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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating time duration or continuity in narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    MLLoader
    -0.56
     Administrativna
    -0.50
    AddWithValue
    -0.49
     russes
    -0.46
     baron
    -0.45
     Laser
    -0.45
    Välislingid
    -0.44
    Laser
    -0.43
     Parson
    -0.43
    ApiModel
    -0.43
    POSITIVE LOGITS
     throughout
    1.95
    throughout
    1.91
    Throughout
    1.68
     Throughout
    1.67
     THRO
    0.96
     boyunca
    0.94
     suốt
    0.87
    ตลอด
    0.86
     протягом
    0.85
     everywhere
    0.82
    Act Density 0.092%

    No Known Activations