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

    Neuronpedia

    INDEX
    Explanations

    specific words related to dishonesty or cheating

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SceneManagement
    -0.76
    gapi
    -0.74
     Koh
    -0.74
     Fonseca
    -0.73
     NCT
    -0.73
     REACT
    -0.73
    ToObject
    -0.73
     DiCaprio
    -0.71
    Volker
    -0.71
    IGraphics
    -0.71
    POSITIVE LOGITS
     Che
    2.11
    Che
    2.00
     che
    1.99
     CHE
    1.84
    che
    1.65
    CHE
    1.53
     cheating
    1.39
     Chet
    1.32
     cheetah
    1.26
     cheats
    1.25
    Act Density 0.057%

    No Known Activations