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

    Neuronpedia

    INDEX
    Explanations

    phrases containing "to" followed by numbers or enumerations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     
    -0.56
     &
    -0.52
     "
    -0.49
    /
    -0.48
     A
    -0.48
     And
    -0.47
    8
    -0.47
     is
    -0.47
    And
    -0.46
    ,
    -0.46
    POSITIVE LOGITS
     itſelf
    1.22
     Савезне
    1.10
    NUMX
    1.08
    writeField
    1.08
     betweenstory
    1.08
    \{\\
    1.08
    AddTagHelper
    1.05
    IndentedString
    1.03
    ſelf
    1.02
    Personensuche
    1.02
    Act Density 0.179%

    No Known Activations