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

    Neuronpedia

    INDEX
    Explanations

    phrases or sentences related to twins

    oai_token-act-pair · gpt-3.5-turbo

    references to twins or twin-related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anwhile
    -0.89
     CoC
    -0.80
    andise
    -0.75
    UME
    -0.75
    ãģĵ
    -0.69
    wikipedia
    -0.68
    uddin
    -0.66
    ACP
    -0.65
    ibaba
    -0.63
    Ô
    -0.63
    POSITIVE LOGITS
    ning
    1.17
    ned
    1.12
    fold
    0.90
     towers
    0.87
     brothers
    0.86
    ples
    0.84
     brother
    0.84
    omial
    0.81
     twin
    0.79
     peaks
    0.79
    Act Density 0.014%

    No Known Activations