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

    Neuronpedia

    INDEX
    Explanations

    references to different models in the context of statistical or scientific discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Kear
    -0.71
    achten
    -0.69
    uptime
    -0.65
    doPost
    -0.64
    Чу
    -0.64
     Susie
    -0.63
    ähän
    -0.63
     sopr
    -0.61
     bapt
    -0.61
    WebVitals
    -0.61
    POSITIVE LOGITS
     MODEL
    1.80
     model
    1.80
     models
    1.78
     Model
    1.74
     Models
    1.61
    model
    1.57
    MODEL
    1.56
    Models
    1.48
     MODELS
    1.48
     modele
    1.48
    Act Density 0.093%

    No Known Activations