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

    Neuronpedia

    INDEX
    Explanations

    questions and expressions related to surprise or disbelief

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     الحره
    -0.49
     computadoras
    -0.48
     Biôgrafia
    -0.46
     régulier
    -0.39
     odeur
    -0.38
     actualidad
    -0.38
     rumahnya
    -0.38
     reproductor
    -0.38
     computadora
    -0.37
     perfección
    -0.37
    POSITIVE LOGITS
     Vir
    0.52
     Frederick
    0.48
    ここまで
    0.46
     Pump
    0.46
     Virgil
    0.45
    これだけ
    0.45
    cited
    0.44
    Vir
    0.44
     Flat
    0.44
    lidene
    0.44
    Act Density 0.045%

    No Known Activations