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

    Neuronpedia

    INDEX
    Explanations

    quotation marks and their usage in code or textual contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    quoted strings, code literals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.40
     jsPsych
    -0.37
     tray
    -0.35
    ulateur
    -0.33
    pantalones
    -0.33
    éric
    -0.32
     trays
    -0.32
    kör
    -0.31
    ตก
    -0.31
     deities
    -0.30
    POSITIVE LOGITS
    "}")
    0.57
     <",
    0.56
    Hentet
    0.56
    IUrlHelper
    0.56
     <<<<<<<<<<<<<<
    0.54
    MessageTagHelper
    0.54
    tagHelperRunner
    0.53
    '])
    0.52
     ***!
    0.51
    })();
    0.50
    Act Density 0.004%

    No Known Activations