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

    Neuronpedia

    INDEX
    Explanations

    variations of the word "different"

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating variations or changes in circumstances or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    laws
    -0.80
    deals
    -0.80
    onies
    -0.80
    phies
    -0.78
    bows
    -0.76
    ammers
    -0.72
    rations
    -0.70
    anches
    -0.69
     WATCHED
    -0.68
    ulations
    -0.68
    POSITIVE LOGITS
    iator
    1.39
    iating
    1.28
     kind
    1.16
     dimension
    1.15
     tack
    1.08
     kettle
    1.07
     angle
    1.07
     perspective
    1.04
     type
    1.00
     sort
    1.00
    Act Density 0.094%

    No Known Activations