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

    Neuronpedia

    INDEX
    Explanations

    words related to historical events

    oai_token-act-pair · gpt-3.5-turbo

    references to historical events or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lain
    -1.03
    geon
    -0.84
    arter
    -0.81
    ned
    -0.79
    PT
    -0.77
    elling
    -0.75
    la
    -0.75
    regon
    -0.74
    amus
    -0.74
    liga
    -0.74
    POSITIVE LOGITS
    orical
    1.00
    orically
    1.00
     resil
    0.92
     accur
    0.86
     dramas
    0.86
     history
    0.85
     historical
    0.83
     preservation
    0.83
     relics
    0.82
     revision
    0.82
    Act Density 0.010%

    No Known Activations