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

    Neuronpedia

    INDEX
    Explanations

    concepts related to complexity and depth in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    outu
    -0.15
    .DAL
    -0.15
    ungle
    -0.14
    Ä±ÅŁÄ±k
    -0.14
    unca
    -0.14
    داÙħ
    -0.14
    amus
    -0.14
     pace
    -0.13
    Ŀ
    -0.13
    -addon
    -0.13
    POSITIVE LOGITS
     depth
    0.16
     Boulevard
    0.16
    бÑĥÑĢг
    0.15
     richer
    0.14
     layer
    0.14
     grad
    0.14
     beta
    0.14
     OnInit
    0.13
    θοÏĤ
    0.13
     Russ
    0.13
    Act Density 0.073%

    No Known Activations