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

    Neuronpedia

    INDEX
    Explanations

    statements and actions characterized by deception or falsehood

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     AssemblyProduct
    -0.80
     виправивши
    -0.76
    autoreleasepool
    -0.76
     onOptions
    -0.75
     calendriers
    -0.74
     AssemblyTitle
    -0.73
    
    -0.68
     >=",
    -0.68
    })));
    -0.67
    참고
    -0.66
    POSITIVE LOGITS
     false
    1.87
     lie
    1.76
     lies
    1.71
     lied
    1.71
     falsehood
    1.67
     mentira
    1.59
    false
    1.58
     False
    1.58
     fake
    1.56
     deception
    1.54
    Act Density 0.778%

    No Known Activations