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

    Neuronpedia

    INDEX
    Explanations

    references to military invasions or attacks

    oai_token-act-pair · gpt-3.5-turbo

    references to invasions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ndra
    -0.81
    mpeg
    -0.77
    uctor
    -0.73
    etooth
    -0.71
    affer
    -0.68
    ector
    -0.68
    WE
    -0.68
    peer
    -0.67
    chain
    -0.67
    spot
    -0.66
    POSITIVE LOGITS
     invasion
    0.85
    ãĥ³ãĤ¸
    0.81
     Barbarian
    0.78
    naires
    0.77
     armies
    0.74
     force
    0.73
    naire
    0.72
     warfare
    0.71
    asions
    0.70
    prising
    0.70
    Act Density 0.046%

    No Known Activations