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

    Neuronpedia

    INDEX
    Explanations

    the presence of LaTeX formatting and mathematical notations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .
    -0.60
     
    -0.60
     "
    -0.59
     (
    -0.59
     B
    -0.53
      
    -0.53
     all
    -0.50
     All
    -0.49
     [
    -0.49
     E
    -0.49
    POSITIVE LOGITS
    tvguidetime
    1.29
     myſelf
    1.27
     Monfieur
    1.27
    MigrationBuilder
    1.22
     houſe
    1.20
     Majefty
    1.20
     iſt
    1.19
    存于互联网档案馆
    1.19
     pleaſure
    1.18
    ſelf
    1.18
    Act Density 0.486%

    No Known Activations