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

    Neuronpedia

    INDEX
    Explanations

    the suffix "-ing" in words

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with judgment or assessment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    soDeliveryDate
    -0.84
    DragonMagazine
    -0.79
     characteristic
    -0.71
    quickShipAvailable
    -0.70
     Ninja
    -0.70
     "$:/
    -0.69
     guiActiveUnfocused
    -0.65
     Sunshine
    -0.65
    lihood
    -0.63
     marks
    -0.62
    POSITIVE LOGITS
    rouse
    1.24
    itate
    1.18
    uate
    1.15
    ulate
    1.15
    ify
    1.13
    pose
    1.07
    perate
    1.03
    ize
    1.01
    imize
    0.99
    iate
    0.99
    Act Density 0.284%

    No Known Activations