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

    Neuronpedia

    INDEX
    Explanations

    concepts related to reciprocity and gratitude in relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    antd
    -0.56
     Schall
    -0.49
     Sanity
    -0.48
     args
    -0.47
     controll
    -0.46
     ſte
    -0.45
     ersch
    -0.45
     Darío
    -0.45
     divorce
    -0.45
     polisi
    -0.45
    POSITIVE LOGITS
     reciprocal
    0.90
     reciprocity
    0.88
     reciproc
    0.87
     Recipro
    0.79
     ungrateful
    0.71
     RECIP
    0.70
     gratitude
    0.69
     Gratitude
    0.68
     recipro
    0.68
     ingrat
    0.67
    Act Density 0.237%

    No Known Activations