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

    Neuronpedia

    INDEX
    Explanations

    phrases related to deception and concealment of wrongdoing

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

    confession of guilt or trouble

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    #+#
    -0.61
    gerie
    -0.53
    mobileqq
    -0.52
    ulfide
    -0.50
    OGND
    -0.48
    Спољашње
    -0.47
     grated
    -0.47
    NOPQRST
    -0.46
    yelitis
    -0.46
    educt
    -0.46
    POSITIVE LOGITS
     confes
    0.48
     confessed
    0.44
     escondido
    0.42
     guilt
    0.40
    Rüyada
    0.38
     confession
    0.38
     Guilt
    0.36
    SupportActionBar
    0.35
     panik
    0.35
     mengakui
    0.34
    Act Density 0.065%

    No Known Activations