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

    Neuronpedia

    INDEX
    Explanations

    instances of deception, falsification, misrepresentation, and misleading statements

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with deception and the act of falsification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aho
    -0.72
    optional
    -0.72
    soc
    -0.69
     Infantry
    -0.67
    lov
    -0.66
    til
    -0.66
    Streamer
    -0.66
    tis
    -0.66
    areth
    -0.66
    bour
    -0.66
    POSITIVE LOGITS
     falsely
    0.98
     deception
    0.97
     misrepresent
    0.97
     allegations
    0.91
     extortion
    0.90
     deceit
    0.89
     omission
    0.88
     accusations
    0.87
     billing
    0.85
     fals
    0.85
    Act Density 0.266%

    No Known Activations