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

    Neuronpedia

    INDEX
    Explanations

    different types of items or objects

    oai_token-act-pair · gpt-3.5-turbo

    nouns related to geological and structural elements, as well as commodities and vehicles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Origins
    -0.59
     Nightmares
    -0.58
     Partnership
    -0.55
     Bulldogs
    -0.55
     Apostle
    -0.53
    owder
    -0.52
    ilogy
    -0.52
    SPONSORED
    -0.51
     predicament
    -0.50
     Neh
    -0.50
    POSITIVE LOGITS
    peed
    1.09
    paces
    1.08
    mith
    1.05
    hift
    1.02
    hips
    1.02
    pace
    1.00
    pring
    0.98
    hip
    0.97
    creen
    0.95
    heet
    0.94
    Act Density 0.658%

    No Known Activations