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

    Neuronpedia

    INDEX
    Explanations

    phrases related to deception and trickery

    oai_token-act-pair · gpt-3.5-turbo

    words related to deception and trickery

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     occupation
    -0.73
    hazard
    -0.62
     fixtures
    -0.62
    Interstitial
    -0.61
     hardships
    -0.60
     fixture
    -0.59
     Cheong
    -0.58
    Ü
    -0.58
     reminder
    -0.57
     cleanup
    -0.57
    POSITIVE LOGITS
     gull
    0.89
    ingly
    0.89
    ulent
    0.82
    glers
    0.79
     unwitting
    0.78
    ibly
    0.78
     deceived
    0.76
    ery
    0.75
     tricked
    0.75
    ython
    0.72
    Act Density 0.039%

    No Known Activations