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

    Neuronpedia

    INDEX
    Explanations

    social and political controversies and related terms

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ©¶æ
    -0.78
    imester
    -0.60
    owler
    -0.59
    htaking
    -0.59
    estern
    -0.56
     Opp
    -0.54
     Mehran
    -0.53
     Nationals
    -0.53
     Zurich
    -0.52
     Suffolk
    -0.51
    POSITIVE LOGITS
     accordingly
    1.28
     instead
    0.94
    '.
    0.92
     therein
    0.90
     altogether
    0.88
     thereof
    0.87
     afterwards
    0.86
     lest
    0.80
     afterward
    0.80
     nonetheless
    0.80
    Act Density 0.882%

    No Known Activations