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

    Neuronpedia

    INDEX
    Explanations

    names of film directors or artists

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     iſt
    -1.19
     myſelf
    -1.16
     itſelf
    -1.14
    rungsseite
    -1.14
     purpoſe
    -1.03
     ſy
    -1.02
     ſind
    -1.01
     ſever
    -1.01
    setVerticalGroup
    -1.01
     ſtate
    -1.00
    POSITIVE LOGITS
     
    0.72
     (
    0.62
    ↵↵
    0.58
     T
    0.54
     &
    0.53
     E
    0.52
     =
    0.51
     W
    0.51
    同上
    0.50
     West
    0.49
    Act Density 0.585%

    No Known Activations