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

    Neuronpedia

    INDEX
    Explanations

    references to twins, particularly identical twins

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     granddaughter
    -0.17
    Ñİн
    -0.15
    cÃŃ
    -0.15
    غاÙĦ
    -0.15
    ãĥĪãĥ«
    -0.15
    èn
    -0.15
     grandson
    -0.14
    ittle
    -0.14
    utsch
    -0.14
    ãĥ³ãĥĶ
    -0.14
    POSITIVE LOGITS
     twins
    0.76
     twin
    0.73
     Twins
    0.66
     Twin
    0.63
     identical
    0.49
     brothers
    0.47
     frat
    0.42
     sisters
    0.40
     Brothers
    0.38
     siblings
    0.35
    Act Density 0.102%

    No Known Activations