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

    Neuronpedia

    INDEX
    Explanations

    word variations related to the concept of "twist."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     للمعارف
    -1.39
     itſelf
    -1.24
    IndentedString
    -1.21
     pleaſure
    -1.21
     Majefty
    -1.19
     Efq
    -1.19
     myſelf
    -1.16
     Houſe
    -1.16
     EconPapers
    -1.14
     Италијани
    -1.09
    POSITIVE LOGITS
    tan
    0.73
    ,
    0.67
     Tan
    0.67
    ↵↵
    0.65
    <eos>
    0.63
     (
    0.62
    ↵
    0.61
      
    0.59
    ​
    0.58
     N
    0.58
    Act Density 0.111%

    No Known Activations