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

    Neuronpedia

    INDEX
    Explanations

    mentions of twins

    oai_token-act-pair · gpt-3.5-turbo

    references to twins

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Explain
    -0.74
    SOURCE
    -0.72
     Clin
    -0.72
    anwhile
    -0.70
    Frag
    -0.69
    vernment
    -0.66
    ãģĵ
    -0.66
     Retrieved
    -0.66
    UME
    -0.66
     Period
    -0.65
    POSITIVE LOGITS
     twin
    1.17
     twins
    0.91
     brother
    0.89
    ning
    0.84
     sister
    0.82
    ned
    0.80
     brothers
    0.79
     sibling
    0.77
    ieth
    0.74
     pillars
    0.71
    Act Density 0.003%

    No Known Activations