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

    Neuronpedia

    INDEX
    Explanations

    quantitative measures or fractions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.08
    1:0.06
    2:0.09
    3:0.09
    4:0.07
    5:0.08
    6:0.07
    7:0.07
    8:0.09
    9:0.09
    10:0.09
    11:0.09
    Negative Logits
    �
    -1.88
    �
    -1.82
    ウス
    -1.82
    �
    -1.81
    �
    -1.76
    龍�
    -1.69
    �
    -1.64
    eto
    -1.63
    bourg
    -1.61
    ocard
    -1.58
    POSITIVE LOGITS
    Reviewer
    2.01
     sightings
    1.90
    staking
    1.79
     Artemis
    1.60
    DragonMagazine
    1.55
    amorph
    1.54
     unmarked
    1.54
    accompanied
    1.48
     previews
    1.48
    properties
    1.48
    Act Density 0.000%

    No Known Activations