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

    Neuronpedia

    INDEX
    Explanations

    mathematical concepts and terms related to computational methods and their properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eurs
    -0.17
     Haut
    -0.16
    ideo
    -0.15
    nil
    -0.14
    assy
    -0.14
    bak
    -0.14
    Functional
    -0.14
     Depend
    -0.14
    dbg
    -0.14
    erie
    -0.13
    POSITIVE LOGITS
     tract
    0.23
     concept
    0.21
     natural
    0.20
    straight
    0.19
     math
    0.19
     intr
    0.18
     comput
    0.17
     straight
    0.17
     observation
    0.17
     conservative
    0.17
    Act Density 0.069%

    No Known Activations