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

    Neuronpedia

    INDEX
    Explanations

    terms related to the Pentagon

    oai_token-act-pair · gpt-3.5-turbo

    references to the Pentagon

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    âĸ¬âĸ¬
    -0.76
    gger
    -0.75
    âĸ¬
    -0.75
    PER
    -0.74
    lihood
    -0.72
    Interstitial
    -0.72
    à
    -0.71
    bars
    -0.67
    Redd
    -0.67
    combe
    -0.63
    POSITIVE LOGITS
     Papers
    1.05
     Pentagon
    0.92
    arium
    0.79
    selage
    0.79
     annex
    0.77
     brass
    0.76
     SEAL
    0.75
     contractors
    0.74
     bureaucracy
    0.74
     Plaza
    0.73
    Act Density 0.013%

    No Known Activations