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

    Neuronpedia

    INDEX
    Explanations

    numeric values related to data or formatting in a technical context

    oai_token-act-pair · gpt-3.5-turbo

    numerical and symbol-based formats, especially in a data or metadata context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     astroph
    -0.69
    PRES
    -0.68
     inj
    -0.66
     Tec
    -0.65
     sidelines
    -0.65
     unders
    -0.65
     diagn
    -0.64
     Pres
    -0.63
     groom
    -0.63
     asthma
    -0.62
    POSITIVE LOGITS
    2
    1.29
    3
    1.24
    ĭ
    1.19
    ĩ
    1.03
    ĺ
    1.01
    1
    1.01
    4
    0.99
    Ģ
    0.96
    ĥ
    0.96
     2
    0.92
    Act Density 0.152%

    No Known Activations