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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating small degrees of intensity or quantity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Fiske
    -0.64
     esclavos
    -0.56
     Harms
    -0.55
    wahlen
    -0.55
    portál
    -0.54
     salvación
    -0.53
     Washburn
    -0.51
     nourrir
    -0.50
     placas
    -0.50
    Vezi
    -0.49
    POSITIVE LOGITS
     bisschen
    1.15
     المعيارى
    1.10
     bit
    1.05
     biraz
    1.05
     trochę
    1.04
     کمی
    1.01
     Etwas
    0.92
    Slightly
    0.87
     etwas
    0.86
     trochu
    0.85
    Act Density 0.095%

    No Known Activations