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

    Neuronpedia

    INDEX
    Explanations

    expressions related to progress or advancement

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate a change or transition in circumstances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    asio
    -0.69
    uman
    -0.68
    alach
    -0.64
    stim
    -0.64
    enza
    -0.62
    hower
    -0.62
    bush
    -0.61
    Price
    -0.59
    Corp
    -0.59
    arity
    -0.57
    POSITIVE LOGITS
     behold
    0.71
     lettuce
    0.58
     fide
    0.58
     cuc
    0.57
     oats
    0.57
     lett
    0.56
     ni
    0.52
    é»Ĵ
    0.51
     fav
    0.51
     fmt
    0.50
    Act Density 0.335%

    No Known Activations