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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "plain."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Explanation
    -0.53
     NUKAT
    -0.53
    лтемелер
    -0.51
    yethyl
    -0.50
     OFDb
    -0.50
    bijt
    -0.46
     Winfield
    -0.45
     bluzka
    -0.45
    MIDDLEWARE
    -0.45
    Destroyer
    -0.45
    POSITIVE LOGITS
     plain
    0.71
     regime
    0.70
     regimes
    0.66
     Regime
    0.65
     boss
    0.62
     boot
    0.60
    Boss
    0.59
     boots
    0.59
     Boss
    0.58
     Boots
    0.58
    Act Density 0.053%

    No Known Activations