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

    Neuronpedia

    INDEX
    Explanations

    concepts related to computational complexity and efficiency in algorithms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    engers
    -0.15
    enin
    -0.15
    ral
    -0.15
    mgr
    -0.15
     Dew
    -0.14
    515
    -0.14
    grim
    -0.14
     Lamb
    -0.14
     verso
    -0.14
    htub
    -0.14
    POSITIVE LOGITS
     worst
    0.25
     O
    0.22
     worse
    0.22
     Worst
    0.20
     Worse
    0.19
     complexity
    0.18
     linear
    0.18
    linear
    0.17
    -linear
    0.17
     Complexity
    0.17
    Act Density 0.052%

    No Known Activations