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

    Neuronpedia

    INDEX
    Explanations

    sentences related to legal and political systems, with a possible focus on reform and discrimination

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -0.85
     cytoplas
    -0.79
     repug
    -0.68
     Bartholo
    -0.66
     ingrat
    -0.66
     déterminé
    -0.64
     Backman
    -0.63
     McLaugh
    -0.63
     Juf
    -0.62
     unspeak
    -0.62
    POSITIVE LOGITS
     outdated
    0.66
     inadequate
    0.56
     needs
    0.53
     inefficient
    0.53
     obsolete
    0.51
     flaws
    0.50
     flawed
    0.47
     malfunction
    0.47
     ineffective
    0.47
     system
    0.47
    Act Density 0.529%

    No Known Activations