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

    Neuronpedia

    INDEX
    Explanations

    references to prior research or studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     QtGui
    -0.93
    -0.90
     bicara
    -0.79
    ISupport
    -0.75
     découv
    -0.73
     DialogInterface
    -0.72
    Amicalement
    -0.72
    Scorecard
    -0.70
    NetworkInfo
    -0.69
    anglicky
    -0.69
    POSITIVE LOGITS
     previous
    1.48
     Previous
    1.42
    Previous
    1.35
    previous
    1.27
     PREVIOUS
    1.25
    PREVIOUS
    1.24
     previos
    1.24
     previously
    1.13
     Previously
    1.11
    previously
    1.07
    Act Density 0.093%

    No Known Activations