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

    Neuronpedia

    INDEX
    Explanations

    symbols and operators commonly used in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itſelf
    -1.30
     myſelf
    -1.28
     themſelves
    -1.24
     Efq
    -1.22
     ―――――
    -1.18
     ་་
    -1.17
     uſed
    -1.13
     Monfieur
    -1.07
     faſt
    -1.07
     Theſe
    -1.06
    POSITIVE LOGITS
     Rosenthal
    0.89
     Gries
    0.83
     _
    0.82
    y
    0.79
     <
    0.79
    ي
    0.76
     #
    0.74
     %
    0.73
    yip
    0.71
    ことです
    0.71
    Act Density 0.311%

    No Known Activations