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

    Neuronpedia

    INDEX
    Explanations

    comparisons using the word "like"

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    Biografía
    -0.43
    营
    -0.42
    утбо
    -0.42
    новништво
    -0.42
     vulnerables
    -0.41
    參考文獻
    -0.40
    OLIC
    -0.40
     ж
    -0.39
    Column
    -0.39
    Kaynakça
    -0.39
    POSITIVE LOGITS
     shenan
    0.80
     nutella
    0.77
     indestru
    0.76
     impra
    0.75
     reluct
    0.75
     thermomix
    0.74
     gild
    0.73
     tupperware
    0.71
     Mlle
    0.71
     viciss
    0.71
    Act Density 0.101%

    No Known Activations