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

    Neuronpedia

    INDEX
    Explanations

    occurrences of quotes or quotation marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     “
    -0.32
     âĢŀ
    -0.29
    ãĢĮ
    -0.23
     ``
    -0.22
     “[
    -0.22
     (“
    -0.21
    ãĢĮãģĤ
    -0.20
     ãĢĮ
    -0.20
    ãĢĮãģĬ
    -0.19
     «
    -0.19
    POSITIVE LOGITS
    []"
    0.19
    ()"
    0.17
    rient
    0.16
    {'
    0.16
    gnore
    0.15
    ¦
    0.15
    !"
    0.14
    alloca
    0.14
    ."↵↵
    0.14
    ","","
    0.14
    Act Density 0.610%

    No Known Activations