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

    Neuronpedia

    INDEX
    Explanations

    words related to deception and dishonesty in communication

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

    telling lies to the public

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    期刊论文
    -0.43
     <=",
    -0.42
     nahilalakip
    -0.40
     Lombardo
    -0.39
    httphttps
    -0.38
    setCellStyle
    -0.38
     jaula
    -0.38
     ẩm
    -0.36
     élev
    -0.36
     Übere
    -0.35
    POSITIVE LOGITS
     viewers
    0.54
     readers
    0.53
     voters
    0.53
     listeners
    0.51
    AutoScaleMode
    0.51
     consumers
    0.50
    makeText
    0.50
     audiences
    0.49
     doInBackground
    0.49
     investors
    0.48
    Act Density 0.106%

    No Known Activations