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

    Neuronpedia

    INDEX
    Explanations

    references to significant battles throughout history

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ascript
    -0.82
    ority
    -0.79
    annel
    -0.78
    ringe
    -0.74
     redistributed
    -0.74
    hift
    -0.74
    rency
    -0.73
    aye
    -0.72
    nsic
    -0.70
    ccording
    -0.70
    POSITIVE LOGITS
     Bunker
    0.98
     Roses
    0.94
     Helm
    0.91
     Armageddon
    0.90
     Hearth
    0.87
     Waterloo
    0.85
     Tours
    0.84
     Hastings
    0.84
     Horn
    0.82
     Olympia
    0.80
    Act Density 0.033%

    No Known Activations