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

    Neuronpedia

    INDEX
    Explanations

    the word "whatever" in various contexts

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

    whatever followed by noun phrase

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Riau
    -0.52
    openqa
    -0.48
    fxml
    -0.47
    sse
    -0.47
     Diagnostics
    -0.46
    mml
    -0.45
    Билгалдахарш
    -0.44
    ⁃
    -0.44
    ských
    -0.43
     Inscrivez
    -0.43
    POSITIVE LOGITS
     whatever
    1.26
    whatever
    1.23
    Whatever
    1.16
     Whatever
    1.11
     whichever
    1.00
    atever
    0.92
     wherever
    0.89
     whoever
    0.87
    Wherever
    0.79
    <bos>
    0.77
    Act Density 0.011%

    No Known Activations