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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Vlad
    -0.77
    ghan
    -0.74
     Chains
    -0.72
    ylan
    -0.67
    emp
    -0.64
     Malf
    -0.63
    uez
    -0.63
    idal
    -0.63
     tours
    -0.61
    maps
    -0.61
    POSITIVE LOGITS
    OTT
    0.71
    Widget
    0.70
    Center
    0.70
     latex
    0.69
    Bottom
    0.66
    Temperature
    0.65
    çī
    0.65
     nutshell
    0.65
     ALP
    0.65
    Cent
    0.64
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.