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

    Neuronpedia

    INDEX
    Explanations

    references to popular television shows or series

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ongo
    -0.19
    erial
    -0.16
    iare
    -0.16
    iano
    -0.15
    Mid
    -0.15
    atori
    -0.15
    inch
    -0.14
    dn
    -0.14
    laus
    -0.14
     tess
    -0.14
    POSITIVE LOGITS
    æľºåħ³
    0.16
    ãĥĥãĥĪ
    0.16
    ãĥ¼ãĥĹ
    0.15
    ync
    0.15
    Inflater
    0.15
     originally
    0.15
    ãĥ³ãĥķ
    0.14
    лива
    0.14
    æģ¯
    0.14
    WR
    0.14
    Act Density 6.857%

    No Known Activations