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

    Neuronpedia

    INDEX
    Explanations

    references to significant events and their impact on society

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Sharing
    -0.17
     AppBundle
    -0.16
     learning
    -0.16
     sharing
    -0.15
    516
    -0.15
    ikan
    -0.15
     attending
    -0.15
    olt
    -0.14
    ĢìĿ´
    -0.14
     suppressed
    -0.14
    POSITIVE LOGITS
     causing
    0.24
     driving
    0.21
     infect
    0.20
     oblig
    0.20
     leaving
    0.19
    Driving
    0.19
     Driving
    0.19
    ãĥªãĥ¼ãĤº
    0.19
     affecting
    0.19
    SETTING
    0.19
    Act Density 0.468%

    No Known Activations