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

    Neuronpedia

    INDEX
    Explanations

    the word "Don" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥĥãĤ¯ãĤ¹
    -0.16
    ÂŃi
    -0.16
    dit
    -0.15
    ást
    -0.14
    ãĥĥãĤ¯
    -0.14
    ÃŃculo
    -0.14
    زÙħ
    -0.14
    ÅĻil
    -0.14
    itious
    -0.14
    manent
    -0.14
    POSITIVE LOGITS
    nelly
    0.26
    ovan
    0.22
    ning
    0.21
    't
    0.21
    uts
    0.20
    ner
    0.20
    961
    0.19
    ations
    0.18
    ned
    0.18
    اÙĦد
    0.18
    Act Density 0.026%

    No Known Activations