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

    Neuronpedia

    INDEX
    Explanations

    various quantified measurements or numerical data points related to research findings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Paglinawan
    -1.49
     resourceCulture
    -1.18
    Autoritní
    -1.17
     itſelf
    -1.08
    contentLoaded
    -1.05
     Савезне
    -1.04
    хьтан
    -1.02
     kaarangay
    -1.02
     EconPapers
    -1.00
     myſelf
    -0.99
    POSITIVE LOGITS
    ,
    0.97
    .
    0.93
     
    0.84
     =
    0.81
    ;
    0.77
    ...
    0.75
    ↵
    0.73
     (
    0.73
    ?
    0.72
     .
    0.71
    Act Density 0.260%

    No Known Activations