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

    Neuronpedia

    INDEX
    Explanations

    mentions of "flip" or "flipping"

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific product, the "Backflip" phone

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Thread
    -0.63
     Person
    -0.63
    Dialogue
    -0.60
    BI
    -0.59
    ZI
    -0.59
     Month
    -0.59
     Scal
    -0.58
     Powers
    -0.58
     Drive
    -0.58
     celebr
    -0.57
    POSITIVE LOGITS
    ãĤ£
    0.99
    ãĤ§
    0.88
    istance
    0.86
    ption
    0.85
    ackers
    0.84
    terday
    0.83
    andise
    0.83
    ruction
    0.81
    ardless
    0.79
    uration
    0.79
    Act Density 0.044%

    No Known Activations