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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political discourse and societal issues

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     CoC
    -0.65
    ãĤ¼ãĤ¦ãĤ¹
    -0.63
     Piper
    -0.57
     Exile
    -0.56
     Sov
    -0.56
     offsets
    -0.56
     subtitles
    -0.55
     tender
    -0.54
     shorth
    -0.54
     substitutes
    -0.53
    POSITIVE LOGITS
    culus
    0.86
    ceans
    0.83
    rient
    0.83
    anmar
    0.82
    arks
    0.81
    uckland
    0.80
    lymp
    0.80
    oops
    0.80
    avascript
    0.79
    berman
    0.76
    Act Density 7.422%

    No Known Activations