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

    Neuronpedia

    INDEX
    Explanations

    email addresses containing numbers

    oai_token-act-pair · gpt-3.5-turbo

    numerical data and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     waiter
    -0.73
     exha
    -0.65
     waitress
    -0.64
     palate
    -0.63
     sacrific
    -0.61
    emort
    -0.61
     mango
    -0.60
    awaru
    -0.59
     transact
    -0.59
     gren
    -0.59
    POSITIVE LOGITS
    wm
    0.90
    nian
    0.81
    mx
    0.79
    cks
    0.77
    e
    0.75
    xus
    0.72
    rez
    0.72
    606
    0.72
    soever
    0.71
    px
    0.71
    Act Density 0.097%

    No Known Activations