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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political and social controversies

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     contex
    -0.78
     Simult
    -0.73
     solidar
    -0.72
     robus
    -0.70
     récolte
    -0.70
     rémun
    -0.68
     metast
    -0.68
     diffusi
    -0.68
     logistique
    -0.67
     hiér
    -0.67
    POSITIVE LOGITS
     of
    0.76
    krivelse
    0.69
     pleaf
    0.63
     caufe
    0.62
     perfons
    0.59
     thereof
    0.58
     ftill
    0.58
     firft
    0.56
     occafion
    0.56
     venit
    0.56
    Act Density 0.434%

    No Known Activations