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

    Neuronpedia

    INDEX
    Explanations

    statements or quotations by individuals in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.04
    1:0.02
    2:0.06
    3:0.15
    4:0.14
    5:0.04
    6:0.04
    7:0.05
    8:0.08
    9:0.11
    10:0.10
    11:0.12
    Negative Logits
     spaceship
    -1.40
     payroll
    -1.39
     expend
    -1.38
     dinosaurs
    -1.38
     infall
    -1.38
     asteroid
    -1.35
    interstitial
    -1.35
     KGB
    -1.33
     fossils
    -1.32
     MPG
    -1.32
    POSITIVE LOGITS
    CCC
    1.59
    JB
    1.53
    guyen
    1.50
     Nguyen
    1.45
    HAM
    1.43
    herty
    1.43
    IDA
    1.39
    letcher
    1.38
    igate
    1.37
    oward
    1.36
    Act Density 0.029%

    No Known Activations