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

    Neuronpedia

    INDEX
    Explanations

    themes related to memories and introspection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    EndContext
    -0.82
    RegressionTest
    -0.77
     propOrder
    -0.75
    transQ
    -0.73
     autorytatywna
    -0.69
     cherchés
    -0.68
     HFILL
    -0.67
     CreateTagHelper
    -0.67
    fromnode
    -0.66
     Italijani
    -0.63
    POSITIVE LOGITS
    Mid
    0.28
     mid
    0.28
     while
    0.28
     midst
    0.27
    mid
    0.27
     līdz
    0.27
     terwijl
    0.27
    middle
    0.26
     middle
    0.26
    Middle
    0.26
    Act Density 1.357%

    No Known Activations