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

    Neuronpedia

    INDEX
    Explanations

    behaviors and traits related to deception and pretense

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

    acting interested or coy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    cakup
    -0.30
     bowiem
    -0.28
     cabinet
    -0.28
     dataSnapshot
    -0.28
     fore
    -0.27
    origami
    -0.26
     무
    -0.26
     Tre
    -0.26
    SqlQuery
    -0.26
    JdbcTemplate
    -0.25
    POSITIVE LOGITS
     pretending
    0.68
     feign
    0.65
    findpost
    0.64
     pretended
    0.62
     pretense
    0.62
     pretends
    0.59
     pretence
    0.57
     PeEnEo
    0.57
    InitVars
    0.55
    asymp
    0.55
    Act Density 0.043%

    No Known Activations