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

    Neuronpedia

    INDEX
    Explanations

    different forms or types of objects or concepts

    oai_token-act-pair · gpt-3.5-turbo

    references to various forms and types

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    some
    -0.81
    days
    -0.79
    eks
    -0.77
    quet
    -0.74
    dash
    -0.73
    few
    -0.73
    kids
    -0.73
    erves
    -0.72
    parts
    -0.72
    esses
    -0.71
    POSITIVE LOGITS
     transportation
    0.91
     warfare
    0.89
     communication
    0.89
     oppression
    0.88
     accommodation
    0.86
     contraception
    0.84
     weaponry
    0.84
     propulsion
    0.84
     activity
    0.84
     organization
    0.84
    Act Density 0.087%

    No Known Activations