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

    Neuronpedia

    INDEX
    Explanations

    words related to changes or modifications

    oai_token-act-pair · gpt-3.5-turbo

    terms related to changes or updates in processes, systems, or definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ships
    -0.96
    emi
    -0.78
    Shop
    -0.75
    ledge
    -0.73
    went
    -0.72
    SPONSORED
    -0.72
    Gate
    -0.72
    acht
    -0.71
    Ring
    -0.71
    enges
    -0.70
    POSITIVE LOGITS
     versions
    1.10
     version
    1.07
     embodiment
    0.81
     edition
    0.80
     interrogation
    0.80
     embodiments
    0.70
     chronological
    0.70
     editions
    0.69
     medieval
    0.69
     portions
    0.68
    Act Density 0.111%

    No Known Activations