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

    Neuronpedia

    INDEX
    Explanations

    references to the term "Twin" and its variations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "Twin" and its variations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Downloadha
    -0.86
    ãģĵ
    -0.81
    lain
    -0.73
    stretched
    -0.72
    rawdownloadcloneembedreportprint
    -0.71
    âĿ
    -0.69
    gettable
    -0.64
    illary
    -0.64
    inventoryQuantity
    -0.63
    tics
    -0.63
    POSITIVE LOGITS
     Peaks
    1.32
     Twin
    1.05
    ĸļ
    0.94
    burgh
    0.92
     Twins
    0.89
     Blades
    0.88
    eteen
    0.87
     Cities
    0.87
    ieth
    0.83
     Turbo
    0.78
    Act Density 0.003%

    No Known Activations