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

    Neuronpedia

    INDEX
    Explanations

    references to locations in Washington, D.C

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.09
    1:0.01
    2:0.04
    3:0.13
    4:0.02
    5:0.05
    6:0.02
    7:0.04
    8:0.46
    9:0.03
    10:0.03
    11:0.02
    Negative Logits
     Tanaka
    -3.62
    ettel
    -3.46
     Scala
    -3.41
    ä
    -3.35
     €
    -3.31
     Sheffield
    -3.26
     �
    -3.23
     Guardiola
    -3.23
     Sergio
    -3.21
    ás
    -3.16
    POSITIVE LOGITS
    Washington
    6.27
     Washington
    5.79
     Capitals
    4.80
     Georgetown
    4.58
     Wizards
    4.49
     Congressional
    4.49
     DC
    4.41
     Dull
    4.30
     Brookings
    4.22
     congressional
    4.22
    Act Density 0.121%

    No Known Activations