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

    Neuronpedia

    INDEX
    Explanations

    phrases that involve the expression of opinions or statements

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

    that said, introducing contrast

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Houſe
    -0.60
    __).
    -0.52
     ویکی‌پدی
    -0.49
     Majefty
    -0.49
    */].
    -0.49
    ReusableCell
    -0.48
    Blockly
    -0.47
     emailAlready
    -0.47
     nakalista
    -0.46
     houſe
    -0.45
    POSITIVE LOGITS
     obstante
    0.56
     albeit
    0.56
     nonetheless
    0.56
     Dennoch
    0.54
     however
    0.53
    Nonetheless
    0.51
    MigrationBuilder
    0.50
     Allerdings
    0.50
    however
    0.50
    Nevertheless
    0.49
    Act Density 0.008%

    No Known Activations