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

    Neuronpedia

    INDEX
    Explanations

    names of politicians and political figures

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    pmwiki
    -0.92
    sites
    -0.83
    exempt
    -0.82
    fecture
    -0.79
    leaders
    -0.77
    cffff
    -0.76
    dayName
    -0.75
    saf
    -0.73
    align
    -0.72
    cffffcc
    -0.71
    POSITIVE LOGITS
     Moore
    1.25
     Roberts
    1.25
     Walsh
    1.24
     Reed
    1.24
     Smith
    1.24
     Hansen
    1.24
     Miller
    1.23
     Evans
    1.22
     Robinson
    1.22
     Dixon
    1.22
    Act Density 2.596%

    No Known Activations