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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing inclusivity or completeness

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

    the word all

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Italijanski
    -0.85
     للاسماء
    -0.83
     noDo
    -0.79
    AnimationsModule
    -0.76
     ModelExpression
    -0.74
    ьаж
    -0.73
    makeText
    -0.72
    queryInterface
    -0.71
     informée
    -0.70
     propOrder
    -0.70
    POSITIVE LOGITS
     individually
    0.40
     again
    0.40
     up
    0.38
     collectively
    0.36
     including
    0.34
    ,
    0.34
     at
    0.33
     separately
    0.32
     She
    0.32
     in
    0.31
    Act Density 0.007%

    No Known Activations