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

    Neuronpedia

    INDEX
    Explanations

    words related to political discussions and public policies

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    eri
    -0.81
    alian
    -0.76
    runs
    -0.74
    onomy
    -0.72
    Ve
    -0.72
    ASED
    -0.70
    esi
    -0.70
    ETF
    -0.70
    CT
    -0.69
    oe
    -0.68
    POSITIVE LOGITS
     importantly
    1.17
     advertised
    0.73
     tempted
    0.70
     surely
    0.70
     stressed
    0.67
    ratulations
    0.65
     happened
    0.64
     embold
    0.63
    pired
    0.62
     important
    0.62
    Act Density 0.070%

    No Known Activations