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

    Neuronpedia

    INDEX
    Explanations

    expressions of good wishes and positive sentiments

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

    "Good luck," "Enjoy," or "Happy" closings

    np_acts-logits-general · gemini-2.0-flash

    wishes and closings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ########.
    -0.95
    SBATCH
    -0.58
    dyž
    -0.57
     BCD
    -0.56
    +#+
    -0.55
     Offisielt
    -0.54
     visst
    -0.53
    RenderAtEndOf
    -0.53
     jsPsych
    -0.53
    DockStyle
    -0.52
    POSITIVE LOGITS
    <eos>
    0.74
    AutoScale
    0.65
    })`
    0.59
    Datuak
    0.57
    TextBoxColumn
    0.57
    setViewportView
    0.56
    mocha
    0.53
     مشين
    0.53
    ↵↵↵↵↵
    0.53
     trừ
    0.53
    Act Density 0.092%

    No Known Activations