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

    Neuronpedia

    INDEX
    Explanations

    references to printing, sharing or sending emails

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Print" and variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hov
    -0.91
    rolet
    -0.85
    hart
    -0.74
    asio
    -0.72
    odka
    -0.66
    onite
    -0.66
    hunt
    -0.65
    aimon
    -0.65
    addons
    -0.64
    acia
    -0.64
    POSITIVE LOGITS
    outs
    0.84
    Print
    0.81
     print
    0.79
     Seym
    0.78
    print
    0.77
     Print
    0.77
     prints
    0.76
    Writer
    0.75
    out
    0.74
    sheet
    0.71
    Act Density 0.023%

    No Known Activations