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

    Neuronpedia

    INDEX
    Explanations

    descriptions or qualities of technological products

    oai_token-act-pair · gpt-3.5-turbo

    statements describing the attributes or functionalities of products or items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Deaths
    -0.75
     laps
    -0.75
     worries
    -0.73
    cern
    -0.71
     woes
    -0.71
    orsi
    -0.70
    lag
    -0.68
     Situation
    -0.68
     wishes
    -0.67
    ÄŁ
    -0.66
    POSITIVE LOGITS
     versatile
    1.28
     designed
    1.26
     compatible
    1.24
     capable
    1.23
     able
    1.20
     resistant
    1.16
     scalable
    1.12
     flexible
    1.12
     economical
    1.11
     powered
    1.09
    Act Density 0.435%

    No Known Activations