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

    Neuronpedia

    INDEX
    Explanations

    various forms of quotation marks and punctuation indicating speech or citation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     «
    -1.03
     '
    -0.84
     "
    -0.81
     ''
    -0.71
    「
    -0.68
     â
    -0.64
    DataPropertyName
    -0.55
     「
    -0.53
     ``
    -0.53
    isInitialized
    -0.53
    POSITIVE LOGITS
    ’”
    1.40
    ’.”
    1.31
    ,’”
    1.26
    ?”,
    1.24
    .”)
    1.20
    .’”
    1.19
    ;”
    1.19
    ?”
    1.19
    ”
    1.16
    …”
    1.13
    Act Density 0.243%

    No Known Activations