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

    Neuronpedia

    INDEX
    Explanations

    calls for audience engagement and feedback

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    renheit
    -0.81
    ranean
    -0.69
     Lauder
    -0.67
    virt
    -0.67
    ritical
    -0.66
    ãĥ³ãĤ¸
    -0.66
    netflix
    -0.64
    literally
    -0.64
    ortality
    -0.63
    alloc
    -0.63
    POSITIVE LOGITS
     suggestions
    1.27
     suggestion
    1.11
     Suggest
    1.07
     helpful
    1.04
     sugg
    1.03
    comments
    1.03
     feedback
    0.99
     corrections
    0.98
     thoughts
    0.98
     comments
    0.96
    Act Density 0.476%

    No Known Activations