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

    Neuronpedia

    INDEX
    Explanations

    linguistic elements indicating user engagement with social media platforms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RunAsync
    -0.75
     lasts
    -0.69
    bcryptjs
    -0.67
     flowed
    -0.64
     виправивши
    -0.62
    djangoproject
    -0.61
    IUrlHelper
    -0.61
     محفوظة
    -0.60
    Tembelea
    -0.60
     occurs
    -0.60
    POSITIVE LOGITS
     believes
    0.60
     willing
    0.56
     merasa
    0.55
     aware
    0.55
    認為
    0.54
     предпочита
    0.54
     дума
    0.54
     believe
    0.54
    believe
    0.53
     thinks
    0.53
    Act Density 0.033%

    No Known Activations