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

    Neuronpedia

    INDEX
    Explanations

    phrases related to duration or continuity of events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    how long events lasted

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    WhiteSpace
    -0.46
    beiro
    -0.46
    iou
    -0.45
     ApiClient
    -0.43
    iettivo
    -0.43
     jersey
    -0.43
     whom
    -0.43
     TreeNode
    -0.43
    Ariel
    -0.43
    ckså
    -0.42
    POSITIVE LOGITS
     lasted
    1.70
     lasts
    1.46
     lasting
    1.19
     Lasting
    1.09
    lasting
    1.09
    lasts
    1.00
     duración
    0.86
     Duration
    0.84
     durer
    0.81
     duration
    0.80
    Act Density 0.003%

    No Known Activations