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

    Neuronpedia

    INDEX
    Explanations

    concepts related to cheating and dishonesty in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ade
    -0.18
     Ø¢Ùħ
    -0.15
    ÑĢен
    -0.14
    usan
    -0.14
    iyan
    -0.14
     bond
    -0.13
    Stripe
    -0.13
     Kültür
    -0.13
    landa
    -0.13
    trand
    -0.13
    POSITIVE LOGITS
     cheating
    0.41
     cheat
    0.39
     che
    0.37
     cheats
    0.35
     Che
    0.33
    -che
    0.31
     cheated
    0.31
     Cheat
    0.30
    _che
    0.29
    che
    0.29
    Act Density 0.143%

    No Known Activations