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

    Neuronpedia

    INDEX
    Explanations

    data related to coding and technical specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Voc
    -0.73
    SHARE
    -0.69
     Cosponsors
    -0.64
     Charity
    -0.64
     Libertarian
    -0.64
     Nass
    -0.63
     Kerry
    -0.62
     Occupations
    -0.61
     Turtles
    -0.59
     Stamford
    -0.59
    POSITIVE LOGITS
    0000
    1.05
    000000
    1.01
    429
    1.01
    644
    0.98
    978
    0.97
    fc
    0.93
    ffe
    0.92
    248
    0.92
    377
    0.92
    368
    0.91
    Act Density 0.016%

    No Known Activations