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

    Neuronpedia

    INDEX
    Explanations

    repeated or emphasized noun phrases, particularly those referencing authority or significant subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     NSCoder
    -0.73
    Lähteet
    -0.60
    jsonwebtoken
    -0.59
    Rüyada
    -0.58
     صوتيه
    -0.57
    fromnode
    -0.53
     the
    -0.51
    RenderAtEndOf
    -0.50
     DataTypes
    -0.49
    ագրություններ
    -0.49
    POSITIVE LOGITS
     iſt
    0.84
     Theſe
    0.72
     itſelf
    0.72
     whoſe
    0.70
     $_"
    0.69
     uſed
    0.69
     Eſ
    0.68
     myſelf
    0.66
     ſhe
    0.66
     themſelves
    0.65
    Act Density 0.066%

    No Known Activations