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

    Neuronpedia

    INDEX
    Explanations

    keywords related to inclusion and exclusion in arguments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     EconPapers
    -0.73
     propOrder
    -0.55
     createSlice
    -0.53
     asemenea
    -0.52
    ();)
    -0.50
    aarrggbb
    -0.49
     ModelExpression
    -0.49
    Хьажоргаш
    -0.49
     ProtoMessage
    -0.46
    +#+#
    -0.46
    POSITIVE LOGITS
     during
    1.16
     via
    1.09
     from
    1.02
     through
    1.01
     in
    0.98
     when
    0.95
     for
    0.94
    during
    0.91
     at
    0.88
     with
    0.86
    Act Density 0.596%

    No Known Activations