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

    Neuronpedia

    INDEX
    Explanations

    references to countries' allies or partnerships

    oai_token-act-pair · gpt-3.5-turbo

    references to allies in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aul
    -0.88
    nit
    -0.79
    Minecraft
    -0.77
    cer
    -0.72
    Luck
    -0.71
    asty
    -0.70
    OUT
    -0.70
    nutrition
    -0.68
    iday
    -0.67
    KEY
    -0.67
    POSITIVE LOGITS
     allies
    1.20
     Allies
    1.04
     ally
    0.98
     foe
    0.90
     collaborators
    0.89
     adversaries
    0.89
     allied
    0.88
     Ally
    0.84
     collaborator
    0.84
     agre
    0.82
    Act Density 0.011%

    No Known Activations