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

    Neuronpedia

    INDEX
    Explanations

    informational resources, such as organizations, websites, and datasets

    oai_token-act-pair · gpt-3.5-turbo

    references to sources or additional information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     unforeseen
    -0.57
    pecting
    -0.54
     resemb
    -0.54
     deadliest
    -0.52
    osuke
    -0.50
     capitalize
    -0.50
     stronghold
    -0.50
     balk
    -0.49
    pects
    -0.49
    ItemTracker
    -0.49
    POSITIVE LOGITS
     HERE
    1.76
     here
    1.55
     below
    1.34
    here
    1.10
    below
    1.07
     online
    1.06
     Here
    1.02
     Below
    1.01
     BELOW
    0.95
     herein
    0.93
    Act Density 0.349%

    No Known Activations