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

    Neuronpedia

    INDEX
    Explanations

    terms indicating statistical comparisons or relationships between multiple groups or variables

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     is
    -0.50
     El
    -0.49
     g
    -0.48
     re
    -0.47
    …
    -0.47
    rel
    -0.47
     s
    -0.47
     A
    -0.47
     G
    -0.46
    </td>
    -0.46
    POSITIVE LOGITS
     Majefty
    1.06
     defaultstate
    1.05
    writeFieldEnd
    0.98
     myſelf
    0.98
    ſelf
    0.97
     NSCoder
    0.97
     ―――――
    0.96
     ComVisible
    0.94
    0.93
     disambiguazione
    0.92
    Act Density 0.726%

    No Known Activations