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

    Neuronpedia

    INDEX
    Explanations

    phrases related to societal issues and controversies

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    Lma
    -0.88
     Darío
    -0.88
    Lmfao
    -0.86
     viciss
    -0.84
     Darum
    -0.80
     suspic
    -0.79
     churrasco
    -0.78
    Hahah
    -0.76
     repug
    -0.74
     doctr
    -0.74
    POSITIVE LOGITS
     These
    0.66
    ↵↵
    0.64
    ‎‎
    0.63
     Such
    0.63
     This
    0.63
     They
    0.59
     %).
    0.59
     Resultat
    0.59
     :</
    0.59
    ),),
    0.58
    Act Density 0.793%

    No Known Activations