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

    Neuronpedia

    INDEX
    Explanations

    phrases discussing differences or comparisons between entities or measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Hawley
    -0.79
    liesslich
    -0.77
    MLLoader
    -0.72
     flèche
    -0.70
     vägen
    -0.70
    ModelAdmin
    -0.69
     Felsen
    -0.67
     eenige
    -0.66
    μιουργ
    -0.66
    {}",
    -0.65
    POSITIVE LOGITS
     difference
    2.34
    difference
    2.19
     DIFFERENCE
    2.17
     differences
    2.12
     Difference
    2.09
    Difference
    2.03
     Differences
    1.96
    differences
    1.86
    Differences
    1.83
     différence
    1.59
    Act Density 0.080%

    No Known Activations