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

    Neuronpedia

    INDEX
    Explanations

    punctuated sentences and their structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     CGRectGet
    -0.14
    quir
    -0.14
    rej
    -0.13
     none
    -0.13
    ysa
    -0.13
    reten
    -0.13
    죽
    -0.13
     gdy
    -0.13
     majority
    -0.13
    kou
    -0.13
    POSITIVE LOGITS
     Drawing
    0.30
    Drawing
    0.28
     drawing
    0.27
     Through
    0.27
     Specifically
    0.25
    drawing
    0.25
    Through
    0.24
     through
    0.23
     Armed
    0.22
     building
    0.21
    Act Density 0.244%

    No Known Activations