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

    Neuronpedia

    INDEX
    Explanations

    questions or inquiries about specific information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Aze
    -0.73
     saites
    -0.72
     Verge
    -0.71
     brook
    -0.71
    Brooks
    -0.68
     hoffe
    -0.67
    timbangkan
    -0.66
    ze
    -0.66
     Pollack
    -0.66
     Geor
    -0.65
    POSITIVE LOGITS
     what
    1.91
    what
    1.87
     WHAT
    1.84
    WHAT
    1.82
    What
    1.80
     What
    1.75
    whats
    1.11
     quelles
    1.04
     wat
    1.00
    Τι
    0.97
    Act Density 0.116%

    No Known Activations