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

    Neuronpedia

    INDEX
    Explanations

    references to numbers and their associated contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    åłĤ
    -0.17
     Ende
    -0.16
    sta
    -0.16
    ockey
    -0.15
    \Active
    -0.15
    ayet
    -0.14
    ган
    -0.14
    _pins
    -0.14
    lland
    -0.14
    uars
    -0.14
    POSITIVE LOGITS
     Citizen
    0.16
    ets
    0.16
     citizen
    0.15
    913
    0.14
     Citizens
    0.14
    891
    0.14
    acre
    0.14
    Å¡et
    0.14
     hands
    0.13
     civ
    0.13
    Act Density 0.009%

    No Known Activations