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

    Neuronpedia

    INDEX
    Explanations

    instances of the letter "W" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ^(@)
    -1.13
     ་་
    -1.12
     ―――――
    -1.10
     myſelf
    -1.04
     iſt
    -1.00
     Theſe
    -0.97
    ')")
    -0.93
     themſelves
    -0.92
     Diſ
    -0.92
     ſmall
    -0.90
    POSITIVE LOGITS
     W
    3.08
    W
    2.23
     w
    2.01
    Ｗ
    1.20
    w
    1.19
     H
    0.99
     V
    0.92
     Ws
    0.87
     E
    0.87
     S
    0.87
    Act Density 0.109%

    No Known Activations