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

    Neuronpedia

    INDEX
    Explanations

    expressions of emphasis or intensity in opinions and descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Christiansen
    -0.78
     Shades
    -0.77
     Boswell
    -0.76
     storici
    -0.75
     perpétu
    -0.75
     Wiseman
    -0.75
     vertes
    -0.74
     nationales
    -0.74
     Dodson
    -0.74
     Kowal
    -0.74
    POSITIVE LOGITS
     really
    2.54
    really
    2.24
     Really
    2.19
    Really
    2.09
     REALLY
    2.05
     realy
    1.78
     vraiment
    1.28
     realmente
    1.21
     truly
    1.18
     wirklich
    1.17
    Act Density 0.056%

    No Known Activations