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

    Neuronpedia

    INDEX
    Explanations

    references to governance and institutional structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ardon
    -0.17
    anford
    -0.15
    acs
    -0.15
    amber
    -0.15
    ehen
    -0.14
    intr
    -0.14
    ots
    -0.14
    ÑĢÑĸд
    -0.14
    atus
    -0.14
    _DSP
    -0.14
    POSITIVE LOGITS
    elman
    0.17
    alem
    0.16
    bote
    0.14
    æIJŃ
    0.14
    rez
    0.14
     Mitt
    0.14
     sÃŃ
    0.14
    036
    0.14
    urtle
    0.14
     pand
    0.13
    Act Density 0.477%

    No Known Activations