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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal disclaimers and conditions

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

    without warranties or conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ScopeManager
    -0.56
    ⤹
    -0.54
    Autoritní
    -0.50
    Geplaatst
    -0.44
     mostrarán
    -0.43
    цезда
    -0.43
    ⟬
    -0.43
    afficheront
    -0.42
    tangentMode
    -0.42
     للاسماء
    -0.41
    POSITIVE LOGITS
     warranties
    0.56
     liability
    0.50
     blessings
    0.50
     warranty
    0.46
     liabilities
    0.45
    ExecuteReader
    0.42
    WriteLiteral
    0.42
     obligations
    0.42
     formalities
    0.39
     commitments
    0.39
    Act Density 0.002%

    No Known Activations