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

    Neuronpedia

    INDEX
    Explanations

    strings and patterns with dollar signs ($) and references to variables

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tanleria
    -0.86
     BorderRadius
    -0.80
     defaultstate
    -0.79
    wahati
    -0.79
    \}\\
    -0.78
     SWE
    -0.78
     Waray
    -0.76
     rhestr
    -0.75
    myspace
    -0.73
    Vorlage
    -0.72
    POSITIVE LOGITS
    $
    1.11
     $
    1.07
     \$
    1.04
    #$
    0.90
    //$
    0.88
    :$
    0.88
    ~$
    0.87
     //$
    0.85
    ='$
    0.84
    $\$
    0.82
    Act Density 0.443%

    No Known Activations