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

    Neuronpedia

    INDEX
    Explanations

    words related to the concept of "go" or "going"

    oai_token-act-pair · gpt-3.5-turbo

    repeated instances of the word "go."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Aram
    -0.70
    dimension
    -0.65
     HH
    -0.65
     arche
    -0.63
     ceilings
    -0.62
     hierarch
    -0.60
     Horus
    -0.60
     relie
    -0.58
    è¦ļéĨĴ
    -0.58
    creen
    -0.58
    POSITIVE LOGITS
    lems
    1.05
    verning
    1.04
    ogly
    0.92
    estone
    0.91
    ethe
    0.90
    ggle
    0.88
    Daddy
    0.88
    forth
    0.88
    ardless
    0.87
    vernment
    0.85
    Act Density 0.007%

    No Known Activations