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

    Neuronpedia

    INDEX
    Explanations

    references to mathematical concepts and terms related to data or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    en
    -0.65
    eniz
    -0.28
    enek
    -0.24
    enor
    -0.23
    enin
    -0.21
    enÃŃ
    -0.20
    Ø©
    -0.18
    UnderTest
    -0.16
    ávka
    -0.16
    enler
    -0.16
    POSITIVE LOGITS
    ens
    0.46
    ener
    0.36
    ene
    0.33
    env
    0.33
    ENS
    0.31
    ensch
    0.30
    ense
    0.30
    ening
    0.29
    ened
    0.28
    enc
    0.27
    Act Density 0.103%

    No Known Activations