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

    Neuronpedia

    INDEX
    Explanations

    phrases that discuss differences or comparisons between entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     xlink
    -0.75
    /"+
    -0.71
     poussière
    -0.70
     Adkins
    -0.69
    {}/
    -0.64
     pesados
    -0.64
     cheminée
    -0.64
     Gelegenheit
    -0.63
     stabilité
    -0.63
    ModelAdmin
    -0.62
    POSITIVE LOGITS
     difference
    2.42
     differences
    2.28
     DIFFERENCE
    2.22
    difference
    2.22
     Difference
    2.13
    Difference
    2.11
     Differences
    2.11
    differences
    2.01
    Differences
    2.00
     verschil
    1.78
    Act Density 0.186%

    No Known Activations