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

    Neuronpedia

    INDEX
    Explanations

    adjectives ending in 'y' with a positive connotation

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    🕗
    -0.81
     Doğ
    -0.71
     Ağ
    -0.69
    alnız
    -0.67
     الحره
    -0.66
    accéder
    -0.65
     simplif
    -0.64
    település
    -0.64
    DataPropertyName
    -0.62
    ędzynarod
    -0.61
    POSITIVE LOGITS
     carina
    0.67
     spacy
    0.64
     sneaky
    0.62
    y
    0.61
    uzzy
    0.61
    licky
    0.60
     bumpy
    0.60
     galleria
    0.60
     vecchia
    0.58
     rainy
    0.58
    Act Density 0.292%

    No Known Activations