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

    Neuronpedia

    INDEX
    Explanations

    countries that vote in a particular way on specific issues or controversies

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    enser
    -0.68
    oler
    -0.68
    catentry
    -0.62
    rome
    -0.61
    pipe
    -0.61
    pecting
    -0.60
    imer
    -0.60
    dayName
    -0.60
    orce
    -0.59
    ammed
    -0.59
    POSITIVE LOGITS
     include
    1.25
    :-
    1.20
     includ
    1.08
    *:
    1.07
    :[
    1.02
     Include
    0.93
     Included
    0.89
    include
    0.88
     varied
    0.87
    :,
    0.86
    Act Density 2.633%

    No Known Activations