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

    Neuronpedia

    INDEX
    Explanations

    phrases related to improvement and enhancement in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ########.
    -0.73
     ModelExpression
    -0.69
    SequentialGroup
    -0.68
    GraphicsUnit
    -0.68
    HasBeenSet
    -0.68
    +#+
    -0.66
    GenerationType
    -0.65
    ⓧ
    -0.64
     nonatomic
    -0.64
     <<-
    -0.61
    POSITIVE LOGITS
     improve
    0.78
     improved
    0.74
    improve
    0.70
     Improve
    0.70
     improvement
    0.69
     superior
    0.69
    Improve
    0.65
     improves
    0.64
    improved
    0.64
    amélioration
    0.64
    Act Density 0.227%

    No Known Activations