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

    Neuronpedia

    INDEX
    Explanations

    geographical locations and regions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.02
    2:0.05
    3:0.23
    4:0.01
    5:0.02
    6:0.14
    7:0.12
    8:0.03
    9:0.06
    10:0.09
    11:0.14
    Negative Logits
    PDATE
    -1.19
    �士
    -1.19
    senal
    -1.13
    querque
    -1.13
    acious
    -1.04
    aciously
    -1.03
    agically
    -1.02
    ysc
    -1.00
     unison
    -0.98
    ufact
    -0.98
    POSITIVE LOGITS
    belt
    1.37
    entin
    1.12
    iHUD
    1.08
    angler
    1.01
    west
    0.99
    agers
    0.94
     prospect
    0.93
     Northwest
    0.92
    east
    0.92
    Impl
    0.91
    Act Density 0.017%

    No Known Activations