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

    Neuronpedia

    INDEX
    Explanations

    instances of scenes or events being shown or featured in videos or images

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "shows" and its variations in relation to visual content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inventoryQuantity
    -1.21
    ãĤ¦ãĤ¹
    -0.92
    soType
    -0.84
    ItemTracker
    -0.80
     Secondly
    -0.77
    iqueness
    -0.77
    ãĤ´ãĥ³
    -0.76
    TI
    -0.74
     proble
    -0.74
    Correct
    -0.74
    POSITIVE LOGITS
     narrator
    1.02
     young
    0.88
     masked
    0.84
     protagonist
    0.82
     singer
    0.81
     smiling
    0.80
     unsuspecting
    0.80
     grinning
    0.80
     contestants
    0.79
     bearded
    0.78
    Act Density 0.233%

    No Known Activations