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

    Neuronpedia

    INDEX
    Explanations

    sections marked with formatting or syntax indicators typical in structured data or code segments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cæsar
    -0.57
     Danza
    -0.57
    tvguidetime
    -0.55
     fubject
    -0.52
     perfons
    -0.52
     ftate
    -0.52
     mwan
    -0.51
     neceff
    -0.50
     Monfieur
    -0.50
     posterity
    -0.49
    POSITIVE LOGITS
    帖最后由
    0.75
     InputDecoration
    0.69
    waitKey
    0.66
    StoreMessageInfo
    0.63
    omiast
    0.61
    willReturn
    0.60
    зулта
    0.60
     autorytatywna
    0.59
    GetMapping
    0.57
    Erreferentziak
    0.57
    Act Density 0.048%

    No Known Activations