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

    Neuronpedia

    INDEX
    Explanations

    expressions of love and affection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     isInitialized
    -0.59
    minator
    -0.55
     NUKAT
    -0.55
     reaper
    -0.54
     transférez
    -0.53
    ("-");
    -0.52
     kasarigan
    -0.52
     propOrder
    -0.51
     său
    -0.51
    énario
    -0.50
    POSITIVE LOGITS
     love
    3.41
     loved
    3.20
     loves
    3.08
     LOVE
    3.00
    love
    2.97
     Love
    2.90
    Love
    2.83
     loving
    2.82
    LOVE
    2.79
    loved
    2.79
    Act Density 0.045%

    No Known Activations