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

    Neuronpedia

    INDEX
    Explanations

    text related to academic research, such as publication references and technical terms

    oai_token-act-pair · gpt-3.5-turbo

    the presence of citations or references within a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DragonMagazine
    -0.57
    astical
    -0.57
    ////////////////////////////////
    -0.54
    ossom
    -0.52
     upgr
    -0.50
    ////////
    -0.49
    clus
    -0.48
    isoft
    -0.48
    Shape
    -0.47
    prus
    -0.47
    POSITIVE LOGITS
     .
    3.23
     ."
    2.26
     .)
    2.21
     '.
    1.91
     ".
    1.89
     ._
    1.87
     ).
    1.80
     ,
    1.77
     ..
    1.65
     ,"
    1.63
    Act Density 0.031%

    No Known Activations