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

    Neuronpedia

    INDEX
    Explanations

    the concept of differences and comparisons in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     poussière
    -0.80
     mijne
    -0.79
    MLLoader
    -0.75
     rubrique
    -0.74
    liesslich
    -0.71
     Hawley
    -0.71
    ModelAdmin
    -0.70
     vidare
    -0.70
     Adkins
    -0.70
     flèche
    -0.68
    POSITIVE LOGITS
     difference
    2.14
     differences
    2.06
     DIFFERENCE
    2.01
    difference
    1.95
     Differences
    1.93
     Difference
    1.92
    Difference
    1.85
    Differences
    1.81
    differences
    1.77
     DIFFER
    1.57
    Act Density 0.180%

    No Known Activations