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

    Neuronpedia

    INDEX
    Explanations

    measurements and quantities in specific units or dimensions

    oai_token-act-pair · gpt-3.5-turbo

    measurements and quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     resent
    -0.68
     Stra
    -0.66
     disple
    -0.66
    christ
    -0.66
    enance
    -0.65
    MJ
    -0.65
    odon
    -0.63
    olia
    -0.62
     stra
    -0.62
    ptroller
    -0.61
    POSITIVE LOGITS
     apiece
    0.81
    ãĥİ
    0.76
    bsp
    0.71
     [+
    0.69
     CSS
    0.67
    ĵĺ
    0.67
     ABV
    0.66
    é¾įå
    0.66
    milo
    0.66
     Siren
    0.65
    Act Density 0.174%

    No Known Activations