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

    Neuronpedia

    INDEX
    Explanations

    interrogative words or phrases, indicating a focus on questions and inquiries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Vorteil
    -0.53
    HtmlAttribute
    -0.53
    MigrationBuilder
    -0.53
     Plummer
    -0.52
     merci
    -0.51
    SharedCtor
    -0.50
    vara
    -0.50
    ец
    -0.50
     layui
    -0.50
    strcat
    -0.49
    POSITIVE LOGITS
    what
    1.10
     what
    1.09
     combien
    1.06
     mitä
    0.95
     WHAT
    0.95
     WHICH
    0.94
    What
    0.92
     whom
    0.91
     Whom
    0.90
    WHAT
    0.90
    Act Density 0.207%

    No Known Activations