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

    Neuronpedia

    INDEX
    Explanations

    words related to categorization or grouping

    oai_token-act-pair · gpt-3.5-turbo

    references to data organization and documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ient
    -0.70
    aughs
    -0.68
    illard
    -0.67
    oute
    -0.65
    urse
    -0.64
     Thing
    -0.61
    BUG
    -0.60
     Empress
    -0.57
    agra
    -0.56
     Tycoon
    -0.55
    POSITIVE LOGITS
    paces
    1.21
    pace
    1.14
    hops
    1.14
    hips
    1.09
    heet
    1.05
    afety
    1.05
    mith
    1.01
    chool
    1.00
    hots
    1.00
    hooting
    1.00
    Act Density 0.285%

    No Known Activations