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

    Neuronpedia

    INDEX
    Explanations

    phrases related to socioeconomic and political topics

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    yss
    -0.54
    oret
    -0.53
     looph
    -0.49
    yip
    -0.48
    DonaldTrump
    -0.48
    ©¶æ
    -0.46
     CLS
    -0.46
    lict
    -0.45
     Aval
    -0.44
     tiss
    -0.44
    POSITIVE LOGITS
     accordingly
    1.12
     thereafter
    1.05
     thereof
    1.01
    .[
    0.98
     respectively
    0.95
    .(
    0.93
     attRot
    0.92
     therein
    0.91
    .
    0.90
     afterwards
    0.88
    Act Density 1.299%

    No Known Activations