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

    Neuronpedia

    INDEX
    Explanations

    references to political and social issues

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÄŁ
    -0.22
    ãĥĥãĥĪ
    -0.21
    DragonMagazine
    -0.21
    emale
    -0.20
     toile
    -0.20
    Þ
    -0.20
    imester
    -0.19
    ÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤ
    -0.19
    Merit
    -0.19
    ÃįÃį
    -0.18
    POSITIVE LOGITS
     meanwhile
    0.21
     similarly
    0.18
     however
    0.17
     nonetheless
    0.17
     similar
    0.17
     comparable
    0.17
    anwhile
    0.17
     paired
    0.17
     meantime
    0.17
     explanatory
    0.17
    Act Density 11.996%

    No Known Activations