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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word 'love' and its variations in different contexts

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

    the word love

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    +#+#
    -0.71
     Thumbnails
    -0.60
    ggior
    -0.59
    huana
    -0.58
     CURIAM
    -0.57
    tioners
    -0.57
    屓
    -0.57
     Shorts
    -0.57
    URDAY
    -0.57
    UTERS
    -0.57
    POSITIVE LOGITS
     love
    1.74
    Love
    1.55
     Love
    1.54
    love
    1.48
     LOVE
    1.44
    LOVE
    1.34
     любви
    0.90
     любовь
    0.90
    爱
    0.88
    愛
    0.85
    Act Density 0.009%

    No Known Activations