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

    Neuronpedia

    INDEX
    Explanations

    expressions of love and emotional interactions between characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    687
    -0.14
     Rosenberg
    -0.13
    afi
    -0.13
    essenger
    -0.13
    ODEV
    -0.13
    ÏĮν
    -0.12
    cir
    -0.12
    Repeat
    -0.12
    (#)
    -0.12
    UPPORT
    -0.12
    POSITIVE LOGITS
     recip
    0.70
     reciprocal
    0.55
     recipro
    0.50
     mutual
    0.42
     retal
    0.38
     reply
    0.38
     retali
    0.38
     response
    0.36
     Mutual
    0.35
     replies
    0.34
    Act Density 0.295%

    No Known Activations