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

    Neuronpedia

    INDEX
    Explanations

    high-ranking government officials and diplomats

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals, particularly officials and their titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Hallow
    -0.76
    juries
    -0.74
     Scand
    -0.73
     Proposition
    -0.72
    race
    -0.70
     Huck
    -0.68
     Crow
    -0.68
    represented
    -0.66
     Avalon
    -0.66
     Crom
    -0.65
    POSITIVE LOGITS
     briefed
    1.08
    enei
    1.06
     Jinping
    0.99
    zinski
    0.98
     Lavrov
    0.97
     confid
    0.97
     briefings
    0.96
     memos
    0.96
    plom
    0.94
     tasked
    0.94
    Act Density 0.195%

    No Known Activations