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

    Neuronpedia

    INDEX
    Explanations

    terms related to rarity and exceptional cases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ModelState
    -0.65
    บาย
    -0.64
     allemaal
    -0.56
    PhysRevD
    -0.56
     springfox
    -0.56
     esternos
    -0.55
    ikkert
    -0.53
    ListNode
    -0.52
    asiest
    -0.51
     instantaneously
    -0.51
    POSITIVE LOGITS
     rare
    1.37
     rarer
    1.22
    Rare
    1.20
     Rare
    1.20
    rare
    1.17
     rarity
    1.14
     rares
    1.05
     RARE
    1.04
     rarest
    1.03
     Rarely
    0.87
    Act Density 0.266%

    No Known Activations