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

    Neuronpedia

    INDEX
    Explanations

    references to couples or paired relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ness
    -0.85
     Lilian
    -0.84
     Ree
    -0.79
    MSR
    -0.77
    Dia
    -0.71
    \|_{\
    -0.70
    NESS
    -0.69
     Jio
    -0.69
     Weid
    -0.69
     Lillian
    -0.68
    POSITIVE LOGITS
    couple
    1.31
    Couple
    1.29
     couple
    1.19
     Couple
    1.17
     couples
    1.08
     Couples
    1.06
    couples
    1.04
     COU
    0.96
     NavController
    0.90
     casal
    0.81
    Act Density 0.055%

    No Known Activations