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

    Neuronpedia

    INDEX
    Explanations

    numerical values and their associated statistical descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ########.
    -0.79
     للمعارف
    -0.77
     ujednoznacz
    -0.71
    ylo
    -0.59
     tartalomajánló
    -0.56
    وتو
    -0.51
    vably
    -0.51
     Bourgoin
    -0.50
    jardins
    -0.50
     CreateTagHelper
    -0.49
    POSITIVE LOGITS
    awtextra
    0.64
    Xna
    0.61
    AddTagHelper
    0.56
    strix
    0.55
    andExpect
    0.53
     acteur
    0.53
     المعيارى
    0.51
    Према
    0.50
     Latent
    0.50
    Clik
    0.50
    Act Density 0.719%

    No Known Activations