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

    fall in love with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     utafitiHapana
    -0.82
     snippetHide
    -0.75
    httphttps
    -0.68
    verwijspagina
    -0.66
    Tikang
    -0.65
     pinulongan
    -0.63
     CURIAM
    -0.61
     disambiguazione
    -0.60
    -------
    -0.58
    ьаж
    -0.57
    POSITIVE LOGITS
     LOVE
    0.57
     enamorado
    0.56
     enamor
    0.56
     love
    0.56
     innamor
    0.48
     apaixon
    0.46
     عاشق
    0.46
     Love
    0.46
     paixão
    0.45
    Love
    0.45
    Act Density 0.005%

    No Known Activations