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

    Neuronpedia

    INDEX
    Explanations

    abbreviations or acronyms related to scientific terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ་་
    -1.31
     itſelf
    -1.22
    Autoritní
    -1.18
     defaultstate
    -1.18
     ―――――
    -1.13
    #+#
    -1.12
    AddTagHelper
    -1.10
    Tikang
    -1.06
     faſt
    -1.04
     myſelf
    -1.01
    POSITIVE LOGITS
     M
    0.84
     P
    0.72
     L
    0.68
     G
    0.67
     R
    0.67
    FO
    0.66
     W
    0.65
     T
    0.65
    p
    0.65
     H
    0.64
    Act Density 0.925%

    No Known Activations