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

    Neuronpedia

    INDEX
    Explanations

    references to governance or government entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     mathemat
    -0.89
    ItemTracker
    -0.73
    ccording
    -0.73
     obser
    -0.72
     nomine
    -0.72
     incent
    -0.70
     Leilan
    -0.69
     skelet
    -0.68
     sacrific
    -0.66
     fict
    -0.66
    POSITIVE LOGITS
    stein
    0.99
    auld
    0.95
    ning
    0.93
    offs
    0.81
    igans
    0.81
    ahan
    0.81
    iew
    0.81
    chest
    0.80
    adoes
    0.78
    erella
    0.78
    Act Density 0.233%

    No Known Activations