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

    Neuronpedia

    INDEX
    Explanations

    sentences that express gratitude or appreciation

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

    starting a phrase

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Transkript
    -0.48
    DockStyle
    -0.45
    MessageOf
    -0.42
    iseite
    -0.38
    endphp
    -0.37
     referenties
    -0.36
    parseDouble
    -0.36
     الاطلاع
    -0.35
    contentLoaded
    -0.35
    .*")]
    -0.34
    POSITIVE LOGITS
     desmotivaciones
    0.54
    principalColumn
    0.52
    inSlope
    0.52
    Rohy
    0.49
    Jereo
    0.48
    Datuak
    0.47
    AsUp
    0.47
    ↹
    0.46
     Italijanski
    0.46
    ⟬
    0.45
    Act Density 1.298%

    No Known Activations