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

    Neuronpedia

    INDEX
    Explanations

    numerical representations or references to counts and measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    an
    -0.50
     catena
    -0.50
    mek
    -0.50
    moo
    -0.48
     for
    -0.48
     from
    -0.48
     Terraria
    -0.47
    <eos>
    -0.46
     липня
    -0.46
     =
    -0.46
    POSITIVE LOGITS
    HtmlAttribute
    0.99
     Савезне
    0.99
     <=",
    0.93
     Мексичка
    0.91
     AssemblyCulture
    0.90
    Autoritní
    0.84
     invokingState
    0.82
     незавершена
    0.82
    Tembelea
    0.82
    idopsis
    0.82
    Act Density 0.144%

    No Known Activations