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

    Neuronpedia

    INDEX
    Explanations

    structural elements and syntax patterns in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ³³
    -0.18
     Âł
    -0.16
    urst
    -0.15
     manner
    -0.15
     Sav
    -0.15
    ago
    -0.15
    udes
    -0.15
    ģ
    -0.14
    icy
    -0.14
     att
    -0.14
    POSITIVE LOGITS
    	↵
    0.22
        ↵
    0.22
            ↵
    0.21
    		↵
    0.20
     ↵↵
    0.17
    ãĢĢ↵
    0.16
    	č↵
    0.16
    			↵
    0.16
    quo
    0.15
    	    ↵
    0.15
    Act Density 0.346%

    No Known Activations