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

    Neuronpedia

    INDEX
    Explanations

    the word "that" and variations on its usage in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Portale
    -0.71
    EOUS
    -0.61
     själva
    -0.57
     Moly
    -0.56
    醐
    -0.56
     Propulsion
    -0.56
    Soli
    -0.55
     trefoil
    -0.55
     Soli
    -0.55
     Umbra
    -0.55
    POSITIVE LOGITS
     which
    1.20
    which
    1.08
     who
    0.99
     والذي
    0.97
     والتي
    0.86
     которая
    0.84
     который
    0.83
     οποίο
    0.82
    Which
    0.81
     котором
    0.81
    Act Density 0.348%

    No Known Activations