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

    Neuronpedia

    INDEX
    Explanations

    words and phrases indicating desires or needs related to relationships and interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ú¯ÛĮ
    -0.15
    echn
    -0.14
    ofday
    -0.14
     Leslie
    -0.14
    onna
    -0.14
    epend
    -0.14
    mani
    -0.14
    endo
    -0.14
    729
    -0.13
    779
    -0.13
    POSITIVE LOGITS
    velle
    0.17
    tü
    0.15
     Ä°h
    0.15
    ounge
    0.15
    æĹıèĩªæ²»
    0.15
    /vendors
    0.15
     INCIDENTAL
    0.15
    âu
    0.14
    ाप
    0.14
    atoon
    0.14
    Act Density 0.007%

    No Known Activations