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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating frequency, particularly the word "mostly" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aise
    -0.16
    asse
    -0.15
    _UNICODE
    -0.15
    /legal
    -0.15
    Å¡tÄĽ
    -0.15
     sometimes
    -0.15
    ivent
    -0.14
    137
    -0.14
    et
    -0.14
    ress
    -0.14
    POSITIVE LOGITS
     Mostly
    0.15
    mostly
    0.15
    à¹Ĩ
    0.14
    MMdd
    0.14
    Periph
    0.14
     à¹Ĩ
    0.14
    597
    0.14
     èī¯
    0.14
    .Toolkit
    0.13
     DevComponents
    0.13
    Act Density 0.042%

    No Known Activations