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

    Neuronpedia

    INDEX
    Explanations

    mentions of military bases

    oai_token-act-pair · gpt-3.5-turbo

    mentions of military bases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    icut
    -0.78
    obs
    -0.73
    ulp
    -0.72
    Interstitial
    -0.68
    icol
    -0.67
    aning
    -0.66
    chrom
    -0.66
    apes
    -0.64
    soDeliveryDate
    -0.64
    inventoryQuantity
    -0.64
    POSITIVE LOGITS
    camp
    1.10
     erosion
    0.85
    BALL
    0.78
     camp
    0.76
     garrison
    0.75
    ball
    0.75
     commander
    0.74
     stationed
    0.73
    achev
    0.73
    bsite
    0.72
    Act Density 0.031%

    No Known Activations