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

    Neuronpedia

    INDEX
    Explanations

    abstract concepts related to philosophical or existential themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uh
    -0.17
    ep
    -0.17
    UCH
    -0.17
    ethe
    -0.16
    uch
    -0.15
    ptune
    -0.14
    figcaption
    -0.14
    icia
    -0.14
    duct
    -0.13
     richt
    -0.13
    POSITIVE LOGITS
    ektor
    0.15
    -Ta
    0.15
    RLF
    0.15
    ClientRect
    0.14
    oulouse
    0.14
    arsers
    0.14
    elerik
    0.14
    zhou
    0.13
    _SU
    0.13
    ManagerInterface
    0.13
    Act Density 0.170%

    No Known Activations