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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude and appreciation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Lottery
    -0.25
     Lifecycle
    -0.25
    Locator
    -0.25
     Lear
    -0.23
    LEC
    -0.23
     Leak
    -0.23
    Lite
    -0.23
     Lowe
    -0.23
     Libre
    -0.22
     Leakage
    -0.22
    POSITIVE LOGITS
    -l
    0.66
     л
    0.52
    _l
    0.50
     l
    0.46
    	l
    0.44
     ल
    0.43
    .l
    0.43
    -L
    0.42
    l
    0.41
    ÂłL
    0.40
    Act Density 0.949%

    No Known Activations