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

    Neuronpedia

    INDEX
    Explanations

    phrases related to sharing recipes or food-related content

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     wien
    -0.93
     maer
    -0.90
     Juf
    -0.81
     lele
    -0.80
     parma
    -0.79
     myn
    -0.79
     lara
    -0.79
     inder
    -0.79
     vespa
    -0.78
     tempe
    -0.78
    POSITIVE LOGITS
     disappoint
    1.05
     disappointment
    0.77
     disappointed
    0.66
     disap
    0.61
     disappointing
    0.59
     exceeded
    0.58
     disappointments
    0.58
     expectations
    0.57
    失望
    0.56
     newOwner
    0.56
    Act Density 0.248%

    No Known Activations