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

    Neuronpedia

    INDEX
    Explanations

    instances of punctuation marks and formatting symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    EMPLARY
    -0.18
    IIIK
    -0.18
     DK
    -0.17
     PK
    -0.17
     WC
    -0.16
    TRGL
    -0.16
     MP
    -0.16
     FC
    -0.16
     LG
    -0.16
     KB
    -0.16
    POSITIVE LOGITS
    SECOND
    0.30
    RIGHT
    0.29
    NUMBER
    0.28
    UNDER
    0.28
    BOUND
    0.28
    ROUND
    0.28
    GROUND
    0.28
    LOWER
    0.28
    OVER
    0.28
    OTHER
    0.28
    Act Density 1.839%

    No Known Activations