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

    Neuronpedia

    INDEX
    Explanations

    numerical and formatting elements commonly used in programming or processing data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ,
    -0.77
     (
    -0.65
    /
    -0.59
    ↵
    -0.58
    .
    -0.55
     or
    -0.54
      
    -0.53
    <eos>
    -0.52
    -
    -0.52
     I
    -0.51
    POSITIVE LOGITS
    ".
    1.29
    */;
    1.28
     iſt
    1.24
     itſelf
    1.22
    ^(@)
    1.22
     ***/
    1.20
     ―――――
    1.20
    ſelf
    1.20
     Efq
    1.19
     $_"
    1.18
    Act Density 0.091%

    No Known Activations