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

    Neuronpedia

    INDEX
    Explanations

    words and phrases indicating persistence or continuity over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ModelExpression
    -0.90
    Autoritní
    -0.88
     autorytatywna
    -0.87
     BoxDecoration
    -0.87
    IndentedString
    -0.87
    )];
    -0.87
    contentLoaded
    -0.83
     ExecuteAsync
    -0.83
    LookAnd
    -0.82
    tahui
    -0.80
    POSITIVE LOGITS
     still
    1.11
    Still
    1.01
    still
    0.99
     Still
    0.98
     ainda
    0.82
     STILL
    0.81
    依然
    0.80
     fortfarande
    0.78
     noch
    0.77
     fortsatt
    0.77
    Act Density 0.328%

    No Known Activations