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

    Neuronpedia

    INDEX
    Explanations

    adverbs and adjectives that express critique or judgment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.11
    1:0.05
    2:0.07
    3:0.24
    4:0.02
    5:0.04
    6:0.02
    7:0.09
    8:0.04
    9:0.02
    10:0.21
    11:0.04
    Negative Logits
    ecause
    -2.34
    Semitism
    -2.27
    rients
    -2.21
    ername
    -2.18
    quickShipAvailable
    -2.14
    >.
    -2.07
    ributes
    -2.06
    rities
    -2.06
    deen
    -2.04
    Shares
    -2.04
    POSITIVE LOGITS
     improbable
    2.70
     unconventional
    2.62
     unlikely
    2.59
     complex
    2.54
     ingenious
    2.25
     labyrinth
    2.24
     elusive
    2.20
     seldom
    2.19
     questionable
    2.18
     convoluted
    2.18
    Act Density 0.072%

    No Known Activations