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

    Neuronpedia

    INDEX
    Explanations

    references to deception or falsehoods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    lie / lies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Woodstock
    -0.58
    Normally
    -0.56
    onato
    -0.56
     PMA
    -0.56
     Carnaval
    -0.55
    GPP
    -0.55
     Ammon
    -0.53
     Carthag
    -0.53
    Davidson
    -0.53
     ECR
    -0.53
    POSITIVE LOGITS
     lies
    1.91
     Lies
    1.78
    Lies
    1.68
     lie
    1.41
    lies
    1.41
     mentiras
    1.27
     mentira
    1.09
     Lie
    1.04
    lie
    1.01
     lying
    0.97
    Act Density 0.007%

    No Known Activations