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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "back" in different contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "back" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Sullivan
    -0.80
    uries
    -0.70
    aukee
    -0.68
    inational
    -0.68
    izo
    -0.66
    ISON
    -0.66
     Polk
    -0.64
    ussen
    -0.64
     Motorsport
    -0.63
     WW
    -0.61
    POSITIVE LOGITS
    bones
    0.94
    side
    0.94
    stretched
    0.91
    yards
    0.90
     dancers
    0.88
    swing
    0.87
    bone
    0.85
    drops
    0.85
    packs
    0.85
    tracking
    0.84
    Act Density 0.028%

    No Known Activations