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

    Neuronpedia

    INDEX
    Explanations

    words related to political analysis and commentary

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    tnc
    -0.76
    enter
    -0.76
    isible
    -0.76
    enture
    -0.74
    inated
    -0.73
    istance
    -0.70
    ut
    -0.69
    edu
    -0.69
    lees
    -0.68
    sbm
    -0.68
    POSITIVE LOGITS
     admittedly
    1.14
     fortunately
    1.00
     thankfully
    0.97
     interestingly
    0.96
     technically
    0.90
     luckily
    0.90
     beware
    0.87
     occasionally
    0.86
     ideally
    0.86
     curiously
    0.85
    Act Density 0.079%

    No Known Activations