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

    Neuronpedia

    INDEX
    Explanations

    references to economic statistics and comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.02
    2:0.16
    3:0.08
    4:0.13
    5:0.02
    6:0.04
    7:0.22
    8:0.03
    9:0.04
    10:0.09
    11:0.08
    Negative Logits
     indifference
    -1.53
    truth
    -1.45
     inexper
    -1.44
     subtle
    -1.41
    idity
    -1.38
    onson
    -1.34
    ensional
    -1.32
    aram
    -1.32
    earance
    -1.30
     desperation
    -1.30
    POSITIVE LOGITS
    quartered
    1.55
    USD
    1.42
    aceae
    1.42
     ever
    1.41
     Compass
    1.38
     Commerce
    1.33
    >,
    1.33
     worldwide
    1.33
     annually
    1.33
     Facilities
    1.32
    Act Density 0.048%

    No Known Activations