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

    Neuronpedia

    INDEX
    Explanations

    instances of numerical data or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.05
    1:0.06
    2:0.05
    3:0.08
    4:0.03
    5:0.04
    6:0.09
    7:0.35
    8:0.02
    9:0.02
    10:0.08
    11:0.07
    Negative Logits
     dissemin
    -1.79
     acceler
    -1.79
     mosqu
    -1.74
     facilit
    -1.67
     Klu
    -1.64
     Pap
    -1.62
     retract
    -1.56
     depos
    -1.56
     integrating
    -1.54
     freshly
    -1.54
    POSITIVE LOGITS
    ↑
    2.20
    $.
    2.12
     ↑
    2.09
    verbs
    1.99
    eteen
    1.96
    #
    1.96
    \.
    1.95
    1.95
    luaj
    1.95
    II
    1.94
    Act Density 0.061%

    No Known Activations