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

    Neuronpedia

    INDEX
    Explanations

    deceptive behavior and dishonesty in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    出版年
    -0.39
    UIControlState
    -0.38
    ụn
    -0.37
    có
    -0.34
    </tfoot>
    -0.34
    demo
    -0.33
     presump
    -0.33
    Zunanje
    -0.33
    too
    -0.32
     Hohen
    -0.32
    POSITIVE LOGITS
     lied
    0.93
     mentiras
    0.84
     Lying
    0.81
     lying
    0.79
     lies
    0.77
     lie
    0.74
     Lies
    0.73
    谎
    0.73
     liar
    0.70
    Lying
    0.70
    Act Density 0.417%

    No Known Activations