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

    Neuronpedia

    INDEX
    Explanations

    phrases related to social structures and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    obook
    -0.75
     unfocusedRange
    -0.70
    ocracy
    -0.64
    chair
    -0.63
    ropolis
    -0.63
    pod
    -0.63
    aroo
    -0.62
    phas
    -0.61
    bus
    -0.61
     Tuc
    -0.59
    POSITIVE LOGITS
     respectively
    1.48
     alike
    1.27
     mutually
    1.03
     intertwined
    1.03
     jointly
    0.99
     trademarks
    0.95
     insepar
    0.92
     examples
    0.90
     fronts
    0.88
     both
    0.86
    Act Density 0.214%

    No Known Activations