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

    Neuronpedia

    INDEX
    Explanations

    references to duration and intensity of events or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ]:
    -0.80
    '}}
    -0.78
    ]++;
    -0.78
     userModel
    -0.77
    ']))
    -0.76
    .\\
    -0.76
    ?\\
    -0.74
    ).\\
    -0.74
    ?\
    -0.74
    "]));
    -0.73
    POSITIVE LOGITS
     duration
    1.87
    duration
    1.78
     Duration
    1.65
    Duration
    1.57
     durations
    1.53
    DURATION
    1.44
     DUR
    1.19
    setDuration
    1.12
    DUR
    1.04
     durée
    1.03
    Act Density 0.075%

    No Known Activations