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

    Neuronpedia

    INDEX
    Explanations

    significant quotes and phrases that encapsulate key ideas or sentiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ần
    -0.15
    onta
    -0.14
    oup
    -0.14
    ForKey
    -0.14
    69
    -0.13
     narratives
    -0.13
     Assurance
    -0.13
    orts
    -0.13
    emark
    -0.13
    ån
    -0.12
    POSITIVE LOGITS
     sum
    0.38
     sums
    0.37
    sum
    0.30
     Sum
    0.30
     summ
    0.28
     summed
    0.27
     encaps
    0.26
    Sum
    0.26
    =sum
    0.26
     captures
    0.26
    Act Density 0.179%

    No Known Activations