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

    Neuronpedia

    INDEX
    Explanations

    descriptions or opinions about favorites or preferences

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     iesp
    -0.58
    Statistiche
    -0.56
    "]));
    -0.54
    ")"
    -0.54
    "/",
    -0.53
    ">...
    -0.52
    ]),
    -0.51
    '])->
    -0.50
    ])){
    -0.50
    ]*(
    -0.49
    POSITIVE LOGITS
     favorite
    0.85
     Favorite
    0.74
     FAVORITE
    0.72
    favorite
    0.70
     favorites
    0.68
     maneu
    0.67
    Favorite
    0.67
     Compañ
    0.66
    orite
    0.65
     favourite
    0.65
    Act Density 0.083%

    No Known Activations