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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing the word "as"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    FTWARE
    -0.77
    iller
    -0.70
    VIDEO
    -0.64
    Published
    -0.62
     showc
    -0.62
     fundament
    -0.61
     srfAttach
    -0.61
    oldown
    -0.59
    vt
    -0.59
    cellaneous
    -0.58
    POSITIVE LOGITS
    inventoryQuantity
    0.77
    lihood
    0.71
    athe
    0.67
     these
    0.65
    phy
    0.65
     sounds
    0.63
    images
    0.62
     initially
    0.61
    utsche
    0.59
     Straw
    0.59
    Act Density 0.035%

    No Known Activations