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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the term "Twin(s)"

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Twin" and its variations in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rawdownloadcloneembedreportprint
    -0.77
     compr
    -0.74
    ãģĵ
    -0.72
    */(
    -0.71
    stretched
    -0.70
    ulative
    -0.70
    riel
    -0.69
    lain
    -0.68
    ARDS
    -0.68
    Downloadha
    -0.66
    POSITIVE LOGITS
     Peaks
    1.22
     Cities
    0.95
    burgh
    0.87
     Falls
    0.87
    ieth
    0.85
     Twins
    0.85
    hower
    0.82
    brook
    0.80
    fuck
    0.80
     Twin
    0.79
    Act Density 0.005%

    No Known Activations