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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "which" in various contexts

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

    phrases of which followed by verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Skate
    -0.36
     شا
    -0.36
    ssk
    -0.35
     locul
    -0.33
     دنبال
    -0.33
    ēc
    -0.32
    lek
    -0.32
    坐
    -0.32
    SKIP
    -0.32
    ylen
    -0.32
    POSITIVE LOGITS
    popd
    0.59
    舺
    0.59
     <>",
    0.56
     AssemblyCulture
    0.56
    jsxFileName
    0.54
    IntoConstraints
    0.54
    reportWebVitals
    0.53
     jsPsych
    0.52
    ']>;
    0.51
    DoubleQuotes
    0.50
    Act Density 0.018%

    No Known Activations