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

    Neuronpedia

    INDEX
    Explanations

    pretend

    np_max-act · gemini-2.0-flash

    instances of the act of pretending or role-playing scenarios.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     whistle
    -0.08
     airstrikes
    -0.07
     subsection
    -0.07
    Analysis
    -0.07
    lemma
    -0.07
     DIS
    -0.07
     IX
    -0.07
     fishermen
    -0.07
     mitochond
    -0.07
     miner
    -0.07
    POSITIVE LOGITS
     pretending
    0.12
     pretend
    0.10
     pretended
    0.09
    ständ
    0.07
     cling
    0.07
    reib
    0.07
     얼굴
    0.07
     pagar
    0.06
    inqu
    0.06
    έντ
    0.06
    Act Density 0.005%

    No Known Activations