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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    lean
    -0.75
    riots
    -0.72
    ikan
    -0.72
    raint
    -0.71
    raints
    -0.69
    utsu
    -0.69
    igl
    -0.69
    ijn
    -0.68
     Xie
    -0.66
    sites
    -0.64
    POSITIVE LOGITS
    AMI
    0.81
    HER
    0.73
     highs
    0.69
    cum
    0.65
     reflection
    0.65
     playable
    0.62
    VK
    0.62
    ACTED
    0.61
    ahime
    0.61
     bearer
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.