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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of "couples" or "pairing"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Lilian
    -0.74
    TEXT
    -0.74
    Dia
    -0.74
    hintText
    -0.72
     Eichen
    -0.69
    ness
    -0.68
     Benn
    -0.68
     Dia
    -0.68
    MSR
    -0.67
     SLS
    -0.66
    POSITIVE LOGITS
    couple
    1.79
    Couple
    1.73
     couple
    1.71
     Couple
    1.62
     couples
    1.46
     Couples
    1.39
    couples
    1.30
     COU
    1.26
     casal
    1.06
    COUP
    1.01
    Act Density 0.055%

    No Known Activations