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

    Neuronpedia

    INDEX
    Explanations

    terms related to software functionalities and capabilities

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    greja
    -0.56
     Vitamina
    -0.56
    URSS
    -0.56
     praktik
    -0.54
     kriminal
    -0.54
    calciatore
    -0.53
    trás
    -0.53
     konserv
    -0.52
     vitamina
    -0.52
     bü
    -0.50
    POSITIVE LOGITS
     hairc
    1.06
     swarovski
    0.96
     gaily
    0.91
     simpsons
    0.86
     apprehen
    0.84
     eiffel
    0.83
     jared
    0.83
     snoopy
    0.82
     tolerably
    0.82
     tupperware
    0.81
    Act Density 0.122%

    No Known Activations