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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate quantities, comparisons, or characteristics about objects or phenomena

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.23
    1:0.04
    2:0.18
    3:0.10
    4:0.04
    5:0.07
    6:0.03
    7:0.07
    8:0.06
    9:0.04
    10:0.07
    11:0.03
    Negative Logits
    izabeth
    -2.79
    isine
    -2.67
     Chess
    -2.56
     textile
    -2.54
     marble
    -2.46
     Haitian
    -2.43
    cloth
    -2.36
     garment
    -2.35
     chess
    -2.32
    Ware
    -2.31
    POSITIVE LOGITS
     flares
    4.75
     flare
    4.13
     Shutdown
    2.99
     MHz
    2.69
     bursts
    2.60
     eru
    2.58
     gamma
    2.58
     launchers
    2.54
     eruption
    2.51
     cancell
    2.49
    Act Density 0.002%

    No Known Activations