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

    Neuronpedia

    INDEX
    Explanations

    references to prior studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tantôt
    -0.76
    ISupport
    -0.76
     gratuits
    -0.73
    -0.72
     françaises
    -0.70
     humaines
    -0.70
     Där
    -0.68
     sauvages
    -0.67
     écout
    -0.66
     payé
    -0.66
    POSITIVE LOGITS
     previous
    2.17
     Previous
    2.10
    Previous
    1.98
    previous
    1.97
     PREVIOUS
    1.84
    PREVIOUS
    1.70
     previously
    1.59
     Previously
    1.55
    previously
    1.51
     previos
    1.46
    Act Density 0.078%

    No Known Activations