
     Jones
    0.77
     Valent
    0.77
    Serv
    0.76
    ilyn
    0.76
     Ortiz
    0.73
     Shields
    0.71
    Act Density 0.023%

    No Known Activations