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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases related to hierarchical structures and levels in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ografija
    -0.64
    Бахар
    -0.58
    tableFuture
    -0.58
    oprecip
    -0.56
     utafitiHapana
    -0.55
     opérateur
    -0.54
     westward
    -0.53
     liberalization
    -0.52
     easements
    -0.52
     Whip
    -0.52
    POSITIVE LOGITS
     levels
    1.32
     layers
    1.31
     level
    1.21
     Levels
    1.15
    levels
    1.15
    level
    1.14
    Levels
    1.13
     Level
    1.12
     layer
    1.11
     LEVELS
    1.11
    Act Density 0.423%

    No Known Activations