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

    Neuronpedia

    INDEX
    Explanations

    intensifiers or adverbs that emphasize strong feelings or opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    udur
    -0.72
     poiché
    -0.71
     springfox
    -0.71
    المصادر
    -0.68
    chec
    -0.68
     sahiptir
    -0.66
    anadas
    -0.66
     Connell
    -0.65
    UNGE
    -0.64
     noires
    -0.64
    POSITIVE LOGITS
     really
    4.70
    really
    4.06
     Really
    3.83
    Really
    3.77
     REALLY
    3.40
     vraiment
    2.75
     realy
    2.70
     realmente
    2.58
     wirklich
    2.46
     virkelig
    2.23
    Act Density 0.038%

    No Known Activations