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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     theorem
    -0.67
    izoph
    -0.67
    .''.
    -0.66
    rera
    -0.65
     Isles
    -0.64
    :'
    -0.63
     misunder
    -0.62
    ?'
    -0.61
    anan
    -0.61
    assian
    -0.61
    POSITIVE LOGITS
    ylum
    0.69
     warmer
    0.65
    ccoli
    0.61
     ARC
    0.61
    yden
    0.59
     brist
    0.59
    ahead
    0.58
     tart
    0.58
     Pavilion
    0.57
    Rust
    0.56
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.