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

    Neuronpedia

    INDEX
    Explanations

    numerical values and their contextual significance in various statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     négociations
    -0.65
    CrossRef
    -0.61
     poveznice
    -0.59
     écrans
    -0.58
     débats
    -0.58
    EndProject
    -0.58
    Variants
    -0.57
     âmes
    -0.57
     mères
    -0.57
     regeringen
    -0.56
    POSITIVE LOGITS
     things
    1.78
    Things
    1.09
     Things
    1.06
     THINGS
    1.02
    things
    1.02
     cosas
    1.00
     Dinge
    0.96
     dingen
    0.94
     coisas
    0.94
     aspects
    0.92
    Act Density 0.350%

    No Known Activations