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

    Neuronpedia

    INDEX
    Explanations

    negations or phrases indicating uncertainty or lack of compliance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ValueStyle
    -0.70
    WebVitals
    -0.68
     ***!
    -0.62
    
    -0.60
     autorytatywna
    -0.59
    Referencie
    -0.58
     CreateTagHelper
    -0.58
    róleo
    -0.58
     ejus
    -0.56
     lenker
    -0.55
    POSITIVE LOGITS
    addComponent
    0.54
    /</
    0.52
    ftagPool
    0.52
    yntaxException
    0.52
    znál
    0.51
    IComponent
    0.51
    RetentionPolicy
    0.51
    ange
    0.51
    Embeddable
    0.50
    ents
    0.49
    Act Density 0.289%

    No Known Activations