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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate a decision or a conclusion regarding someone's career

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ContentAsync
    -0.62
    chism
    -0.59
    tonode
    -0.59
     autorytatywna
    -0.58
    Autoritní
    -0.58
    :+:
    -0.56
     الحره
    -0.54
    nemonic
    -0.52
    onViewCreated
    -0.52
    ariate
    -0.52
    POSITIVE LOGITS
     farewell
    0.98
     parting
    0.97
     goodbye
    0.94
     leaving
    0.93
    Leaving
    0.92
    Farewell
    0.92
     departing
    0.87
     Leaving
    0.87
     departure
    0.86
    Goodbye
    0.85
    Act Density 0.254%

    No Known Activations