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

    Neuronpedia

    INDEX
    Explanations

    phrases related to patriotism and national identity

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing community ties and the importance of local values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DoS
    -0.85
    ebin
    -0.75
     scenarios
    -0.70
     spoilers
    -0.70
    obin
    -0.68
     Correct
    -0.66
     dummy
    -0.65
     indications
    -0.65
     escalating
    -0.65
     escalation
    -0.65
    POSITIVE LOGITS
     cherish
    0.99
     cherished
    0.94
     heritage
    0.92
     embodies
    0.92
     nurt
    0.90
    pires
    0.88
     humankind
    0.88
     traditions
    0.86
     cornerstone
    0.85
     dearly
    0.84
    Act Density 0.604%

    No Known Activations