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

    Neuronpedia

    INDEX
    Explanations

    HTML tags in the form of closing tags and attributes

    oai_token-act-pair · gpt-3.5-turbo

    HTML tags or attributes in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etheless
    -1.16
     buoy
    -0.75
     weary
    -0.75
    Ĥİ
    -0.72
     veter
    -0.70
     whistle
    -0.70
     councill
    -0.70
     branching
    -0.70
     amnesty
    -0.69
     quir
    -0.69
    POSITIVE LOGITS
    FIR
    0.99
    PIN
    0.97
    {{
    0.97
    Appearance
    0.94
    Hello
    0.92
    Insert
    0.91
    )</
    0.88
     <!--
    0.88
     <
    0.88
    Unknown
    0.87
    Act Density 0.017%

    No Known Activations