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

    Neuronpedia

    INDEX
    Explanations

    different versions or variations of a particular story or concept

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "different" and its variations in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bows
    -0.71
    ammers
    -0.69
    ennes
    -0.67
    deals
    -0.66
     DRAG
    -0.62
     WATCHED
    -0.61
    md
    -0.61
     Butterfly
    -0.61
    RF
    -0.60
    ENTS
    -0.60
    POSITIVE LOGITS
    iating
    1.40
    iator
    1.24
    iates
    1.17
    worldly
    1.09
     dimension
    0.93
     kind
    0.91
    iable
    0.91
     Kind
    0.86
    iated
    0.85
    bie
    0.83
    Act Density 0.033%

    No Known Activations