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

    Neuronpedia

    INDEX
    Explanations

    references to community and collaborative efforts regarding development projects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ucker
    -0.15
     Parking
    -0.14
    ypy
    -0.14
    алÑİ
    -0.14
    ASIC
    -0.13
    .Atomic
    -0.13
    ди
    -0.13
    OTA
    -0.13
    bra
    -0.13
     Zheng
    -0.13
    POSITIVE LOGITS
     train
    0.32
     capacity
    0.30
     Capacity
    0.28
    capacity
    0.27
    Capacity
    0.27
    train
    0.27
     Train
    0.26
     capac
    0.25
     capacities
    0.25
     trainers
    0.24
    Act Density 0.094%

    No Known Activations