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

    Neuronpedia

    INDEX
    Explanations

    programming constructs and method call patterns in code snippets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ersh
    -0.17
    βά
    -0.15
    asInstanceOf
    -0.14
    avenport
    -0.14
    utches
    -0.14
    ->[
    -0.14
     prob
    -0.14
    cken
    -0.14
    (delegate
    -0.14
     Able
    -0.13
    POSITIVE LOGITS
     null
    0.23
     new
    0.23
    new
    0.23
    (new
    0.20
    null
    0.20
     Arrays
    0.19
    æĸ°çļĦ
    0.19
    ,new
    0.19
    :new
    0.17
    	new
    0.17
    Act Density 0.098%

    No Known Activations