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

    Neuronpedia

    INDEX
    Explanations

    complex programming structures and assertions in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ar
    -0.25
     al
    -0.22
     alex
    -0.21
     arb
    -0.19
     aph
    -0.19
     ag
    -0.18
     alice
    -0.18
    (aa
    -0.18
     apache
    -0.18
     alo
    -0.18
    POSITIVE LOGITS
     App
    0.35
     Ax
    0.34
     Ac
    0.33
     Assert
    0.33
     Ap
    0.33
    	Assert
    0.32
     Air
    0.30
    	App
    0.29
    -A
    0.29
     ãĤ¢
    0.29
    Act Density 0.177%

    No Known Activations