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

    Neuronpedia

    INDEX
    Explanations

    words related to geographical features or locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.03
    1:0.04
    2:0.06
    3:0.31
    4:0.03
    5:0.02
    6:0.12
    7:0.09
    8:0.04
    9:0.06
    10:0.07
    11:0.08
    Negative Logits
    chwitz
    -1.29
     Cosponsors
    -1.27
    ć
    -1.18
    oğ
    -1.13
    wordpress
    -1.13
    ansas
    -1.09
    aldehyde
    -1.05
     Upton
    -1.05
    lyak
    -1.04
    eto
    -1.04
    POSITIVE LOGITS
    ヴァ
    1.20
    Rog
    1.06
     hail
    1.05
    Driver
    1.02
     Fam
    0.97
    sein
    0.94
    bery
    0.94
    Witness
    0.93
    oppers
    0.93
    DERR
    0.92
    Act Density 0.008%

    No Known Activations