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

    Neuronpedia

    INDEX
    Explanations

    political terms and names

    oai_token-act-pair · gpt-3.5-turbo

    a particular symbol or character across various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Tid
    -0.71
     Tunis
    -0.67
     Niet
    -0.63
     polyg
    -0.62
     NEC
    -0.61
     Bak
    -0.61
     Borough
    -0.61
     extrap
    -0.61
     pastry
    -0.60
     Mous
    -0.59
    POSITIVE LOGITS
    Ļ
    1.33
    ª
    1.32
    ¡
    1.24
    ı
    1.20
    ħ
    1.20
    ĸ
    1.14
    ¬
    1.13
    Ĵ
    1.11
    Ģ
    1.09
    ¼
    1.09
    Act Density 0.428%

    No Known Activations