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

    Neuronpedia

    INDEX
    Explanations

    locations, particularly states and cities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.02
    2:0.12
    3:0.06
    4:0.10
    5:0.04
    6:0.06
    7:0.29
    8:0.03
    9:0.04
    10:0.08
    11:0.08
    Negative Logits
    icter
    -1.45
     strides
    -1.39
     exaggerated
    -1.34
     sqor
    -1.32
    eless
    -1.28
     resultant
    -1.27
     stride
    -1.27
    ��
    -1.26
    phabet
    -1.26
     pressing
    -1.26
    POSITIVE LOGITS
     Avalon
    1.76
     Zot
    1.57
     Tripoli
    1.52
     mosqu
    1.51
     Alexandria
    1.47
     Canaveral
    1.46
    hess
    1.45
     Frie
    1.44
     Antioch
    1.44
    ometown
    1.38
    Act Density 0.009%

    No Known Activations