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

    Neuronpedia

    INDEX
    Explanations

    phrases related to distraction or covering up potential issues

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to distraction techniques or obfuscation strategies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    romy
    -0.80
     varies
    -0.71
    ®,
    -0.70
    throp
    -0.67
    azes
    -0.66
    uties
    -0.66
    rones
    -0.65
    cients
    -0.65
     molded
    -0.65
    FTWARE
    -0.64
    POSITIVE LOGITS
     publicity
    1.28
     embarrassing
    1.14
     embarrassment
    1.12
     retribution
    1.01
     retaliation
    0.98
     incrim
    0.95
     discredit
    0.94
     embarrass
    0.94
     scapego
    0.88
     retali
    0.87
    Act Density 0.743%

    No Known Activations