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

    Neuronpedia

    INDEX
    Explanations

    words related to computer programming and coding

    oai_token-act-pair · gpt-3.5-turbo

    specific jargon or terms related to various fields such as medicine, technology, and popular culture

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ende
    -0.74
     streng
    -0.74
     nodd
    -0.67
     confir
    -0.65
     agre
    -0.64
     territ
    -0.63
     caut
    -0.61
     undermin
    -0.61
     manufact
    -0.60
     comprom
    -0.59
    POSITIVE LOGITS
    ,
    0.82
    âĢİ
    0.81
    âĦ¢
    0.74
    ,[
    0.72
    ohydrate
    0.69
    âĢ³
    0.69
     &&
    0.69
    ãĥ»
    0.68
    ®,
    0.66
     ||
    0.64
    Act Density 0.562%

    No Known Activations