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

    Neuronpedia

    INDEX
    Explanations

    references to centers or hubs of activity and community

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sample
    -0.39
     full
    -0.39
     FULL
    -0.38
     Voll
    -0.37
    dagangan
    -0.37
    命名
    -0.36
     маль
    -0.35
    abar
    -0.35
     propor
    -0.35
     semp
    -0.35
    POSITIVE LOGITS
     centres
    0.84
     centers
    0.80
     foci
    0.79
     Centres
    0.68
    centers
    0.66
    focus
    0.65
    Centers
    0.62
     Focus
    0.61
    Focus
    0.61
     hotspots
    0.60
    Act Density 0.499%

    No Known Activations