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

    Neuronpedia

    INDEX
    Explanations

    key terms and phrases related to technology and scientific research

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Clik
    -0.70
    ADVERTISEMENT
    -0.69
     p
    -0.66
     Pender
    -0.64
    d
    -0.62
    Datuak
    -0.61
     createState
    -0.61
     Gur
    -0.61
    extAlignment
    -0.60
     Sut
    -0.60
    POSITIVE LOGITS
     himſelf
    1.49
     myſelf
    1.47
     themſelves
    1.45
     whoſe
    1.35
     itſelf
    1.32
     ſeveral
    1.31
     ſtill
    1.26
     againſt
    1.26
     ſy
    1.24
     neceſſ
    1.23
    Act Density 4.474%

    No Known Activations