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

    Neuronpedia

    INDEX
    Explanations

    hierarchical structures and relationships within nested data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     
    -0.58
     Cap
    -0.53
    <eos>
    -0.51
    ;
    -0.50
     let
    -0.50
     V
    -0.50
      
    -0.49
     A
    -0.49
     pré
    -0.49
     [
    -0.47
    POSITIVE LOGITS
     Anſ
    1.04
     recursively
    1.03
     Houſe
    1.02
     itſelf
    1.02
     Jefus
    1.00
     themſelves
    1.00
     Efq
    0.98
     myſelf
    0.97
     Majefty
    0.96
     houſe
    0.95
    Act Density 1.039%

    No Known Activations