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

    Neuronpedia

    INDEX
    Explanations

    phrases related to international politics and nuclear programs

    oai_token-act-pair · gpt-3.5-turbo

    references to nuclear weapons and related military actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Died
    -0.84
    iences
    -0.82
    letcher
    -0.73
    phies
    -0.73
    JECT
    -0.73
     Alloy
    -0.72
     Slot
    -0.69
     folders
    -0.67
     Ellison
    -0.67
     DeL
    -0.67
    POSITIVE LOGITS
     annexed
    1.23
     sovereign
    1.08
     Lavrov
    1.04
     annexation
    1.04
     diplomatic
    1.01
     sovereignty
    0.99
     territorial
    0.99
     authoritarian
    0.98
     milit
    0.95
     destabil
    0.95
    Act Density 0.556%

    No Known Activations