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

    Neuronpedia

    INDEX
    Explanations

    words related to deception through falsification

    oai_token-act-pair · gpt-3.5-turbo

    terms related to falsification or deception

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Kingdoms
    -0.76
    gamer
    -0.67
     Empires
    -0.67
     Revenue
    -0.67
     Gamer
    -0.66
    Battle
    -0.64
    VIS
    -0.64
    AMA
    -0.63
    USA
    -0.62
     Surv
    -0.62
    POSITIVE LOGITS
     fals
    1.19
    ified
    1.02
    ifiable
    1.01
    esty
    0.98
    ifiers
    0.97
    eness
    0.96
    ifying
    0.94
    ifier
    0.92
    acies
    0.91
    arial
    0.90
    Act Density 0.007%

    No Known Activations