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

    Neuronpedia

    INDEX
    Explanations

    phrases related to being caught in a negative or incriminating situation

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "caught"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    issance
    -0.65
    study
    -0.65
    ukong
    -0.64
    guided
    -0.64
    olas
    -0.64
    VERTISEMENT
    -0.61
    enthal
    -0.61
     ceremonies
    -0.61
    profits
    -0.60
    urai
    -0.59
    POSITIVE LOGITS
     unprepared
    1.13
     cheating
    0.91
     plagiar
    0.91
     stealing
    0.91
     tampering
    0.90
     unaware
    0.90
     violating
    0.75
     sneaking
    0.74
    gling
    0.74
     dere
    0.74
    Act Density 0.026%

    No Known Activations