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

    Neuronpedia

    INDEX
    Explanations

    scientific or technical terms related to various subjects

    oai_token-act-pair · gpt-3.5-turbo

    key terms related to finance and taxation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bows
    -0.89
    wolves
    -0.83
     cocktails
    -0.81
    skirts
    -0.80
     diets
    -0.79
     noses
    -0.77
    bats
    -0.77
     ceilings
    -0.77
     belts
    -0.77
     Governments
    -0.76
    POSITIVE LOGITS
     item
    1.38
     member
    1.18
     unit
    1.15
     entity
    1.14
     participant
    1.11
     node
    1.10
     piece
    1.06
     element
    1.06
    unit
    1.01
     segment
    1.00
    Act Density 0.560%

    No Known Activations