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

    Neuronpedia

    INDEX
    Explanations

    references to ex-partners and failed relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     former
    -0.20
     formerly
    -0.16
     Former
    -0.15
     pedig
    -0.15
    918
    -0.14
    ibraltar
    -0.14
    chron
    -0.14
    /he
    -0.14
     cousin
    -0.14
     extracts
    -0.14
    POSITIVE LOGITS
     flame
    0.28
     flames
    0.23
     employer
    0.20
    /current
    0.20
     Flame
    0.19
     employers
    0.19
     boss
    0.19
    employer
    0.18
    -girl
    0.18
     Flames
    0.17
    Act Density 0.017%

    No Known Activations