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

    Neuronpedia

    INDEX
    Explanations

    opinions expressed about political views and statements

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Faster
    -0.67
    delay
    -0.63
    aunts
    -0.63
    trap
    -0.61
     Furious
    -0.59
    asks
    -0.59
    gins
    -0.58
    rolled
    -0.58
     brut
    -0.58
    gi
    -0.57
    POSITIVE LOGITS
     editorial
    0.94
     opinions
    0.86
    ãĥĦ
    0.74
     affiliate
    0.72
     endorsement
    0.72
     Editorial
    0.71
     satire
    0.69
     opinion
    0.68
    EngineDebug
    0.68
     subjective
    0.67
    Act Density 0.256%

    No Known Activations