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

    Neuronpedia

    INDEX
    Explanations

    nuanced questions and reflections on societal and ethical issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sst
    -0.17
    cad
    -0.17
    ????????
    -0.16
    hift
    -0.15
     ??
    -0.15
    alia
    -0.15
    retty
    -0.15
    æĿī
    -0.15
    CDATA
    -0.14
    zung
    -0.14
    POSITIVE LOGITS
    akis
    0.16
     or
    0.16
     Abs
    0.15
    âĢIJ
    0.15
    ãģ®ãĤĪãģĨãģ«
    0.14
     exit
    0.14
     absent
    0.14
    ?↵
    0.14
     Gloss
    0.14
     yoksa
    0.14
    Act Density 0.491%

    No Known Activations