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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating candidacy and political elections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     saites
    -0.86
    saraba
    -0.71
    InteropServices
    -0.67
    LabelTagHelper
    -0.66
    GeneratedValue
    -0.64
     Commencez
    -0.63
    titian
    -0.61
     setuptools
    -0.60
    </tfoot>
    -0.60
    atouille
    -0.59
    POSITIVE LOGITS
     candidates
    1.00
     candidate
    0.97
     candidacy
    0.86
    candidate
    0.85
     Candidates
    0.85
     Candidate
    0.83
    candidates
    0.79
    Candidates
    0.78
    andid
    0.76
     kandid
    0.74
    Act Density 0.249%

    No Known Activations