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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to military personnel and operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SourceFile
    -0.76
    pher
    -0.74
     skelet
    -0.73
    ramid
    -0.69
    phrine
    -0.68
     queens
    -0.68
    */(
    -0.67
     opera
    -0.66
     rhy
    -0.65
    estone
    -0.65
    POSITIVE LOGITS
     Mattis
    1.05
     David
    0.87
     Douglas
    0.87
     Michael
    0.85
     Larry
    0.85
     John
    0.84
     Pierre
    0.84
     Philip
    0.84
     Lawrence
    0.83
     Jeffrey
    0.83
    Act Density 0.011%

    No Known Activations