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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "However" and other conjunctive phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SourceFile
    -0.90
    ãĤ¼ãĤ¦ãĤ¹
    -0.80
    oodle
    -0.69
    ULAR
    -0.69
    ioxide
    -0.64
    obyl
    -0.64
    Widget
    -0.64
    MpServer
    -0.62
    apest
    -0.62
    è¦ļéĨĴ
    -0.62
    POSITIVE LOGITS
     unlike
    1.14
     despite
    1.13
     due
    0.98
     owing
    0.97
     since
    0.94
     contrary
    0.93
     while
    0.92
     because
    0.90
     although
    0.90
     unless
    0.90
    Act Density 0.189%

    No Known Activations