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

    Neuronpedia

    INDEX
    Explanations

    references to legal cases and judicial terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Hang
    -0.15
     inval
    -0.14
    ansa
    -0.14
    antro
    -0.14
     State
    -0.14
    yla
    -0.14
    EDA
    -0.14
    heits
    -0.14
     Bias
    -0.13
    cala
    -0.13
    POSITIVE LOGITS
    ÑĤÑĮ
    0.17
    ether
    0.16
     Lower
    0.15
    538
    0.15
    imer
    0.14
    urai
    0.14
     Gentle
    0.14
     Upper
    0.14
    ообÑĢаз
    0.14
     Madden
    0.13
    Act Density 0.191%

    No Known Activations