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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    NESS
    -0.67
     Dating
    -0.66
    Friend
    -0.63
    thal
    -0.62
    ãĤĮ
    -0.62
    Person
    -0.62
     Anger
    -0.61
    Shape
    -0.60
    venient
    -0.60
    NECT
    -0.60
    POSITIVE LOGITS
    arnaev
    0.78
    etheless
    0.72
    pert
    0.71
     Tsarnaev
    0.70
    ansky
    0.70
    ayers
    0.62
    ult
    0.61
    vae
    0.61
    oooooooooooooooo
    0.60
    uld
    0.59
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.