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

    Neuronpedia

    INDEX
    Explanations

    phrases related to ongoing or continuously changing situations

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating continuous changes or developments over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Solitaire
    -0.73
     Rite
    -0.72
     Grade
    -0.71
     WOM
    -0.69
     Tags
    -0.68
     Lime
    -0.66
     purse
    -0.66
     Relief
    -0.65
     Sack
    -0.64
     Moe
    -0.64
    POSITIVE LOGITS
    present
    1.32
    changing
    1.28
    growing
    1.27
    increasing
    1.27
    shr
    1.17
    exp
    1.14
    lasting
    1.09
    wid
    1.09
    impro
    1.08
    popular
    1.03
    Act Density 0.038%

    No Known Activations