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

    Neuronpedia

    INDEX
    Explanations

    references to loved ones and emotional connections

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

    being loved

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     GenerationType
    -0.52
    mybatisplus
    -0.51
     utafitiHapana
    -0.46
    AndEndTag
    -0.46
    TagMode
    -0.46
    anch
    -0.46
     Gilli
    -0.46
     abortions
    -0.44
    GenerationType
    -0.44
    AutoField
    -0.44
    POSITIVE LOGITS
     loved
    1.27
    loved
    1.11
     Loved
    1.11
    Loved
    0.96
     LOVED
    0.91
     amado
    0.62
    love
    0.58
     عزی
    0.56
     queridos
    0.56
     beloved
    0.54
    Act Density 0.004%

    No Known Activations