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

    Neuronpedia

    INDEX
    Explanations

    modifiers that indicate a degree or extent

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     igenom
    -0.33
    无数
    -0.31
    ennom
    -0.31
     aveug
    -0.30
     lyck
    -0.30
     dø
    -0.30
     HasFactory
    -0.29
     enfans
    -0.29
     syke
    -0.29
     binnen
    -0.29
    POSITIVE LOGITS
     bit
    1.21
    slightly
    1.05
     slightly
    1.02
     Slightly
    1.01
    Slightly
    0.98
     beetje
    0.96
     trochu
    0.96
     Somewhat
    0.95
    Somewhat
    0.94
     nieco
    0.93
    Act Density 0.186%

    No Known Activations