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

    Neuronpedia

    INDEX
    Explanations

    intensifiers or modifiers that emphasize the degree of something, particularly the word "really"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    really followed by adjective

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nakalista
    -0.69
    #
    -0.55
    Portály
    -0.55
    rungsseite
    -0.53
     kaarangay
    -0.53
     enää
    -0.50
    лтемелер
    -0.49
     quæ
    -0.49
    ModelSerializer
    -0.49
    msgTypes
    -0.49
    POSITIVE LOGITS
    Really
    0.69
    really
    0.68
     Really
    0.66
     good
    0.65
     really
    0.64
     terrific
    0.63
     nice
    0.62
     fantastic
    0.61
    good
    0.60
     GOOD
    0.60
    Act Density 0.007%

    No Known Activations