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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Rebell
    -0.90
    ourning
    -0.69
     Collider
    -0.67
    rit
    -0.64
     Lords
    -0.64
    ãĥ¯ãĥ³
    -0.63
    entanyl
    -0.62
     Hue
    -0.60
     Forge
    -0.60
     mathemat
    -0.59
    POSITIVE LOGITS
    DEN
    0.79
    eways
    0.75
    hots
    0.74
    cliffe
    0.74
    eeper
    0.73
    pell
    0.72
    bars
    0.69
    amba
    0.69
    bolt
    0.69
    cape
    0.69
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.