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

    Neuronpedia

    INDEX
    Explanations

    technical issues or problems in a context

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     vogli
    -0.66
     voglio
    -0.65
    Serviço
    -0.64
     vedo
    -0.61
    Personendaten
    -0.61
     interessa
    -0.60
     vogliamo
    -0.59
     penso
    -0.59
     vorrei
    -0.59
    Ilustra
    -0.58
    POSITIVE LOGITS
     tolerably
    0.94
     nobly
    0.86
     gaily
    0.86
     beaute
    0.84
     withal
    0.82
     unwarran
    0.82
     unce
    0.80
     pite
    0.79
     schoolmaster
    0.78
     surmounted
    0.76
    Act Density 0.380%

    No Known Activations