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

    Neuronpedia

    INDEX
    Explanations

    quantifiers and modifiers indicating amount or quantity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.16
    1:0.30
    2:0.04
    3:0.04
    4:0.03
    5:0.15
    6:0.03
    7:0.02
    8:0.06
    9:0.05
    10:0.04
    11:0.04
    Negative Logits
     Jobs
    -1.89
     MISS
    -1.87
     Poison
    -1.75
     Index
    -1.74
     HTML
    -1.71
     +++
    -1.71
     MAP
    -1.69
     Bolivia
    -1.68
     PEOPLE
    -1.65
     Haiti
    -1.65
    POSITIVE LOGITS
    theless
    2.15
    vag
    2.11
    erd
    2.03
    uin
    2.01
    oqu
    1.98
    odon
    1.98
    bowl
    1.96
    dain
    1.83
    ofi
    1.78
    vc
    1.78
    Act Density 0.003%

    No Known Activations