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

    Neuronpedia

    INDEX
    Explanations

    attends to tokens related to specific characters and structures from arbitrary tokens

    oai_attention-head · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.09
    1:0.10
    2:0.12
    3:0.14
    4:0.10
    5:0.06
    6:0.21
    7:0.14
    Negative Logits
    us
    -0.28
    Hochspringen
    -0.27
      
    -0.23
     e
    -0.23
     E
    -0.23
     am
    -0.22
    …
    -0.21
     میان
    -0.21
    sik
    -0.20
    CloseOperation
    -0.20
    POSITIVE LOGITS
    wieś
    0.40
     Ressource
    0.38
     myſelf
    0.35
    ειτουργ
    0.34
     becauſe
    0.33
     caufe
    0.32
     whoſe
    0.32
     poffible
    0.32
     bezeichneter
    0.32
    +#+#
    0.32
    Act Density 0.000%

    No Known Activations