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

    Neuronpedia

    INDEX
    Explanations

    phrases related to central concepts or themes

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     paesaggio
    -0.59
     villaggio
    -0.56
     medesimo
    -0.54
     tramonto
    -0.52
     Isid
    -0.52
    sieur
    -0.51
     prolon
    -0.50
     sabato
    -0.49
     Campionato
    -0.48
     cammino
    -0.48
    POSITIVE LOGITS
     core
    1.34
     Core
    1.26
    core
    1.24
    Core
    1.21
    CORE
    1.10
     CORE
    1.09
     cores
    1.08
    Cores
    0.85
     Cores
    0.82
    cores
    0.76
    Act Density 0.065%

    No Known Activations